diff options
Diffstat (limited to 'arch')
1052 files changed, 19181 insertions, 21355 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/configs/defconfig b/arch/alpha/configs/defconfig index f4ec420d7f2d..3a132c91d45b 100644 --- a/arch/alpha/configs/defconfig +++ b/arch/alpha/configs/defconfig @@ -36,7 +36,6 @@ CONFIG_BLK_DEV_CY82C693=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_SCSI_AIC7XXX=m CONFIG_AIC7XXX_CMDS_PER_DEVICE=253 # CONFIG_AIC7XXX_DEBUG_ENABLE is not set diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index 89e87bbc987f..42911c8340c7 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -1,17 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h -generic-y += compat.h -generic-y += exec.h generic-y += export.h -generic-y += fb.h -generic-y += irq_work.h generic-y += kvm_para.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += preempt.h -generic-y += sections.h -generic-y += trace_clock.h -generic-y += current.h -generic-y += kprobes.h 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/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 741e61ef9d3f..c2d7b6d7bac7 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -89,7 +89,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, const struct exception_table_entry *fixup; int si_code = SEGV_MAPERR; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; /* As of EV6, a load into $31/$f31 is a prefetch, and never faults (or is suppressed by the PALcode). Support that for older CPUs @@ -150,7 +150,7 @@ retry: the fault. */ fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -169,7 +169,7 @@ retry: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would * have already released it in __lock_page_or_retry 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/Kbuild b/arch/arc/include/asm/Kbuild index 1b505694691e..81f4edec0c2a 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -1,28 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += bugs.h -generic-y += compat.h -generic-y += device.h -generic-y += div64.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h generic-y += extable.h -generic-y += ftrace.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h generic-y += parport.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += topology.h -generic-y += trace_clock.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h 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/arc/mm/fault.c b/arch/arc/mm/fault.c index fb86bc3e9b35..92b339c7adba 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -100,7 +100,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) (regs->ecr_cause == ECR_C_PROTV_INST_FETCH)) exec = 1; - flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + flags = FAULT_FLAG_DEFAULT; if (user_mode(regs)) flags |= FAULT_FLAG_USER; if (write) @@ -133,29 +133,20 @@ retry: fault = handle_mm_fault(vma, address, flags); + /* Quick path to respond to signals */ + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + goto no_context; + return; + } + /* - * Fault retry nuances + * Fault retry nuances, mmap_sem already relinquished by core mm */ - if (unlikely(fault & VM_FAULT_RETRY)) { - - /* - * If fault needs to be retried, handle any pending signals - * first (by returning to user mode). - * mmap_sem already relinquished by core mm for RETRY case - */ - if (fatal_signal_pending(current)) { - if (!user_mode(regs)) - goto no_context; - return; - } - /* - * retry state machine - */ - if (flags & FAULT_FLAG_ALLOW_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; - flags |= FAULT_FLAG_TRIED; - goto retry; - } + if (unlikely((fault & VM_FAULT_RETRY) && + (flags & FAULT_FLAG_ALLOW_RETRY))) { + flags |= FAULT_FLAG_TRIED; + goto retry; } bad_area: diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 97864aabc2a6..66a04f6f4775 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -3,7 +3,6 @@ config ARM bool default y select ARCH_32BIT_OFF_T - select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_BINFMT_FLAT select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEVMEM_IS_ALLOWED @@ -2091,5 +2090,3 @@ source "drivers/firmware/Kconfig" if CRYPTO source "arch/arm/crypto/Kconfig" endif - -source "arch/arm/kvm/Kconfig" diff --git a/arch/arm/Makefile b/arch/arm/Makefile index db857d07114f..e1d13d779e08 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -278,7 +278,6 @@ core-$(CONFIG_FPE_NWFPE) += arch/arm/nwfpe/ core-$(CONFIG_FPE_FASTFPE) += $(patsubst $(srctree)/%,%,$(wildcard $(srctree)/arch/arm/fastfpe/)) core-$(CONFIG_VFP) += arch/arm/vfp/ core-$(CONFIG_XEN) += arch/arm/xen/ -core-$(CONFIG_KVM_ARM_HOST) += arch/arm/kvm/ core-$(CONFIG_VDSO) += arch/arm/vdso/ # If we have a machine-specific directory, then include it in the build. @@ -307,13 +306,15 @@ endif ifeq ($(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-apalis.dtsi b/arch/arm/boot/dts/imx6qdl-apalis.dtsi index 1b5bc6b5e806..347a5edc6927 100644 --- a/arch/arm/boot/dts/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/imx6qdl-apalis.dtsi @@ -180,7 +180,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy>; phy-reset-duration = <10>; phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; 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/mmp2-brownstone.dts b/arch/arm/boot/dts/mmp2-brownstone.dts index aaedc4c742ea..04f1ae1382e7 100644 --- a/arch/arm/boot/dts/mmp2-brownstone.dts +++ b/arch/arm/boot/dts/mmp2-brownstone.dts @@ -19,176 +19,174 @@ device_type = "memory"; reg = <0x00000000 0x08000000>; }; +}; + +&uart3 { + status = "okay"; +}; - soc { - apb@d4000000 { - uart3: uart@d4018000 { - status = "okay"; - }; - twsi1: i2c@d4011000 { - status = "okay"; - pmic: max8925@3c { - compatible = "maxium,max8925"; - reg = <0x3c>; - interrupts = <1>; - interrupt-parent = <&intcmux4>; - interrupt-controller; - #interrupt-cells = <1>; - maxim,tsc-irq = <0>; +&twsi1 { + status = "okay"; + pmic: max8925@3c { + compatible = "maxium,max8925"; + reg = <0x3c>; + interrupts = <1>; + interrupt-parent = <&intcmux4>; + interrupt-controller; + #interrupt-cells = <1>; + maxim,tsc-irq = <0>; - regulators { - SDV1 { - regulator-min-microvolt = <637500>; - regulator-max-microvolt = <1425000>; - regulator-boot-on; - regulator-always-on; - }; - SDV2 { - regulator-min-microvolt = <650000>; - regulator-max-microvolt = <2225000>; - regulator-boot-on; - regulator-always-on; - }; - SDV3 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO1 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO2 { - regulator-min-microvolt = <650000>; - regulator-max-microvolt = <2250000>; - regulator-boot-on; - regulator-always-on; - }; - LDO3 { - regulator-min-microvolt = <650000>; - regulator-max-microvolt = <2250000>; - regulator-boot-on; - regulator-always-on; - }; - LDO4 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO5 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO6 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO7 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO8 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO9 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO10 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - }; - LDO11 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO12 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO13 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO14 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO15 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO16 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO17 { - regulator-min-microvolt = <650000>; - regulator-max-microvolt = <2250000>; - regulator-boot-on; - regulator-always-on; - }; - LDO18 { - regulator-min-microvolt = <650000>; - regulator-max-microvolt = <2250000>; - regulator-boot-on; - regulator-always-on; - }; - LDO19 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO20 { - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <3900000>; - regulator-boot-on; - regulator-always-on; - }; - }; - backlight { - maxim,max8925-dual-string = <0>; - }; - charger { - batt-detect = <0>; - topoff-threshold = <1>; - fast-charge = <7>; - no-temp-support = <0>; - no-insert-detect = <0>; - }; - }; - }; - rtc: rtc@d4010000 { - status = "okay"; + regulators { + SDV1 { + regulator-min-microvolt = <637500>; + regulator-max-microvolt = <1425000>; + regulator-boot-on; + regulator-always-on; + }; + SDV2 { + regulator-min-microvolt = <650000>; + regulator-max-microvolt = <2225000>; + regulator-boot-on; + regulator-always-on; + }; + SDV3 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO1 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO2 { + regulator-min-microvolt = <650000>; + regulator-max-microvolt = <2250000>; + regulator-boot-on; + regulator-always-on; + }; + LDO3 { + regulator-min-microvolt = <650000>; + regulator-max-microvolt = <2250000>; + regulator-boot-on; + regulator-always-on; + }; + LDO4 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO5 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO6 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO7 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO8 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO9 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO10 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; }; + LDO11 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO12 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO13 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO14 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO15 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO16 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO17 { + regulator-min-microvolt = <650000>; + regulator-max-microvolt = <2250000>; + regulator-boot-on; + regulator-always-on; + }; + LDO18 { + regulator-min-microvolt = <650000>; + regulator-max-microvolt = <2250000>; + regulator-boot-on; + regulator-always-on; + }; + LDO19 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO20 { + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <3900000>; + regulator-boot-on; + regulator-always-on; + }; + }; + backlight { + maxim,max8925-dual-string = <0>; + }; + charger { + batt-detect = <0>; + topoff-threshold = <1>; + fast-charge = <7>; + no-temp-support = <0>; + no-insert-detect = <0>; }; }; }; + +&rtc { + status = "okay"; +}; diff --git a/arch/arm/boot/dts/mmp2.dtsi b/arch/arm/boot/dts/mmp2.dtsi index 6a2f072c1d0a..da10567b5aca 100644 --- a/arch/arm/boot/dts/mmp2.dtsi +++ b/arch/arm/boot/dts/mmp2.dtsi @@ -208,8 +208,8 @@ clocks = <&soc_clocks MMP2_CLK_TIMER>; }; - uart1: uart@d4030000 { - compatible = "mrvl,mmp-uart"; + uart1: serial@d4030000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4030000 0x1000>; interrupts = <27>; clocks = <&soc_clocks MMP2_CLK_UART0>; @@ -218,8 +218,8 @@ status = "disabled"; }; - uart2: uart@d4017000 { - compatible = "mrvl,mmp-uart"; + uart2: serial@d4017000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4017000 0x1000>; interrupts = <28>; clocks = <&soc_clocks MMP2_CLK_UART1>; @@ -228,8 +228,8 @@ status = "disabled"; }; - uart3: uart@d4018000 { - compatible = "mrvl,mmp-uart"; + uart3: serial@d4018000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4018000 0x1000>; interrupts = <24>; clocks = <&soc_clocks MMP2_CLK_UART2>; @@ -238,8 +238,8 @@ status = "disabled"; }; - uart4: uart@d4016000 { - compatible = "mrvl,mmp-uart"; + uart4: serial@d4016000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4016000 0x1000>; interrupts = <46>; clocks = <&soc_clocks MMP2_CLK_UART3>; diff --git a/arch/arm/boot/dts/mmp3.dtsi b/arch/arm/boot/dts/mmp3.dtsi index 59a108e49b41..9b5087a95e73 100644 --- a/arch/arm/boot/dts/mmp3.dtsi +++ b/arch/arm/boot/dts/mmp3.dtsi @@ -318,8 +318,8 @@ clocks = <&soc_clocks MMP2_CLK_TIMER>; }; - uart1: uart@d4030000 { - compatible = "mrvl,mmp-uart"; + uart1: serial@d4030000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4030000 0x1000>; interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>; clocks = <&soc_clocks MMP2_CLK_UART0>; @@ -328,8 +328,8 @@ status = "disabled"; }; - uart2: uart@d4017000 { - compatible = "mrvl,mmp-uart"; + uart2: serial@d4017000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4017000 0x1000>; interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>; clocks = <&soc_clocks MMP2_CLK_UART1>; @@ -338,8 +338,8 @@ status = "disabled"; }; - uart3: uart@d4018000 { - compatible = "mrvl,mmp-uart"; + uart3: serial@d4018000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4018000 0x1000>; interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; clocks = <&soc_clocks MMP2_CLK_UART2>; @@ -348,8 +348,8 @@ status = "disabled"; }; - uart4: uart@d4016000 { - compatible = "mrvl,mmp-uart"; + uart4: serial@d4016000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4016000 0x1000>; interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>; clocks = <&soc_clocks MMP2_CLK_UART3>; 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/pxa168-aspenite.dts b/arch/arm/boot/dts/pxa168-aspenite.dts index 2ad40e373194..8bade6bf395b 100644 --- a/arch/arm/boot/dts/pxa168-aspenite.dts +++ b/arch/arm/boot/dts/pxa168-aspenite.dts @@ -18,18 +18,16 @@ memory { reg = <0x00000000 0x04000000>; }; +}; - soc { - apb@d4000000 { - uart1: uart@d4017000 { - status = "okay"; - }; - twsi1: i2c@d4011000 { - status = "okay"; - }; - rtc: rtc@d4010000 { - status = "okay"; - }; - }; - }; +&uart1 { + status = "okay"; +}; + +&twsi1 { + status = "okay"; +}; + +&rtc { + status = "okay"; }; diff --git a/arch/arm/boot/dts/pxa168.dtsi b/arch/arm/boot/dts/pxa168.dtsi index 72f8cb60cb53..9a9e38245e88 100644 --- a/arch/arm/boot/dts/pxa168.dtsi +++ b/arch/arm/boot/dts/pxa168.dtsi @@ -55,27 +55,30 @@ interrupts = <13>; }; - uart1: uart@d4017000 { - compatible = "mrvl,mmp-uart"; + uart1: serial@d4017000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4017000 0x1000>; + reg-shift = <2>; interrupts = <27>; clocks = <&soc_clocks PXA168_CLK_UART0>; resets = <&soc_clocks PXA168_CLK_UART0>; status = "disabled"; }; - uart2: uart@d4018000 { - compatible = "mrvl,mmp-uart"; + uart2: serial@d4018000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4018000 0x1000>; + reg-shift = <2>; interrupts = <28>; clocks = <&soc_clocks PXA168_CLK_UART1>; resets = <&soc_clocks PXA168_CLK_UART1>; status = "disabled"; }; - uart3: uart@d4026000 { - compatible = "mrvl,mmp-uart"; + uart3: serial@d4026000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4026000 0x1000>; + reg-shift = <2>; interrupts = <29>; clocks = <&soc_clocks PXA168_CLK_UART2>; resets = <&soc_clocks PXA168_CLK_UART2>; diff --git a/arch/arm/boot/dts/pxa910-dkb.dts b/arch/arm/boot/dts/pxa910-dkb.dts index 0f899e672e82..ce76158867c7 100644 --- a/arch/arm/boot/dts/pxa910-dkb.dts +++ b/arch/arm/boot/dts/pxa910-dkb.dts @@ -18,155 +18,153 @@ memory { reg = <0x00000000 0x10000000>; }; +}; - soc { - apb@d4000000 { - uart1: uart@d4017000 { - status = "okay"; - }; - twsi1: i2c@d4011000 { - status = "okay"; +&uart1 { + status = "okay"; +}; + +&twsi1 { + status = "okay"; - pmic: 88pm860x@34 { - compatible = "marvell,88pm860x"; - reg = <0x34>; - interrupts = <4>; - interrupt-parent = <&intc>; - interrupt-controller; - #interrupt-cells = <1>; + pmic: 88pm860x@34 { + compatible = "marvell,88pm860x"; + reg = <0x34>; + interrupts = <4>; + interrupt-parent = <&intc>; + interrupt-controller; + #interrupt-cells = <1>; - marvell,88pm860x-irq-read-clr; - marvell,88pm860x-slave-addr = <0x11>; + marvell,88pm860x-irq-read-clr; + marvell,88pm860x-slave-addr = <0x11>; - regulators { - BUCK1 { - regulator-min-microvolt = <1000000>; - regulator-max-microvolt = <1500000>; - regulator-boot-on; - regulator-always-on; - }; - BUCK2 { - regulator-min-microvolt = <1000000>; - regulator-max-microvolt = <1500000>; - regulator-boot-on; - regulator-always-on; - }; - BUCK3 { - regulator-min-microvolt = <1000000>; - regulator-max-microvolt = <3000000>; - regulator-boot-on; - regulator-always-on; - }; - LDO1 { - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <2800000>; - regulator-boot-on; - regulator-always-on; - }; - LDO2 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - LDO3 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - LDO4 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - }; - LDO5 { - regulator-min-microvolt = <2900000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - LDO6 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - LDO7 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <2900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO8 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <2900000>; - regulator-boot-on; - regulator-always-on; - }; - LDO9 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - LDO10 { - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - LDO12 { - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - }; - LDO13 { - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - }; - LDO14 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - }; - }; - rtc { - marvell,88pm860x-vrtc = <1>; - }; - touch { - marvell,88pm860x-gpadc-prebias = <1>; - marvell,88pm860x-gpadc-slot-cycle = <1>; - marvell,88pm860x-tsi-prebias = <6>; - marvell,88pm860x-pen-prebias = <16>; - marvell,88pm860x-pen-prechg = <2>; - marvell,88pm860x-resistor-X = <300>; - }; - backlights { - backlight-0 { - marvell,88pm860x-iset = <4>; - marvell,88pm860x-pwm = <3>; - }; - backlight-2 { - }; - }; - leds { - led0-red { - marvell,88pm860x-iset = <12>; - }; - led0-green { - marvell,88pm860x-iset = <12>; - }; - led0-blue { - marvell,88pm860x-iset = <12>; - }; - }; - }; - }; - rtc: rtc@d4010000 { - status = "okay"; + regulators { + BUCK1 { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1500000>; + regulator-boot-on; + regulator-always-on; + }; + BUCK2 { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1500000>; + regulator-boot-on; + regulator-always-on; + }; + BUCK3 { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3000000>; + regulator-boot-on; + regulator-always-on; + }; + LDO1 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <2800000>; + regulator-boot-on; + regulator-always-on; + }; + LDO2 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + LDO3 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + LDO4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + LDO5 { + regulator-min-microvolt = <2900000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + LDO6 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + LDO7 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO8 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-boot-on; + regulator-always-on; + }; + LDO9 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + LDO10 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + LDO12 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + LDO13 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + LDO14 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + }; + rtc { + marvell,88pm860x-vrtc = <1>; + }; + touch { + marvell,88pm860x-gpadc-prebias = <1>; + marvell,88pm860x-gpadc-slot-cycle = <1>; + marvell,88pm860x-tsi-prebias = <6>; + marvell,88pm860x-pen-prebias = <16>; + marvell,88pm860x-pen-prechg = <2>; + marvell,88pm860x-resistor-X = <300>; + }; + backlights { + backlight-0 { + marvell,88pm860x-iset = <4>; + marvell,88pm860x-pwm = <3>; + }; + backlight-2 { + }; + }; + leds { + led0-red { + marvell,88pm860x-iset = <12>; + }; + led0-green { + marvell,88pm860x-iset = <12>; + }; + led0-blue { + marvell,88pm860x-iset = <12>; }; }; }; }; + +&rtc { + status = "okay"; +}; diff --git a/arch/arm/boot/dts/pxa910.dtsi b/arch/arm/boot/dts/pxa910.dtsi index b3d6182d4de4..587a5e7f0702 100644 --- a/arch/arm/boot/dts/pxa910.dtsi +++ b/arch/arm/boot/dts/pxa910.dtsi @@ -67,27 +67,30 @@ status = "disabled"; }; - uart1: uart@d4017000 { - compatible = "mrvl,mmp-uart"; + uart1: serial@d4017000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4017000 0x1000>; + reg-shift = <2>; interrupts = <27>; clocks = <&soc_clocks PXA910_CLK_UART0>; resets = <&soc_clocks PXA910_CLK_UART0>; status = "disabled"; }; - uart2: uart@d4018000 { - compatible = "mrvl,mmp-uart"; + uart2: serial@d4018000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4018000 0x1000>; + reg-shift = <2>; interrupts = <28>; clocks = <&soc_clocks PXA910_CLK_UART1>; resets = <&soc_clocks PXA910_CLK_UART1>; status = "disabled"; }; - uart3: uart@d4036000 { - compatible = "mrvl,mmp-uart"; + uart3: serial@d4036000 { + compatible = "mrvl,mmp-uart", "intel,xscale-uart"; reg = <0xd4036000 0x1000>; + reg-shift = <2>; interrupts = <59>; clocks = <&soc_clocks PXA910_CLK_UART2>; resets = <&soc_clocks PXA910_CLK_UART2>; 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/stih410-b2260.dts b/arch/arm/boot/dts/stih410-b2260.dts index 4fbd8e9eb5b7..e2bb59783146 100644 --- a/arch/arm/boot/dts/stih410-b2260.dts +++ b/arch/arm/boot/dts/stih410-b2260.dts @@ -178,9 +178,6 @@ phy-mode = "rgmii"; pinctrl-0 = <&pinctrl_rgmii1 &pinctrl_rgmii1_mdio_1>; - snps,phy-bus-name = "stmmac"; - snps,phy-bus-id = <0>; - snps,phy-addr = <0>; snps,reset-gpio = <&pio0 7 0>; snps,reset-active-low; snps,reset-delays-us = <0 10000 1000000>; diff --git a/arch/arm/boot/dts/stihxxx-b2120.dtsi b/arch/arm/boot/dts/stihxxx-b2120.dtsi index 60e11045ad76..d051f080e52e 100644 --- a/arch/arm/boot/dts/stihxxx-b2120.dtsi +++ b/arch/arm/boot/dts/stihxxx-b2120.dtsi @@ -46,7 +46,7 @@ /* DAC */ format = "i2s"; mclk-fs = <256>; - frame-inversion = <1>; + frame-inversion; cpu { sound-dai = <&sti_uni_player2>; }; 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 b9c45aa8f21f..769efb4d7775 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/boot/dts/tango4-common.dtsi b/arch/arm/boot/dts/tango4-common.dtsi index ff72a8efb73d..54fd522badfc 100644 --- a/arch/arm/boot/dts/tango4-common.dtsi +++ b/arch/arm/boot/dts/tango4-common.dtsi @@ -85,7 +85,7 @@ }; uart: serial@10700 { - compatible = "ralink,rt2880-uart"; + compatible = "ralink,rt2880-uart", "ns16550a"; reg = <0x10700 0x30>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; clock-frequency = <7372800>; 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/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig index 622436f44783..f56ac394caf1 100644 --- a/arch/arm/configs/am200epdkit_defconfig +++ b/arch/arm/configs/am200epdkit_defconfig @@ -11,8 +11,6 @@ CONFIG_SLAB=y CONFIG_MODULES=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_ARCH_PXA=y CONFIG_ARCH_GUMSTIX=y CONFIG_PCCARD=y diff --git a/arch/arm/configs/axm55xx_defconfig b/arch/arm/configs/axm55xx_defconfig index f53634af014b..46075216ee6d 100644 --- a/arch/arm/configs/axm55xx_defconfig +++ b/arch/arm/configs/axm55xx_defconfig @@ -25,7 +25,6 @@ CONFIG_EMBEDDED=y CONFIG_PROFILING=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set CONFIG_ARCH_AXXIA=y CONFIG_GPIO_PCA953X=y CONFIG_ARM_LPAE=y @@ -237,5 +236,3 @@ CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_XCBC=y CONFIG_CRYPTO_SHA256=y # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_VIRTUALIZATION=y -CONFIG_KVM=y 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/clps711x_defconfig b/arch/arm/configs/clps711x_defconfig index c255dab36bde..63a153f5cf68 100644 --- a/arch/arm/configs/clps711x_defconfig +++ b/arch/arm/configs/clps711x_defconfig @@ -7,7 +7,6 @@ CONFIG_EMBEDDED=y CONFIG_SLOB=y CONFIG_JUMP_LABEL=y CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_CLPS711X=y CONFIG_ARCH_AUTCPU12=y CONFIG_ARCH_CDB89712=y diff --git a/arch/arm/configs/cns3420vb_defconfig b/arch/arm/configs/cns3420vb_defconfig index 89df0a55a065..66a80b46038d 100644 --- a/arch/arm/configs/cns3420vb_defconfig +++ b/arch/arm/configs/cns3420vb_defconfig @@ -17,7 +17,7 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set -CONFIG_IOSCHED_CFQ=m +CONFIG_IOSCHED_BFQ=m CONFIG_ARCH_MULTI_V6=y #CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_CNS3XXX=y diff --git a/arch/arm/configs/colibri_pxa300_defconfig b/arch/arm/configs/colibri_pxa300_defconfig index 446134c70a33..0dae3b185284 100644 --- a/arch/arm/configs/colibri_pxa300_defconfig +++ b/arch/arm/configs/colibri_pxa300_defconfig @@ -43,7 +43,6 @@ CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_STORAGE=y CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_PXA=y CONFIG_EXT3_FS=y CONFIG_NFS_FS=y diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig index e6df11e906ba..36384fd575f8 100644 --- a/arch/arm/configs/collie_defconfig +++ b/arch/arm/configs/collie_defconfig @@ -7,8 +7,6 @@ CONFIG_EXPERT=y # CONFIG_BASE_FULL is not set # CONFIG_EPOLL is not set CONFIG_SLOB=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_SA1100=y CONFIG_SA1100_COLLIE=y CONFIG_PCCARD=y diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index 231f8973bbb2..e849367c0566 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -15,8 +15,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_MULTIPLATFORM=y CONFIG_ARCH_MULTI_V7=n CONFIG_ARCH_MULTI_V5=y @@ -160,7 +158,7 @@ CONFIG_VIDEO_TVP514X=m CONFIG_VIDEO_ADV7343=m CONFIG_DRM=m CONFIG_DRM_TILCDC=m -CONFIG_DRM_DUMB_VGA_DAC=m +CONFIG_DRM_SIMPLE_BRIDGE=m CONFIG_DRM_TINYDRM=m CONFIG_TINYDRM_ST7586=m CONFIG_FB=y diff --git a/arch/arm/configs/efm32_defconfig b/arch/arm/configs/efm32_defconfig index 10ea92513a69..46213f0530c4 100644 --- a/arch/arm/configs/efm32_defconfig +++ b/arch/arm/configs/efm32_defconfig @@ -12,8 +12,6 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set # CONFIG_MMU is not set CONFIG_ARM_SINGLE_ARMV7M=y CONFIG_ARCH_EFM32=y diff --git a/arch/arm/configs/ep93xx_defconfig b/arch/arm/configs/ep93xx_defconfig index ef2d2a820c30..cd16fb6eb8e6 100644 --- a/arch/arm/configs/ep93xx_defconfig +++ b/arch/arm/configs/ep93xx_defconfig @@ -11,7 +11,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_EP93XX=y CONFIG_CRUNCH=y CONFIG_MACH_ADSSPHERE=y diff --git a/arch/arm/configs/eseries_pxa_defconfig b/arch/arm/configs/eseries_pxa_defconfig index 56452fa03d56..046f4dc2e18e 100644 --- a/arch/arm/configs/eseries_pxa_defconfig +++ b/arch/arm/configs/eseries_pxa_defconfig @@ -9,8 +9,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_ARCH_PXA_ESERIES=y # CONFIG_ARM_THUMB is not set diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig index 4e28771beecd..bd7b7f945e01 100644 --- a/arch/arm/configs/ezx_defconfig +++ b/arch/arm/configs/ezx_defconfig @@ -14,7 +14,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_PXA_EZX=y CONFIG_NO_HZ=y diff --git a/arch/arm/configs/h3600_defconfig b/arch/arm/configs/h3600_defconfig index 4d91e41cb628..c02b3e409610 100644 --- a/arch/arm/configs/h3600_defconfig +++ b/arch/arm/configs/h3600_defconfig @@ -5,8 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_SA1100=y CONFIG_SA1100_H3600=y CONFIG_PCCARD=y diff --git a/arch/arm/configs/h5000_defconfig b/arch/arm/configs/h5000_defconfig index 3946c6087327..f5a338fefda8 100644 --- a/arch/arm/configs/h5000_defconfig +++ b/arch/arm/configs/h5000_defconfig @@ -10,7 +10,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_H5000=y CONFIG_AEABI=y diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig index 770469f61c3e..05c5515fa871 100644 --- a/arch/arm/configs/imote2_defconfig +++ b/arch/arm/configs/imote2_defconfig @@ -13,7 +13,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_INTELMOTE2=y CONFIG_NO_HZ=y diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index 2b2d617e279d..3df90fc38398 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -32,8 +32,6 @@ CONFIG_KPROBES=y CONFIG_MODULES=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_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index 2f0a762dc3a0..a9755c501bec 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -55,7 +55,7 @@ CONFIG_SMC91X=y # CONFIG_KEYBOARD_ATKBD is not set # CONFIG_SERIO_SERPORT is not set CONFIG_DRM=y -CONFIG_DRM_DUMB_VGA_DAC=y +CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_MATROX=y diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig index e518168a0627..be882ea0eee4 100644 --- a/arch/arm/configs/lpc18xx_defconfig +++ b/arch/arm/configs/lpc18xx_defconfig @@ -1,4 +1,3 @@ -CONFIG_CROSS_COMPILE="arm-linux-gnueabihf-" CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT=y CONFIG_BLK_DEV_INITRD=y @@ -28,10 +27,7 @@ CONFIG_FLASH_SIZE=0x00080000 CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y CONFIG_BINFMT_SHARED_FLAT=y diff --git a/arch/arm/configs/magician_defconfig b/arch/arm/configs/magician_defconfig index e6486c959220..d2e684f6565a 100644 --- a/arch/arm/configs/magician_defconfig +++ b/arch/arm/configs/magician_defconfig @@ -9,8 +9,6 @@ CONFIG_SLAB=y CONFIG_MODULES=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_ARCH_PXA=y CONFIG_MACH_H4700=y CONFIG_MACH_MAGICIAN=y diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig index 45d27190c9c9..6834e97af348 100644 --- a/arch/arm/configs/moxart_defconfig +++ b/arch/arm/configs/moxart_defconfig @@ -15,7 +15,6 @@ CONFIG_EMBEDDED=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set CONFIG_ARCH_MULTI_V4=y # CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_MOXART=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 017d65f86eba..0b020863abdb 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -670,11 +670,11 @@ CONFIG_DRM_PANEL_ORISETECH_OTM8009A=m CONFIG_DRM_PANEL_RAYDIUM_RM68200=m CONFIG_DRM_PANEL_SAMSUNG_S6E63J0X03=m CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=m -CONFIG_DRM_DUMB_VGA_DAC=m CONFIG_DRM_NXP_PTN3460=m CONFIG_DRM_PARADE_PS8622=m CONFIG_DRM_SII902X=m CONFIG_DRM_SII9234=m +CONFIG_DRM_SIMPLE_BRIDGE=m CONFIG_DRM_TOSHIBA_TC358764=m CONFIG_DRM_I2C_ADV7511=m CONFIG_DRM_I2C_ADV7511_AUDIO=y diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index 2773899c21b3..a9c6f32a9b1c 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -25,8 +25,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_BLK_DEV_INTEGRITY=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig index 0c43c589f191..3b6e7452609b 100644 --- a/arch/arm/configs/omap1_defconfig +++ b/arch/arm/configs/omap1_defconfig @@ -18,8 +18,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_OMAP=y CONFIG_ARCH_OMAP1=y CONFIG_OMAP_RESET_CLOCKS=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index c32c338f7704..54f1a21de7e0 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -350,14 +350,13 @@ CONFIG_DRM_OMAP=m CONFIG_OMAP5_DSS_HDMI=y CONFIG_OMAP2_DSS_SDI=y CONFIG_OMAP2_DSS_DSI=y -CONFIG_DRM_OMAP_ENCODER_OPA362=m -CONFIG_DRM_OMAP_ENCODER_TPD12S015=m -CONFIG_DRM_OMAP_CONNECTOR_HDMI=m -CONFIG_DRM_OMAP_CONNECTOR_ANALOG_TV=m CONFIG_DRM_OMAP_PANEL_DSI_CM=m CONFIG_DRM_TILCDC=m CONFIG_DRM_PANEL_SIMPLE=m +CONFIG_DRM_DISPLAY_CONNECTOR=m +CONFIG_DRM_SIMPLE_BRIDGE=m CONFIG_DRM_TI_TFP410=m +CONFIG_DRM_TI_TPD12S015=m CONFIG_DRM_PANEL_LG_LB035Q02=m CONFIG_DRM_PANEL_NEC_NL8048HL11=m CONFIG_DRM_PANEL_SHARP_LS037V7DW01=m @@ -375,6 +374,7 @@ 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/palmz72_defconfig b/arch/arm/configs/palmz72_defconfig index 4a3fd82c2a0c..b47c8abe85bc 100644 --- a/arch/arm/configs/palmz72_defconfig +++ b/arch/arm/configs/palmz72_defconfig @@ -7,8 +7,6 @@ CONFIG_SLAB=y CONFIG_MODULES=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_ARCH_PXA=y CONFIG_ARCH_PXA_PALM=y # CONFIG_MACH_PALMTX is not set diff --git a/arch/arm/configs/pcm027_defconfig b/arch/arm/configs/pcm027_defconfig index a8c53228b0c1..e97a158081fc 100644 --- a/arch/arm/configs/pcm027_defconfig +++ b/arch/arm/configs/pcm027_defconfig @@ -13,8 +13,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_PCM027=y CONFIG_MACH_PCM990_BASEBOARD=y diff --git a/arch/arm/configs/pleb_defconfig b/arch/arm/configs/pleb_defconfig index f0541b060cfa..2170148b975c 100644 --- a/arch/arm/configs/pleb_defconfig +++ b/arch/arm/configs/pleb_defconfig @@ -6,8 +6,6 @@ CONFIG_EXPERT=y # CONFIG_HOTPLUG is not set # CONFIG_SHMEM is not set CONFIG_MODULES=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_SA1100=y CONFIG_SA1100_PLEB=y CONFIG_ZBOOT_ROM_TEXT=0x0 diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig index 8a056cc0c1ec..70e2c74a9f32 100644 --- a/arch/arm/configs/realview_defconfig +++ b/arch/arm/configs/realview_defconfig @@ -8,7 +8,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_MULTI_V6=y CONFIG_ARCH_REALVIEW=y CONFIG_MACH_REALVIEW_EB=y diff --git a/arch/arm/configs/rpc_defconfig b/arch/arm/configs/rpc_defconfig index 3b82b64950d9..c090643b1ecb 100644 --- a/arch/arm/configs/rpc_defconfig +++ b/arch/arm/configs/rpc_defconfig @@ -32,7 +32,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig index 73ed73a8785a..153009130dab 100644 --- a/arch/arm/configs/s3c2410_defconfig +++ b/arch/arm/configs/s3c2410_defconfig @@ -202,7 +202,6 @@ CONFIG_EEPROM_AT24=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_CONSTANTS=y diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index 27f6135c4ee7..bab7861443dc 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -14,8 +14,6 @@ CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_AT91=y CONFIG_SOC_SAMA5D2=y CONFIG_SOC_SAMA5D3=y @@ -182,7 +180,6 @@ CONFIG_USB_GADGET=y CONFIG_USB_ATMEL_USBA=y CONFIG_USB_G_SERIAL=y CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_OF_AT91=y diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig index 64fa849f8bbe..838307a9bb92 100644 --- a/arch/arm/configs/shmobile_defconfig +++ b/arch/arm/configs/shmobile_defconfig @@ -125,9 +125,9 @@ CONFIG_VIDEO_ML86V7667=y CONFIG_DRM=y CONFIG_DRM_RCAR_DU=y CONFIG_DRM_PANEL_SIMPLE=y -CONFIG_DRM_DUMB_VGA_DAC=y CONFIG_DRM_LVDS_CODEC=y CONFIG_DRM_SII902X=y +CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_I2C_ADV7511=y CONFIG_DRM_I2C_ADV7511_AUDIO=y CONFIG_FB_SH_MOBILE_LCDC=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/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig index 152321d2893e..551db328009d 100644 --- a/arch/arm/configs/stm32_defconfig +++ b/arch/arm/configs/stm32_defconfig @@ -14,8 +14,6 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set # CONFIG_MMU is not set CONFIG_ARCH_STM32=y CONFIG_CPU_V7M_NUM_IRQ=240 diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 3f5d727efc41..61b8be19e527 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -85,6 +85,7 @@ CONFIG_BATTERY_AXP20X=y CONFIG_AXP20X_POWER=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y +CONFIG_SUN8I_THERMAL=y CONFIG_WATCHDOG=y CONFIG_SUNXI_WATCHDOG=y CONFIG_MFD_AC100=y @@ -100,7 +101,7 @@ CONFIG_RC_DEVICES=y CONFIG_IR_SUNXI=y CONFIG_DRM=y CONFIG_DRM_SUN4I=y -CONFIG_DRM_DUMB_VGA_DAC=y +CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_FB_SIMPLE=y CONFIG_SOUND=y CONFIG_SND=y diff --git a/arch/arm/configs/u300_defconfig b/arch/arm/configs/u300_defconfig index 8223397db047..543f07338100 100644 --- a/arch/arm/configs/u300_defconfig +++ b/arch/arm/configs/u300_defconfig @@ -11,7 +11,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set # CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_U300=y CONFIG_MACH_U300_SPIDUMMY=y @@ -46,7 +45,6 @@ CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_USB_SUPPORT is not set CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_ARMMMCI=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set diff --git a/arch/arm/configs/versatile_defconfig b/arch/arm/configs/versatile_defconfig index fe4d4b596585..767935337413 100644 --- a/arch/arm/configs/versatile_defconfig +++ b/arch/arm/configs/versatile_defconfig @@ -59,7 +59,7 @@ CONFIG_GPIO_PL061=y CONFIG_DRM=y CONFIG_DRM_PANEL_ARM_VERSATILE=y CONFIG_DRM_PANEL_SIMPLE=y -CONFIG_DRM_DUMB_VGA_DAC=y +CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y CONFIG_FB_MODE_HELPERS=y CONFIG_BACKLIGHT_CLASS_DEVICE=y diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig index 25753552277a..c01baf7d6e37 100644 --- a/arch/arm/configs/vexpress_defconfig +++ b/arch/arm/configs/vexpress_defconfig @@ -15,8 +15,6 @@ CONFIG_OPROFILE=y CONFIG_MODULES=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_ARCH_VEXPRESS=y CONFIG_ARCH_VEXPRESS_DCSCB=y CONFIG_ARCH_VEXPRESS_TC2_PM=y diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig index 2ff16168d9c2..989599ce5300 100644 --- a/arch/arm/configs/viper_defconfig +++ b/arch/arm/configs/viper_defconfig @@ -9,7 +9,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_ARCH_VIPER=y CONFIG_IWMMXT=y diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig index aa3023c9a011..d3b98c4d225b 100644 --- a/arch/arm/configs/zeus_defconfig +++ b/arch/arm/configs/zeus_defconfig @@ -4,7 +4,6 @@ CONFIG_LOG_BUF_SHIFT=13 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y CONFIG_MACH_ARCOM_ZEUS=y CONFIG_PCCARD=m @@ -137,7 +136,6 @@ CONFIG_USB_MASS_STORAGE=m CONFIG_USB_G_SERIAL=m CONFIG_USB_G_PRINTER=m CONFIG_MMC=y -# CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_PXA=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=m diff --git a/arch/arm/configs/zx_defconfig b/arch/arm/configs/zx_defconfig index 4d2ef785ed34..a046a492bfa7 100644 --- a/arch/arm/configs/zx_defconfig +++ b/arch/arm/configs/zx_defconfig @@ -16,7 +16,6 @@ CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_ZX=y CONFIG_SOC_ZX296702=y # CONFIG_SWP_EMULATE is not set diff --git a/arch/arm/crypto/.gitignore b/arch/arm/crypto/.gitignore index 31e1f538df7d..a3c7ad52a469 100644 --- a/arch/arm/crypto/.gitignore +++ b/arch/arm/crypto/.gitignore @@ -1,3 +1,4 @@ aesbs-core.S sha256-core.S sha512-core.S +poly1305-core.S diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c index e85839a8aaeb..e6fd32919c81 100644 --- a/arch/arm/crypto/aes-neonbs-glue.c +++ b/arch/arm/crypto/aes-neonbs-glue.c @@ -138,6 +138,7 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key, kernel_neon_begin(); aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds); kernel_neon_end(); + memzero_explicit(&rk, sizeof(rk)); return crypto_cipher_setkey(ctx->enc_tfm, in_key, key_len); } diff --git a/arch/arm/crypto/ghash-ce-core.S b/arch/arm/crypto/ghash-ce-core.S index 534c9647726d..9f51e3fa4526 100644 --- a/arch/arm/crypto/ghash-ce-core.S +++ b/arch/arm/crypto/ghash-ce-core.S @@ -8,6 +8,9 @@ #include <linux/linkage.h> #include <asm/assembler.h> + .arch armv8-a + .fpu crypto-neon-fp-armv8 + SHASH .req q0 T1 .req q1 XL .req q2 @@ -88,8 +91,6 @@ T3_H .req d17 .text - .arch armv8-a - .fpu crypto-neon-fp-armv8 .macro __pmull_p64, rd, rn, rm, b1, b2, b3, b4 vmull.p64 \rd, \rn, \rm diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index fa579b23b4df..383635b68763 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -1,22 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += compat.h -generic-y += current.h generic-y += early_ioremap.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h generic-y += flat.h -generic-y += irq_regs.h -generic-y += kdebug.h -generic-y += local.h generic-y += local64.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h generic-y += parport.h -generic-y += preempt.h generic-y += seccomp.h -generic-y += serial.h -generic-y += trace_clock.h generated-y += mach-types.h generated-y += unistd-nr.h diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index c815477b4303..413abfb42989 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -38,71 +38,6 @@ #define ICC_AP1R2 __ICC_AP1Rx(2) #define ICC_AP1R3 __ICC_AP1Rx(3) -#define ICC_HSRE __ACCESS_CP15(c12, 4, c9, 5) - -#define ICH_VSEIR __ACCESS_CP15(c12, 4, c9, 4) -#define ICH_HCR __ACCESS_CP15(c12, 4, c11, 0) -#define ICH_VTR __ACCESS_CP15(c12, 4, c11, 1) -#define ICH_MISR __ACCESS_CP15(c12, 4, c11, 2) -#define ICH_EISR __ACCESS_CP15(c12, 4, c11, 3) -#define ICH_ELRSR __ACCESS_CP15(c12, 4, c11, 5) -#define ICH_VMCR __ACCESS_CP15(c12, 4, c11, 7) - -#define __LR0(x) __ACCESS_CP15(c12, 4, c12, x) -#define __LR8(x) __ACCESS_CP15(c12, 4, c13, x) - -#define ICH_LR0 __LR0(0) -#define ICH_LR1 __LR0(1) -#define ICH_LR2 __LR0(2) -#define ICH_LR3 __LR0(3) -#define ICH_LR4 __LR0(4) -#define ICH_LR5 __LR0(5) -#define ICH_LR6 __LR0(6) -#define ICH_LR7 __LR0(7) -#define ICH_LR8 __LR8(0) -#define ICH_LR9 __LR8(1) -#define ICH_LR10 __LR8(2) -#define ICH_LR11 __LR8(3) -#define ICH_LR12 __LR8(4) -#define ICH_LR13 __LR8(5) -#define ICH_LR14 __LR8(6) -#define ICH_LR15 __LR8(7) - -/* LR top half */ -#define __LRC0(x) __ACCESS_CP15(c12, 4, c14, x) -#define __LRC8(x) __ACCESS_CP15(c12, 4, c15, x) - -#define ICH_LRC0 __LRC0(0) -#define ICH_LRC1 __LRC0(1) -#define ICH_LRC2 __LRC0(2) -#define ICH_LRC3 __LRC0(3) -#define ICH_LRC4 __LRC0(4) -#define ICH_LRC5 __LRC0(5) -#define ICH_LRC6 __LRC0(6) -#define ICH_LRC7 __LRC0(7) -#define ICH_LRC8 __LRC8(0) -#define ICH_LRC9 __LRC8(1) -#define ICH_LRC10 __LRC8(2) -#define ICH_LRC11 __LRC8(3) -#define ICH_LRC12 __LRC8(4) -#define ICH_LRC13 __LRC8(5) -#define ICH_LRC14 __LRC8(6) -#define ICH_LRC15 __LRC8(7) - -#define __ICH_AP0Rx(x) __ACCESS_CP15(c12, 4, c8, x) -#define ICH_AP0R0 __ICH_AP0Rx(0) -#define ICH_AP0R1 __ICH_AP0Rx(1) -#define ICH_AP0R2 __ICH_AP0Rx(2) -#define ICH_AP0R3 __ICH_AP0Rx(3) - -#define __ICH_AP1Rx(x) __ACCESS_CP15(c12, 4, c9, x) -#define ICH_AP1R0 __ICH_AP1Rx(0) -#define ICH_AP1R1 __ICH_AP1Rx(1) -#define ICH_AP1R2 __ICH_AP1Rx(2) -#define ICH_AP1R3 __ICH_AP1Rx(3) - -/* A32-to-A64 mappings used by VGIC save/restore */ - #define CPUIF_MAP(a32, a64) \ static inline void write_ ## a64(u32 val) \ { \ @@ -113,21 +48,6 @@ static inline u32 read_ ## a64(void) \ return read_sysreg(a32); \ } \ -#define CPUIF_MAP_LO_HI(a32lo, a32hi, a64) \ -static inline void write_ ## a64(u64 val) \ -{ \ - write_sysreg(lower_32_bits(val), a32lo);\ - write_sysreg(upper_32_bits(val), a32hi);\ -} \ -static inline u64 read_ ## a64(void) \ -{ \ - u64 val = read_sysreg(a32lo); \ - \ - val |= (u64)read_sysreg(a32hi) << 32; \ - \ - return val; \ -} - CPUIF_MAP(ICC_PMR, ICC_PMR_EL1) CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1) CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1) @@ -138,40 +58,6 @@ CPUIF_MAP(ICC_AP1R1, ICC_AP1R1_EL1) CPUIF_MAP(ICC_AP1R2, ICC_AP1R2_EL1) CPUIF_MAP(ICC_AP1R3, ICC_AP1R3_EL1) -CPUIF_MAP(ICH_HCR, ICH_HCR_EL2) -CPUIF_MAP(ICH_VTR, ICH_VTR_EL2) -CPUIF_MAP(ICH_MISR, ICH_MISR_EL2) -CPUIF_MAP(ICH_EISR, ICH_EISR_EL2) -CPUIF_MAP(ICH_ELRSR, ICH_ELRSR_EL2) -CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2) -CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2) -CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2) -CPUIF_MAP(ICH_AP0R1, ICH_AP0R1_EL2) -CPUIF_MAP(ICH_AP0R0, ICH_AP0R0_EL2) -CPUIF_MAP(ICH_AP1R3, ICH_AP1R3_EL2) -CPUIF_MAP(ICH_AP1R2, ICH_AP1R2_EL2) -CPUIF_MAP(ICH_AP1R1, ICH_AP1R1_EL2) -CPUIF_MAP(ICH_AP1R0, ICH_AP1R0_EL2) -CPUIF_MAP(ICC_HSRE, ICC_SRE_EL2) -CPUIF_MAP(ICC_SRE, ICC_SRE_EL1) - -CPUIF_MAP_LO_HI(ICH_LR15, ICH_LRC15, ICH_LR15_EL2) -CPUIF_MAP_LO_HI(ICH_LR14, ICH_LRC14, ICH_LR14_EL2) -CPUIF_MAP_LO_HI(ICH_LR13, ICH_LRC13, ICH_LR13_EL2) -CPUIF_MAP_LO_HI(ICH_LR12, ICH_LRC12, ICH_LR12_EL2) -CPUIF_MAP_LO_HI(ICH_LR11, ICH_LRC11, ICH_LR11_EL2) -CPUIF_MAP_LO_HI(ICH_LR10, ICH_LRC10, ICH_LR10_EL2) -CPUIF_MAP_LO_HI(ICH_LR9, ICH_LRC9, ICH_LR9_EL2) -CPUIF_MAP_LO_HI(ICH_LR8, ICH_LRC8, ICH_LR8_EL2) -CPUIF_MAP_LO_HI(ICH_LR7, ICH_LRC7, ICH_LR7_EL2) -CPUIF_MAP_LO_HI(ICH_LR6, ICH_LRC6, ICH_LR6_EL2) -CPUIF_MAP_LO_HI(ICH_LR5, ICH_LRC5, ICH_LR5_EL2) -CPUIF_MAP_LO_HI(ICH_LR4, ICH_LRC4, ICH_LR4_EL2) -CPUIF_MAP_LO_HI(ICH_LR3, ICH_LRC3, ICH_LR3_EL2) -CPUIF_MAP_LO_HI(ICH_LR2, ICH_LRC2, ICH_LR2_EL2) -CPUIF_MAP_LO_HI(ICH_LR1, ICH_LRC1, ICH_LR1_EL2) -CPUIF_MAP_LO_HI(ICH_LR0, ICH_LRC0, ICH_LR0_EL2) - #define read_gicreg(r) read_##r() #define write_gicreg(v, r) write_##r(v) diff --git a/arch/arm/include/asm/clocksource.h b/arch/arm/include/asm/clocksource.h index 0b350a7e26f3..13651c731a81 100644 --- a/arch/arm/include/asm/clocksource.h +++ b/arch/arm/include/asm/clocksource.h @@ -1,8 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_CLOCKSOURCE_H #define _ASM_CLOCKSOURCE_H -struct arch_clocksource_data { - bool vdso_direct; /* Usable for direct VDSO access? */ -}; +#include <asm/vdso/clocksource.h> -#endif +#endif /* _ASM_CLOCKSOURCE_H */ diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index d2453e2d3f1f..a54230e65647 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -50,25 +50,7 @@ #ifdef CONFIG_CPU_CP15 -#define __ACCESS_CP15(CRn, Op1, CRm, Op2) \ - "mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32 -#define __ACCESS_CP15_64(Op1, CRm) \ - "mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64 - -#define __read_sysreg(r, w, c, t) ({ \ - t __val; \ - asm volatile(r " " c : "=r" (__val)); \ - __val; \ -}) -#define read_sysreg(...) __read_sysreg(__VA_ARGS__) - -#define __write_sysreg(v, r, w, c, t) asm volatile(w " " c : : "r" ((t)(v))) -#define write_sysreg(v, ...) __write_sysreg(v, __VA_ARGS__) - -#define BPIALL __ACCESS_CP15(c7, 0, c5, 6) -#define ICIALLU __ACCESS_CP15(c7, 0, c5, 0) - -#define CNTVCT __ACCESS_CP15_64(1, c14) +#include <asm/vdso/cp15.h> extern unsigned long cr_alignment; /* defined in entry-armv.S */ 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_arm.h b/arch/arm/include/asm/kvm_arm.h deleted file mode 100644 index 9c04bd810d07..000000000000 --- a/arch/arm/include/asm/kvm_arm.h +++ /dev/null @@ -1,239 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_ARM_H__ -#define __ARM_KVM_ARM_H__ - -#include <linux/const.h> -#include <linux/types.h> - -/* Hyp Configuration Register (HCR) bits */ -#define HCR_TGE (1 << 27) -#define HCR_TVM (1 << 26) -#define HCR_TTLB (1 << 25) -#define HCR_TPU (1 << 24) -#define HCR_TPC (1 << 23) -#define HCR_TSW (1 << 22) -#define HCR_TAC (1 << 21) -#define HCR_TIDCP (1 << 20) -#define HCR_TSC (1 << 19) -#define HCR_TID3 (1 << 18) -#define HCR_TID2 (1 << 17) -#define HCR_TID1 (1 << 16) -#define HCR_TID0 (1 << 15) -#define HCR_TWE (1 << 14) -#define HCR_TWI (1 << 13) -#define HCR_DC (1 << 12) -#define HCR_BSU (3 << 10) -#define HCR_BSU_IS (1 << 10) -#define HCR_FB (1 << 9) -#define HCR_VA (1 << 8) -#define HCR_VI (1 << 7) -#define HCR_VF (1 << 6) -#define HCR_AMO (1 << 5) -#define HCR_IMO (1 << 4) -#define HCR_FMO (1 << 3) -#define HCR_PTW (1 << 2) -#define HCR_SWIO (1 << 1) -#define HCR_VM 1 - -/* - * The bits we set in HCR: - * TAC: Trap ACTLR - * TSC: Trap SMC - * TVM: Trap VM ops (until MMU and caches are on) - * TSW: Trap cache operations by set/way - * TWI: Trap WFI - * TWE: Trap WFE - * TIDCP: Trap L2CTLR/L2ECTLR - * BSU_IS: Upgrade barriers to the inner shareable domain - * FB: Force broadcast of all maintainance operations - * AMO: Override CPSR.A and enable signaling with VA - * IMO: Override CPSR.I and enable signaling with VI - * FMO: Override CPSR.F and enable signaling with VF - * SWIO: Turn set/way invalidates into set/way clean+invalidate - */ -#define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ - HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ - HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP) - -/* System Control Register (SCTLR) bits */ -#define SCTLR_TE (1 << 30) -#define SCTLR_EE (1 << 25) -#define SCTLR_V (1 << 13) - -/* Hyp System Control Register (HSCTLR) bits */ -#define HSCTLR_TE (1 << 30) -#define HSCTLR_EE (1 << 25) -#define HSCTLR_FI (1 << 21) -#define HSCTLR_WXN (1 << 19) -#define HSCTLR_I (1 << 12) -#define HSCTLR_C (1 << 2) -#define HSCTLR_A (1 << 1) -#define HSCTLR_M 1 -#define HSCTLR_MASK (HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I | \ - HSCTLR_WXN | HSCTLR_FI | HSCTLR_EE | HSCTLR_TE) - -/* TTBCR and HTCR Registers bits */ -#define TTBCR_EAE (1 << 31) -#define TTBCR_IMP (1 << 30) -#define TTBCR_SH1 (3 << 28) -#define TTBCR_ORGN1 (3 << 26) -#define TTBCR_IRGN1 (3 << 24) -#define TTBCR_EPD1 (1 << 23) -#define TTBCR_A1 (1 << 22) -#define TTBCR_T1SZ (7 << 16) -#define TTBCR_SH0 (3 << 12) -#define TTBCR_ORGN0 (3 << 10) -#define TTBCR_IRGN0 (3 << 8) -#define TTBCR_EPD0 (1 << 7) -#define TTBCR_T0SZ (7 << 0) -#define HTCR_MASK (TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0) - -/* Hyp System Trap Register */ -#define HSTR_T(x) (1 << x) -#define HSTR_TTEE (1 << 16) -#define HSTR_TJDBX (1 << 17) - -/* Hyp Coprocessor Trap Register */ -#define HCPTR_TCP(x) (1 << x) -#define HCPTR_TCP_MASK (0x3fff) -#define HCPTR_TASE (1 << 15) -#define HCPTR_TTA (1 << 20) -#define HCPTR_TCPAC (1 << 31) - -/* Hyp Debug Configuration Register bits */ -#define HDCR_TDRA (1 << 11) -#define HDCR_TDOSA (1 << 10) -#define HDCR_TDA (1 << 9) -#define HDCR_TDE (1 << 8) -#define HDCR_HPME (1 << 7) -#define HDCR_TPM (1 << 6) -#define HDCR_TPMCR (1 << 5) -#define HDCR_HPMN_MASK (0x1F) - -/* - * The architecture supports 40-bit IPA as input to the 2nd stage translations - * and PTRS_PER_S2_PGD becomes 1024, because each entry covers 1GB of address - * space. - */ -#define KVM_PHYS_SHIFT (40) - -#define PTRS_PER_S2_PGD (_AC(1, ULL) << (KVM_PHYS_SHIFT - 30)) - -/* Virtualization Translation Control Register (VTCR) bits */ -#define VTCR_SH0 (3 << 12) -#define VTCR_ORGN0 (3 << 10) -#define VTCR_IRGN0 (3 << 8) -#define VTCR_SL0 (3 << 6) -#define VTCR_S (1 << 4) -#define VTCR_T0SZ (0xf) -#define VTCR_MASK (VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0 | VTCR_SL0 | \ - VTCR_S | VTCR_T0SZ) -#define VTCR_HTCR_SH (VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0) -#define VTCR_SL_L2 (0 << 6) /* Starting-level: 2 */ -#define VTCR_SL_L1 (1 << 6) /* Starting-level: 1 */ -#define KVM_VTCR_SL0 VTCR_SL_L1 -/* stage-2 input address range defined as 2^(32-T0SZ) */ -#define KVM_T0SZ (32 - KVM_PHYS_SHIFT) -#define KVM_VTCR_T0SZ (KVM_T0SZ & VTCR_T0SZ) -#define KVM_VTCR_S ((KVM_VTCR_T0SZ << 1) & VTCR_S) - -/* Virtualization Translation Table Base Register (VTTBR) bits */ -#if KVM_VTCR_SL0 == VTCR_SL_L2 /* see ARM DDI 0406C: B4-1720 */ -#define VTTBR_X (14 - KVM_T0SZ) -#else -#define VTTBR_X (5 - KVM_T0SZ) -#endif -#define VTTBR_CNP_BIT _AC(1, UL) -#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X) -#define VTTBR_VMID_SHIFT _AC(48, ULL) -#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) - -/* Hyp Syndrome Register (HSR) bits */ -#define HSR_EC_SHIFT (26) -#define HSR_EC (_AC(0x3f, UL) << HSR_EC_SHIFT) -#define HSR_IL (_AC(1, UL) << 25) -#define HSR_ISS (HSR_IL - 1) -#define HSR_ISV_SHIFT (24) -#define HSR_ISV (_AC(1, UL) << HSR_ISV_SHIFT) -#define HSR_SRT_SHIFT (16) -#define HSR_SRT_MASK (0xf << HSR_SRT_SHIFT) -#define HSR_CM (1 << 8) -#define HSR_FSC (0x3f) -#define HSR_FSC_TYPE (0x3c) -#define HSR_SSE (1 << 21) -#define HSR_WNR (1 << 6) -#define HSR_CV_SHIFT (24) -#define HSR_CV (_AC(1, UL) << HSR_CV_SHIFT) -#define HSR_COND_SHIFT (20) -#define HSR_COND (_AC(0xf, UL) << HSR_COND_SHIFT) - -#define FSC_FAULT (0x04) -#define FSC_ACCESS (0x08) -#define FSC_PERM (0x0c) -#define FSC_SEA (0x10) -#define FSC_SEA_TTW0 (0x14) -#define FSC_SEA_TTW1 (0x15) -#define FSC_SEA_TTW2 (0x16) -#define FSC_SEA_TTW3 (0x17) -#define FSC_SECC (0x18) -#define FSC_SECC_TTW0 (0x1c) -#define FSC_SECC_TTW1 (0x1d) -#define FSC_SECC_TTW2 (0x1e) -#define FSC_SECC_TTW3 (0x1f) - -/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ -#define HPFAR_MASK (~0xf) - -#define HSR_EC_UNKNOWN (0x00) -#define HSR_EC_WFI (0x01) -#define HSR_EC_CP15_32 (0x03) -#define HSR_EC_CP15_64 (0x04) -#define HSR_EC_CP14_MR (0x05) -#define HSR_EC_CP14_LS (0x06) -#define HSR_EC_CP_0_13 (0x07) -#define HSR_EC_CP10_ID (0x08) -#define HSR_EC_JAZELLE (0x09) -#define HSR_EC_BXJ (0x0A) -#define HSR_EC_CP14_64 (0x0C) -#define HSR_EC_SVC_HYP (0x11) -#define HSR_EC_HVC (0x12) -#define HSR_EC_SMC (0x13) -#define HSR_EC_IABT (0x20) -#define HSR_EC_IABT_HYP (0x21) -#define HSR_EC_DABT (0x24) -#define HSR_EC_DABT_HYP (0x25) -#define HSR_EC_MAX (0x3f) - -#define HSR_WFI_IS_WFE (_AC(1, UL) << 0) - -#define HSR_HVC_IMM_MASK ((_AC(1, UL) << 16) - 1) - -#define HSR_DABT_S1PTW (_AC(1, UL) << 7) -#define HSR_DABT_CM (_AC(1, UL) << 8) - -#define kvm_arm_exception_type \ - {0, "RESET" }, \ - {1, "UNDEFINED" }, \ - {2, "SOFTWARE" }, \ - {3, "PREF_ABORT" }, \ - {4, "DATA_ABORT" }, \ - {5, "IRQ" }, \ - {6, "FIQ" }, \ - {7, "HVC" } - -#define HSRECN(x) { HSR_EC_##x, #x } - -#define kvm_arm_exception_class \ - HSRECN(UNKNOWN), HSRECN(WFI), HSRECN(CP15_32), HSRECN(CP15_64), \ - HSRECN(CP14_MR), HSRECN(CP14_LS), HSRECN(CP_0_13), HSRECN(CP10_ID), \ - HSRECN(JAZELLE), HSRECN(BXJ), HSRECN(CP14_64), HSRECN(SVC_HYP), \ - HSRECN(HVC), HSRECN(SMC), HSRECN(IABT), HSRECN(IABT_HYP), \ - HSRECN(DABT), HSRECN(DABT_HYP) - - -#endif /* __ARM_KVM_ARM_H__ */ diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h deleted file mode 100644 index f615830f9f57..000000000000 --- a/arch/arm/include/asm/kvm_asm.h +++ /dev/null @@ -1,77 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_ASM_H__ -#define __ARM_KVM_ASM_H__ - -#include <asm/virt.h> - -#define ARM_EXIT_WITH_ABORT_BIT 31 -#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_ABORT_BIT)) -#define ARM_EXCEPTION_IS_TRAP(x) \ - (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_PREF_ABORT || \ - ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_DATA_ABORT || \ - ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_HVC) -#define ARM_ABORT_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_ABORT_BIT)) - -#define ARM_EXCEPTION_RESET 0 -#define ARM_EXCEPTION_UNDEFINED 1 -#define ARM_EXCEPTION_SOFTWARE 2 -#define ARM_EXCEPTION_PREF_ABORT 3 -#define ARM_EXCEPTION_DATA_ABORT 4 -#define ARM_EXCEPTION_IRQ 5 -#define ARM_EXCEPTION_FIQ 6 -#define ARM_EXCEPTION_HVC 7 -#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR -/* - * The rr_lo_hi macro swaps a pair of registers depending on - * current endianness. It is used in conjunction with ldrd and strd - * instructions that load/store a 64-bit value from/to memory to/from - * a pair of registers which are used with the mrrc and mcrr instructions. - * If used with the ldrd/strd instructions, the a1 parameter is the first - * source/destination register and the a2 parameter is the second - * source/destination register. Note that the ldrd/strd instructions - * already swap the bytes within the words correctly according to the - * endianness setting, but the order of the registers need to be effectively - * swapped when used with the mrrc/mcrr instructions. - */ -#ifdef CONFIG_CPU_ENDIAN_BE8 -#define rr_lo_hi(a1, a2) a2, a1 -#else -#define rr_lo_hi(a1, a2) a1, a2 -#endif - -#define kvm_ksym_ref(kva) (kva) - -#ifndef __ASSEMBLY__ -struct kvm; -struct kvm_vcpu; - -extern char __kvm_hyp_init[]; -extern char __kvm_hyp_init_end[]; - -extern void __kvm_flush_vm_context(void); -extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); -extern void __kvm_tlb_flush_vmid(struct kvm *kvm); -extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu); - -extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high); - -/* no VHE on 32-bit :( */ -static inline int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { BUG(); return 0; } - -extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu); - -extern void __init_stage2_translation(void); - -extern u64 __vgic_v3_get_ich_vtr_el2(void); -extern u64 __vgic_v3_read_vmcr(void); -extern void __vgic_v3_write_vmcr(u32 vmcr); -extern void __vgic_v3_init_lrs(void); - -#endif - -#endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm/include/asm/kvm_coproc.h b/arch/arm/include/asm/kvm_coproc.h deleted file mode 100644 index a23826117dd6..000000000000 --- a/arch/arm/include/asm/kvm_coproc.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 Rusty Russell IBM Corporation - */ - -#ifndef __ARM_KVM_COPROC_H__ -#define __ARM_KVM_COPROC_H__ -#include <linux/kvm_host.h> - -void kvm_reset_coprocs(struct kvm_vcpu *vcpu); - -struct kvm_coproc_target_table { - unsigned target; - const struct coproc_reg *table; - size_t num; -}; -void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table); - -int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run); - -unsigned long kvm_arm_num_guest_msrs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_msrindices(struct kvm_vcpu *vcpu, u64 __user *uindices); -void kvm_coproc_table_init(void); - -struct kvm_one_reg; -int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu); -#endif /* __ARM_KVM_COPROC_H__ */ diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h deleted file mode 100644 index 3944305e81df..000000000000 --- a/arch/arm/include/asm/kvm_emulate.h +++ /dev/null @@ -1,372 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_EMULATE_H__ -#define __ARM_KVM_EMULATE_H__ - -#include <linux/kvm_host.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_arm.h> -#include <asm/cputype.h> - -/* arm64 compatibility macros */ -#define PSR_AA32_MODE_FIQ FIQ_MODE -#define PSR_AA32_MODE_SVC SVC_MODE -#define PSR_AA32_MODE_ABT ABT_MODE -#define PSR_AA32_MODE_UND UND_MODE -#define PSR_AA32_T_BIT PSR_T_BIT -#define PSR_AA32_F_BIT PSR_F_BIT -#define PSR_AA32_I_BIT PSR_I_BIT -#define PSR_AA32_A_BIT PSR_A_BIT -#define PSR_AA32_E_BIT PSR_E_BIT -#define PSR_AA32_IT_MASK PSR_IT_MASK -#define PSR_AA32_GE_MASK 0x000f0000 -#define PSR_AA32_DIT_BIT 0x00200000 -#define PSR_AA32_PAN_BIT 0x00400000 -#define PSR_AA32_SSBS_BIT 0x00800000 -#define PSR_AA32_Q_BIT PSR_Q_BIT -#define PSR_AA32_V_BIT PSR_V_BIT -#define PSR_AA32_C_BIT PSR_C_BIT -#define PSR_AA32_Z_BIT PSR_Z_BIT -#define PSR_AA32_N_BIT PSR_N_BIT - -unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); - -static inline unsigned long *vcpu_reg32(struct kvm_vcpu *vcpu, u8 reg_num) -{ - return vcpu_reg(vcpu, reg_num); -} - -unsigned long *__vcpu_spsr(struct kvm_vcpu *vcpu); - -static inline unsigned long vpcu_read_spsr(struct kvm_vcpu *vcpu) -{ - return *__vcpu_spsr(vcpu); -} - -static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) -{ - *__vcpu_spsr(vcpu) = v; -} - -static inline unsigned long host_spsr_to_spsr32(unsigned long spsr) -{ - return spsr; -} - -static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu, - u8 reg_num) -{ - return *vcpu_reg(vcpu, reg_num); -} - -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, - unsigned long val) -{ - *vcpu_reg(vcpu, reg_num) = val; -} - -bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); -void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr); -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); -void kvm_inject_vabt(struct kvm_vcpu *vcpu); - -static inline void kvm_inject_undefined(struct kvm_vcpu *vcpu) -{ - kvm_inject_undef32(vcpu); -} - -static inline void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) -{ - kvm_inject_dabt32(vcpu, addr); -} - -static inline void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) -{ - kvm_inject_pabt32(vcpu, addr); -} - -static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) -{ - return kvm_condition_valid32(vcpu); -} - -static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) -{ - kvm_skip_instr32(vcpu, is_wide_instr); -} - -static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr = HCR_GUEST_MASK; -} - -static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu) -{ - return (unsigned long *)&vcpu->arch.hcr; -} - -static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr &= ~HCR_TWE; -} - -static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr |= HCR_TWE; -} - -static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) -{ - return true; -} - -static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu) -{ - return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_pc; -} - -static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) -{ - return (unsigned long *)&vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr; -} - -static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) -{ - *vcpu_cpsr(vcpu) |= PSR_T_BIT; -} - -static inline bool mode_has_spsr(struct kvm_vcpu *vcpu) -{ - unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK; - return (cpsr_mode > USR_MODE && cpsr_mode < SYSTEM_MODE); -} - -static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu) -{ - unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK; - return cpsr_mode > USR_MODE; -} - -static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) -{ - return vcpu->arch.fault.hsr; -} - -static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) -{ - u32 hsr = kvm_vcpu_get_hsr(vcpu); - - if (hsr & HSR_CV) - return (hsr & HSR_COND) >> HSR_COND_SHIFT; - - return -1; -} - -static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.fault.hxfar; -} - -static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu) -{ - return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8; -} - -static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_ISV; -} - -static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & (HSR_CM | HSR_WNR | HSR_FSC); -} - -static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_WNR; -} - -static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_SSE; -} - -static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu) -{ - return false; -} - -static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) -{ - return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; -} - -static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; -} - -static inline bool kvm_vcpu_dabt_is_cm(struct kvm_vcpu *vcpu) -{ - return !!(kvm_vcpu_get_hsr(vcpu) & HSR_DABT_CM); -} - -/* Get Access Size from a data abort */ -static inline unsigned int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu) -{ - switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) { - case 0: - return 1; - case 1: - return 2; - case 2: - return 4; - default: - kvm_err("Hardware is weird: SAS 0b11 is reserved\n"); - return 4; - } -} - -/* This one is not specific to Data Abort */ -static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_IL; -} - -static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; -} - -static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; -} - -static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_FSC; -} - -static inline u8 kvm_vcpu_trap_get_fault_type(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE; -} - -static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu) -{ - switch (kvm_vcpu_trap_get_fault(vcpu)) { - case FSC_SEA: - case FSC_SEA_TTW0: - case FSC_SEA_TTW1: - case FSC_SEA_TTW2: - case FSC_SEA_TTW3: - case FSC_SECC: - case FSC_SECC_TTW0: - case FSC_SECC_TTW1: - case FSC_SECC_TTW2: - case FSC_SECC_TTW3: - return true; - default: - return false; - } -} - -static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) -{ - if (kvm_vcpu_trap_is_iabt(vcpu)) - return false; - - return kvm_vcpu_dabt_iswrite(vcpu); -} - -static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; -} - -static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) -{ - return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK; -} - -static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu) -{ - return false; -} - -static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu, - bool flag) -{ -} - -static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) -{ - *vcpu_cpsr(vcpu) |= PSR_E_BIT; -} - -static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) -{ - return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT); -} - -static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, - unsigned long data, - unsigned int len) -{ - if (kvm_vcpu_is_be(vcpu)) { - switch (len) { - case 1: - return data & 0xff; - case 2: - return be16_to_cpu(data & 0xffff); - default: - return be32_to_cpu(data); - } - } else { - switch (len) { - case 1: - return data & 0xff; - case 2: - return le16_to_cpu(data & 0xffff); - default: - return le32_to_cpu(data); - } - } -} - -static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, - unsigned long data, - unsigned int len) -{ - if (kvm_vcpu_is_be(vcpu)) { - switch (len) { - case 1: - return data & 0xff; - case 2: - return cpu_to_be16(data & 0xffff); - default: - return cpu_to_be32(data); - } - } else { - switch (len) { - case 1: - return data & 0xff; - case 2: - return cpu_to_le16(data & 0xffff); - default: - return cpu_to_le32(data); - } - } -} - -static inline void vcpu_ptrauth_setup_lazy(struct kvm_vcpu *vcpu) {} - -#endif /* __ARM_KVM_EMULATE_H__ */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h deleted file mode 100644 index c3314b286a61..000000000000 --- a/arch/arm/include/asm/kvm_host.h +++ /dev/null @@ -1,459 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_HOST_H__ -#define __ARM_KVM_HOST_H__ - -#include <linux/arm-smccc.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/kvm_types.h> -#include <asm/cputype.h> -#include <asm/kvm.h> -#include <asm/kvm_asm.h> -#include <asm/fpstate.h> -#include <kvm/arm_arch_timer.h> - -#define __KVM_HAVE_ARCH_INTC_INITIALIZED - -#define KVM_USER_MEM_SLOTS 32 -#define KVM_HAVE_ONE_REG -#define KVM_HALT_POLL_NS_DEFAULT 500000 - -#define KVM_VCPU_MAX_FEATURES 2 - -#include <kvm/arm_vgic.h> - - -#ifdef CONFIG_ARM_GIC_V3 -#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS -#else -#define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS -#endif - -#define KVM_REQ_SLEEP \ - KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) -#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) -#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) - -DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); - -static inline int kvm_arm_init_sve(void) { return 0; } - -u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); -int __attribute_const__ kvm_target_cpu(void); -int kvm_reset_vcpu(struct kvm_vcpu *vcpu); -void kvm_reset_coprocs(struct kvm_vcpu *vcpu); - -struct kvm_vmid { - /* The VMID generation used for the virt. memory system */ - u64 vmid_gen; - u32 vmid; -}; - -struct kvm_arch { - /* The last vcpu id that ran on each physical CPU */ - int __percpu *last_vcpu_ran; - - /* - * Anything that is not used directly from assembly code goes - * here. - */ - - /* The VMID generation used for the virt. memory system */ - struct kvm_vmid vmid; - - /* Stage-2 page table */ - pgd_t *pgd; - phys_addr_t pgd_phys; - - /* Interrupt controller */ - struct vgic_dist vgic; - int max_vcpus; - - /* Mandated version of PSCI */ - u32 psci_version; - - /* - * If we encounter a data abort without valid instruction syndrome - * information, report this to user space. User space can (and - * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is - * supported. - */ - bool return_nisv_io_abort_to_user; -}; - -#define KVM_NR_MEM_OBJS 40 - -/* - * We don't want allocation failures within the mmu code, so we preallocate - * enough memory for a single page fault in a cache. - */ -struct kvm_mmu_memory_cache { - int nobjs; - void *objects[KVM_NR_MEM_OBJS]; -}; - -struct kvm_vcpu_fault_info { - u32 hsr; /* Hyp Syndrome Register */ - u32 hxfar; /* Hyp Data/Inst. Fault Address Register */ - u32 hpfar; /* Hyp IPA Fault Address Register */ -}; - -/* - * 0 is reserved as an invalid value. - * Order should be kept in sync with the save/restore code. - */ -enum vcpu_sysreg { - __INVALID_SYSREG__, - c0_MPIDR, /* MultiProcessor ID Register */ - c0_CSSELR, /* Cache Size Selection Register */ - c1_SCTLR, /* System Control Register */ - c1_ACTLR, /* Auxiliary Control Register */ - c1_CPACR, /* Coprocessor Access Control */ - c2_TTBR0, /* Translation Table Base Register 0 */ - c2_TTBR0_high, /* TTBR0 top 32 bits */ - c2_TTBR1, /* Translation Table Base Register 1 */ - c2_TTBR1_high, /* TTBR1 top 32 bits */ - c2_TTBCR, /* Translation Table Base Control R. */ - c3_DACR, /* Domain Access Control Register */ - c5_DFSR, /* Data Fault Status Register */ - c5_IFSR, /* Instruction Fault Status Register */ - c5_ADFSR, /* Auxilary Data Fault Status R */ - c5_AIFSR, /* Auxilary Instrunction Fault Status R */ - c6_DFAR, /* Data Fault Address Register */ - c6_IFAR, /* Instruction Fault Address Register */ - c7_PAR, /* Physical Address Register */ - c7_PAR_high, /* PAR top 32 bits */ - c9_L2CTLR, /* Cortex A15/A7 L2 Control Register */ - c10_PRRR, /* Primary Region Remap Register */ - c10_NMRR, /* Normal Memory Remap Register */ - c12_VBAR, /* Vector Base Address Register */ - c13_CID, /* Context ID Register */ - c13_TID_URW, /* Thread ID, User R/W */ - c13_TID_URO, /* Thread ID, User R/O */ - c13_TID_PRIV, /* Thread ID, Privileged */ - c14_CNTKCTL, /* Timer Control Register (PL1) */ - c10_AMAIR0, /* Auxilary Memory Attribute Indirection Reg0 */ - c10_AMAIR1, /* Auxilary Memory Attribute Indirection Reg1 */ - NR_CP15_REGS /* Number of regs (incl. invalid) */ -}; - -struct kvm_cpu_context { - struct kvm_regs gp_regs; - struct vfp_hard_struct vfp; - u32 cp15[NR_CP15_REGS]; -}; - -struct kvm_host_data { - struct kvm_cpu_context host_ctxt; -}; - -typedef struct kvm_host_data kvm_host_data_t; - -static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) -{ - /* The host's MPIDR is immutable, so let's set it up at boot time */ - cpu_ctxt->cp15[c0_MPIDR] = read_cpuid_mpidr(); -} - -struct vcpu_reset_state { - unsigned long pc; - unsigned long r0; - bool be; - bool reset; -}; - -struct kvm_vcpu_arch { - struct kvm_cpu_context ctxt; - - int target; /* Processor target */ - DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); - - /* The CPU type we expose to the VM */ - u32 midr; - - /* HYP trapping configuration */ - u32 hcr; - - /* Exception Information */ - struct kvm_vcpu_fault_info fault; - - /* Host FP context */ - struct kvm_cpu_context *host_cpu_context; - - /* VGIC state */ - struct vgic_cpu vgic_cpu; - struct arch_timer_cpu timer_cpu; - - /* - * Anything that is not used directly from assembly code goes - * here. - */ - - /* vcpu power-off state */ - bool power_off; - - /* Don't run the guest (internal implementation need) */ - bool pause; - - /* Cache some mmu pages needed inside spinlock regions */ - struct kvm_mmu_memory_cache mmu_page_cache; - - struct vcpu_reset_state reset_state; - - /* Detect first run of a vcpu */ - bool has_run_once; -}; - -struct kvm_vm_stat { - ulong remote_tlb_flush; -}; - -struct kvm_vcpu_stat { - u64 halt_successful_poll; - u64 halt_attempted_poll; - u64 halt_poll_invalid; - u64 halt_wakeup; - u64 hvc_exit_stat; - u64 wfe_exit_stat; - u64 wfi_exit_stat; - u64 mmio_exit_user; - u64 mmio_exit_kernel; - u64 exits; -}; - -#define vcpu_cp15(v,r) (v)->arch.ctxt.cp15[r] - -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); -unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); -int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); - -unsigned long __kvm_call_hyp(void *hypfn, ...); - -/* - * The has_vhe() part doesn't get emitted, but is used for type-checking. - */ -#define kvm_call_hyp(f, ...) \ - do { \ - if (has_vhe()) { \ - f(__VA_ARGS__); \ - } else { \ - __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \ - } \ - } while(0) - -#define kvm_call_hyp_ret(f, ...) \ - ({ \ - typeof(f(__VA_ARGS__)) ret; \ - \ - if (has_vhe()) { \ - ret = f(__VA_ARGS__); \ - } else { \ - ret = __kvm_call_hyp(kvm_ksym_ref(f), \ - ##__VA_ARGS__); \ - } \ - \ - ret; \ - }) - -void force_vm_exit(const cpumask_t *mask); -int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events); - -int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events); - -#define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); -int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); - -unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); -int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); -int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); - -void kvm_arm_halt_guest(struct kvm *kvm); -void kvm_arm_resume_guest(struct kvm *kvm); - -int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu); -int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); - -int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index); - -static inline void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index) {} - -/* MMIO helpers */ -void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); -unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); - -int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); -int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, - phys_addr_t fault_ipa); - -static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, - unsigned long hyp_stack_ptr, - unsigned long vector_ptr) -{ - /* - * Call initialization code, and switch to the full blown HYP - * code. The init code doesn't need to preserve these - * registers as r0-r3 are already callee saved according to - * the AAPCS. - * Note that we slightly misuse the prototype by casting the - * stack pointer to a void *. - - * The PGDs are always passed as the third argument, in order - * to be passed into r2-r3 to the init code (yes, this is - * compliant with the PCS!). - */ - - __kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr); -} - -static inline void __cpu_init_stage2(void) -{ - kvm_call_hyp(__init_stage2_translation); -} - -static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) -{ - return 0; -} - -int kvm_perf_init(void); -int kvm_perf_teardown(void); - -static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) -{ - return SMCCC_RET_NOT_SUPPORTED; -} - -static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) -{ - return GPA_INVALID; -} - -static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu) -{ -} - -static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) -{ -} - -static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) -{ - return false; -} - -void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); - -struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); - -static inline bool kvm_arch_requires_vhe(void) { return false; } -static inline void kvm_arch_hardware_unsetup(void) {} -static inline void kvm_arch_sync_events(struct kvm *kvm) {} -static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) {} - -static inline void kvm_arm_init_debug(void) {} -static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {} - -int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr); -int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr); -int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr); - -/* - * VFP/NEON switching is all done by the hyp switch code, so no need to - * coordinate with host context handling for this state: - */ -static inline void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) {} -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 - -static inline int kvm_arm_harden_branch_predictor(void) -{ - switch(read_cpuid_part()) { -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR - case ARM_CPU_PART_BRAHMA_B15: - case ARM_CPU_PART_CORTEX_A12: - case ARM_CPU_PART_CORTEX_A15: - case ARM_CPU_PART_CORTEX_A17: - return KVM_BP_HARDEN_WA_NEEDED; -#endif - case ARM_CPU_PART_CORTEX_A7: - return KVM_BP_HARDEN_NOT_REQUIRED; - default: - return KVM_BP_HARDEN_UNKNOWN; - } -} - -#define KVM_SSBD_UNKNOWN -1 -#define KVM_SSBD_FORCE_DISABLE 0 -#define KVM_SSBD_KERNEL 1 -#define KVM_SSBD_FORCE_ENABLE 2 -#define KVM_SSBD_MITIGATED 3 - -static inline int kvm_arm_have_ssbd(void) -{ - /* No way to detect it yet, pretend it is not there. */ - return KVM_SSBD_UNKNOWN; -} - -static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {} -static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {} - -#define __KVM_HAVE_ARCH_VM_ALLOC -struct kvm *kvm_arch_alloc_vm(void); -void kvm_arch_free_vm(struct kvm *kvm); - -static inline int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type) -{ - /* - * On 32bit ARM, VMs get a static 40bit IPA stage2 setup, - * so any non-zero value used as type is illegal. - */ - if (type) - return -EINVAL; - return 0; -} - -static inline int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature) -{ - return -EINVAL; -} - -static inline bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) -{ - return true; -} - -#endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h deleted file mode 100644 index 3c1b55ecc578..000000000000 --- a/arch/arm/include/asm/kvm_hyp.h +++ /dev/null @@ -1,127 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#ifndef __ARM_KVM_HYP_H__ -#define __ARM_KVM_HYP_H__ - -#include <linux/compiler.h> -#include <linux/kvm_host.h> -#include <asm/cp15.h> -#include <asm/kvm_arm.h> -#include <asm/vfp.h> - -#define __hyp_text __section(.hyp.text) notrace - -#define __ACCESS_VFP(CRn) \ - "mrc", "mcr", __stringify(p10, 7, %0, CRn, cr0, 0), u32 - -#define write_special(v, r) \ - asm volatile("msr " __stringify(r) ", %0" : : "r" (v)) -#define read_special(r) ({ \ - u32 __val; \ - asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ - __val; \ -}) - -#define TTBR0 __ACCESS_CP15_64(0, c2) -#define TTBR1 __ACCESS_CP15_64(1, c2) -#define VTTBR __ACCESS_CP15_64(6, c2) -#define PAR __ACCESS_CP15_64(0, c7) -#define CNTP_CVAL __ACCESS_CP15_64(2, c14) -#define CNTV_CVAL __ACCESS_CP15_64(3, c14) -#define CNTVOFF __ACCESS_CP15_64(4, c14) - -#define MIDR __ACCESS_CP15(c0, 0, c0, 0) -#define CSSELR __ACCESS_CP15(c0, 2, c0, 0) -#define VPIDR __ACCESS_CP15(c0, 4, c0, 0) -#define VMPIDR __ACCESS_CP15(c0, 4, c0, 5) -#define SCTLR __ACCESS_CP15(c1, 0, c0, 0) -#define CPACR __ACCESS_CP15(c1, 0, c0, 2) -#define HCR __ACCESS_CP15(c1, 4, c1, 0) -#define HDCR __ACCESS_CP15(c1, 4, c1, 1) -#define HCPTR __ACCESS_CP15(c1, 4, c1, 2) -#define HSTR __ACCESS_CP15(c1, 4, c1, 3) -#define TTBCR __ACCESS_CP15(c2, 0, c0, 2) -#define HTCR __ACCESS_CP15(c2, 4, c0, 2) -#define VTCR __ACCESS_CP15(c2, 4, c1, 2) -#define DACR __ACCESS_CP15(c3, 0, c0, 0) -#define DFSR __ACCESS_CP15(c5, 0, c0, 0) -#define IFSR __ACCESS_CP15(c5, 0, c0, 1) -#define ADFSR __ACCESS_CP15(c5, 0, c1, 0) -#define AIFSR __ACCESS_CP15(c5, 0, c1, 1) -#define HSR __ACCESS_CP15(c5, 4, c2, 0) -#define DFAR __ACCESS_CP15(c6, 0, c0, 0) -#define IFAR __ACCESS_CP15(c6, 0, c0, 2) -#define HDFAR __ACCESS_CP15(c6, 4, c0, 0) -#define HIFAR __ACCESS_CP15(c6, 4, c0, 2) -#define HPFAR __ACCESS_CP15(c6, 4, c0, 4) -#define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0) -#define BPIALLIS __ACCESS_CP15(c7, 0, c1, 6) -#define ICIMVAU __ACCESS_CP15(c7, 0, c5, 1) -#define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0) -#define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0) -#define TLBIALL __ACCESS_CP15(c8, 0, c7, 0) -#define TLBIALLNSNHIS __ACCESS_CP15(c8, 4, c3, 4) -#define PRRR __ACCESS_CP15(c10, 0, c2, 0) -#define NMRR __ACCESS_CP15(c10, 0, c2, 1) -#define AMAIR0 __ACCESS_CP15(c10, 0, c3, 0) -#define AMAIR1 __ACCESS_CP15(c10, 0, c3, 1) -#define VBAR __ACCESS_CP15(c12, 0, c0, 0) -#define CID __ACCESS_CP15(c13, 0, c0, 1) -#define TID_URW __ACCESS_CP15(c13, 0, c0, 2) -#define TID_URO __ACCESS_CP15(c13, 0, c0, 3) -#define TID_PRIV __ACCESS_CP15(c13, 0, c0, 4) -#define HTPIDR __ACCESS_CP15(c13, 4, c0, 2) -#define CNTKCTL __ACCESS_CP15(c14, 0, c1, 0) -#define CNTP_CTL __ACCESS_CP15(c14, 0, c2, 1) -#define CNTV_CTL __ACCESS_CP15(c14, 0, c3, 1) -#define CNTHCTL __ACCESS_CP15(c14, 4, c1, 0) - -#define VFP_FPEXC __ACCESS_VFP(FPEXC) - -/* AArch64 compatibility macros, only for the timer so far */ -#define read_sysreg_el0(r) read_sysreg(r##_EL0) -#define write_sysreg_el0(v, r) write_sysreg(v, r##_EL0) - -#define SYS_CNTP_CTL_EL0 CNTP_CTL -#define SYS_CNTP_CVAL_EL0 CNTP_CVAL -#define SYS_CNTV_CTL_EL0 CNTV_CTL -#define SYS_CNTV_CVAL_EL0 CNTV_CVAL - -#define cntvoff_el2 CNTVOFF -#define cnthctl_el2 CNTHCTL - -void __timer_enable_traps(struct kvm_vcpu *vcpu); -void __timer_disable_traps(struct kvm_vcpu *vcpu); - -void __vgic_v2_save_state(struct kvm_vcpu *vcpu); -void __vgic_v2_restore_state(struct kvm_vcpu *vcpu); - -void __sysreg_save_state(struct kvm_cpu_context *ctxt); -void __sysreg_restore_state(struct kvm_cpu_context *ctxt); - -void __vgic_v3_save_state(struct kvm_vcpu *vcpu); -void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); -void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu); -void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu); -void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu); -void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu); - -asmlinkage void __vfp_save_state(struct vfp_hard_struct *vfp); -asmlinkage void __vfp_restore_state(struct vfp_hard_struct *vfp); -static inline bool __vfp_enabled(void) -{ - return !(read_sysreg(HCPTR) & (HCPTR_TCP(11) | HCPTR_TCP(10))); -} - -void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt); -void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt); - -asmlinkage int __guest_enter(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *host); -asmlinkage int __hyp_do_panic(const char *, int, u32); - -#endif /* __ARM_KVM_HYP_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h deleted file mode 100644 index 0d84d50bf9ba..000000000000 --- a/arch/arm/include/asm/kvm_mmu.h +++ /dev/null @@ -1,435 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_MMU_H__ -#define __ARM_KVM_MMU_H__ - -#include <asm/memory.h> -#include <asm/page.h> - -/* - * We directly use the kernel VA for the HYP, as we can directly share - * the mapping (HTTBR "covers" TTBR1). - */ -#define kern_hyp_va(kva) (kva) - -/* Contrary to arm64, there is no need to generate a PC-relative address */ -#define hyp_symbol_addr(s) \ - ({ \ - typeof(s) *addr = &(s); \ - addr; \ - }) - -#ifndef __ASSEMBLY__ - -#include <linux/highmem.h> -#include <asm/cacheflush.h> -#include <asm/cputype.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_hyp.h> -#include <asm/pgalloc.h> -#include <asm/stage2_pgtable.h> - -/* Ensure compatibility with arm64 */ -#define VA_BITS 32 - -#define kvm_phys_shift(kvm) KVM_PHYS_SHIFT -#define kvm_phys_size(kvm) (1ULL << kvm_phys_shift(kvm)) -#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - 1ULL) -#define kvm_vttbr_baddr_mask(kvm) VTTBR_BADDR_MASK - -#define stage2_pgd_size(kvm) (PTRS_PER_S2_PGD * sizeof(pgd_t)) - -int create_hyp_mappings(void *from, void *to, pgprot_t prot); -int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, - void __iomem **kaddr, - void __iomem **haddr); -int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, - void **haddr); -void free_hyp_pgds(void); - -void stage2_unmap_vm(struct kvm *kvm); -int kvm_alloc_stage2_pgd(struct kvm *kvm); -void kvm_free_stage2_pgd(struct kvm *kvm); -int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, - phys_addr_t pa, unsigned long size, bool writable); - -int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run); - -void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu); - -phys_addr_t kvm_mmu_get_httbr(void); -phys_addr_t kvm_get_idmap_vector(void); -int kvm_mmu_init(void); -void kvm_clear_hyp_idmap(void); - -#define kvm_mk_pmd(ptep) __pmd(__pa(ptep) | PMD_TYPE_TABLE) -#define kvm_mk_pud(pmdp) __pud(__pa(pmdp) | PMD_TYPE_TABLE) -#define kvm_mk_pgd(pudp) ({ BUILD_BUG(); 0; }) - -#define kvm_pfn_pte(pfn, prot) pfn_pte(pfn, prot) -#define kvm_pfn_pmd(pfn, prot) pfn_pmd(pfn, prot) -#define kvm_pfn_pud(pfn, prot) (__pud(0)) - -#define kvm_pud_pfn(pud) ({ WARN_ON(1); 0; }) - - -#define kvm_pmd_mkhuge(pmd) pmd_mkhuge(pmd) -/* No support for pud hugepages */ -#define kvm_pud_mkhuge(pud) ( {WARN_ON(1); pud; }) - -/* - * The following kvm_*pud*() functions are provided strictly to allow - * sharing code with arm64. They should never be called in practice. - */ -static inline void kvm_set_s2pud_readonly(pud_t *pud) -{ - WARN_ON(1); -} - -static inline bool kvm_s2pud_readonly(pud_t *pud) -{ - WARN_ON(1); - return false; -} - -static inline void kvm_set_pud(pud_t *pud, pud_t new_pud) -{ - WARN_ON(1); -} - -static inline pud_t kvm_s2pud_mkwrite(pud_t pud) -{ - WARN_ON(1); - return pud; -} - -static inline pud_t kvm_s2pud_mkexec(pud_t pud) -{ - WARN_ON(1); - return pud; -} - -static inline bool kvm_s2pud_exec(pud_t *pud) -{ - WARN_ON(1); - return false; -} - -static inline pud_t kvm_s2pud_mkyoung(pud_t pud) -{ - BUG(); - return pud; -} - -static inline bool kvm_s2pud_young(pud_t pud) -{ - WARN_ON(1); - return false; -} - -static inline pte_t kvm_s2pte_mkwrite(pte_t pte) -{ - pte_val(pte) |= L_PTE_S2_RDWR; - return pte; -} - -static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd) -{ - pmd_val(pmd) |= L_PMD_S2_RDWR; - return pmd; -} - -static inline pte_t kvm_s2pte_mkexec(pte_t pte) -{ - pte_val(pte) &= ~L_PTE_XN; - return pte; -} - -static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) -{ - pmd_val(pmd) &= ~PMD_SECT_XN; - return pmd; -} - -static inline void kvm_set_s2pte_readonly(pte_t *pte) -{ - pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY; -} - -static inline bool kvm_s2pte_readonly(pte_t *pte) -{ - return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY; -} - -static inline bool kvm_s2pte_exec(pte_t *pte) -{ - return !(pte_val(*pte) & L_PTE_XN); -} - -static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) -{ - pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY; -} - -static inline bool kvm_s2pmd_readonly(pmd_t *pmd) -{ - return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY; -} - -static inline bool kvm_s2pmd_exec(pmd_t *pmd) -{ - return !(pmd_val(*pmd) & PMD_SECT_XN); -} - -static inline bool kvm_page_empty(void *ptr) -{ - struct page *ptr_page = virt_to_page(ptr); - return page_count(ptr_page) == 1; -} - -#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) -#define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) -#define kvm_pud_table_empty(kvm, pudp) false - -#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep) -#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp) -#define hyp_pud_table_empty(pudp) false - -struct kvm; - -#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l)) - -static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) -{ - return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101; -} - -static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) -{ - /* - * Clean the dcache to the Point of Coherency. - * - * We need to do this through a kernel mapping (using the - * user-space mapping has proved to be the wrong - * solution). For that, we need to kmap one page at a time, - * and iterate over the range. - */ - - VM_BUG_ON(size & ~PAGE_MASK); - - while (size) { - void *va = kmap_atomic_pfn(pfn); - - kvm_flush_dcache_to_poc(va, PAGE_SIZE); - - size -= PAGE_SIZE; - pfn++; - - kunmap_atomic(va); - } -} - -static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn, - unsigned long size) -{ - u32 iclsz; - - /* - * If we are going to insert an instruction page and the icache is - * either VIPT or PIPT, there is a potential problem where the host - * (or another VM) may have used the same page as this guest, and we - * read incorrect data from the icache. If we're using a PIPT cache, - * we can invalidate just that page, but if we are using a VIPT cache - * we need to invalidate the entire icache - damn shame - as written - * in the ARM ARM (DDI 0406C.b - Page B3-1393). - * - * VIVT caches are tagged using both the ASID and the VMID and doesn't - * need any kind of flushing (DDI 0406C.b - Page B3-1392). - */ - - VM_BUG_ON(size & ~PAGE_MASK); - - if (icache_is_vivt_asid_tagged()) - return; - - if (!icache_is_pipt()) { - /* any kind of VIPT cache */ - __flush_icache_all(); - return; - } - - /* - * CTR IminLine contains Log2 of the number of words in the - * cache line, so we can get the number of words as - * 2 << (IminLine - 1). To get the number of bytes, we - * multiply by 4 (the number of bytes in a 32-bit word), and - * get 4 << (IminLine). - */ - iclsz = 4 << (read_cpuid(CPUID_CACHETYPE) & 0xf); - - while (size) { - void *va = kmap_atomic_pfn(pfn); - void *end = va + PAGE_SIZE; - void *addr = va; - - do { - write_sysreg(addr, ICIMVAU); - addr += iclsz; - } while (addr < end); - - dsb(ishst); - isb(); - - size -= PAGE_SIZE; - pfn++; - - kunmap_atomic(va); - } - - /* Check if we need to invalidate the BTB */ - if ((read_cpuid_ext(CPUID_EXT_MMFR1) >> 28) != 4) { - write_sysreg(0, BPIALLIS); - dsb(ishst); - isb(); - } -} - -static inline void __kvm_flush_dcache_pte(pte_t pte) -{ - void *va = kmap_atomic(pte_page(pte)); - - kvm_flush_dcache_to_poc(va, PAGE_SIZE); - - kunmap_atomic(va); -} - -static inline void __kvm_flush_dcache_pmd(pmd_t pmd) -{ - unsigned long size = PMD_SIZE; - kvm_pfn_t pfn = pmd_pfn(pmd); - - while (size) { - void *va = kmap_atomic_pfn(pfn); - - kvm_flush_dcache_to_poc(va, PAGE_SIZE); - - pfn++; - size -= PAGE_SIZE; - - kunmap_atomic(va); - } -} - -static inline void __kvm_flush_dcache_pud(pud_t pud) -{ -} - -#define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) - -void kvm_set_way_flush(struct kvm_vcpu *vcpu); -void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); - -static inline bool __kvm_cpu_uses_extended_idmap(void) -{ - return false; -} - -static inline unsigned long __kvm_idmap_ptrs_per_pgd(void) -{ - return PTRS_PER_PGD; -} - -static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd, - pgd_t *hyp_pgd, - pgd_t *merged_hyp_pgd, - unsigned long hyp_idmap_start) { } - -static inline unsigned int kvm_get_vmid_bits(void) -{ - return 8; -} - -/* - * We are not in the kvm->srcu critical section most of the time, so we take - * the SRCU read lock here. Since we copy the data from the user page, we - * can immediately drop the lock again. - */ -static inline int kvm_read_guest_lock(struct kvm *kvm, - gpa_t gpa, void *data, unsigned long len) -{ - int srcu_idx = srcu_read_lock(&kvm->srcu); - int ret = kvm_read_guest(kvm, gpa, data, len); - - srcu_read_unlock(&kvm->srcu, srcu_idx); - - return ret; -} - -static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, - const void *data, unsigned long len) -{ - int srcu_idx = srcu_read_lock(&kvm->srcu); - int ret = kvm_write_guest(kvm, gpa, data, len); - - srcu_read_unlock(&kvm->srcu, srcu_idx); - - return ret; -} - -static inline void *kvm_get_hyp_vector(void) -{ - switch(read_cpuid_part()) { -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR - case ARM_CPU_PART_CORTEX_A12: - case ARM_CPU_PART_CORTEX_A17: - { - extern char __kvm_hyp_vector_bp_inv[]; - return kvm_ksym_ref(__kvm_hyp_vector_bp_inv); - } - - case ARM_CPU_PART_BRAHMA_B15: - case ARM_CPU_PART_CORTEX_A15: - { - extern char __kvm_hyp_vector_ic_inv[]; - return kvm_ksym_ref(__kvm_hyp_vector_ic_inv); - } -#endif - default: - { - extern char __kvm_hyp_vector[]; - return kvm_ksym_ref(__kvm_hyp_vector); - } - } -} - -static inline int kvm_map_vectors(void) -{ - return 0; -} - -static inline int hyp_map_aux_data(void) -{ - return 0; -} - -#define kvm_phys_to_vttbr(addr) (addr) - -static inline void kvm_set_ipa_limit(void) {} - -static __always_inline u64 kvm_get_vttbr(struct kvm *kvm) -{ - struct kvm_vmid *vmid = &kvm->arch.vmid; - u64 vmid_field, baddr; - - baddr = kvm->arch.pgd_phys; - vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT; - return kvm_phys_to_vttbr(baddr) | vmid_field; -} - -#endif /* !__ASSEMBLY__ */ - -#endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/kvm_ras.h b/arch/arm/include/asm/kvm_ras.h deleted file mode 100644 index e9577292dfe4..000000000000 --- a/arch/arm/include/asm/kvm_ras.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2018 - Arm Ltd */ - -#ifndef __ARM_KVM_RAS_H__ -#define __ARM_KVM_RAS_H__ - -#include <linux/types.h> - -static inline int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr) -{ - return -1; -} - -#endif /* __ARM_KVM_RAS_H__ */ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index ad55ab068dbf..36805f94939e 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -104,26 +104,6 @@ */ #define L_PGD_SWAPPER (_AT(pgdval_t, 1) << 55) /* swapper_pg_dir entry */ -/* - * 2nd stage PTE definitions for LPAE. - */ -#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x0) << 2) /* strongly ordered */ -#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* normal inner write-through */ -#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* normal inner write-back */ -#define L_PTE_S2_MT_DEV_SHARED (_AT(pteval_t, 0x1) << 2) /* device */ -#define L_PTE_S2_MT_MASK (_AT(pteval_t, 0xf) << 2) - -#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ - -#define L_PMD_S2_RDONLY (_AT(pmdval_t, 1) << 6) /* HAP[1] */ -#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ - -/* - * Hyp-mode PL2 PTE definitions for LPAE. - */ -#define L_PTE_HYP L_PTE_USER - #ifndef __ASSEMBLY__ #define pud_none(pud) (!pud_val(pud)) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index eabcb48a7840..0483cf413315 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -80,9 +80,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); extern pgprot_t pgprot_user; extern pgprot_t pgprot_kernel; -extern pgprot_t pgprot_hyp_device; -extern pgprot_t pgprot_s2; -extern pgprot_t pgprot_s2_device; #define _MOD_PROT(p, b) __pgprot(pgprot_val(p) | (b)) @@ -95,12 +92,6 @@ extern pgprot_t pgprot_s2_device; #define PAGE_READONLY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY) #define PAGE_KERNEL _MOD_PROT(pgprot_kernel, L_PTE_XN) #define PAGE_KERNEL_EXEC pgprot_kernel -#define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_XN) -#define PAGE_HYP_EXEC _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY) -#define PAGE_HYP_RO _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN) -#define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP) -#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY | L_PTE_XN) -#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY | L_PTE_XN) #define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE) #define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN) diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 614bf829e454..b9241051e5cb 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -14,6 +14,7 @@ #include <asm/ptrace.h> #include <asm/types.h> #include <asm/unified.h> +#include <asm/vdso/processor.h> #ifdef __KERNEL__ #define STACK_TOP ((current->personality & ADDR_LIMIT_32BIT) ? \ @@ -85,16 +86,6 @@ extern void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); -#if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327) -#define cpu_relax() \ - do { \ - smp_mb(); \ - __asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;"); \ - } while (0) -#else -#define cpu_relax() barrier() -#endif - #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1) diff --git a/arch/arm/include/asm/sections.h b/arch/arm/include/asm/sections.h index 4ceb4f757d4d..700b8bcdf9bd 100644 --- a/arch/arm/include/asm/sections.h +++ b/arch/arm/include/asm/sections.h @@ -10,8 +10,6 @@ extern char __idmap_text_start[]; extern char __idmap_text_end[]; extern char __entry_text_start[]; extern char __entry_text_end[]; -extern char __hyp_idmap_text_start[]; -extern char __hyp_idmap_text_end[]; static inline bool in_entry_text(unsigned long addr) { @@ -22,9 +20,7 @@ static inline bool in_entry_text(unsigned long addr) static inline bool in_idmap_text(unsigned long addr) { void *a = (void *)addr; - return memory_contains(__idmap_text_start, __idmap_text_end, a, 1) || - memory_contains(__hyp_idmap_text_start, __hyp_idmap_text_end, - a, 1); + return memory_contains(__idmap_text_start, __idmap_text_end, a, 1); } #endif /* _ASM_ARM_SECTIONS_H */ diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h deleted file mode 100644 index aaceec7855ec..000000000000 --- a/arch/arm/include/asm/stage2_pgtable.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2016 - ARM Ltd - * - * stage2 page table helpers - */ - -#ifndef __ARM_S2_PGTABLE_H_ -#define __ARM_S2_PGTABLE_H_ - -/* - * kvm_mmu_cache_min_pages() is the number of pages required - * to install a stage-2 translation. We pre-allocate the entry - * level table at VM creation. Since we have a 3 level page-table, - * we need only two pages to add a new mapping. - */ -#define kvm_mmu_cache_min_pages(kvm) 2 - -#define stage2_pgd_none(kvm, pgd) pgd_none(pgd) -#define stage2_pgd_clear(kvm, pgd) pgd_clear(pgd) -#define stage2_pgd_present(kvm, pgd) pgd_present(pgd) -#define stage2_pgd_populate(kvm, pgd, pud) pgd_populate(NULL, pgd, pud) -#define stage2_pud_offset(kvm, pgd, address) pud_offset(pgd, address) -#define stage2_pud_free(kvm, pud) do { } while (0) - -#define stage2_pud_none(kvm, pud) pud_none(pud) -#define stage2_pud_clear(kvm, pud) pud_clear(pud) -#define stage2_pud_present(kvm, pud) pud_present(pud) -#define stage2_pud_populate(kvm, pud, pmd) pud_populate(NULL, pud, pmd) -#define stage2_pmd_offset(kvm, pud, address) pmd_offset(pud, address) -#define stage2_pmd_free(kvm, pmd) free_page((unsigned long)pmd) - -#define stage2_pud_huge(kvm, pud) pud_huge(pud) - -/* Open coded p*d_addr_end that can deal with 64bit addresses */ -static inline phys_addr_t -stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + PGDIR_SIZE) & PGDIR_MASK; - - return (boundary - 1 < end - 1) ? boundary : end; -} - -#define stage2_pud_addr_end(kvm, addr, end) (end) - -static inline phys_addr_t -stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + PMD_SIZE) & PMD_MASK; - - return (boundary - 1 < end - 1) ? boundary : end; -} - -#define stage2_pgd_index(kvm, addr) pgd_index(addr) - -#define stage2_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) -#define stage2_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) -#define stage2_pud_table_empty(kvm, pudp) false - -static inline bool kvm_stage2_has_pud(struct kvm *kvm) -{ - return false; -} - -#define S2_PMD_MASK PMD_MASK -#define S2_PMD_SIZE PMD_SIZE -#define S2_PUD_MASK PUD_MASK -#define S2_PUD_SIZE PUD_SIZE - -static inline bool kvm_stage2_has_pmd(struct kvm *kvm) -{ - return true; -} - -#endif /* __ARM_S2_PGTABLE_H_ */ 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/include/asm/vdso/clocksource.h b/arch/arm/include/asm/vdso/clocksource.h new file mode 100644 index 000000000000..50c0b19fb755 --- /dev/null +++ b/arch/arm/include/asm/vdso/clocksource.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSOCLOCKSOURCE_H +#define __ASM_VDSOCLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES \ + VDSO_CLOCKMODE_ARCHTIMER + +#endif /* __ASM_VDSOCLOCKSOURCE_H */ diff --git a/arch/arm/include/asm/vdso/cp15.h b/arch/arm/include/asm/vdso/cp15.h new file mode 100644 index 000000000000..bed16fa1865e --- /dev/null +++ b/arch/arm/include/asm/vdso/cp15.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_VDSO_CP15_H +#define __ASM_VDSO_CP15_H + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_CPU_CP15 + +#include <linux/stringify.h> + +#define __ACCESS_CP15(CRn, Op1, CRm, Op2) \ + "mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32 +#define __ACCESS_CP15_64(Op1, CRm) \ + "mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64 + +#define __read_sysreg(r, w, c, t) ({ \ + t __val; \ + asm volatile(r " " c : "=r" (__val)); \ + __val; \ +}) +#define read_sysreg(...) __read_sysreg(__VA_ARGS__) + +#define __write_sysreg(v, r, w, c, t) asm volatile(w " " c : : "r" ((t)(v))) +#define write_sysreg(v, ...) __write_sysreg(v, __VA_ARGS__) + +#define BPIALL __ACCESS_CP15(c7, 0, c5, 6) +#define ICIALLU __ACCESS_CP15(c7, 0, c5, 0) + +#define CNTVCT __ACCESS_CP15_64(1, c14) + +#endif /* CONFIG_CPU_CP15 */ + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_VDSO_CP15_H */ diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h index fe6e1f65932d..36dc18553ed8 100644 --- a/arch/arm/include/asm/vdso/gettimeofday.h +++ b/arch/arm/include/asm/vdso/gettimeofday.h @@ -7,9 +7,9 @@ #ifndef __ASSEMBLY__ -#include <asm/barrier.h> -#include <asm/cp15.h> +#include <asm/errno.h> #include <asm/unistd.h> +#include <asm/vdso/cp15.h> #include <uapi/linux/time.h> #define VDSO_HAS_CLOCK_GETRES 1 @@ -106,20 +106,32 @@ static __always_inline int clock_getres32_fallback( return ret; } +static inline bool arm_vdso_hres_capable(void) +{ + return IS_ENABLED(CONFIG_ARM_ARCH_TIMER); +} +#define __arch_vdso_hres_capable arm_vdso_hres_capable + static __always_inline u64 __arch_get_hw_counter(int clock_mode) { #ifdef CONFIG_ARM_ARCH_TIMER u64 cycle_now; - if (!clock_mode) - return -EINVAL; + /* + * Core checks for mode already, so this raced against a concurrent + * update. Return something. Core will do another round and then + * see the mode change and fallback to the syscall. + */ + if (clock_mode == VDSO_CLOCKMODE_NONE) + return 0; isb(); cycle_now = read_sysreg(CNTVCT); return cycle_now; #else - return -EINVAL; /* use fallback */ + /* Make GCC happy. This is compiled out anyway */ + return 0; #endif } diff --git a/arch/arm/include/asm/vdso/processor.h b/arch/arm/include/asm/vdso/processor.h new file mode 100644 index 000000000000..45efb3ff511c --- /dev/null +++ b/arch/arm/include/asm/vdso/processor.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_VDSO_PROCESSOR_H +#define __ASM_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLY__ + +#if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327) +#define cpu_relax() \ + do { \ + smp_mb(); \ + __asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;"); \ + } while (0) +#else +#define cpu_relax() barrier() +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/arm/include/asm/vdso/vsyscall.h b/arch/arm/include/asm/vdso/vsyscall.h index cff87d8d30da..47e41ae8ccd0 100644 --- a/arch/arm/include/asm/vdso/vsyscall.h +++ b/arch/arm/include/asm/vdso/vsyscall.h @@ -11,18 +11,6 @@ extern struct vdso_data *vdso_data; extern bool cntvct_ok; -static __always_inline -bool tk_is_cntvct(const struct timekeeper *tk) -{ - if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) - return false; - - if (!tk->tkr_mono.clock->archdata.vdso_direct) - return false; - - return true; -} - /* * Update the vDSO data page to keep in sync with kernel timekeeping. */ @@ -34,29 +22,6 @@ struct vdso_data *__arm_get_k_vdso_data(void) #define __arch_get_k_vdso_data __arm_get_k_vdso_data static __always_inline -bool __arm_update_vdso_data(void) -{ - return cntvct_ok; -} -#define __arch_update_vdso_data __arm_update_vdso_data - -static __always_inline -int __arm_get_clock_mode(struct timekeeper *tk) -{ - u32 __tk_is_cntvct = tk_is_cntvct(tk); - - return __tk_is_cntvct; -} -#define __arch_get_clock_mode __arm_get_clock_mode - -static __always_inline -int __arm_use_vsyscall(struct vdso_data *vdata) -{ - return vdata[CS_HRES_COARSE].clock_mode; -} -#define __arch_use_vsyscall __arm_use_vsyscall - -static __always_inline void __arm_sync_vdso_data(struct vdso_data *vdata) { flush_dcache_page(virt_to_page(vdata)); diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h index 17c26ccd126d..dd9697b2bde8 100644 --- a/arch/arm/include/asm/virt.h +++ b/arch/arm/include/asm/virt.h @@ -39,8 +39,6 @@ static inline void sync_boot_mode(void) sync_cache_r(&__boot_cpu_mode); } -void __hyp_set_vectors(unsigned long phys_vector_base); -void __hyp_reset_vectors(void); #else #define __boot_cpu_mode (SVC_MODE) #define sync_boot_mode() @@ -67,18 +65,6 @@ static inline bool is_kernel_in_hyp_mode(void) return false; } -static inline bool has_vhe(void) -{ - return false; -} - -/* The section containing the hypervisor idmap text */ -extern char __hyp_idmap_text_start[]; -extern char __hyp_idmap_text_end[]; - -/* The section containing the hypervisor text */ -extern char __hyp_text_start[]; -extern char __hyp_text_end[]; #endif #else @@ -87,9 +73,6 @@ extern char __hyp_text_end[]; #define HVC_SET_VECTORS 0 #define HVC_SOFT_RESTART 1 -#define HVC_RESET_VECTORS 2 - -#define HVC_STUB_HCALL_NR 3 #endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h deleted file mode 100644 index 03cd7c19a683..000000000000 --- a/arch/arm/include/uapi/asm/kvm.h +++ /dev/null @@ -1,314 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License, version 2, as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - */ - -#ifndef __ARM_KVM_H__ -#define __ARM_KVM_H__ - -#include <linux/types.h> -#include <linux/psci.h> -#include <asm/ptrace.h> - -#define __KVM_HAVE_GUEST_DEBUG -#define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM -#define __KVM_HAVE_VCPU_EVENTS - -#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 - -#define KVM_REG_SIZE(id) \ - (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) - -/* Valid for svc_regs, abt_regs, und_regs, irq_regs in struct kvm_regs */ -#define KVM_ARM_SVC_sp svc_regs[0] -#define KVM_ARM_SVC_lr svc_regs[1] -#define KVM_ARM_SVC_spsr svc_regs[2] -#define KVM_ARM_ABT_sp abt_regs[0] -#define KVM_ARM_ABT_lr abt_regs[1] -#define KVM_ARM_ABT_spsr abt_regs[2] -#define KVM_ARM_UND_sp und_regs[0] -#define KVM_ARM_UND_lr und_regs[1] -#define KVM_ARM_UND_spsr und_regs[2] -#define KVM_ARM_IRQ_sp irq_regs[0] -#define KVM_ARM_IRQ_lr irq_regs[1] -#define KVM_ARM_IRQ_spsr irq_regs[2] - -/* Valid only for fiq_regs in struct kvm_regs */ -#define KVM_ARM_FIQ_r8 fiq_regs[0] -#define KVM_ARM_FIQ_r9 fiq_regs[1] -#define KVM_ARM_FIQ_r10 fiq_regs[2] -#define KVM_ARM_FIQ_fp fiq_regs[3] -#define KVM_ARM_FIQ_ip fiq_regs[4] -#define KVM_ARM_FIQ_sp fiq_regs[5] -#define KVM_ARM_FIQ_lr fiq_regs[6] -#define KVM_ARM_FIQ_spsr fiq_regs[7] - -struct kvm_regs { - struct pt_regs usr_regs; /* R0_usr - R14_usr, PC, CPSR */ - unsigned long svc_regs[3]; /* SP_svc, LR_svc, SPSR_svc */ - unsigned long abt_regs[3]; /* SP_abt, LR_abt, SPSR_abt */ - unsigned long und_regs[3]; /* SP_und, LR_und, SPSR_und */ - unsigned long irq_regs[3]; /* SP_irq, LR_irq, SPSR_irq */ - unsigned long fiq_regs[8]; /* R8_fiq - R14_fiq, SPSR_fiq */ -}; - -/* Supported Processor Types */ -#define KVM_ARM_TARGET_CORTEX_A15 0 -#define KVM_ARM_TARGET_CORTEX_A7 1 -#define KVM_ARM_NUM_TARGETS 2 - -/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ -#define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT) -#define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT) - -/* Supported device IDs */ -#define KVM_ARM_DEVICE_VGIC_V2 0 - -/* Supported VGIC address types */ -#define KVM_VGIC_V2_ADDR_TYPE_DIST 0 -#define KVM_VGIC_V2_ADDR_TYPE_CPU 1 - -#define KVM_VGIC_V2_DIST_SIZE 0x1000 -#define KVM_VGIC_V2_CPU_SIZE 0x2000 - -/* Supported VGICv3 address types */ -#define KVM_VGIC_V3_ADDR_TYPE_DIST 2 -#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 -#define KVM_VGIC_ITS_ADDR_TYPE 4 -#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5 - -#define KVM_VGIC_V3_DIST_SIZE SZ_64K -#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) -#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) - -#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ -#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */ - -struct kvm_vcpu_init { - __u32 target; - __u32 features[7]; -}; - -struct kvm_sregs { -}; - -struct kvm_fpu { -}; - -struct kvm_guest_debug_arch { -}; - -struct kvm_debug_exit_arch { -}; - -struct kvm_sync_regs { - /* Used with KVM_CAP_ARM_USER_IRQ */ - __u64 device_irq_level; -}; - -struct kvm_arch_memory_slot { -}; - -/* for KVM_GET/SET_VCPU_EVENTS */ -struct kvm_vcpu_events { - struct { - __u8 serror_pending; - __u8 serror_has_esr; - __u8 ext_dabt_pending; - /* Align it to 8 bytes */ - __u8 pad[5]; - __u64 serror_esr; - } exception; - __u32 reserved[12]; -}; - -/* If you need to interpret the index values, here is the key: */ -#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 -#define KVM_REG_ARM_COPROC_SHIFT 16 -#define KVM_REG_ARM_32_OPC2_MASK 0x0000000000000007 -#define KVM_REG_ARM_32_OPC2_SHIFT 0 -#define KVM_REG_ARM_OPC1_MASK 0x0000000000000078 -#define KVM_REG_ARM_OPC1_SHIFT 3 -#define KVM_REG_ARM_CRM_MASK 0x0000000000000780 -#define KVM_REG_ARM_CRM_SHIFT 7 -#define KVM_REG_ARM_32_CRN_MASK 0x0000000000007800 -#define KVM_REG_ARM_32_CRN_SHIFT 11 -/* - * For KVM currently all guest registers are nonsecure, but we reserve a bit - * in the encoding to distinguish secure from nonsecure for AArch32 system - * registers that are banked by security. This is 1 for the secure banked - * register, and 0 for the nonsecure banked register or if the register is - * not banked by security. - */ -#define KVM_REG_ARM_SECURE_MASK 0x0000000010000000 -#define KVM_REG_ARM_SECURE_SHIFT 28 - -#define ARM_CP15_REG_SHIFT_MASK(x,n) \ - (((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK) - -#define __ARM_CP15_REG(op1,crn,crm,op2) \ - (KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT) | \ - ARM_CP15_REG_SHIFT_MASK(op1, OPC1) | \ - ARM_CP15_REG_SHIFT_MASK(crn, 32_CRN) | \ - ARM_CP15_REG_SHIFT_MASK(crm, CRM) | \ - ARM_CP15_REG_SHIFT_MASK(op2, 32_OPC2)) - -#define ARM_CP15_REG32(...) (__ARM_CP15_REG(__VA_ARGS__) | KVM_REG_SIZE_U32) - -#define __ARM_CP15_REG64(op1,crm) \ - (__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64) -#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__) - -/* PL1 Physical Timer Registers */ -#define KVM_REG_ARM_PTIMER_CTL ARM_CP15_REG32(0, 14, 2, 1) -#define KVM_REG_ARM_PTIMER_CNT ARM_CP15_REG64(0, 14) -#define KVM_REG_ARM_PTIMER_CVAL ARM_CP15_REG64(2, 14) - -/* Virtual Timer Registers */ -#define KVM_REG_ARM_TIMER_CTL ARM_CP15_REG32(0, 14, 3, 1) -#define KVM_REG_ARM_TIMER_CNT ARM_CP15_REG64(1, 14) -#define KVM_REG_ARM_TIMER_CVAL ARM_CP15_REG64(3, 14) - -/* Normal registers are mapped as coprocessor 16. */ -#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_CORE_REG(name) (offsetof(struct kvm_regs, name) / 4) - -/* Some registers need more space to represent values. */ -#define KVM_REG_ARM_DEMUX (0x0011 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_DEMUX_ID_MASK 0x000000000000FF00 -#define KVM_REG_ARM_DEMUX_ID_SHIFT 8 -#define KVM_REG_ARM_DEMUX_ID_CCSIDR (0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT) -#define KVM_REG_ARM_DEMUX_VAL_MASK 0x00000000000000FF -#define KVM_REG_ARM_DEMUX_VAL_SHIFT 0 - -/* VFP registers: we could overload CP10 like ARM does, but that's ugly. */ -#define KVM_REG_ARM_VFP (0x0012 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_VFP_MASK 0x000000000000FFFF -#define KVM_REG_ARM_VFP_BASE_REG 0x0 -#define KVM_REG_ARM_VFP_FPSID 0x1000 -#define KVM_REG_ARM_VFP_FPSCR 0x1001 -#define KVM_REG_ARM_VFP_MVFR1 0x1006 -#define KVM_REG_ARM_VFP_MVFR0 0x1007 -#define KVM_REG_ARM_VFP_FPEXC 0x1008 -#define KVM_REG_ARM_VFP_FPINST 0x1009 -#define KVM_REG_ARM_VFP_FPINST2 0x100A - -/* KVM-as-firmware specific pseudo-registers */ -#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ - KVM_REG_ARM_FW | ((r) & 0xffff)) -#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) - /* Higher values mean better protection. */ -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) - /* Higher values mean better protection. */ -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) - -/* Device Control API: ARM VGIC */ -#define KVM_DEV_ARM_VGIC_GRP_ADDR 0 -#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 -#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 -#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 -#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) -#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 -#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ - (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) -#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 -#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) -#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) -#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 -#define KVM_DEV_ARM_VGIC_GRP_CTRL 4 -#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 -#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 -#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 -#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8 -#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 -#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ - (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) -#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff -#define VGIC_LEVEL_INFO_LINE_LEVEL 0 - -/* Device Control API on vcpu fd */ -#define KVM_ARM_VCPU_PMU_V3_CTRL 0 -#define KVM_ARM_VCPU_PMU_V3_IRQ 0 -#define KVM_ARM_VCPU_PMU_V3_INIT 1 -#define KVM_ARM_VCPU_TIMER_CTRL 1 -#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 -#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 - -#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 -#define KVM_DEV_ARM_ITS_SAVE_TABLES 1 -#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 -#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 -#define KVM_DEV_ARM_ITS_CTRL_RESET 4 - -/* KVM_IRQ_LINE irq field index values */ -#define KVM_ARM_IRQ_VCPU2_SHIFT 28 -#define KVM_ARM_IRQ_VCPU2_MASK 0xf -#define KVM_ARM_IRQ_TYPE_SHIFT 24 -#define KVM_ARM_IRQ_TYPE_MASK 0xf -#define KVM_ARM_IRQ_VCPU_SHIFT 16 -#define KVM_ARM_IRQ_VCPU_MASK 0xff -#define KVM_ARM_IRQ_NUM_SHIFT 0 -#define KVM_ARM_IRQ_NUM_MASK 0xffff - -/* irq_type field */ -#define KVM_ARM_IRQ_TYPE_CPU 0 -#define KVM_ARM_IRQ_TYPE_SPI 1 -#define KVM_ARM_IRQ_TYPE_PPI 2 - -/* out-of-kernel GIC cpu interrupt injection irq_number field */ -#define KVM_ARM_IRQ_CPU_IRQ 0 -#define KVM_ARM_IRQ_CPU_FIQ 1 - -/* - * This used to hold the highest supported SPI, but it is now obsolete - * and only here to provide source code level compatibility with older - * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS. - */ -#ifndef __KERNEL__ -#define KVM_ARM_IRQ_GIC_MAX 127 -#endif - -/* One single KVM irqchip, ie. the VGIC */ -#define KVM_NR_IRQCHIPS 1 - -/* PSCI interface */ -#define KVM_PSCI_FN_BASE 0x95c1ba5e -#define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) - -#define KVM_PSCI_FN_CPU_SUSPEND KVM_PSCI_FN(0) -#define KVM_PSCI_FN_CPU_OFF KVM_PSCI_FN(1) -#define KVM_PSCI_FN_CPU_ON KVM_PSCI_FN(2) -#define KVM_PSCI_FN_MIGRATE KVM_PSCI_FN(3) - -#define KVM_PSCI_RET_SUCCESS PSCI_RET_SUCCESS -#define KVM_PSCI_RET_NI PSCI_RET_NOT_SUPPORTED -#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS -#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED - -#endif /* __ARM_KVM_H__ */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index c773b829ee8e..c036a4a2f8e2 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -11,9 +11,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/dma-mapping.h> -#ifdef CONFIG_KVM_ARM_HOST -#include <linux/kvm_host.h> -#endif #include <asm/cacheflush.h> #include <asm/glue-df.h> #include <asm/glue-pf.h> @@ -167,14 +164,6 @@ int main(void) DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER); DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE); BLANK(); -#ifdef CONFIG_KVM_ARM_HOST - DEFINE(VCPU_GUEST_CTXT, offsetof(struct kvm_vcpu, arch.ctxt)); - DEFINE(VCPU_HOST_CTXT, offsetof(struct kvm_vcpu, arch.host_cpu_context)); - DEFINE(CPU_CTXT_VFP, offsetof(struct kvm_cpu_context, vfp)); - DEFINE(CPU_CTXT_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); - DEFINE(GP_REGS_USR, offsetof(struct kvm_regs, usr_regs)); -#endif - BLANK(); #ifdef CONFIG_VDSO DEFINE(VDSO_DATA_SIZE, sizeof(union vdso_data_store)); #endif diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 2a5ff69c28e6..10499d44964a 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -78,13 +78,10 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, { unsigned long replaced; - if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) old = __opcode_to_mem_thumb32(old); - new = __opcode_to_mem_thumb32(new); - } else { + else old = __opcode_to_mem_arm(old); - new = __opcode_to_mem_arm(new); - } if (validate) { if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE)) diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 6607fa817bba..26d8e03b1dd3 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -189,19 +189,19 @@ ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE ENDPROC(__hyp_stub_install_secondary) __hyp_stub_do_trap: +#ifdef ZIMAGE teq r0, #HVC_SET_VECTORS bne 1f + /* Only the ZIMAGE stubs can change the HYP vectors */ mcr p15, 4, r1, c12, c0, 0 @ set HVBAR b __hyp_stub_exit +#endif 1: teq r0, #HVC_SOFT_RESTART - bne 1f + bne 2f bx r1 -1: teq r0, #HVC_RESET_VECTORS - beq __hyp_stub_exit - - ldr r0, =HVC_STUB_ERR +2: ldr r0, =HVC_STUB_ERR __ERET __hyp_stub_exit: @@ -210,26 +210,9 @@ __hyp_stub_exit: ENDPROC(__hyp_stub_do_trap) /* - * __hyp_set_vectors: Call this after boot to set the initial hypervisor - * vectors as part of hypervisor installation. On an SMP system, this should - * be called on each CPU. - * - * r0 must be the physical address of the new vector table (which must lie in - * the bottom 4GB of physical address space. - * - * r0 must be 32-byte aligned. - * - * Before calling this, you must check that the stub hypervisor is installed - * everywhere, by waiting for any secondary CPUs to be brought up and then - * checking that BOOT_CPU_MODE_HAVE_HYP(__boot_cpu_mode) is true. - * - * If not, there is a pre-existing hypervisor, some CPUs failed to boot, or - * something else went wrong... in such cases, trying to install a new - * hypervisor is unlikely to work as desired. - * - * When you call into your shiny new hypervisor, sp_hyp will contain junk, - * so you will need to set that to something sensible at the new hypervisor's - * initialisation entry point. + * __hyp_set_vectors is only used when ZIMAGE must bounce between HYP + * and SVC. For the kernel itself, the vectors are set once and for + * all by the stubs. */ ENTRY(__hyp_set_vectors) mov r1, r0 @@ -245,12 +228,6 @@ ENTRY(__hyp_soft_restart) ret lr ENDPROC(__hyp_soft_restart) -ENTRY(__hyp_reset_vectors) - mov r0, #HVC_RESET_VECTORS - __HVC(0) - ret lr -ENDPROC(__hyp_reset_vectors) - #ifndef ZIMAGE .align 2 .L__boot_cpu_mode_offset: diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c index d0a05a3bdb96..e9e828b6bb30 100644 --- a/arch/arm/kernel/patch.c +++ b/arch/arm/kernel/patch.c @@ -16,10 +16,10 @@ struct patch { unsigned int insn; }; +#ifdef CONFIG_MMU static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) - __acquires(&patch_lock) { unsigned int uintaddr = (uintptr_t) addr; bool module = !core_kernel_text(uintaddr); @@ -34,8 +34,6 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) if (flags) raw_spin_lock_irqsave(&patch_lock, *flags); - else - __acquire(&patch_lock); set_fixmap(fixmap, page_to_phys(page)); @@ -43,15 +41,19 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) } static void __kprobes patch_unmap(int fixmap, unsigned long *flags) - __releases(&patch_lock) { clear_fixmap(fixmap); if (flags) raw_spin_unlock_irqrestore(&patch_lock, *flags); - else - __release(&patch_lock); } +#else +static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) +{ + return addr; +} +static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { } +#endif void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) { @@ -64,8 +66,6 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) if (remap) waddr = patch_map(addr, FIX_TEXT_POKE0, &flags); - else - __acquire(&patch_lock); if (thumb2 && __opcode_is_thumb16(insn)) { *(u16 *)waddr = __opcode_to_mem_thumb16(insn); @@ -102,8 +102,7 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) if (waddr != addr) { flush_kernel_vmap_range(waddr, twopage ? size / 2 : size); patch_unmap(FIX_TEXT_POKE0, &flags); - } else - __release(&patch_lock); + } flush_icache_range((uintptr_t)(addr), (uintptr_t)(addr) + size); 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/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index 21b8b271c80d..6d2be994ae58 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -162,14 +162,6 @@ SECTIONS ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support") ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") -/* - * The HYP init code can't be more than a page long, - * and should not cross a page boundary. - * The above comment applies as well. - */ -ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE, - "HYP init code too big or misaligned") - #ifdef CONFIG_XIP_DEFLATED_DATA /* * The .bss is used as a stack area for __inflate_kernel_data() whose stack diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 319ccb10846a..88a720da443b 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -170,12 +170,4 @@ __start_rodata_section_aligned = ALIGN(__start_rodata, 1 << SECTION_SHIFT); ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support") ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") -/* - * The HYP init code can't be more than a page long, - * and should not cross a page boundary. - * The above comment applies as well. - */ -ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE, - "HYP init code too big or misaligned") - #endif /* CONFIG_XIP_KERNEL */ diff --git a/arch/arm/kernel/vmlinux.lds.h b/arch/arm/kernel/vmlinux.lds.h index 8247bc15addc..381a8e105fa5 100644 --- a/arch/arm/kernel/vmlinux.lds.h +++ b/arch/arm/kernel/vmlinux.lds.h @@ -31,20 +31,11 @@ *(.proc.info.init) \ __proc_info_end = .; -#define HYPERVISOR_TEXT \ - __hyp_text_start = .; \ - *(.hyp.text) \ - __hyp_text_end = .; - #define IDMAP_TEXT \ ALIGN_FUNCTION(); \ __idmap_text_start = .; \ *(.idmap.text) \ __idmap_text_end = .; \ - . = ALIGN(PAGE_SIZE); \ - __hyp_idmap_text_start = .; \ - *(.hyp.idmap.text) \ - __hyp_idmap_text_end = .; #define ARM_DISCARD \ *(.ARM.exidx.exit.text) \ @@ -72,7 +63,6 @@ SCHED_TEXT \ CPUIDLE_TEXT \ LOCK_TEXT \ - HYPERVISOR_TEXT \ KPROBES_TEXT \ *(.gnu.warning) \ *(.glue_7) \ diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig deleted file mode 100644 index f591026347a5..000000000000 --- a/arch/arm/kvm/Kconfig +++ /dev/null @@ -1,59 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# KVM configuration -# - -source "virt/kvm/Kconfig" -source "virt/lib/Kconfig" - -menuconfig VIRTUALIZATION - bool "Virtualization" - ---help--- - Say Y here to get to see options for using your Linux host to run - other operating systems inside virtual machines (guests). - This option alone does not add any kernel code. - - If you say N, all options in this submenu will be skipped and - disabled. - -if VIRTUALIZATION - -config KVM - bool "Kernel-based Virtual Machine (KVM) support" - depends on MMU && OF - select PREEMPT_NOTIFIERS - select ARM_GIC - select ARM_GIC_V3 - select ARM_GIC_V3_ITS - select HAVE_KVM_CPU_RELAX_INTERCEPT - select HAVE_KVM_ARCH_TLB_FLUSH_ALL - select KVM_MMIO - select KVM_ARM_HOST - select KVM_GENERIC_DIRTYLOG_READ_PROTECT - select SRCU - select MMU_NOTIFIER - select KVM_VFIO - select HAVE_KVM_EVENTFD - select HAVE_KVM_IRQFD - select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQ_ROUTING - select HAVE_KVM_MSI - select IRQ_BYPASS_MANAGER - select HAVE_KVM_IRQ_BYPASS - depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER - ---help--- - Support hosting virtualized guest machines. - - This module provides access to the hardware capabilities through - a character device node named /dev/kvm. - - If unsure, say N. - -config KVM_ARM_HOST - bool - ---help--- - Provides host support for ARM processors. - -source "drivers/vhost/Kconfig" - -endif # VIRTUALIZATION diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile deleted file mode 100644 index e442d82821df..000000000000 --- a/arch/arm/kvm/Makefile +++ /dev/null @@ -1,43 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for Kernel-based Virtual Machine module -# - -plus_virt := $(call as-instr,.arch_extension virt,+virt) -ifeq ($(plus_virt),+virt) - plus_virt_def := -DREQUIRES_VIRT=1 -endif - -KVM := ../../../virt/kvm - -ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic -CFLAGS_$(KVM)/arm/arm.o := $(plus_virt_def) - -AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) -AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) - -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o - -obj-$(CONFIG_KVM_ARM_HOST) += hyp/ - -obj-y += kvm-arm.o init.o interrupts.o -obj-y += handle_exit.o guest.o emulate.o reset.o -obj-y += coproc.o coproc_a15.o coproc_a7.o vgic-v3-coproc.o -obj-y += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o -obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o $(KVM)/arm/hypercalls.o -obj-y += $(KVM)/arm/aarch32.o - -obj-y += $(KVM)/arm/vgic/vgic.o -obj-y += $(KVM)/arm/vgic/vgic-init.o -obj-y += $(KVM)/arm/vgic/vgic-irqfd.o -obj-y += $(KVM)/arm/vgic/vgic-v2.o -obj-y += $(KVM)/arm/vgic/vgic-v3.o -obj-y += $(KVM)/arm/vgic/vgic-v4.o -obj-y += $(KVM)/arm/vgic/vgic-mmio.o -obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o -obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o -obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o -obj-y += $(KVM)/arm/vgic/vgic-its.o -obj-y += $(KVM)/arm/vgic/vgic-debug.o -obj-y += $(KVM)/irqchip.o -obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c deleted file mode 100644 index 07745ee022a1..000000000000 --- a/arch/arm/kvm/coproc.c +++ /dev/null @@ -1,1455 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Authors: Rusty Russell <rusty@rustcorp.com.au> - * Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/bsearch.h> -#include <linux/mm.h> -#include <linux/kvm_host.h> -#include <linux/uaccess.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_host.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_mmu.h> -#include <asm/cacheflush.h> -#include <asm/cputype.h> -#include <trace/events/kvm.h> -#include <asm/vfp.h> -#include "../vfp/vfpinstr.h" - -#define CREATE_TRACE_POINTS -#include "trace.h" -#include "coproc.h" - - -/****************************************************************************** - * Co-processor emulation - *****************************************************************************/ - -static bool write_to_read_only(struct kvm_vcpu *vcpu, - const struct coproc_params *params) -{ - WARN_ONCE(1, "CP15 write to read-only register\n"); - print_cp_instr(params); - kvm_inject_undefined(vcpu); - return false; -} - -static bool read_from_write_only(struct kvm_vcpu *vcpu, - const struct coproc_params *params) -{ - WARN_ONCE(1, "CP15 read to write-only register\n"); - print_cp_instr(params); - kvm_inject_undefined(vcpu); - return false; -} - -/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */ -static u32 cache_levels; - -/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ -#define CSSELR_MAX 12 - -/* - * kvm_vcpu_arch.cp15 holds cp15 registers as an array of u32, but some - * of cp15 registers can be viewed either as couple of two u32 registers - * or one u64 register. Current u64 register encoding is that least - * significant u32 word is followed by most significant u32 word. - */ -static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu, - const struct coproc_reg *r, - u64 val) -{ - vcpu_cp15(vcpu, r->reg) = val & 0xffffffff; - vcpu_cp15(vcpu, r->reg + 1) = val >> 32; -} - -static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu, - const struct coproc_reg *r) -{ - u64 val; - - val = vcpu_cp15(vcpu, r->reg + 1); - val = val << 32; - val = val | vcpu_cp15(vcpu, r->reg); - return val; -} - -int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - kvm_inject_undefined(vcpu); - return 1; -} - -int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* - * We can get here, if the host has been built without VFPv3 support, - * but the guest attempted a floating point operation. - */ - kvm_inject_undefined(vcpu); - return 1; -} - -int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - kvm_inject_undefined(vcpu); - return 1; -} - -static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - /* - * Compute guest MPIDR. We build a virtual cluster out of the - * vcpu_id, but we read the 'U' bit from the underlying - * hardware directly. - */ - vcpu_cp15(vcpu, c0_MPIDR) = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) | - ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) | - (vcpu->vcpu_id & 3)); -} - -/* TRM entries A7:4.3.31 A15:4.3.28 - RO WI */ -static bool access_actlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c1_ACTLR); - return true; -} - -/* TRM entries A7:4.3.56, A15:4.3.60 - R/O. */ -static bool access_cbar(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return write_to_read_only(vcpu, p); - return read_zero(vcpu, p); -} - -/* TRM entries A7:4.3.49, A15:4.3.48 - R/O WI */ -static bool access_l2ctlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c9_L2CTLR); - return true; -} - -static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - u32 l2ctlr, ncores; - - asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr)); - l2ctlr &= ~(3 << 24); - ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1; - /* How many cores in the current cluster and the next ones */ - ncores -= (vcpu->vcpu_id & ~3); - /* Cap it to the maximum number of cores in a single cluster */ - ncores = min(ncores, 3U); - l2ctlr |= (ncores & 3) << 24; - - vcpu_cp15(vcpu, c9_L2CTLR) = l2ctlr; -} - -static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - u32 actlr; - - /* ACTLR contains SMP bit: make sure you create all cpus first! */ - asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr)); - /* Make the SMP bit consistent with the guest configuration */ - if (atomic_read(&vcpu->kvm->online_vcpus) > 1) - actlr |= 1U << 6; - else - actlr &= ~(1U << 6); - - vcpu_cp15(vcpu, c1_ACTLR) = actlr; -} - -/* - * TRM entries: A7:4.3.50, A15:4.3.49 - * R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). - */ -static bool access_l2ectlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = 0; - return true; -} - -/* - * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). - */ -static bool access_dcsw(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (!p->is_write) - return read_from_write_only(vcpu, p); - - kvm_set_way_flush(vcpu); - return true; -} - -/* - * Generic accessor for VM registers. Only called as long as HCR_TVM - * is set. If the guest enables the MMU, we stop trapping the VM - * sys_regs and leave it in complete control of the caches. - * - * Used by the cpu-specific code. - */ -bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - bool was_enabled = vcpu_has_cache_enabled(vcpu); - - BUG_ON(!p->is_write); - - vcpu_cp15(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt1); - if (p->is_64bit) - vcpu_cp15(vcpu, r->reg + 1) = *vcpu_reg(vcpu, p->Rt2); - - kvm_toggle_cache(vcpu, was_enabled); - return true; -} - -static bool access_gic_sgi(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u64 reg; - bool g1; - - if (!p->is_write) - return read_from_write_only(vcpu, p); - - reg = (u64)*vcpu_reg(vcpu, p->Rt2) << 32; - reg |= *vcpu_reg(vcpu, p->Rt1) ; - - /* - * In a system where GICD_CTLR.DS=1, a ICC_SGI0R access generates - * Group0 SGIs only, while ICC_SGI1R can generate either group, - * depending on the SGI configuration. ICC_ASGI1R is effectively - * equivalent to ICC_SGI0R, as there is no "alternative" secure - * group. - */ - switch (p->Op1) { - default: /* Keep GCC quiet */ - case 0: /* ICC_SGI1R */ - g1 = true; - break; - case 1: /* ICC_ASGI1R */ - case 2: /* ICC_SGI0R */ - g1 = false; - break; - } - - vgic_v3_dispatch_sgi(vcpu, reg, g1); - - return true; -} - -static bool access_gic_sre(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre; - - return true; -} - -static bool access_cntp_tval(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u32 val; - - if (p->is_write) { - val = *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_write_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_TVAL, val); - } else { - val = kvm_arm_timer_read_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_TVAL); - *vcpu_reg(vcpu, p->Rt1) = val; - } - - return true; -} - -static bool access_cntp_ctl(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u32 val; - - if (p->is_write) { - val = *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_write_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CTL, val); - } else { - val = kvm_arm_timer_read_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CTL); - *vcpu_reg(vcpu, p->Rt1) = val; - } - - return true; -} - -static bool access_cntp_cval(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u64 val; - - if (p->is_write) { - val = (u64)*vcpu_reg(vcpu, p->Rt2) << 32; - val |= *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_write_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CVAL, val); - } else { - val = kvm_arm_timer_read_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CVAL); - *vcpu_reg(vcpu, p->Rt1) = val; - *vcpu_reg(vcpu, p->Rt2) = val >> 32; - } - - return true; -} - -/* - * We could trap ID_DFR0 and tell the guest we don't support performance - * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was - * NAKed, so it will read the PMCR anyway. - * - * Therefore we tell the guest we have 0 counters. Unfortunately, we - * must always support PMCCNTR (the cycle counter): we just RAZ/WI for - * all PM registers, which doesn't crash the guest kernel at least. - */ -static bool trap_raz_wi(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - else - return read_zero(vcpu, p); -} - -#define access_pmcr trap_raz_wi -#define access_pmcntenset trap_raz_wi -#define access_pmcntenclr trap_raz_wi -#define access_pmovsr trap_raz_wi -#define access_pmselr trap_raz_wi -#define access_pmceid0 trap_raz_wi -#define access_pmceid1 trap_raz_wi -#define access_pmccntr trap_raz_wi -#define access_pmxevtyper trap_raz_wi -#define access_pmxevcntr trap_raz_wi -#define access_pmuserenr trap_raz_wi -#define access_pmintenset trap_raz_wi -#define access_pmintenclr trap_raz_wi - -/* Architected CP15 registers. - * CRn denotes the primary register number, but is copied to the CRm in the - * user space API for 64-bit register access in line with the terminology used - * in the ARM ARM. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit - * registers preceding 32-bit ones. - */ -static const struct coproc_reg cp15_regs[] = { - /* MPIDR: we use VMPIDR for guest access. */ - { CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32, - NULL, reset_mpidr, c0_MPIDR }, - - /* CSSELR: swapped by interrupt.S. */ - { CRn( 0), CRm( 0), Op1( 2), Op2( 0), is32, - NULL, reset_unknown, c0_CSSELR }, - - /* ACTLR: trapped by HCR.TAC bit. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32, - access_actlr, reset_actlr, c1_ACTLR }, - - /* CPACR: swapped by interrupt.S. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32, - NULL, reset_val, c1_CPACR, 0x00000000 }, - - /* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */ - { CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 }, - { CRn(2), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c2_TTBR0 }, - { CRn(2), CRm( 0), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c2_TTBR1 }, - { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32, - access_vm_reg, reset_val, c2_TTBCR, 0x00000000 }, - { CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 }, - - - /* DACR: swapped by interrupt.S. */ - { CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c3_DACR }, - - /* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */ - { CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c5_DFSR }, - { CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c5_IFSR }, - { CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c5_ADFSR }, - { CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c5_AIFSR }, - - /* DFAR/IFAR: swapped by interrupt.S. */ - { CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c6_DFAR }, - { CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32, - access_vm_reg, reset_unknown, c6_IFAR }, - - /* PAR swapped by interrupt.S */ - { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, - - /* - * DC{C,I,CI}SW operations: - */ - { CRn( 7), CRm( 6), Op1( 0), Op2( 2), is32, access_dcsw}, - { CRn( 7), CRm(10), Op1( 0), Op2( 2), is32, access_dcsw}, - { CRn( 7), CRm(14), Op1( 0), Op2( 2), is32, access_dcsw}, - /* - * L2CTLR access (guest wants to know #CPUs). - */ - { CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32, - access_l2ctlr, reset_l2ctlr, c9_L2CTLR }, - { CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr}, - - /* - * Dummy performance monitor implementation. - */ - { CRn( 9), CRm(12), Op1( 0), Op2( 0), is32, access_pmcr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 1), is32, access_pmcntenset}, - { CRn( 9), CRm(12), Op1( 0), Op2( 2), is32, access_pmcntenclr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 3), is32, access_pmovsr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 5), is32, access_pmselr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 6), is32, access_pmceid0}, - { CRn( 9), CRm(12), Op1( 0), Op2( 7), is32, access_pmceid1}, - { CRn( 9), CRm(13), Op1( 0), Op2( 0), is32, access_pmccntr}, - { CRn( 9), CRm(13), Op1( 0), Op2( 1), is32, access_pmxevtyper}, - { CRn( 9), CRm(13), Op1( 0), Op2( 2), is32, access_pmxevcntr}, - { CRn( 9), CRm(14), Op1( 0), Op2( 0), is32, access_pmuserenr}, - { CRn( 9), CRm(14), Op1( 0), Op2( 1), is32, access_pmintenset}, - { CRn( 9), CRm(14), Op1( 0), Op2( 2), is32, access_pmintenclr}, - - /* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */ - { CRn(10), CRm( 2), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c10_PRRR}, - { CRn(10), CRm( 2), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c10_NMRR}, - - /* AMAIR0/AMAIR1: swapped by interrupt.S. */ - { CRn(10), CRm( 3), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c10_AMAIR0}, - { CRn(10), CRm( 3), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c10_AMAIR1}, - - /* ICC_SGI1R */ - { CRm64(12), Op1( 0), is64, access_gic_sgi}, - - /* VBAR: swapped by interrupt.S. */ - { CRn(12), CRm( 0), Op1( 0), Op2( 0), is32, - NULL, reset_val, c12_VBAR, 0x00000000 }, - - /* ICC_ASGI1R */ - { CRm64(12), Op1( 1), is64, access_gic_sgi}, - /* ICC_SGI0R */ - { CRm64(12), Op1( 2), is64, access_gic_sgi}, - /* ICC_SRE */ - { CRn(12), CRm(12), Op1( 0), Op2(5), is32, access_gic_sre }, - - /* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */ - { CRn(13), CRm( 0), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_val, c13_CID, 0x00000000 }, - { CRn(13), CRm( 0), Op1( 0), Op2( 2), is32, - NULL, reset_unknown, c13_TID_URW }, - { CRn(13), CRm( 0), Op1( 0), Op2( 3), is32, - NULL, reset_unknown, c13_TID_URO }, - { CRn(13), CRm( 0), Op1( 0), Op2( 4), is32, - NULL, reset_unknown, c13_TID_PRIV }, - - /* CNTP */ - { CRm64(14), Op1( 2), is64, access_cntp_cval}, - - /* CNTKCTL: swapped by interrupt.S. */ - { CRn(14), CRm( 1), Op1( 0), Op2( 0), is32, - NULL, reset_val, c14_CNTKCTL, 0x00000000 }, - - /* CNTP */ - { CRn(14), CRm( 2), Op1( 0), Op2( 0), is32, access_cntp_tval }, - { CRn(14), CRm( 2), Op1( 0), Op2( 1), is32, access_cntp_ctl }, - - /* The Configuration Base Address Register. */ - { CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar}, -}; - -static int check_reg_table(const struct coproc_reg *table, unsigned int n) -{ - unsigned int i; - - for (i = 1; i < n; i++) { - if (cmp_reg(&table[i-1], &table[i]) >= 0) { - kvm_err("reg table %p out of order (%d)\n", table, i - 1); - return 1; - } - } - - return 0; -} - -/* Target specific emulation tables */ -static struct kvm_coproc_target_table *target_tables[KVM_ARM_NUM_TARGETS]; - -void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table) -{ - BUG_ON(check_reg_table(table->table, table->num)); - target_tables[table->target] = table; -} - -/* Get specific register table for this target. */ -static const struct coproc_reg *get_target_table(unsigned target, size_t *num) -{ - struct kvm_coproc_target_table *table; - - table = target_tables[target]; - *num = table->num; - return table->table; -} - -#define reg_to_match_value(x) \ - ({ \ - unsigned long val; \ - val = (x)->CRn << 11; \ - val |= (x)->CRm << 7; \ - val |= (x)->Op1 << 4; \ - val |= (x)->Op2 << 1; \ - val |= !(x)->is_64bit; \ - val; \ - }) - -static int match_reg(const void *key, const void *elt) -{ - const unsigned long pval = (unsigned long)key; - const struct coproc_reg *r = elt; - - return pval - reg_to_match_value(r); -} - -static const struct coproc_reg *find_reg(const struct coproc_params *params, - const struct coproc_reg table[], - unsigned int num) -{ - unsigned long pval = reg_to_match_value(params); - - return bsearch((void *)pval, table, num, sizeof(table[0]), match_reg); -} - -static int emulate_cp15(struct kvm_vcpu *vcpu, - const struct coproc_params *params) -{ - size_t num; - const struct coproc_reg *table, *r; - - trace_kvm_emulate_cp15_imp(params->Op1, params->Rt1, params->CRn, - params->CRm, params->Op2, params->is_write); - - table = get_target_table(vcpu->arch.target, &num); - - /* Search target-specific then generic table. */ - r = find_reg(params, table, num); - if (!r) - r = find_reg(params, cp15_regs, ARRAY_SIZE(cp15_regs)); - - if (likely(r)) { - /* If we don't have an accessor, we should never get here! */ - BUG_ON(!r->access); - - if (likely(r->access(vcpu, params, r))) { - /* Skip instruction, since it was emulated */ - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - } - } else { - /* If access function fails, it should complain. */ - kvm_err("Unsupported guest CP15 access at: %08lx [%08lx]\n", - *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); - print_cp_instr(params); - kvm_inject_undefined(vcpu); - } - - return 1; -} - -static struct coproc_params decode_64bit_hsr(struct kvm_vcpu *vcpu) -{ - struct coproc_params params; - - params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; - params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; - params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); - params.is_64bit = true; - - params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf; - params.Op2 = 0; - params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; - params.CRm = 0; - - return params; -} - -/** - * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_64bit_hsr(vcpu); - - return emulate_cp15(vcpu, ¶ms); -} - -/** - * kvm_handle_cp14_64 -- handles a mrrc/mcrr trap on a guest CP14 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_64bit_hsr(vcpu); - - /* raz_wi cp14 */ - trap_raz_wi(vcpu, ¶ms, NULL); - - /* handled */ - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; -} - -static void reset_coproc_regs(struct kvm_vcpu *vcpu, - const struct coproc_reg *table, size_t num, - unsigned long *bmap) -{ - unsigned long i; - - for (i = 0; i < num; i++) - if (table[i].reset) { - int reg = table[i].reg; - - table[i].reset(vcpu, &table[i]); - if (reg > 0 && reg < NR_CP15_REGS) { - set_bit(reg, bmap); - if (table[i].is_64bit) - set_bit(reg + 1, bmap); - } - } -} - -static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu) -{ - struct coproc_params params; - - params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; - params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; - params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); - params.is_64bit = false; - - params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; - params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 14) & 0x7; - params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7; - params.Rt2 = 0; - - return params; -} - -/** - * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_32bit_hsr(vcpu); - return emulate_cp15(vcpu, ¶ms); -} - -/** - * kvm_handle_cp14_32 -- handles a mrc/mcr trap on a guest CP14 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_32bit_hsr(vcpu); - - /* raz_wi cp14 */ - trap_raz_wi(vcpu, ¶ms, NULL); - - /* handled */ - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; -} - -/****************************************************************************** - * Userspace API - *****************************************************************************/ - -static bool index_to_params(u64 id, struct coproc_params *params) -{ - switch (id & KVM_REG_SIZE_MASK) { - case KVM_REG_SIZE_U32: - /* Any unused index bits means it's not valid. */ - if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK - | KVM_REG_ARM_COPROC_MASK - | KVM_REG_ARM_32_CRN_MASK - | KVM_REG_ARM_CRM_MASK - | KVM_REG_ARM_OPC1_MASK - | KVM_REG_ARM_32_OPC2_MASK)) - return false; - - params->is_64bit = false; - params->CRn = ((id & KVM_REG_ARM_32_CRN_MASK) - >> KVM_REG_ARM_32_CRN_SHIFT); - params->CRm = ((id & KVM_REG_ARM_CRM_MASK) - >> KVM_REG_ARM_CRM_SHIFT); - params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) - >> KVM_REG_ARM_OPC1_SHIFT); - params->Op2 = ((id & KVM_REG_ARM_32_OPC2_MASK) - >> KVM_REG_ARM_32_OPC2_SHIFT); - return true; - case KVM_REG_SIZE_U64: - /* Any unused index bits means it's not valid. */ - if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK - | KVM_REG_ARM_COPROC_MASK - | KVM_REG_ARM_CRM_MASK - | KVM_REG_ARM_OPC1_MASK)) - return false; - params->is_64bit = true; - /* CRm to CRn: see cp15_to_index for details */ - params->CRn = ((id & KVM_REG_ARM_CRM_MASK) - >> KVM_REG_ARM_CRM_SHIFT); - params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) - >> KVM_REG_ARM_OPC1_SHIFT); - params->Op2 = 0; - params->CRm = 0; - return true; - default: - return false; - } -} - -/* Decode an index value, and find the cp15 coproc_reg entry. */ -static const struct coproc_reg *index_to_coproc_reg(struct kvm_vcpu *vcpu, - u64 id) -{ - size_t num; - const struct coproc_reg *table, *r; - struct coproc_params params; - - /* We only do cp15 for now. */ - if ((id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT != 15) - return NULL; - - if (!index_to_params(id, ¶ms)) - return NULL; - - table = get_target_table(vcpu->arch.target, &num); - r = find_reg(¶ms, table, num); - if (!r) - r = find_reg(¶ms, cp15_regs, ARRAY_SIZE(cp15_regs)); - - /* Not saved in the cp15 array? */ - if (r && !r->reg) - r = NULL; - - return r; -} - -/* - * These are the invariant cp15 registers: we let the guest see the host - * versions of these, so they're part of the guest state. - * - * A future CPU may provide a mechanism to present different values to - * the guest, or a future kvm may trap them. - */ -/* Unfortunately, there's no register-argument for mrc, so generate. */ -#define FUNCTION_FOR32(crn, crm, op1, op2, name) \ - static void get_##name(struct kvm_vcpu *v, \ - const struct coproc_reg *r) \ - { \ - u32 val; \ - \ - asm volatile("mrc p15, " __stringify(op1) \ - ", %0, c" __stringify(crn) \ - ", c" __stringify(crm) \ - ", " __stringify(op2) "\n" : "=r" (val)); \ - ((struct coproc_reg *)r)->val = val; \ - } - -FUNCTION_FOR32(0, 0, 0, 0, MIDR) -FUNCTION_FOR32(0, 0, 0, 1, CTR) -FUNCTION_FOR32(0, 0, 0, 2, TCMTR) -FUNCTION_FOR32(0, 0, 0, 3, TLBTR) -FUNCTION_FOR32(0, 0, 0, 6, REVIDR) -FUNCTION_FOR32(0, 1, 0, 0, ID_PFR0) -FUNCTION_FOR32(0, 1, 0, 1, ID_PFR1) -FUNCTION_FOR32(0, 1, 0, 2, ID_DFR0) -FUNCTION_FOR32(0, 1, 0, 3, ID_AFR0) -FUNCTION_FOR32(0, 1, 0, 4, ID_MMFR0) -FUNCTION_FOR32(0, 1, 0, 5, ID_MMFR1) -FUNCTION_FOR32(0, 1, 0, 6, ID_MMFR2) -FUNCTION_FOR32(0, 1, 0, 7, ID_MMFR3) -FUNCTION_FOR32(0, 2, 0, 0, ID_ISAR0) -FUNCTION_FOR32(0, 2, 0, 1, ID_ISAR1) -FUNCTION_FOR32(0, 2, 0, 2, ID_ISAR2) -FUNCTION_FOR32(0, 2, 0, 3, ID_ISAR3) -FUNCTION_FOR32(0, 2, 0, 4, ID_ISAR4) -FUNCTION_FOR32(0, 2, 0, 5, ID_ISAR5) -FUNCTION_FOR32(0, 0, 1, 1, CLIDR) -FUNCTION_FOR32(0, 0, 1, 7, AIDR) - -/* ->val is filled in by kvm_invariant_coproc_table_init() */ -static struct coproc_reg invariant_cp15[] = { - { CRn( 0), CRm( 0), Op1( 0), Op2( 0), is32, NULL, get_MIDR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 1), is32, NULL, get_CTR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 2), is32, NULL, get_TCMTR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 3), is32, NULL, get_TLBTR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 6), is32, NULL, get_REVIDR }, - - { CRn( 0), CRm( 0), Op1( 1), Op2( 1), is32, NULL, get_CLIDR }, - { CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR }, - - { CRn( 0), CRm( 1), Op1( 0), Op2( 0), is32, NULL, get_ID_PFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 1), is32, NULL, get_ID_PFR1 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 2), is32, NULL, get_ID_DFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 3), is32, NULL, get_ID_AFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 4), is32, NULL, get_ID_MMFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 5), is32, NULL, get_ID_MMFR1 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 6), is32, NULL, get_ID_MMFR2 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 7), is32, NULL, get_ID_MMFR3 }, - - { CRn( 0), CRm( 2), Op1( 0), Op2( 0), is32, NULL, get_ID_ISAR0 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 1), is32, NULL, get_ID_ISAR1 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 2), is32, NULL, get_ID_ISAR2 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 3), is32, NULL, get_ID_ISAR3 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 4), is32, NULL, get_ID_ISAR4 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 5), is32, NULL, get_ID_ISAR5 }, -}; - -/* - * Reads a register value from a userspace address to a kernel - * variable. Make sure that register size matches sizeof(*__val). - */ -static int reg_from_user(void *val, const void __user *uaddr, u64 id) -{ - if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0) - return -EFAULT; - return 0; -} - -/* - * Writes a register value to a userspace address from a kernel variable. - * Make sure that register size matches sizeof(*__val). - */ -static int reg_to_user(void __user *uaddr, const void *val, u64 id) -{ - if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0) - return -EFAULT; - return 0; -} - -static int get_invariant_cp15(u64 id, void __user *uaddr) -{ - struct coproc_params params; - const struct coproc_reg *r; - int ret; - - if (!index_to_params(id, ¶ms)) - return -ENOENT; - - r = find_reg(¶ms, invariant_cp15, ARRAY_SIZE(invariant_cp15)); - if (!r) - return -ENOENT; - - ret = -ENOENT; - if (KVM_REG_SIZE(id) == 4) { - u32 val = r->val; - - ret = reg_to_user(uaddr, &val, id); - } else if (KVM_REG_SIZE(id) == 8) { - ret = reg_to_user(uaddr, &r->val, id); - } - return ret; -} - -static int set_invariant_cp15(u64 id, void __user *uaddr) -{ - struct coproc_params params; - const struct coproc_reg *r; - int err; - u64 val; - - if (!index_to_params(id, ¶ms)) - return -ENOENT; - r = find_reg(¶ms, invariant_cp15, ARRAY_SIZE(invariant_cp15)); - if (!r) - return -ENOENT; - - err = -ENOENT; - if (KVM_REG_SIZE(id) == 4) { - u32 val32; - - err = reg_from_user(&val32, uaddr, id); - if (!err) - val = val32; - } else if (KVM_REG_SIZE(id) == 8) { - err = reg_from_user(&val, uaddr, id); - } - if (err) - return err; - - /* This is what we mean by invariant: you can't change it. */ - if (r->val != val) - return -EINVAL; - - return 0; -} - -static bool is_valid_cache(u32 val) -{ - u32 level, ctype; - - if (val >= CSSELR_MAX) - return false; - - /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ - level = (val >> 1); - ctype = (cache_levels >> (level * 3)) & 7; - - switch (ctype) { - case 0: /* No cache */ - return false; - case 1: /* Instruction cache only */ - return (val & 1); - case 2: /* Data cache only */ - case 4: /* Unified cache */ - return !(val & 1); - case 3: /* Separate instruction and data caches */ - return true; - default: /* Reserved: we can't know instruction or data. */ - return false; - } -} - -/* Which cache CCSIDR represents depends on CSSELR value. */ -static u32 get_ccsidr(u32 csselr) -{ - u32 ccsidr; - - /* Make sure noone else changes CSSELR during this! */ - local_irq_disable(); - /* Put value into CSSELR */ - asm volatile("mcr p15, 2, %0, c0, c0, 0" : : "r" (csselr)); - isb(); - /* Read result out of CCSIDR */ - asm volatile("mrc p15, 1, %0, c0, c0, 0" : "=r" (ccsidr)); - local_irq_enable(); - - return ccsidr; -} - -static int demux_c15_get(u64 id, void __user *uaddr) -{ - u32 val; - u32 __user *uval = uaddr; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { - case KVM_REG_ARM_DEMUX_ID_CCSIDR: - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) - >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) - return -ENOENT; - - return put_user(get_ccsidr(val), uval); - default: - return -ENOENT; - } -} - -static int demux_c15_set(u64 id, void __user *uaddr) -{ - u32 val, newval; - u32 __user *uval = uaddr; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { - case KVM_REG_ARM_DEMUX_ID_CCSIDR: - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) - >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) - return -ENOENT; - - if (get_user(newval, uval)) - return -EFAULT; - - /* This is also invariant: you can't change it. */ - if (newval != get_ccsidr(val)) - return -EINVAL; - return 0; - default: - return -ENOENT; - } -} - -#ifdef CONFIG_VFPv3 -static const int vfp_sysregs[] = { KVM_REG_ARM_VFP_FPEXC, - KVM_REG_ARM_VFP_FPSCR, - KVM_REG_ARM_VFP_FPINST, - KVM_REG_ARM_VFP_FPINST2, - KVM_REG_ARM_VFP_MVFR0, - KVM_REG_ARM_VFP_MVFR1, - KVM_REG_ARM_VFP_FPSID }; - -static unsigned int num_fp_regs(void) -{ - if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK) >> MVFR0_A_SIMD_BIT) == 2) - return 32; - else - return 16; -} - -static unsigned int num_vfp_regs(void) -{ - /* Normal FP regs + control regs. */ - return num_fp_regs() + ARRAY_SIZE(vfp_sysregs); -} - -static int copy_vfp_regids(u64 __user *uindices) -{ - unsigned int i; - const u64 u32reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP; - const u64 u64reg = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP; - - for (i = 0; i < num_fp_regs(); i++) { - if (put_user((u64reg | KVM_REG_ARM_VFP_BASE_REG) + i, - uindices)) - return -EFAULT; - uindices++; - } - - for (i = 0; i < ARRAY_SIZE(vfp_sysregs); i++) { - if (put_user(u32reg | vfp_sysregs[i], uindices)) - return -EFAULT; - uindices++; - } - - return num_vfp_regs(); -} - -static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) -{ - u32 vfpid = (id & KVM_REG_ARM_VFP_MASK); - u32 val; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - if (vfpid < num_fp_regs()) { - if (KVM_REG_SIZE(id) != 8) - return -ENOENT; - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpregs[vfpid], - id); - } - - /* FP control registers are all 32 bit. */ - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - - switch (vfpid) { - case KVM_REG_ARM_VFP_FPEXC: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpexc, id); - case KVM_REG_ARM_VFP_FPSCR: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpscr, id); - case KVM_REG_ARM_VFP_FPINST: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst, id); - case KVM_REG_ARM_VFP_FPINST2: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst2, id); - case KVM_REG_ARM_VFP_MVFR0: - val = fmrx(MVFR0); - return reg_to_user(uaddr, &val, id); - case KVM_REG_ARM_VFP_MVFR1: - val = fmrx(MVFR1); - return reg_to_user(uaddr, &val, id); - case KVM_REG_ARM_VFP_FPSID: - val = fmrx(FPSID); - return reg_to_user(uaddr, &val, id); - default: - return -ENOENT; - } -} - -static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr) -{ - u32 vfpid = (id & KVM_REG_ARM_VFP_MASK); - u32 val; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - if (vfpid < num_fp_regs()) { - if (KVM_REG_SIZE(id) != 8) - return -ENOENT; - return reg_from_user(&vcpu->arch.ctxt.vfp.fpregs[vfpid], - uaddr, id); - } - - /* FP control registers are all 32 bit. */ - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - - switch (vfpid) { - case KVM_REG_ARM_VFP_FPEXC: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpexc, uaddr, id); - case KVM_REG_ARM_VFP_FPSCR: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpscr, uaddr, id); - case KVM_REG_ARM_VFP_FPINST: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst, uaddr, id); - case KVM_REG_ARM_VFP_FPINST2: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst2, uaddr, id); - /* These are invariant. */ - case KVM_REG_ARM_VFP_MVFR0: - if (reg_from_user(&val, uaddr, id)) - return -EFAULT; - if (val != fmrx(MVFR0)) - return -EINVAL; - return 0; - case KVM_REG_ARM_VFP_MVFR1: - if (reg_from_user(&val, uaddr, id)) - return -EFAULT; - if (val != fmrx(MVFR1)) - return -EINVAL; - return 0; - case KVM_REG_ARM_VFP_FPSID: - if (reg_from_user(&val, uaddr, id)) - return -EFAULT; - if (val != fmrx(FPSID)) - return -EINVAL; - return 0; - default: - return -ENOENT; - } -} -#else /* !CONFIG_VFPv3 */ -static unsigned int num_vfp_regs(void) -{ - return 0; -} - -static int copy_vfp_regids(u64 __user *uindices) -{ - return 0; -} - -static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) -{ - return -ENOENT; -} - -static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr) -{ - return -ENOENT; -} -#endif /* !CONFIG_VFPv3 */ - -int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - const struct coproc_reg *r; - void __user *uaddr = (void __user *)(long)reg->addr; - int ret; - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_get(reg->id, uaddr); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_VFP) - return vfp_get_reg(vcpu, reg->id, uaddr); - - r = index_to_coproc_reg(vcpu, reg->id); - if (!r) - return get_invariant_cp15(reg->id, uaddr); - - ret = -ENOENT; - if (KVM_REG_SIZE(reg->id) == 8) { - u64 val; - - val = vcpu_cp15_reg64_get(vcpu, r); - ret = reg_to_user(uaddr, &val, reg->id); - } else if (KVM_REG_SIZE(reg->id) == 4) { - ret = reg_to_user(uaddr, &vcpu_cp15(vcpu, r->reg), reg->id); - } - - return ret; -} - -int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - const struct coproc_reg *r; - void __user *uaddr = (void __user *)(long)reg->addr; - int ret; - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_set(reg->id, uaddr); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_VFP) - return vfp_set_reg(vcpu, reg->id, uaddr); - - r = index_to_coproc_reg(vcpu, reg->id); - if (!r) - return set_invariant_cp15(reg->id, uaddr); - - ret = -ENOENT; - if (KVM_REG_SIZE(reg->id) == 8) { - u64 val; - - ret = reg_from_user(&val, uaddr, reg->id); - if (!ret) - vcpu_cp15_reg64_set(vcpu, r, val); - } else if (KVM_REG_SIZE(reg->id) == 4) { - ret = reg_from_user(&vcpu_cp15(vcpu, r->reg), uaddr, reg->id); - } - - return ret; -} - -static unsigned int num_demux_regs(void) -{ - unsigned int i, count = 0; - - for (i = 0; i < CSSELR_MAX; i++) - if (is_valid_cache(i)) - count++; - - return count; -} - -static int write_demux_regids(u64 __user *uindices) -{ - u64 val = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX; - unsigned int i; - - val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; - for (i = 0; i < CSSELR_MAX; i++) { - if (!is_valid_cache(i)) - continue; - if (put_user(val | i, uindices)) - return -EFAULT; - uindices++; - } - return 0; -} - -static u64 cp15_to_index(const struct coproc_reg *reg) -{ - u64 val = KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT); - if (reg->is_64bit) { - val |= KVM_REG_SIZE_U64; - val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); - /* - * CRn always denotes the primary coproc. reg. nr. for the - * in-kernel representation, but the user space API uses the - * CRm for the encoding, because it is modelled after the - * MRRC/MCRR instructions: see the ARM ARM rev. c page - * B3-1445 - */ - val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT); - } else { - val |= KVM_REG_SIZE_U32; - val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); - val |= (reg->Op2 << KVM_REG_ARM_32_OPC2_SHIFT); - val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT); - val |= (reg->CRn << KVM_REG_ARM_32_CRN_SHIFT); - } - return val; -} - -static bool copy_reg_to_user(const struct coproc_reg *reg, u64 __user **uind) -{ - if (!*uind) - return true; - - if (put_user(cp15_to_index(reg), *uind)) - return false; - - (*uind)++; - return true; -} - -/* Assumed ordered tables, see kvm_coproc_table_init. */ -static int walk_cp15(struct kvm_vcpu *vcpu, u64 __user *uind) -{ - const struct coproc_reg *i1, *i2, *end1, *end2; - unsigned int total = 0; - size_t num; - - /* We check for duplicates here, to allow arch-specific overrides. */ - i1 = get_target_table(vcpu->arch.target, &num); - end1 = i1 + num; - i2 = cp15_regs; - end2 = cp15_regs + ARRAY_SIZE(cp15_regs); - - BUG_ON(i1 == end1 || i2 == end2); - - /* Walk carefully, as both tables may refer to the same register. */ - while (i1 || i2) { - int cmp = cmp_reg(i1, i2); - /* target-specific overrides generic entry. */ - if (cmp <= 0) { - /* Ignore registers we trap but don't save. */ - if (i1->reg) { - if (!copy_reg_to_user(i1, &uind)) - return -EFAULT; - total++; - } - } else { - /* Ignore registers we trap but don't save. */ - if (i2->reg) { - if (!copy_reg_to_user(i2, &uind)) - return -EFAULT; - total++; - } - } - - if (cmp <= 0 && ++i1 == end1) - i1 = NULL; - if (cmp >= 0 && ++i2 == end2) - i2 = NULL; - } - return total; -} - -unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu) -{ - return ARRAY_SIZE(invariant_cp15) - + num_demux_regs() - + num_vfp_regs() - + walk_cp15(vcpu, (u64 __user *)NULL); -} - -int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - unsigned int i; - int err; - - /* Then give them all the invariant registers' indices. */ - for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++) { - if (put_user(cp15_to_index(&invariant_cp15[i]), uindices)) - return -EFAULT; - uindices++; - } - - err = walk_cp15(vcpu, uindices); - if (err < 0) - return err; - uindices += err; - - err = copy_vfp_regids(uindices); - if (err < 0) - return err; - uindices += err; - - return write_demux_regids(uindices); -} - -void kvm_coproc_table_init(void) -{ - unsigned int i; - - /* Make sure tables are unique and in order. */ - BUG_ON(check_reg_table(cp15_regs, ARRAY_SIZE(cp15_regs))); - BUG_ON(check_reg_table(invariant_cp15, ARRAY_SIZE(invariant_cp15))); - - /* We abuse the reset function to overwrite the table itself. */ - for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++) - invariant_cp15[i].reset(NULL, &invariant_cp15[i]); - - /* - * CLIDR format is awkward, so clean it up. See ARM B4.1.20: - * - * If software reads the Cache Type fields from Ctype1 - * upwards, once it has seen a value of 0b000, no caches - * exist at further-out levels of the hierarchy. So, for - * example, if Ctype3 is the first Cache Type field with a - * value of 0b000, the values of Ctype4 to Ctype7 must be - * ignored. - */ - asm volatile("mrc p15, 1, %0, c0, c0, 1" : "=r" (cache_levels)); - for (i = 0; i < 7; i++) - if (((cache_levels >> (i*3)) & 7) == 0) - break; - /* Clear all higher bits. */ - cache_levels &= (1 << (i*3))-1; -} - -/** - * kvm_reset_coprocs - sets cp15 registers to reset value - * @vcpu: The VCPU pointer - * - * This function finds the right table above and sets the registers on the - * virtual CPU struct to their architecturally defined reset values. - */ -void kvm_reset_coprocs(struct kvm_vcpu *vcpu) -{ - size_t num; - const struct coproc_reg *table; - DECLARE_BITMAP(bmap, NR_CP15_REGS) = { 0, }; - - /* Generic chip reset first (so target could override). */ - reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs), bmap); - - table = get_target_table(vcpu->arch.target, &num); - reset_coproc_regs(vcpu, table, num, bmap); - - for (num = 1; num < NR_CP15_REGS; num++) - WARN(!test_bit(num, bmap), - "Didn't reset vcpu_cp15(vcpu, %zi)", num); -} diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h deleted file mode 100644 index 637065b13012..000000000000 --- a/arch/arm/kvm/coproc.h +++ /dev/null @@ -1,130 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Authors: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_COPROC_LOCAL_H__ -#define __ARM_KVM_COPROC_LOCAL_H__ - -struct coproc_params { - unsigned long CRn; - unsigned long CRm; - unsigned long Op1; - unsigned long Op2; - unsigned long Rt1; - unsigned long Rt2; - bool is_64bit; - bool is_write; -}; - -struct coproc_reg { - /* MRC/MCR/MRRC/MCRR instruction which accesses it. */ - unsigned long CRn; - unsigned long CRm; - unsigned long Op1; - unsigned long Op2; - - bool is_64bit; - - /* Trapped access from guest, if non-NULL. */ - bool (*access)(struct kvm_vcpu *, - const struct coproc_params *, - const struct coproc_reg *); - - /* Initialization for vcpu. */ - void (*reset)(struct kvm_vcpu *, const struct coproc_reg *); - - /* Index into vcpu_cp15(vcpu, ...), or 0 if we don't need to save it. */ - unsigned long reg; - - /* Value (usually reset value) */ - u64 val; -}; - -static inline void print_cp_instr(const struct coproc_params *p) -{ - /* Look, we even formatted it for you to paste into the table! */ - if (p->is_64bit) { - kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n", - p->CRn, p->Op1, p->is_write ? "write" : "read"); - } else { - kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32," - " func_%s },\n", - p->CRn, p->CRm, p->Op1, p->Op2, - p->is_write ? "write" : "read"); - } -} - -static inline bool ignore_write(struct kvm_vcpu *vcpu, - const struct coproc_params *p) -{ - return true; -} - -static inline bool read_zero(struct kvm_vcpu *vcpu, - const struct coproc_params *p) -{ - *vcpu_reg(vcpu, p->Rt1) = 0; - return true; -} - -/* Reset functions */ -static inline void reset_unknown(struct kvm_vcpu *vcpu, - const struct coproc_reg *r) -{ - BUG_ON(!r->reg); - BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15)); - vcpu_cp15(vcpu, r->reg) = 0xdecafbad; -} - -static inline void reset_val(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - BUG_ON(!r->reg); - BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15)); - vcpu_cp15(vcpu, r->reg) = r->val; -} - -static inline void reset_unknown64(struct kvm_vcpu *vcpu, - const struct coproc_reg *r) -{ - BUG_ON(!r->reg); - BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.ctxt.cp15)); - - vcpu_cp15(vcpu, r->reg) = 0xdecafbad; - vcpu_cp15(vcpu, r->reg+1) = 0xd0c0ffee; -} - -static inline int cmp_reg(const struct coproc_reg *i1, - const struct coproc_reg *i2) -{ - BUG_ON(i1 == i2); - if (!i1) - return 1; - else if (!i2) - return -1; - if (i1->CRn != i2->CRn) - return i1->CRn - i2->CRn; - if (i1->CRm != i2->CRm) - return i1->CRm - i2->CRm; - if (i1->Op1 != i2->Op1) - return i1->Op1 - i2->Op1; - if (i1->Op2 != i2->Op2) - return i1->Op2 - i2->Op2; - return i2->is_64bit - i1->is_64bit; -} - - -#define CRn(_x) .CRn = _x -#define CRm(_x) .CRm = _x -#define CRm64(_x) .CRn = _x, .CRm = 0 -#define Op1(_x) .Op1 = _x -#define Op2(_x) .Op2 = _x -#define is64 .is_64bit = true -#define is32 .is_64bit = false - -bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r); - -#endif /* __ARM_KVM_COPROC_LOCAL_H__ */ diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c deleted file mode 100644 index 36bf15421ae8..000000000000 --- a/arch/arm/kvm/coproc_a15.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Authors: Rusty Russell <rusty@rustcorp.au> - * Christoffer Dall <c.dall@virtualopensystems.com> - */ -#include <linux/kvm_host.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_emulate.h> -#include <linux/init.h> - -#include "coproc.h" - -/* - * A15-specific CP15 registers. - * CRn denotes the primary register number, but is copied to the CRm in the - * user space API for 64-bit register access in line with the terminology used - * in the ARM ARM. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit - * registers preceding 32-bit ones. - */ -static const struct coproc_reg a15_regs[] = { - /* SCTLR: swapped by interrupt.S. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_val, c1_SCTLR, 0x00C50078 }, -}; - -static struct kvm_coproc_target_table a15_target_table = { - .target = KVM_ARM_TARGET_CORTEX_A15, - .table = a15_regs, - .num = ARRAY_SIZE(a15_regs), -}; - -static int __init coproc_a15_init(void) -{ - kvm_register_target_coproc_table(&a15_target_table); - return 0; -} -late_initcall(coproc_a15_init); diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c deleted file mode 100644 index 40f643e1e05c..000000000000 --- a/arch/arm/kvm/coproc_a7.c +++ /dev/null @@ -1,42 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Copyright (C) 2013 - ARM Ltd - * - * Authors: Rusty Russell <rusty@rustcorp.au> - * Christoffer Dall <c.dall@virtualopensystems.com> - * Jonathan Austin <jonathan.austin@arm.com> - */ -#include <linux/kvm_host.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_emulate.h> -#include <linux/init.h> - -#include "coproc.h" - -/* - * Cortex-A7 specific CP15 registers. - * CRn denotes the primary register number, but is copied to the CRm in the - * user space API for 64-bit register access in line with the terminology used - * in the ARM ARM. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit - * registers preceding 32-bit ones. - */ -static const struct coproc_reg a7_regs[] = { - /* SCTLR: swapped by interrupt.S. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_val, c1_SCTLR, 0x00C50878 }, -}; - -static struct kvm_coproc_target_table a7_target_table = { - .target = KVM_ARM_TARGET_CORTEX_A7, - .table = a7_regs, - .num = ARRAY_SIZE(a7_regs), -}; - -static int __init coproc_a7_init(void) -{ - kvm_register_target_coproc_table(&a7_target_table); - return 0; -} -late_initcall(coproc_a7_init); diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c deleted file mode 100644 index 29bb852140c5..000000000000 --- a/arch/arm/kvm/emulate.c +++ /dev/null @@ -1,166 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/mm.h> -#include <linux/kvm_host.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_emulate.h> -#include <asm/opcodes.h> -#include <trace/events/kvm.h> - -#include "trace.h" - -#define VCPU_NR_MODES 6 -#define VCPU_REG_OFFSET_USR 0 -#define VCPU_REG_OFFSET_FIQ 1 -#define VCPU_REG_OFFSET_IRQ 2 -#define VCPU_REG_OFFSET_SVC 3 -#define VCPU_REG_OFFSET_ABT 4 -#define VCPU_REG_OFFSET_UND 5 -#define REG_OFFSET(_reg) \ - (offsetof(struct kvm_regs, _reg) / sizeof(u32)) - -#define USR_REG_OFFSET(_num) REG_OFFSET(usr_regs.uregs[_num]) - -static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = { - /* USR/SYS Registers */ - [VCPU_REG_OFFSET_USR] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), USR_REG_OFFSET(13), USR_REG_OFFSET(14), - }, - - /* FIQ Registers */ - [VCPU_REG_OFFSET_FIQ] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), - REG_OFFSET(fiq_regs[0]), /* r8 */ - REG_OFFSET(fiq_regs[1]), /* r9 */ - REG_OFFSET(fiq_regs[2]), /* r10 */ - REG_OFFSET(fiq_regs[3]), /* r11 */ - REG_OFFSET(fiq_regs[4]), /* r12 */ - REG_OFFSET(fiq_regs[5]), /* r13 */ - REG_OFFSET(fiq_regs[6]), /* r14 */ - }, - - /* IRQ Registers */ - [VCPU_REG_OFFSET_IRQ] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(irq_regs[0]), /* r13 */ - REG_OFFSET(irq_regs[1]), /* r14 */ - }, - - /* SVC Registers */ - [VCPU_REG_OFFSET_SVC] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(svc_regs[0]), /* r13 */ - REG_OFFSET(svc_regs[1]), /* r14 */ - }, - - /* ABT Registers */ - [VCPU_REG_OFFSET_ABT] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(abt_regs[0]), /* r13 */ - REG_OFFSET(abt_regs[1]), /* r14 */ - }, - - /* UND Registers */ - [VCPU_REG_OFFSET_UND] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(und_regs[0]), /* r13 */ - REG_OFFSET(und_regs[1]), /* r14 */ - }, -}; - -/* - * Return a pointer to the register number valid in the current mode of - * the virtual CPU. - */ -unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) -{ - unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs; - unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; - - switch (mode) { - case USR_MODE...SVC_MODE: - mode &= ~MODE32_BIT; /* 0 ... 3 */ - break; - - case ABT_MODE: - mode = VCPU_REG_OFFSET_ABT; - break; - - case UND_MODE: - mode = VCPU_REG_OFFSET_UND; - break; - - case SYSTEM_MODE: - mode = VCPU_REG_OFFSET_USR; - break; - - default: - BUG(); - } - - return reg_array + vcpu_reg_offsets[mode][reg_num]; -} - -/* - * Return the SPSR for the current mode of the virtual CPU. - */ -unsigned long *__vcpu_spsr(struct kvm_vcpu *vcpu) -{ - unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; - switch (mode) { - case SVC_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_SVC_spsr; - case ABT_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_ABT_spsr; - case UND_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_UND_spsr; - case IRQ_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_IRQ_spsr; - case FIQ_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_FIQ_spsr; - default: - BUG(); - } -} - -/****************************************************************************** - * Inject exceptions into the guest - */ - -/** - * kvm_inject_vabt - inject an async abort / SError into the guest - * @vcpu: The VCPU to receive the exception - * - * It is assumed that this code is called from the VCPU thread and that the - * VCPU therefore is not currently executing guest code. - */ -void kvm_inject_vabt(struct kvm_vcpu *vcpu) -{ - *vcpu_hcr(vcpu) |= HCR_VA; -} diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c deleted file mode 100644 index 9f7ae0d8690f..000000000000 --- a/arch/arm/kvm/guest.c +++ /dev/null @@ -1,387 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/errno.h> -#include <linux/err.h> -#include <linux/kvm_host.h> -#include <linux/module.h> -#include <linux/vmalloc.h> -#include <linux/fs.h> -#include <kvm/arm_psci.h> -#include <asm/cputype.h> -#include <linux/uaccess.h> -#include <asm/kvm.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> - -#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM } -#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } - -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT(halt_successful_poll), - VCPU_STAT(halt_attempted_poll), - VCPU_STAT(halt_poll_invalid), - VCPU_STAT(halt_wakeup), - VCPU_STAT(hvc_exit_stat), - VCPU_STAT(wfe_exit_stat), - VCPU_STAT(wfi_exit_stat), - VCPU_STAT(mmio_exit_user), - VCPU_STAT(mmio_exit_kernel), - VCPU_STAT(exits), - { NULL } -}; - -static u64 core_reg_offset_from_id(u64 id) -{ - return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); -} - -static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - u32 __user *uaddr = (u32 __user *)(long)reg->addr; - struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs; - u64 off; - - if (KVM_REG_SIZE(reg->id) != 4) - return -ENOENT; - - /* Our ID is an index into the kvm_regs struct. */ - off = core_reg_offset_from_id(reg->id); - if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id)) - return -ENOENT; - - return put_user(((u32 *)regs)[off], uaddr); -} - -static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - u32 __user *uaddr = (u32 __user *)(long)reg->addr; - struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs; - u64 off, val; - - if (KVM_REG_SIZE(reg->id) != 4) - return -ENOENT; - - /* Our ID is an index into the kvm_regs struct. */ - off = core_reg_offset_from_id(reg->id); - if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id)) - return -ENOENT; - - if (get_user(val, uaddr) != 0) - return -EFAULT; - - if (off == KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr)) { - unsigned long mode = val & MODE_MASK; - switch (mode) { - case USR_MODE: - case FIQ_MODE: - case IRQ_MODE: - case SVC_MODE: - case ABT_MODE: - case UND_MODE: - break; - default: - return -EINVAL; - } - } - - ((u32 *)regs)[off] = val; - return 0; -} - -int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) -{ - return -EINVAL; -} - -#define NUM_TIMER_REGS 3 - -static bool is_timer_reg(u64 index) -{ - switch (index) { - case KVM_REG_ARM_TIMER_CTL: - case KVM_REG_ARM_TIMER_CNT: - case KVM_REG_ARM_TIMER_CVAL: - return true; - } - return false; -} - -static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - if (put_user(KVM_REG_ARM_TIMER_CTL, uindices)) - return -EFAULT; - uindices++; - if (put_user(KVM_REG_ARM_TIMER_CNT, uindices)) - return -EFAULT; - uindices++; - if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices)) - return -EFAULT; - - return 0; -} - -static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - int ret; - - ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)); - if (ret != 0) - return -EFAULT; - - return kvm_arm_timer_set_reg(vcpu, reg->id, val); -} - -static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - - val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; -} - -static unsigned long num_core_regs(void) -{ - return sizeof(struct kvm_regs) / sizeof(u32); -} - -/** - * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG - * - * This is for all registers. - */ -unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) -{ - return num_core_regs() + kvm_arm_num_coproc_regs(vcpu) - + kvm_arm_get_fw_num_regs(vcpu) - + NUM_TIMER_REGS; -} - -/** - * kvm_arm_copy_reg_indices - get indices of all registers. - * - * We do core registers right here, then we append coproc regs. - */ -int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - unsigned int i; - const u64 core_reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE; - int ret; - - for (i = 0; i < sizeof(struct kvm_regs)/sizeof(u32); i++) { - if (put_user(core_reg | i, uindices)) - return -EFAULT; - uindices++; - } - - ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); - if (ret) - return ret; - uindices += kvm_arm_get_fw_num_regs(vcpu); - - ret = copy_timer_indices(vcpu, uindices); - if (ret) - return ret; - uindices += NUM_TIMER_REGS; - - return kvm_arm_copy_coproc_indices(vcpu, uindices); -} - -int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - /* We currently use nothing arch-specific in upper 32 bits */ - if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM >> 32) - return -EINVAL; - - /* Register group 16 means we want a core register. */ - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) - return get_core_reg(vcpu, reg); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) - return kvm_arm_get_fw_reg(vcpu, reg); - - if (is_timer_reg(reg->id)) - return get_timer_reg(vcpu, reg); - - return kvm_arm_coproc_get_reg(vcpu, reg); -} - -int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - /* We currently use nothing arch-specific in upper 32 bits */ - if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM >> 32) - return -EINVAL; - - /* Register group 16 means we set a core register. */ - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) - return set_core_reg(vcpu, reg); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) - return kvm_arm_set_fw_reg(vcpu, reg); - - if (is_timer_reg(reg->id)) - return set_timer_reg(vcpu, reg); - - return kvm_arm_coproc_set_reg(vcpu, reg); -} - -int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - return -EINVAL; -} - - -int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events) -{ - events->exception.serror_pending = !!(*vcpu_hcr(vcpu) & HCR_VA); - - /* - * We never return a pending ext_dabt here because we deliver it to - * the virtual CPU directly when setting the event and it's no longer - * 'pending' at this point. - */ - - return 0; -} - -int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events) -{ - bool serror_pending = events->exception.serror_pending; - bool has_esr = events->exception.serror_has_esr; - bool ext_dabt_pending = events->exception.ext_dabt_pending; - - if (serror_pending && has_esr) - return -EINVAL; - else if (serror_pending) - kvm_inject_vabt(vcpu); - - if (ext_dabt_pending) - kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - - return 0; -} - -int __attribute_const__ kvm_target_cpu(void) -{ - switch (read_cpuid_part()) { - case ARM_CPU_PART_CORTEX_A7: - return KVM_ARM_TARGET_CORTEX_A7; - case ARM_CPU_PART_CORTEX_A15: - return KVM_ARM_TARGET_CORTEX_A15; - default: - return -EINVAL; - } -} - -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) -{ - int target = kvm_target_cpu(); - - if (target < 0) - return -ENODEV; - - memset(init, 0, sizeof(*init)); - - /* - * For now, we don't return any features. - * In future, we might use features to return target - * specific features available for the preferred - * target type. - */ - init->target = (__u32)target; - - return 0; -} - -int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, - struct kvm_translation *tr) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg) -{ - return -EINVAL; -} - -int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr) -{ - int ret; - - switch (attr->group) { - case KVM_ARM_VCPU_TIMER_CTRL: - ret = kvm_arm_timer_set_attr(vcpu, attr); - break; - default: - ret = -ENXIO; - break; - } - - return ret; -} - -int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr) -{ - int ret; - - switch (attr->group) { - case KVM_ARM_VCPU_TIMER_CTRL: - ret = kvm_arm_timer_get_attr(vcpu, attr); - break; - default: - ret = -ENXIO; - break; - } - - return ret; -} - -int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr) -{ - int ret; - - switch (attr->group) { - case KVM_ARM_VCPU_TIMER_CTRL: - ret = kvm_arm_timer_has_attr(vcpu, attr); - break; - default: - ret = -ENXIO; - break; - } - - return ret; -} diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c deleted file mode 100644 index e58a89d2f13f..000000000000 --- a/arch/arm/kvm/handle_exit.c +++ /dev/null @@ -1,175 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_mmu.h> -#include <kvm/arm_hypercalls.h> -#include <trace/events/kvm.h> - -#include "trace.h" - -typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); - -static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - int ret; - - trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), - kvm_vcpu_hvc_get_imm(vcpu)); - vcpu->stat.hvc_exit_stat++; - - ret = kvm_hvc_call_handler(vcpu); - if (ret < 0) { - vcpu_set_reg(vcpu, 0, ~0UL); - return 1; - } - - return ret; -} - -static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* - * "If an SMC instruction executed at Non-secure EL1 is - * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a - * Trap exception, not a Secure Monitor Call exception [...]" - * - * We need to advance the PC after the trap, as it would - * otherwise return to the same address... - */ - vcpu_set_reg(vcpu, 0, ~0UL); - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; -} - -/** - * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests - * @vcpu: the vcpu pointer - * @run: the kvm_run structure pointer - * - * WFE: Yield the CPU and come back to this vcpu when the scheduler - * decides to. - * WFI: Simply call kvm_vcpu_block(), which will halt execution of - * world-switches and schedule other host processes until there is an - * incoming IRQ or FIQ to the VM. - */ -static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) { - trace_kvm_wfx(*vcpu_pc(vcpu), true); - vcpu->stat.wfe_exit_stat++; - kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu)); - } else { - trace_kvm_wfx(*vcpu_pc(vcpu), false); - vcpu->stat.wfi_exit_stat++; - kvm_vcpu_block(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); - } - - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - - return 1; -} - -static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - u32 hsr = kvm_vcpu_get_hsr(vcpu); - - kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n", - hsr); - - kvm_inject_undefined(vcpu); - return 1; -} - -static exit_handle_fn arm_exit_handlers[] = { - [0 ... HSR_EC_MAX] = kvm_handle_unknown_ec, - [HSR_EC_WFI] = kvm_handle_wfx, - [HSR_EC_CP15_32] = kvm_handle_cp15_32, - [HSR_EC_CP15_64] = kvm_handle_cp15_64, - [HSR_EC_CP14_MR] = kvm_handle_cp14_32, - [HSR_EC_CP14_LS] = kvm_handle_cp14_load_store, - [HSR_EC_CP14_64] = kvm_handle_cp14_64, - [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, - [HSR_EC_CP10_ID] = kvm_handle_cp10_id, - [HSR_EC_HVC] = handle_hvc, - [HSR_EC_SMC] = handle_smc, - [HSR_EC_IABT] = kvm_handle_guest_abort, - [HSR_EC_DABT] = kvm_handle_guest_abort, -}; - -static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) -{ - u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); - - return arm_exit_handlers[hsr_ec]; -} - -/* - * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on - * proper exit to userspace. - */ -int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index) -{ - exit_handle_fn exit_handler; - - if (ARM_ABORT_PENDING(exception_index)) { - u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); - - /* - * HVC/SMC already have an adjusted PC, which we need - * to correct in order to return to after having - * injected the abort. - */ - if (hsr_ec == HSR_EC_HVC || hsr_ec == HSR_EC_SMC) { - u32 adj = kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2; - *vcpu_pc(vcpu) -= adj; - } - - kvm_inject_vabt(vcpu); - return 1; - } - - exception_index = ARM_EXCEPTION_CODE(exception_index); - - switch (exception_index) { - case ARM_EXCEPTION_IRQ: - return 1; - case ARM_EXCEPTION_HVC: - /* - * See ARM ARM B1.14.1: "Hyp traps on instructions - * that fail their condition code check" - */ - if (!kvm_condition_valid(vcpu)) { - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; - } - - exit_handler = kvm_get_exit_handler(vcpu); - - return exit_handler(vcpu, run); - case ARM_EXCEPTION_DATA_ABORT: - kvm_inject_vabt(vcpu); - return 1; - case ARM_EXCEPTION_HYP_GONE: - /* - * HYP has been reset to the hyp-stub. This happens - * when a guest is pre-empted by kvm_reboot()'s - * shutdown call. - */ - run->exit_reason = KVM_EXIT_FAIL_ENTRY; - return 0; - default: - kvm_pr_unimpl("Unsupported exception type: %d", - exception_index); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - return 0; - } -} diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile deleted file mode 100644 index ba88b1eca93c..000000000000 --- a/arch/arm/kvm/hyp/Makefile +++ /dev/null @@ -1,34 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for Kernel-based Virtual Machine module, HYP part -# - -ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING - -KVM=../../../../virt/kvm - -CFLAGS_ARMV7VE :=$(call cc-option, -march=armv7ve) - -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o - -obj-$(CONFIG_KVM_ARM_HOST) += tlb.o -obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += vfp.o -obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o -CFLAGS_banked-sr.o += $(CFLAGS_ARMV7VE) - -obj-$(CONFIG_KVM_ARM_HOST) += entry.o -obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o -obj-$(CONFIG_KVM_ARM_HOST) += switch.o -CFLAGS_switch.o += $(CFLAGS_ARMV7VE) -obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o - -# KVM code is run at a different exception code with a different map, so -# compiler instrumentation that inserts callbacks or checks into the code may -# cause crashes. Just disable it. -GCOV_PROFILE := n -KASAN_SANITIZE := n -UBSAN_SANITIZE := n -KCOV_INSTRUMENT := n diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c deleted file mode 100644 index c4632ed9e819..000000000000 --- a/arch/arm/kvm/hyp/banked-sr.c +++ /dev/null @@ -1,70 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Original code: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <asm/kvm_hyp.h> - -/* - * gcc before 4.9 doesn't understand -march=armv7ve, so we have to - * trick the assembler. - */ -__asm__(".arch_extension virt"); - -void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt) -{ - ctxt->gp_regs.usr_regs.ARM_sp = read_special(SP_usr); - ctxt->gp_regs.usr_regs.ARM_pc = read_special(ELR_hyp); - ctxt->gp_regs.usr_regs.ARM_cpsr = read_special(SPSR); - ctxt->gp_regs.KVM_ARM_SVC_sp = read_special(SP_svc); - ctxt->gp_regs.KVM_ARM_SVC_lr = read_special(LR_svc); - ctxt->gp_regs.KVM_ARM_SVC_spsr = read_special(SPSR_svc); - ctxt->gp_regs.KVM_ARM_ABT_sp = read_special(SP_abt); - ctxt->gp_regs.KVM_ARM_ABT_lr = read_special(LR_abt); - ctxt->gp_regs.KVM_ARM_ABT_spsr = read_special(SPSR_abt); - ctxt->gp_regs.KVM_ARM_UND_sp = read_special(SP_und); - ctxt->gp_regs.KVM_ARM_UND_lr = read_special(LR_und); - ctxt->gp_regs.KVM_ARM_UND_spsr = read_special(SPSR_und); - ctxt->gp_regs.KVM_ARM_IRQ_sp = read_special(SP_irq); - ctxt->gp_regs.KVM_ARM_IRQ_lr = read_special(LR_irq); - ctxt->gp_regs.KVM_ARM_IRQ_spsr = read_special(SPSR_irq); - ctxt->gp_regs.KVM_ARM_FIQ_r8 = read_special(R8_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_r9 = read_special(R9_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_r10 = read_special(R10_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_fp = read_special(R11_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_ip = read_special(R12_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_sp = read_special(SP_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_lr = read_special(LR_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_spsr = read_special(SPSR_fiq); -} - -void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt) -{ - write_special(ctxt->gp_regs.usr_regs.ARM_sp, SP_usr); - write_special(ctxt->gp_regs.usr_regs.ARM_pc, ELR_hyp); - write_special(ctxt->gp_regs.usr_regs.ARM_cpsr, SPSR_cxsf); - write_special(ctxt->gp_regs.KVM_ARM_SVC_sp, SP_svc); - write_special(ctxt->gp_regs.KVM_ARM_SVC_lr, LR_svc); - write_special(ctxt->gp_regs.KVM_ARM_SVC_spsr, SPSR_svc); - write_special(ctxt->gp_regs.KVM_ARM_ABT_sp, SP_abt); - write_special(ctxt->gp_regs.KVM_ARM_ABT_lr, LR_abt); - write_special(ctxt->gp_regs.KVM_ARM_ABT_spsr, SPSR_abt); - write_special(ctxt->gp_regs.KVM_ARM_UND_sp, SP_und); - write_special(ctxt->gp_regs.KVM_ARM_UND_lr, LR_und); - write_special(ctxt->gp_regs.KVM_ARM_UND_spsr, SPSR_und); - write_special(ctxt->gp_regs.KVM_ARM_IRQ_sp, SP_irq); - write_special(ctxt->gp_regs.KVM_ARM_IRQ_lr, LR_irq); - write_special(ctxt->gp_regs.KVM_ARM_IRQ_spsr, SPSR_irq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_r8, R8_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_r9, R9_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_r10, R10_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_fp, R11_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_ip, R12_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_sp, SP_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_lr, LR_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_spsr, SPSR_fiq); -} diff --git a/arch/arm/kvm/hyp/cp15-sr.c b/arch/arm/kvm/hyp/cp15-sr.c deleted file mode 100644 index e6923306f698..000000000000 --- a/arch/arm/kvm/hyp/cp15-sr.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Original code: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <asm/kvm_hyp.h> - -static u64 *cp15_64(struct kvm_cpu_context *ctxt, int idx) -{ - return (u64 *)(ctxt->cp15 + idx); -} - -void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt) -{ - ctxt->cp15[c0_CSSELR] = read_sysreg(CSSELR); - ctxt->cp15[c1_SCTLR] = read_sysreg(SCTLR); - ctxt->cp15[c1_CPACR] = read_sysreg(CPACR); - *cp15_64(ctxt, c2_TTBR0) = read_sysreg(TTBR0); - *cp15_64(ctxt, c2_TTBR1) = read_sysreg(TTBR1); - ctxt->cp15[c2_TTBCR] = read_sysreg(TTBCR); - ctxt->cp15[c3_DACR] = read_sysreg(DACR); - ctxt->cp15[c5_DFSR] = read_sysreg(DFSR); - ctxt->cp15[c5_IFSR] = read_sysreg(IFSR); - ctxt->cp15[c5_ADFSR] = read_sysreg(ADFSR); - ctxt->cp15[c5_AIFSR] = read_sysreg(AIFSR); - ctxt->cp15[c6_DFAR] = read_sysreg(DFAR); - ctxt->cp15[c6_IFAR] = read_sysreg(IFAR); - *cp15_64(ctxt, c7_PAR) = read_sysreg(PAR); - ctxt->cp15[c10_PRRR] = read_sysreg(PRRR); - ctxt->cp15[c10_NMRR] = read_sysreg(NMRR); - ctxt->cp15[c10_AMAIR0] = read_sysreg(AMAIR0); - ctxt->cp15[c10_AMAIR1] = read_sysreg(AMAIR1); - ctxt->cp15[c12_VBAR] = read_sysreg(VBAR); - ctxt->cp15[c13_CID] = read_sysreg(CID); - ctxt->cp15[c13_TID_URW] = read_sysreg(TID_URW); - ctxt->cp15[c13_TID_URO] = read_sysreg(TID_URO); - ctxt->cp15[c13_TID_PRIV] = read_sysreg(TID_PRIV); - ctxt->cp15[c14_CNTKCTL] = read_sysreg(CNTKCTL); -} - -void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt) -{ - write_sysreg(ctxt->cp15[c0_MPIDR], VMPIDR); - write_sysreg(ctxt->cp15[c0_CSSELR], CSSELR); - write_sysreg(ctxt->cp15[c1_SCTLR], SCTLR); - write_sysreg(ctxt->cp15[c1_CPACR], CPACR); - write_sysreg(*cp15_64(ctxt, c2_TTBR0), TTBR0); - write_sysreg(*cp15_64(ctxt, c2_TTBR1), TTBR1); - write_sysreg(ctxt->cp15[c2_TTBCR], TTBCR); - write_sysreg(ctxt->cp15[c3_DACR], DACR); - write_sysreg(ctxt->cp15[c5_DFSR], DFSR); - write_sysreg(ctxt->cp15[c5_IFSR], IFSR); - write_sysreg(ctxt->cp15[c5_ADFSR], ADFSR); - write_sysreg(ctxt->cp15[c5_AIFSR], AIFSR); - write_sysreg(ctxt->cp15[c6_DFAR], DFAR); - write_sysreg(ctxt->cp15[c6_IFAR], IFAR); - write_sysreg(*cp15_64(ctxt, c7_PAR), PAR); - write_sysreg(ctxt->cp15[c10_PRRR], PRRR); - write_sysreg(ctxt->cp15[c10_NMRR], NMRR); - write_sysreg(ctxt->cp15[c10_AMAIR0], AMAIR0); - write_sysreg(ctxt->cp15[c10_AMAIR1], AMAIR1); - write_sysreg(ctxt->cp15[c12_VBAR], VBAR); - write_sysreg(ctxt->cp15[c13_CID], CID); - write_sysreg(ctxt->cp15[c13_TID_URW], TID_URW); - write_sysreg(ctxt->cp15[c13_TID_URO], TID_URO); - write_sysreg(ctxt->cp15[c13_TID_PRIV], TID_PRIV); - write_sysreg(ctxt->cp15[c14_CNTKCTL], CNTKCTL); -} diff --git a/arch/arm/kvm/hyp/entry.S b/arch/arm/kvm/hyp/entry.S deleted file mode 100644 index 4bd1f6a74180..000000000000 --- a/arch/arm/kvm/hyp/entry.S +++ /dev/null @@ -1,121 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2016 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> -*/ - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> - - .arch_extension virt - - .text - .pushsection .hyp.text, "ax" - -#define USR_REGS_OFFSET (CPU_CTXT_GP_REGS + GP_REGS_USR) - -/* int __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host) */ -ENTRY(__guest_enter) - @ Save host registers - add r1, r1, #(USR_REGS_OFFSET + S_R4) - stm r1!, {r4-r12} - str lr, [r1, #4] @ Skip SP_usr (already saved) - - @ Restore guest registers - add r0, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0) - ldr lr, [r0, #S_LR] - ldm r0, {r0-r12} - - clrex - eret -ENDPROC(__guest_enter) - -ENTRY(__guest_exit) - /* - * return convention: - * guest r0, r1, r2 saved on the stack - * r0: vcpu pointer - * r1: exception code - */ - - add r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R3) - stm r2!, {r3-r12} - str lr, [r2, #4] - add r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0) - pop {r3, r4, r5} @ r0, r1, r2 - stm r2, {r3-r5} - - ldr r0, [r0, #VCPU_HOST_CTXT] - add r0, r0, #(USR_REGS_OFFSET + S_R4) - ldm r0!, {r4-r12} - ldr lr, [r0, #4] - - mov r0, r1 - mrs r1, SPSR - mrs r2, ELR_hyp - mrc p15, 4, r3, c5, c2, 0 @ HSR - - /* - * Force loads and stores to complete before unmasking aborts - * and forcing the delivery of the exception. This gives us a - * single instruction window, which the handler will try to - * match. - */ - dsb sy - cpsie a - - .global abort_guest_exit_start -abort_guest_exit_start: - - isb - - .global abort_guest_exit_end -abort_guest_exit_end: - - /* - * If we took an abort, r0[31] will be set, and cmp will set - * the N bit in PSTATE. - */ - cmp r0, #0 - msrmi SPSR_cxsf, r1 - msrmi ELR_hyp, r2 - mcrmi p15, 4, r3, c5, c2, 0 @ HSR - - bx lr -ENDPROC(__guest_exit) - -/* - * If VFPv3 support is not available, then we will not switch the VFP - * registers; however cp10 and cp11 accesses will still trap and fallback - * to the regular coprocessor emulation code, which currently will - * inject an undefined exception to the guest. - */ -#ifdef CONFIG_VFPv3 -ENTRY(__vfp_guest_restore) - push {r3, r4, lr} - - @ NEON/VFP used. Turn on VFP access. - mrc p15, 4, r1, c1, c1, 2 @ HCPTR - bic r1, r1, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - mcr p15, 4, r1, c1, c1, 2 @ HCPTR - isb - - @ Switch VFP/NEON hardware state to the guest's - mov r4, r0 - ldr r0, [r0, #VCPU_HOST_CTXT] - add r0, r0, #CPU_CTXT_VFP - bl __vfp_save_state - add r0, r4, #(VCPU_GUEST_CTXT + CPU_CTXT_VFP) - bl __vfp_restore_state - - pop {r3, r4, lr} - pop {r0, r1, r2} - clrex - eret -ENDPROC(__vfp_guest_restore) -#endif - - .popsection - diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S deleted file mode 100644 index fe3d7811a908..000000000000 --- a/arch/arm/kvm/hyp/hyp-entry.S +++ /dev/null @@ -1,295 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/arm-smccc.h> -#include <linux/linkage.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> - - .arch_extension virt - - .text - .pushsection .hyp.text, "ax" - -.macro load_vcpu reg - mrc p15, 4, \reg, c13, c0, 2 @ HTPIDR -.endm - -/******************************************************************** - * Hypervisor exception vector and handlers - * - * - * The KVM/ARM Hypervisor ABI is defined as follows: - * - * Entry to Hyp mode from the host kernel will happen _only_ when an HVC - * instruction is issued since all traps are disabled when running the host - * kernel as per the Hyp-mode initialization at boot time. - * - * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc - * below) when the HVC instruction is called from SVC mode (i.e. a guest or the - * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC - * instructions are called from within Hyp-mode. - * - * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode): - * Switching to Hyp mode is done through a simple HVC #0 instruction. The - * exception vector code will check that the HVC comes from VMID==0. - * - r0 contains a pointer to a HYP function - * - r1, r2, and r3 contain arguments to the above function. - * - The HYP function will be called with its arguments in r0, r1 and r2. - * On HYP function return, we return directly to SVC. - * - * Note that the above is used to execute code in Hyp-mode from a host-kernel - * point of view, and is a different concept from performing a world-switch and - * executing guest code SVC mode (with a VMID != 0). - */ - - .align 5 -__kvm_hyp_vector: - .global __kvm_hyp_vector - - @ Hyp-mode exception vector - W(b) hyp_reset - W(b) hyp_undef - W(b) hyp_svc - W(b) hyp_pabt - W(b) hyp_dabt - W(b) hyp_hvc - W(b) hyp_irq - W(b) hyp_fiq - -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR - .align 5 -__kvm_hyp_vector_ic_inv: - .global __kvm_hyp_vector_ic_inv - - /* - * We encode the exception entry in the bottom 3 bits of - * SP, and we have to guarantee to be 8 bytes aligned. - */ - W(add) sp, sp, #1 /* Reset 7 */ - W(add) sp, sp, #1 /* Undef 6 */ - W(add) sp, sp, #1 /* Syscall 5 */ - W(add) sp, sp, #1 /* Prefetch abort 4 */ - W(add) sp, sp, #1 /* Data abort 3 */ - W(add) sp, sp, #1 /* HVC 2 */ - W(add) sp, sp, #1 /* IRQ 1 */ - W(nop) /* FIQ 0 */ - - mcr p15, 0, r0, c7, c5, 0 /* ICIALLU */ - isb - - b decode_vectors - - .align 5 -__kvm_hyp_vector_bp_inv: - .global __kvm_hyp_vector_bp_inv - - /* - * We encode the exception entry in the bottom 3 bits of - * SP, and we have to guarantee to be 8 bytes aligned. - */ - W(add) sp, sp, #1 /* Reset 7 */ - W(add) sp, sp, #1 /* Undef 6 */ - W(add) sp, sp, #1 /* Syscall 5 */ - W(add) sp, sp, #1 /* Prefetch abort 4 */ - W(add) sp, sp, #1 /* Data abort 3 */ - W(add) sp, sp, #1 /* HVC 2 */ - W(add) sp, sp, #1 /* IRQ 1 */ - W(nop) /* FIQ 0 */ - - mcr p15, 0, r0, c7, c5, 6 /* BPIALL */ - isb - -decode_vectors: - -#ifdef CONFIG_THUMB2_KERNEL - /* - * Yet another silly hack: Use VPIDR as a temp register. - * Thumb2 is really a pain, as SP cannot be used with most - * of the bitwise instructions. The vect_br macro ensures - * things gets cleaned-up. - */ - mcr p15, 4, r0, c0, c0, 0 /* VPIDR */ - mov r0, sp - and r0, r0, #7 - sub sp, sp, r0 - push {r1, r2} - mov r1, r0 - mrc p15, 4, r0, c0, c0, 0 /* VPIDR */ - mrc p15, 0, r2, c0, c0, 0 /* MIDR */ - mcr p15, 4, r2, c0, c0, 0 /* VPIDR */ -#endif - -.macro vect_br val, targ -ARM( eor sp, sp, #\val ) -ARM( tst sp, #7 ) -ARM( eorne sp, sp, #\val ) - -THUMB( cmp r1, #\val ) -THUMB( popeq {r1, r2} ) - - beq \targ -.endm - - vect_br 0, hyp_fiq - vect_br 1, hyp_irq - vect_br 2, hyp_hvc - vect_br 3, hyp_dabt - vect_br 4, hyp_pabt - vect_br 5, hyp_svc - vect_br 6, hyp_undef - vect_br 7, hyp_reset -#endif - -.macro invalid_vector label, cause - .align -\label: mov r0, #\cause - b __hyp_panic -.endm - - invalid_vector hyp_reset ARM_EXCEPTION_RESET - invalid_vector hyp_undef ARM_EXCEPTION_UNDEFINED - invalid_vector hyp_svc ARM_EXCEPTION_SOFTWARE - invalid_vector hyp_pabt ARM_EXCEPTION_PREF_ABORT - invalid_vector hyp_fiq ARM_EXCEPTION_FIQ - -ENTRY(__hyp_do_panic) - mrs lr, cpsr - bic lr, lr, #MODE_MASK - orr lr, lr, #SVC_MODE -THUMB( orr lr, lr, #PSR_T_BIT ) - msr spsr_cxsf, lr - ldr lr, =panic - msr ELR_hyp, lr - ldr lr, =__kvm_call_hyp - clrex - eret -ENDPROC(__hyp_do_panic) - -hyp_hvc: - /* - * Getting here is either because of a trap from a guest, - * or from executing HVC from the host kernel, which means - * "do something in Hyp mode". - */ - push {r0, r1, r2} - - @ Check syndrome register - mrc p15, 4, r1, c5, c2, 0 @ HSR - lsr r0, r1, #HSR_EC_SHIFT - cmp r0, #HSR_EC_HVC - bne guest_trap @ Not HVC instr. - - /* - * Let's check if the HVC came from VMID 0 and allow simple - * switch to Hyp mode - */ - mrrc p15, 6, r0, r2, c2 - lsr r2, r2, #16 - and r2, r2, #0xff - cmp r2, #0 - bne guest_hvc_trap @ Guest called HVC - - /* - * Getting here means host called HVC, we shift parameters and branch - * to Hyp function. - */ - pop {r0, r1, r2} - - /* - * Check if we have a kernel function, which is guaranteed to be - * bigger than the maximum hyp stub hypercall - */ - cmp r0, #HVC_STUB_HCALL_NR - bhs 1f - - /* - * Not a kernel function, treat it as a stub hypercall. - * Compute the physical address for __kvm_handle_stub_hvc - * (as the code lives in the idmaped page) and branch there. - * We hijack ip (r12) as a tmp register. - */ - push {r1} - ldr r1, =kimage_voffset - ldr r1, [r1] - ldr ip, =__kvm_handle_stub_hvc - sub ip, ip, r1 - pop {r1} - - bx ip - -1: - /* - * Pushing r2 here is just a way of keeping the stack aligned to - * 8 bytes on any path that can trigger a HYP exception. Here, - * we may well be about to jump into the guest, and the guest - * exit would otherwise be badly decoded by our fancy - * "decode-exception-without-a-branch" code... - */ - push {r2, lr} - - mov lr, r0 - mov r0, r1 - mov r1, r2 - mov r2, r3 - -THUMB( orr lr, #1) - blx lr @ Call the HYP function - - pop {r2, lr} - eret - -guest_hvc_trap: - movw r2, #:lower16:ARM_SMCCC_ARCH_WORKAROUND_1 - movt r2, #:upper16:ARM_SMCCC_ARCH_WORKAROUND_1 - ldr r0, [sp] @ Guest's r0 - teq r0, r2 - bne guest_trap - add sp, sp, #12 - @ Returns: - @ r0 = 0 - @ r1 = HSR value (perfectly predictable) - @ r2 = ARM_SMCCC_ARCH_WORKAROUND_1 - mov r0, #0 - eret - -guest_trap: - load_vcpu r0 @ Load VCPU pointer to r0 - -#ifdef CONFIG_VFPv3 - @ Check for a VFP access - lsr r1, r1, #HSR_EC_SHIFT - cmp r1, #HSR_EC_CP_0_13 - beq __vfp_guest_restore -#endif - - mov r1, #ARM_EXCEPTION_HVC - b __guest_exit - -hyp_irq: - push {r0, r1, r2} - mov r1, #ARM_EXCEPTION_IRQ - load_vcpu r0 @ Load VCPU pointer to r0 - b __guest_exit - -hyp_dabt: - push {r0, r1} - mrs r0, ELR_hyp - ldr r1, =abort_guest_exit_start -THUMB( add r1, r1, #1) - cmp r0, r1 - ldrne r1, =abort_guest_exit_end -THUMB( addne r1, r1, #1) - cmpne r0, r1 - pop {r0, r1} - bne __hyp_panic - - orr r0, r0, #(1 << ARM_EXIT_WITH_ABORT_BIT) - eret - - .ltorg - - .popsection diff --git a/arch/arm/kvm/hyp/s2-setup.c b/arch/arm/kvm/hyp/s2-setup.c deleted file mode 100644 index 5dfbea5adf65..000000000000 --- a/arch/arm/kvm/hyp/s2-setup.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2016 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <linux/types.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_hyp.h> - -void __hyp_text __init_stage2_translation(void) -{ - u64 val; - - val = read_sysreg(VTCR) & ~VTCR_MASK; - - val |= read_sysreg(HTCR) & VTCR_HTCR_SH; - val |= KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S; - - write_sysreg(val, VTCR); -} diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c deleted file mode 100644 index 1efeef3fd0ee..000000000000 --- a/arch/arm/kvm/hyp/switch.c +++ /dev/null @@ -1,242 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ -#include <linux/jump_label.h> - -#include <asm/kvm_asm.h> -#include <asm/kvm_hyp.h> -#include <asm/kvm_mmu.h> - -__asm__(".arch_extension virt"); - -/* - * Activate the traps, saving the host's fpexc register before - * overwriting it. We'll restore it on VM exit. - */ -static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host) -{ - u32 val; - - /* - * We are about to set HCPTR.TCP10/11 to trap all floating point - * register accesses to HYP, however, the ARM ARM clearly states that - * traps are only taken to HYP if the operation would not otherwise - * trap to SVC. Therefore, always make sure that for 32-bit guests, - * we set FPEXC.EN to prevent traps to SVC, when setting the TCP bits. - */ - val = read_sysreg(VFP_FPEXC); - *fpexc_host = val; - if (!(val & FPEXC_EN)) { - write_sysreg(val | FPEXC_EN, VFP_FPEXC); - isb(); - } - - write_sysreg(vcpu->arch.hcr, HCR); - /* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */ - write_sysreg(HSTR_T(15), HSTR); - write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR); - val = read_sysreg(HDCR); - val |= HDCR_TPM | HDCR_TPMCR; /* trap performance monitors */ - val |= HDCR_TDRA | HDCR_TDOSA | HDCR_TDA; /* trap debug regs */ - write_sysreg(val, HDCR); -} - -static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) -{ - u32 val; - - /* - * If we pended a virtual abort, preserve it until it gets - * cleared. See B1.9.9 (Virtual Abort exception) for details, - * but the crucial bit is the zeroing of HCR.VA in the - * pseudocode. - */ - if (vcpu->arch.hcr & HCR_VA) - vcpu->arch.hcr = read_sysreg(HCR); - - write_sysreg(0, HCR); - write_sysreg(0, HSTR); - val = read_sysreg(HDCR); - write_sysreg(val & ~(HDCR_TPM | HDCR_TPMCR), HDCR); - write_sysreg(0, HCPTR); -} - -static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = kern_hyp_va(vcpu->kvm); - write_sysreg(kvm_get_vttbr(kvm), VTTBR); - write_sysreg(vcpu->arch.midr, VPIDR); -} - -static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu) -{ - write_sysreg(0, VTTBR); - write_sysreg(read_sysreg(MIDR), VPIDR); -} - - -static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu) -{ - if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_save_state(vcpu); - __vgic_v3_deactivate_traps(vcpu); - } -} - -static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu) -{ - if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_activate_traps(vcpu); - __vgic_v3_restore_state(vcpu); - } -} - -static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) -{ - u32 hsr = read_sysreg(HSR); - u8 ec = hsr >> HSR_EC_SHIFT; - u32 hpfar, far; - - vcpu->arch.fault.hsr = hsr; - - if (ec == HSR_EC_IABT) - far = read_sysreg(HIFAR); - else if (ec == HSR_EC_DABT) - far = read_sysreg(HDFAR); - else - return true; - - /* - * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode: - * - * Abort on the stage 2 translation for a memory access from a - * Non-secure PL1 or PL0 mode: - * - * For any Access flag fault or Translation fault, and also for any - * Permission fault on the stage 2 translation of a memory access - * made as part of a translation table walk for a stage 1 translation, - * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR - * is UNKNOWN. - */ - if (!(hsr & HSR_DABT_S1PTW) && (hsr & HSR_FSC_TYPE) == FSC_PERM) { - u64 par, tmp; - - par = read_sysreg(PAR); - write_sysreg(far, ATS1CPR); - isb(); - - tmp = read_sysreg(PAR); - write_sysreg(par, PAR); - - if (unlikely(tmp & 1)) - return false; /* Translation failed, back to guest */ - - hpfar = ((tmp >> 12) & ((1UL << 28) - 1)) << 4; - } else { - hpfar = read_sysreg(HPFAR); - } - - vcpu->arch.fault.hxfar = far; - vcpu->arch.fault.hpfar = hpfar; - return true; -} - -int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) -{ - struct kvm_cpu_context *host_ctxt; - struct kvm_cpu_context *guest_ctxt; - bool fp_enabled; - u64 exit_code; - u32 fpexc; - - vcpu = kern_hyp_va(vcpu); - write_sysreg(vcpu, HTPIDR); - - host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); - guest_ctxt = &vcpu->arch.ctxt; - - __sysreg_save_state(host_ctxt); - __banked_save_state(host_ctxt); - - __activate_traps(vcpu, &fpexc); - __activate_vm(vcpu); - - __vgic_restore_state(vcpu); - __timer_enable_traps(vcpu); - - __sysreg_restore_state(guest_ctxt); - __banked_restore_state(guest_ctxt); - - /* Jump in the fire! */ -again: - exit_code = __guest_enter(vcpu, host_ctxt); - /* And we're baaack! */ - - if (exit_code == ARM_EXCEPTION_HVC && !__populate_fault_info(vcpu)) - goto again; - - fp_enabled = __vfp_enabled(); - - __banked_save_state(guest_ctxt); - __sysreg_save_state(guest_ctxt); - __timer_disable_traps(vcpu); - - __vgic_save_state(vcpu); - - __deactivate_traps(vcpu); - __deactivate_vm(vcpu); - - __banked_restore_state(host_ctxt); - __sysreg_restore_state(host_ctxt); - - if (fp_enabled) { - __vfp_save_state(&guest_ctxt->vfp); - __vfp_restore_state(&host_ctxt->vfp); - } - - write_sysreg(fpexc, VFP_FPEXC); - - return exit_code; -} - -static const char * const __hyp_panic_string[] = { - [ARM_EXCEPTION_RESET] = "\nHYP panic: RST PC:%08x CPSR:%08x", - [ARM_EXCEPTION_UNDEFINED] = "\nHYP panic: UNDEF PC:%08x CPSR:%08x", - [ARM_EXCEPTION_SOFTWARE] = "\nHYP panic: SVC PC:%08x CPSR:%08x", - [ARM_EXCEPTION_PREF_ABORT] = "\nHYP panic: PABRT PC:%08x CPSR:%08x", - [ARM_EXCEPTION_DATA_ABORT] = "\nHYP panic: DABRT PC:%08x ADDR:%08x", - [ARM_EXCEPTION_IRQ] = "\nHYP panic: IRQ PC:%08x CPSR:%08x", - [ARM_EXCEPTION_FIQ] = "\nHYP panic: FIQ PC:%08x CPSR:%08x", - [ARM_EXCEPTION_HVC] = "\nHYP panic: HVC PC:%08x CPSR:%08x", -}; - -void __hyp_text __noreturn __hyp_panic(int cause) -{ - u32 elr = read_special(ELR_hyp); - u32 val; - - if (cause == ARM_EXCEPTION_DATA_ABORT) - val = read_sysreg(HDFAR); - else - val = read_special(SPSR); - - if (read_sysreg(VTTBR)) { - struct kvm_vcpu *vcpu; - struct kvm_cpu_context *host_ctxt; - - vcpu = (struct kvm_vcpu *)read_sysreg(HTPIDR); - host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); - __timer_disable_traps(vcpu); - __deactivate_traps(vcpu); - __deactivate_vm(vcpu); - __banked_restore_state(host_ctxt); - __sysreg_restore_state(host_ctxt); - } - - /* Call panic for real */ - __hyp_do_panic(__hyp_panic_string[cause], elr, val); - - unreachable(); -} diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c deleted file mode 100644 index 848f27bbad9d..000000000000 --- a/arch/arm/kvm/hyp/tlb.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Original code: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <asm/kvm_hyp.h> -#include <asm/kvm_mmu.h> - -/** - * Flush per-VMID TLBs - * - * __kvm_tlb_flush_vmid(struct kvm *kvm); - * - * We rely on the hardware to broadcast the TLB invalidation to all CPUs - * inside the inner-shareable domain (which is the case for all v7 - * implementations). If we come across a non-IS SMP implementation, we'll - * have to use an IPI based mechanism. Until then, we stick to the simple - * hardware assisted version. - * - * As v7 does not support flushing per IPA, just nuke the whole TLB - * instead, ignoring the ipa value. - */ -void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) -{ - dsb(ishst); - - /* Switch to requested VMID */ - kvm = kern_hyp_va(kvm); - write_sysreg(kvm_get_vttbr(kvm), VTTBR); - isb(); - - write_sysreg(0, TLBIALLIS); - dsb(ish); - isb(); - - write_sysreg(0, VTTBR); -} - -void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) -{ - __kvm_tlb_flush_vmid(kvm); -} - -void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); - - /* Switch to requested VMID */ - write_sysreg(kvm_get_vttbr(kvm), VTTBR); - isb(); - - write_sysreg(0, TLBIALL); - dsb(nsh); - isb(); - - write_sysreg(0, VTTBR); -} - -void __hyp_text __kvm_flush_vm_context(void) -{ - write_sysreg(0, TLBIALLNSNHIS); - write_sysreg(0, ICIALLUIS); - dsb(ish); -} diff --git a/arch/arm/kvm/hyp/vfp.S b/arch/arm/kvm/hyp/vfp.S deleted file mode 100644 index 675a52348d8d..000000000000 --- a/arch/arm/kvm/hyp/vfp.S +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/linkage.h> -#include <asm/vfpmacros.h> - - .text - .pushsection .hyp.text, "ax" - -/* void __vfp_save_state(struct vfp_hard_struct *vfp); */ -ENTRY(__vfp_save_state) - push {r4, r5} - VFPFMRX r1, FPEXC - - @ Make sure *really* VFP is enabled so we can touch the registers. - orr r5, r1, #FPEXC_EN - tst r5, #FPEXC_EX @ Check for VFP Subarchitecture - bic r5, r5, #FPEXC_EX @ FPEXC_EX disable - VFPFMXR FPEXC, r5 - isb - - VFPFMRX r2, FPSCR - beq 1f - - @ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so - @ we only need to save them if FPEXC_EX is set. - VFPFMRX r3, FPINST - tst r5, #FPEXC_FP2V - VFPFMRX r4, FPINST2, ne @ vmrsne -1: - VFPFSTMIA r0, r5 @ Save VFP registers - stm r0, {r1-r4} @ Save FPEXC, FPSCR, FPINST, FPINST2 - pop {r4, r5} - bx lr -ENDPROC(__vfp_save_state) - -/* void __vfp_restore_state(struct vfp_hard_struct *vfp); - * Assume FPEXC_EN is on and FPEXC_EX is off */ -ENTRY(__vfp_restore_state) - VFPFLDMIA r0, r1 @ Load VFP registers - ldm r0, {r0-r3} @ Load FPEXC, FPSCR, FPINST, FPINST2 - - VFPFMXR FPSCR, r1 - tst r0, #FPEXC_EX @ Check for VFP Subarchitecture - beq 1f - VFPFMXR FPINST, r2 - tst r0, #FPEXC_FP2V - VFPFMXR FPINST2, r3, ne -1: - VFPFMXR FPEXC, r0 @ FPEXC (last, in case !EN) - bx lr -ENDPROC(__vfp_restore_state) - - .popsection diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S deleted file mode 100644 index 33e34b6d24b2..000000000000 --- a/arch/arm/kvm/init.S +++ /dev/null @@ -1,157 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/unified.h> -#include <asm/asm-offsets.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_mmu.h> -#include <asm/virt.h> - -/******************************************************************** - * Hypervisor initialization - * - should be called with: - * r0 = top of Hyp stack (kernel VA) - * r1 = pointer to hyp vectors - * r2,r3 = Hypervisor pgd pointer - * - * The init scenario is: - * - We jump in HYP with 3 parameters: runtime HYP pgd, runtime stack, - * runtime vectors - * - Invalidate TLBs - * - Set stack and vectors - * - Setup the page tables - * - Enable the MMU - * - Profit! (or eret, if you only care about the code). - * - * Another possibility is to get a HYP stub hypercall. - * We discriminate between the two by checking if r0 contains a value - * that is less than HVC_STUB_HCALL_NR. - */ - - .text - .pushsection .hyp.idmap.text,"ax" - .align 5 -__kvm_hyp_init: - .globl __kvm_hyp_init - - @ Hyp-mode exception vector - W(b) . - W(b) . - W(b) . - W(b) . - W(b) . - W(b) __do_hyp_init - W(b) . - W(b) . - -__do_hyp_init: - @ Check for a stub hypercall - cmp r0, #HVC_STUB_HCALL_NR - blo __kvm_handle_stub_hvc - - @ Set stack pointer - mov sp, r0 - - @ Set HVBAR to point to the HYP vectors - mcr p15, 4, r1, c12, c0, 0 @ HVBAR - - @ Set the HTTBR to point to the hypervisor PGD pointer passed - mcrr p15, 4, rr_lo_hi(r2, r3), c2 - - @ Set the HTCR and VTCR to the same shareability and cacheability - @ settings as the non-secure TTBCR and with T0SZ == 0. - mrc p15, 4, r0, c2, c0, 2 @ HTCR - ldr r2, =HTCR_MASK - bic r0, r0, r2 - mrc p15, 0, r1, c2, c0, 2 @ TTBCR - and r1, r1, #(HTCR_MASK & ~TTBCR_T0SZ) - orr r0, r0, r1 - mcr p15, 4, r0, c2, c0, 2 @ HTCR - - @ Use the same memory attributes for hyp. accesses as the kernel - @ (copy MAIRx ro HMAIRx). - mrc p15, 0, r0, c10, c2, 0 - mcr p15, 4, r0, c10, c2, 0 - mrc p15, 0, r0, c10, c2, 1 - mcr p15, 4, r0, c10, c2, 1 - - @ Invalidate the stale TLBs from Bootloader - mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH - dsb ish - - @ Set the HSCTLR to: - @ - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel) - @ - Endianness: Kernel config - @ - Fast Interrupt Features: Kernel config - @ - Write permission implies XN: disabled - @ - Instruction cache: enabled - @ - Data/Unified cache: enabled - @ - MMU: enabled (this code must be run from an identity mapping) - mrc p15, 4, r0, c1, c0, 0 @ HSCR - ldr r2, =HSCTLR_MASK - bic r0, r0, r2 - mrc p15, 0, r1, c1, c0, 0 @ SCTLR - ldr r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C) - and r1, r1, r2 - ARM( ldr r2, =(HSCTLR_M) ) - THUMB( ldr r2, =(HSCTLR_M | HSCTLR_TE) ) - orr r1, r1, r2 - orr r0, r0, r1 - mcr p15, 4, r0, c1, c0, 0 @ HSCR - isb - - eret - -ENTRY(__kvm_handle_stub_hvc) - cmp r0, #HVC_SOFT_RESTART - bne 1f - - /* The target is expected in r1 */ - msr ELR_hyp, r1 - mrs r0, cpsr - bic r0, r0, #MODE_MASK - orr r0, r0, #HYP_MODE -THUMB( orr r0, r0, #PSR_T_BIT ) - msr spsr_cxsf, r0 - b reset - -1: cmp r0, #HVC_RESET_VECTORS - bne 1f - -reset: - /* We're now in idmap, disable MMU */ - mrc p15, 4, r1, c1, c0, 0 @ HSCTLR - ldr r0, =(HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I) - bic r1, r1, r0 - mcr p15, 4, r1, c1, c0, 0 @ HSCTLR - - /* - * Install stub vectors, using ardb's VA->PA trick. - */ -0: adr r0, 0b @ PA(0) - movw r1, #:lower16:__hyp_stub_vectors - 0b @ VA(stub) - VA(0) - movt r1, #:upper16:__hyp_stub_vectors - 0b - add r1, r1, r0 @ PA(stub) - mcr p15, 4, r1, c12, c0, 0 @ HVBAR - b exit - -1: ldr r0, =HVC_STUB_ERR - eret - -exit: - mov r0, #0 - eret -ENDPROC(__kvm_handle_stub_hvc) - - .ltorg - - .globl __kvm_hyp_init_end -__kvm_hyp_init_end: - - .popsection diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S deleted file mode 100644 index 064f4f118ca7..000000000000 --- a/arch/arm/kvm/interrupts.S +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/linkage.h> - - .text - -/******************************************************************** - * Call function in Hyp mode - * - * - * unsigned long kvm_call_hyp(void *hypfn, ...); - * - * This is not really a variadic function in the classic C-way and care must - * be taken when calling this to ensure parameters are passed in registers - * only, since the stack will change between the caller and the callee. - * - * Call the function with the first argument containing a pointer to the - * function you wish to call in Hyp mode, and subsequent arguments will be - * passed as r0, r1, and r2 (a maximum of 3 arguments in addition to the - * function pointer can be passed). The function being called must be mapped - * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are - * passed in r0 (strictly 32bit). - * - * The calling convention follows the standard AAPCS: - * r0 - r3: caller save - * r12: caller save - * rest: callee save - */ -ENTRY(__kvm_call_hyp) - hvc #0 - bx lr -ENDPROC(__kvm_call_hyp) diff --git a/arch/arm/kvm/irq.h b/arch/arm/kvm/irq.h deleted file mode 100644 index 0d257de42c10..000000000000 --- a/arch/arm/kvm/irq.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * irq.h: in kernel interrupt controller related definitions - * Copyright (c) 2016 Red Hat, Inc. - * - * This header is included by irqchip.c. However, on ARM, interrupt - * controller declarations are located in include/kvm/arm_vgic.h since - * they are mostly shared between arm and arm64. - */ - -#ifndef __IRQ_H -#define __IRQ_H - -#include <kvm/arm_vgic.h> - -#endif diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c deleted file mode 100644 index eb4174f6ebbd..000000000000 --- a/arch/arm/kvm/reset.c +++ /dev/null @@ -1,86 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ -#include <linux/compiler.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kvm_host.h> -#include <linux/kvm.h> - -#include <asm/unified.h> -#include <asm/ptrace.h> -#include <asm/cputype.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_emulate.h> - -#include <kvm/arm_arch_timer.h> - -/****************************************************************************** - * Cortex-A15 and Cortex-A7 Reset Values - */ - -static struct kvm_regs cortexa_regs_reset = { - .usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT, -}; - - -/******************************************************************************* - * Exported reset function - */ - -/** - * kvm_reset_vcpu - sets core registers and cp15 registers to reset value - * @vcpu: The VCPU pointer - * - * This function finds the right table above and sets the registers on the - * virtual CPU struct to their architecturally defined reset values. - */ -int kvm_reset_vcpu(struct kvm_vcpu *vcpu) -{ - struct kvm_regs *reset_regs; - - switch (vcpu->arch.target) { - case KVM_ARM_TARGET_CORTEX_A7: - case KVM_ARM_TARGET_CORTEX_A15: - reset_regs = &cortexa_regs_reset; - vcpu->arch.midr = read_cpuid_id(); - break; - default: - return -ENODEV; - } - - /* Reset core registers */ - memcpy(&vcpu->arch.ctxt.gp_regs, reset_regs, sizeof(vcpu->arch.ctxt.gp_regs)); - - /* Reset CP15 registers */ - kvm_reset_coprocs(vcpu); - - /* - * Additional reset state handling that PSCI may have imposed on us. - * Must be done after all the sys_reg reset. - */ - if (READ_ONCE(vcpu->arch.reset_state.reset)) { - unsigned long target_pc = vcpu->arch.reset_state.pc; - - /* Gracefully handle Thumb2 entry point */ - if (target_pc & 1) { - target_pc &= ~1UL; - vcpu_set_thumb(vcpu); - } - - /* Propagate caller endianness */ - if (vcpu->arch.reset_state.be) - kvm_vcpu_set_be(vcpu); - - *vcpu_pc(vcpu) = target_pc; - vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); - - vcpu->arch.reset_state.reset = false; - } - - /* Reset arch_timer context */ - return kvm_timer_vcpu_reset(vcpu); -} diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h deleted file mode 100644 index 69a9d62a0ac6..000000000000 --- a/arch/arm/kvm/trace.h +++ /dev/null @@ -1,86 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#if !defined(_TRACE_ARM_KVM_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_ARM_KVM_H - -#include <linux/tracepoint.h> - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM kvm - -/* Architecturally implementation defined CP15 register access */ -TRACE_EVENT(kvm_emulate_cp15_imp, - TP_PROTO(unsigned long Op1, unsigned long Rt1, unsigned long CRn, - unsigned long CRm, unsigned long Op2, bool is_write), - TP_ARGS(Op1, Rt1, CRn, CRm, Op2, is_write), - - TP_STRUCT__entry( - __field( unsigned int, Op1 ) - __field( unsigned int, Rt1 ) - __field( unsigned int, CRn ) - __field( unsigned int, CRm ) - __field( unsigned int, Op2 ) - __field( bool, is_write ) - ), - - TP_fast_assign( - __entry->is_write = is_write; - __entry->Op1 = Op1; - __entry->Rt1 = Rt1; - __entry->CRn = CRn; - __entry->CRm = CRm; - __entry->Op2 = Op2; - ), - - TP_printk("Implementation defined CP15: %s\tp15, %u, r%u, c%u, c%u, %u", - (__entry->is_write) ? "mcr" : "mrc", - __entry->Op1, __entry->Rt1, __entry->CRn, - __entry->CRm, __entry->Op2) -); - -TRACE_EVENT(kvm_wfx, - TP_PROTO(unsigned long vcpu_pc, bool is_wfe), - TP_ARGS(vcpu_pc, is_wfe), - - TP_STRUCT__entry( - __field( unsigned long, vcpu_pc ) - __field( bool, is_wfe ) - ), - - TP_fast_assign( - __entry->vcpu_pc = vcpu_pc; - __entry->is_wfe = is_wfe; - ), - - TP_printk("guest executed wf%c at: 0x%08lx", - __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) -); - -TRACE_EVENT(kvm_hvc, - TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), - TP_ARGS(vcpu_pc, r0, imm), - - TP_STRUCT__entry( - __field( unsigned long, vcpu_pc ) - __field( unsigned long, r0 ) - __field( unsigned long, imm ) - ), - - TP_fast_assign( - __entry->vcpu_pc = vcpu_pc; - __entry->r0 = r0; - __entry->imm = imm; - ), - - TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx", - __entry->vcpu_pc, __entry->r0, __entry->imm) -); - -#endif /* _TRACE_ARM_KVM_H */ - -#undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . -#undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE trace - -/* This part must be outside protection */ -#include <trace/define_trace.h> diff --git a/arch/arm/kvm/vgic-v3-coproc.c b/arch/arm/kvm/vgic-v3-coproc.c deleted file mode 100644 index ed3b2e4759ce..000000000000 --- a/arch/arm/kvm/vgic-v3-coproc.c +++ /dev/null @@ -1,27 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * VGIC system registers handling functions for AArch32 mode - */ - -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <asm/kvm_emulate.h> -#include "vgic.h" - -int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id, - u64 *reg) -{ - /* - * TODO: Implement for AArch32 - */ - return -ENXIO; -} - -int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id, - u64 *reg) -{ - /* - * TODO: Implement for AArch32 - */ - return -ENXIO; -} 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-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index cbbe03e96de8..76838255b5fa 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -21,7 +21,7 @@ menuconfig ARCH_EXYNOS select EXYNOS_SROM select EXYNOS_PM_DOMAINS if PM_GENERIC_DOMAINS select GPIOLIB - select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 && VIRTUALIZATION + select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 select HAVE_ARM_SCU if SMP select HAVE_S3C2410_I2C if I2C select HAVE_S3C2410_WATCHDOG if WATCHDOG 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-npcm/Kconfig b/arch/arm/mach-npcm/Kconfig index 880bc2a5cada..7f7002dc2b21 100644 --- a/arch/arm/mach-npcm/Kconfig +++ b/arch/arm/mach-npcm/Kconfig @@ -11,7 +11,7 @@ config ARCH_NPCM7XX depends on ARCH_MULTI_V7 select PINCTRL_NPCM7XX select NPCM7XX_TIMER - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select CACHE_L2X0 select ARM_GIC select HAVE_ARM_TWD if SMP diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index a2aa7a12b374..8d32894ecd2e 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -17,6 +17,8 @@ #include <linux/input.h> #include <linux/interrupt.h> #include <linux/leds.h> +#include <linux/mtd/nand-gpio.h> +#include <linux/mtd/partitions.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> #include <linux/regulator/fixed.h> @@ -294,9 +296,42 @@ struct modem_private_data { static struct modem_private_data modem_priv; +/* + * Define partitions for flash device + */ + +static struct mtd_partition partition_info[] = { + { .name = "Kernel", + .offset = 0, + .size = 3 * SZ_1M + SZ_512K }, + { .name = "u-boot", + .offset = 3 * SZ_1M + SZ_512K, + .size = SZ_256K }, + { .name = "u-boot params", + .offset = 3 * SZ_1M + SZ_512K + SZ_256K, + .size = SZ_256K }, + { .name = "Amstrad LDR", + .offset = 4 * SZ_1M, + .size = SZ_256K }, + { .name = "File system", + .offset = 4 * SZ_1M + 1 * SZ_256K, + .size = 27 * SZ_1M }, + { .name = "PBL reserved", + .offset = 32 * SZ_1M - 3 * SZ_256K, + .size = 3 * SZ_256K }, +}; + +static struct gpio_nand_platdata nand_platdata = { + .parts = partition_info, + .num_parts = ARRAY_SIZE(partition_info), +}; + static struct platform_device ams_delta_nand_device = { .name = "ams-delta-nand", .id = -1, + .dev = { + .platform_data = &nand_platdata, + }, }; #define OMAP_GPIO_LABEL "gpio-0-15" @@ -306,10 +341,14 @@ static struct gpiod_lookup_table ams_delta_nand_gpio_table = { .table = { GPIO_LOOKUP(OMAP_GPIO_LABEL, AMS_DELTA_GPIO_PIN_NAND_RB, "rdy", 0), - GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NCE, "nce", 0), - GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NRE, "nre", 0), - GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NWP, "nwp", 0), - GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NWE, "nwe", 0), + GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NCE, "nce", + GPIO_ACTIVE_LOW), + GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NRE, "nre", + GPIO_ACTIVE_LOW), + GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NWP, "nwp", + GPIO_ACTIVE_LOW), + GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NWE, "nwe", + GPIO_ACTIVE_LOW), GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_ALE, "ale", 0), GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_CLE, "cle", 0), GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 0, "data", 0, 0), 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/arm/mm/fault.c b/arch/arm/mm/fault.c index bd0f4821f7e1..b598e6978b29 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -241,7 +241,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) struct mm_struct *mm; int sig, code; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; if (kprobe_page_fault(regs, fsr)) return 0; @@ -295,7 +295,7 @@ retry: * signal first. We do not need to release the mmap_sem because * it would already be released in __lock_page_or_retry in * mm/filemap.c. */ - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { + if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; @@ -319,9 +319,6 @@ retry: regs, addr); } if (fault & VM_FAULT_RETRY) { - /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk - * of starvation. */ - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; goto retry; } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 5d0d0f86e790..69a337df619f 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -63,9 +63,6 @@ static unsigned int cachepolicy __initdata = CPOLICY_WRITEBACK; static unsigned int ecc_mask __initdata = 0; pgprot_t pgprot_user; pgprot_t pgprot_kernel; -pgprot_t pgprot_hyp_device; -pgprot_t pgprot_s2; -pgprot_t pgprot_s2_device; EXPORT_SYMBOL(pgprot_user); EXPORT_SYMBOL(pgprot_kernel); @@ -75,15 +72,8 @@ struct cachepolicy { unsigned int cr_mask; pmdval_t pmd; pteval_t pte; - pteval_t pte_s2; }; -#ifdef CONFIG_ARM_LPAE -#define s2_policy(policy) policy -#else -#define s2_policy(policy) 0 -#endif - unsigned long kimage_voffset __ro_after_init; static struct cachepolicy cache_policies[] __initdata = { @@ -92,31 +82,26 @@ static struct cachepolicy cache_policies[] __initdata = { .cr_mask = CR_W|CR_C, .pmd = PMD_SECT_UNCACHED, .pte = L_PTE_MT_UNCACHED, - .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "buffered", .cr_mask = CR_C, .pmd = PMD_SECT_BUFFERED, .pte = L_PTE_MT_BUFFERABLE, - .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "writethrough", .cr_mask = 0, .pmd = PMD_SECT_WT, .pte = L_PTE_MT_WRITETHROUGH, - .pte_s2 = s2_policy(L_PTE_S2_MT_WRITETHROUGH), }, { .policy = "writeback", .cr_mask = 0, .pmd = PMD_SECT_WB, .pte = L_PTE_MT_WRITEBACK, - .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), }, { .policy = "writealloc", .cr_mask = 0, .pmd = PMD_SECT_WBWA, .pte = L_PTE_MT_WRITEALLOC, - .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), } }; @@ -246,9 +231,6 @@ static struct mem_type mem_types[] __ro_after_init = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, - .prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) | - s2_policy(L_PTE_S2_MT_DEV_SHARED) | - L_PTE_SHARED, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PROT_SECT_DEVICE | PMD_SECT_S, .domain = DOMAIN_IO, @@ -434,7 +416,6 @@ static void __init build_mem_type_table(void) struct cachepolicy *cp; unsigned int cr = get_cr(); pteval_t user_pgprot, kern_pgprot, vecs_pgprot; - pteval_t hyp_device_pgprot, s2_pgprot, s2_device_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -558,9 +539,6 @@ static void __init build_mem_type_table(void) */ cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; - s2_pgprot = cp->pte_s2; - hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte; - s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2; #ifndef CONFIG_ARM_LPAE /* @@ -604,7 +582,6 @@ static void __init build_mem_type_table(void) user_pgprot |= L_PTE_SHARED; kern_pgprot |= L_PTE_SHARED; vecs_pgprot |= L_PTE_SHARED; - s2_pgprot |= L_PTE_SHARED; mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED; mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; @@ -666,9 +643,6 @@ static void __init build_mem_type_table(void) pgprot_user = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot); pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | kern_pgprot); - pgprot_s2 = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | s2_pgprot); - pgprot_s2_device = __pgprot(s2_device_pgprot); - pgprot_hyp_device = __pgprot(hyp_device_pgprot); mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 0b30e884e088..6e41c4b62607 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -9,7 +9,6 @@ config ARM64 select ACPI_MCFG if (ACPI && PCI) select ACPI_SPCR_TABLE if ACPI select ACPI_PPTT if ACPI - select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_PREP_COHERENT @@ -118,6 +117,7 @@ config ARM64 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_BITREVERSE + select HAVE_ARCH_COMPILER_H select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE @@ -281,6 +281,9 @@ config ZONE_DMA32 config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y +config ARCH_ENABLE_MEMORY_HOTREMOVE + def_bool y + config SMP def_bool y @@ -952,11 +955,11 @@ config HOTPLUG_CPU # Common NUMA Features config NUMA - bool "Numa Memory Allocation and Scheduler Support" + bool "NUMA Memory Allocation and Scheduler Support" select ACPI_NUMA if ACPI select OF_NUMA help - Enable NUMA (Non Uniform Memory Access) support. + Enable NUMA (Non-Uniform Memory Access) support. The kernel will try to allocate memory used by a CPU on the local memory of the CPU and add some more @@ -1498,6 +1501,9 @@ config ARM64_PTR_AUTH bool "Enable support for pointer authentication" default y depends on !KVM || ARM64_VHE + depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC + depends on CC_IS_GCC || (CC_IS_CLANG && AS_HAS_CFI_NEGATE_RA_STATE) + depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help Pointer authentication (part of the ARMv8.3 Extensions) provides instructions for signing and authenticating pointers against secret @@ -1505,16 +1511,72 @@ config ARM64_PTR_AUTH and other attacks. This option enables these instructions at EL0 (i.e. for userspace). - Choosing this option will cause the kernel to initialise secret keys for each process at exec() time, with these keys being context-switched along with the process. + If the compiler supports the -mbranch-protection or + -msign-return-address flag (e.g. GCC 7 or later), then this option + will also cause the kernel itself to be compiled with return address + protection. In this case, and if the target hardware is known to + support pointer authentication, then CONFIG_STACKPROTECTOR can be + disabled with minimal loss of protection. + The feature is detected at runtime. If the feature is not present in hardware it will not be advertised to userspace/KVM guest nor will it be enabled. However, KVM guest also require VHE mode and hence CONFIG_ARM64_VHE=y option to use this feature. + If the feature is present on the boot CPU but not on a late CPU, then + the late CPU will be parked. Also, if the boot CPU does not have + address auth and the late CPU has then the late CPU will still boot + but with the feature disabled. On such a system, this option should + not be selected. + + This feature works with FUNCTION_GRAPH_TRACER option only if + DYNAMIC_FTRACE_WITH_REGS is enabled. + +config CC_HAS_BRANCH_PROT_PAC_RET + # GCC 9 or later, clang 8 or later + def_bool $(cc-option,-mbranch-protection=pac-ret+leaf) + +config CC_HAS_SIGN_RETURN_ADDRESS + # GCC 7, 8 + def_bool $(cc-option,-msign-return-address=all) + +config AS_HAS_PAC + def_bool $(as-option,-Wa$(comma)-march=armv8.3-a) + +config AS_HAS_CFI_NEGATE_RA_STATE + def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n) + +endmenu + +menu "ARMv8.4 architectural features" + +config ARM64_AMU_EXTN + bool "Enable support for the Activity Monitors Unit CPU extension" + default y + help + The activity monitors extension is an optional extension introduced + by the ARMv8.4 CPU architecture. This enables support for version 1 + of the activity monitors architecture, AMUv1. + + To enable the use of this extension on CPUs that implement it, say Y. + + Note that for architectural reasons, firmware _must_ implement AMU + support when running on CPUs that present the activity monitors + extension. The required support is present in: + * Version 1.5 and later of the ARM Trusted Firmware + + For kernels that have this configuration enabled but boot with broken + firmware, you may need to say N here until the firmware is fixed. + Otherwise you may experience firmware panics or lockups when + accessing the counter registers. Even if you are not observing these + symptoms, the values returned by the register reads might not + correctly reflect reality. Most commonly, the value read will be 0, + indicating that the counter is not enabled. + endmenu menu "ARMv8.5 architectural features" diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index b2b504ea6fd6..76778b2f520d 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -249,7 +249,7 @@ config ARCH_TEGRA This enables support for the NVIDIA Tegra SoC family. config ARCH_SPRD - bool "Spreadtrum SoC platform" + tristate "Spreadtrum SoC platform" help Support for Spreadtrum ARM based SoCs diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index dca1a97751ab..f15f92ba53e6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -65,6 +65,17 @@ stack_protector_prepare: prepare0 include/generated/asm-offsets.h)) endif +ifeq ($(CONFIG_ARM64_PTR_AUTH),y) +branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all +branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf +# -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the +# compiler to generate them and consequently to break the single image contract +# we pass it only to the assembler. This option is utilized only in case of non +# integrated assemblers. +branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a +KBUILD_CFLAGS += $(branch-prot-flags-y) +endif + ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ 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/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index 62ab0d54ff71..335fff762451 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -161,10 +161,10 @@ bus-range = <0x0 0x1>; reg = <0x0 0x40000000 0x0 0x10000000>; ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>; - interrupt-map = <0 0 0 1 &gic GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 2 &gic GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 3 &gic GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 4 &gic GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &gic 0 0 GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &gic 0 0 GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &gic 0 0 GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>; interrupt-map-mask = <0x0 0x0 0x0 0x7>; msi-map = <0x0 &its 0x0 0x10000>; iommu-map = <0x0 &smmu 0x0 0x10000>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 0bf375ec959b..c28a25b145ae 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"; @@ -333,6 +333,79 @@ status = "disabled"; }; + + lpuart0: serial@2260000 { + compatible = "fsl,ls1028a-lpuart"; + reg = <0x0 0x2260000 0x0 0x1000>; + interrupts = <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>; + clock-names = "ipg"; + dma-names = "rx","tx"; + dmas = <&edma0 1 32>, + <&edma0 1 33>; + status = "disabled"; + }; + + lpuart1: serial@2270000 { + compatible = "fsl,ls1028a-lpuart"; + reg = <0x0 0x2270000 0x0 0x1000>; + interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>; + clock-names = "ipg"; + dma-names = "rx","tx"; + dmas = <&edma0 1 30>, + <&edma0 1 31>; + status = "disabled"; + }; + + lpuart2: serial@2280000 { + compatible = "fsl,ls1028a-lpuart"; + reg = <0x0 0x2280000 0x0 0x1000>; + interrupts = <GIC_SPI 234 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>; + clock-names = "ipg"; + dma-names = "rx","tx"; + dmas = <&edma0 1 28>, + <&edma0 1 29>; + status = "disabled"; + }; + + lpuart3: serial@2290000 { + compatible = "fsl,ls1028a-lpuart"; + reg = <0x0 0x2290000 0x0 0x1000>; + interrupts = <GIC_SPI 235 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>; + clock-names = "ipg"; + dma-names = "rx","tx"; + dmas = <&edma0 1 26>, + <&edma0 1 27>; + status = "disabled"; + }; + + lpuart4: serial@22a0000 { + compatible = "fsl,ls1028a-lpuart"; + reg = <0x0 0x22a0000 0x0 0x1000>; + interrupts = <GIC_SPI 236 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>; + clock-names = "ipg"; + dma-names = "rx","tx"; + dmas = <&edma0 1 24>, + <&edma0 1 25>; + status = "disabled"; + }; + + lpuart5: serial@22b0000 { + compatible = "fsl,ls1028a-lpuart"; + reg = <0x0 0x22b0000 0x0 0x1000>; + interrupts = <GIC_SPI 237 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>; + clock-names = "ipg"; + dma-names = "rx","tx"; + dmas = <&edma0 1 22>, + <&edma0 1 23>; + status = "disabled"; + }; + edma0: dma-controller@22c0000 { #dma-cells = <2>; compatible = "fsl,ls1028a-edma"; 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/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi index 92629cbdc184..cbf97b621931 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi @@ -187,4 +187,53 @@ #size-cells = <0>; }; }; + + mcu_cpsw: ethernet@46000000 { + compatible = "ti,am654-cpsw-nuss"; + #address-cells = <2>; + #size-cells = <2>; + reg = <0x0 0x46000000 0x0 0x200000>; + reg-names = "cpsw_nuss"; + ranges = <0x0 0x0 0x0 0x46000000 0x0 0x200000>; + dma-coherent; + clocks = <&k3_clks 5 10>; + clock-names = "fck"; + power-domains = <&k3_pds 5 TI_SCI_PD_EXCLUSIVE>; + + dmas = <&mcu_udmap 0xf000>, + <&mcu_udmap 0xf001>, + <&mcu_udmap 0xf002>, + <&mcu_udmap 0xf003>, + <&mcu_udmap 0xf004>, + <&mcu_udmap 0xf005>, + <&mcu_udmap 0xf006>, + <&mcu_udmap 0xf007>, + <&mcu_udmap 0x7000>; + dma-names = "tx0", "tx1", "tx2", "tx3", + "tx4", "tx5", "tx6", "tx7", + "rx"; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + cpsw_port1: port@1 { + reg = <1>; + ti,mac-only; + label = "port1"; + ti,syscon-efuse = <&mcu_conf 0x200>; + phys = <&phy_gmii_sel 1>; + }; + }; + + davinci_mdio: mdio@f00 { + compatible = "ti,cpsw-mdio","ti,davinci_mdio"; + reg = <0x0 0xf00 0x0 0x100>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&k3_clks 5 10>; + clock-names = "fck"; + bus_freq = <1000000>; + }; + }; }; diff --git a/arch/arm64/boot/dts/ti/k3-am65.dtsi b/arch/arm64/boot/dts/ti/k3-am65.dtsi index aea36e29dd32..5be75e430965 100644 --- a/arch/arm64/boot/dts/ti/k3-am65.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65.dtsi @@ -30,6 +30,7 @@ i2c3 = &main_i2c1; i2c4 = &main_i2c2; i2c5 = &main_i2c3; + ethernet0 = &cpsw_port1; }; chosen { }; diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts index 1700996800eb..2f3d3316a1cf 100644 --- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts +++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts @@ -7,6 +7,7 @@ #include "k3-am654.dtsi" #include <dt-bindings/input/input.h> +#include <dt-bindings/net/ti-dp83867.h> / { compatible = "ti,am654-evm", "ti,am654"; @@ -95,7 +96,30 @@ wkup_pca554_default: wkup_pca554_default { pinctrl-single,pins = < AM65X_WKUP_IOPAD(0x0034, PIN_INPUT, 7) /* (T1) MCU_OSPI1_CLK.WKUP_GPIO0_25 */ + >; + }; + + mcu_cpsw_pins_default: mcu_cpsw_pins_default { + pinctrl-single,pins = < + AM65X_WKUP_IOPAD(0x0058, PIN_OUTPUT, 0) /* (N4) MCU_RGMII1_TX_CTL */ + AM65X_WKUP_IOPAD(0x005c, PIN_INPUT, 0) /* (N5) MCU_RGMII1_RX_CTL */ + AM65X_WKUP_IOPAD(0x0060, PIN_OUTPUT, 0) /* (M2) MCU_RGMII1_TD3 */ + AM65X_WKUP_IOPAD(0x0064, PIN_OUTPUT, 0) /* (M3) MCU_RGMII1_TD2 */ + AM65X_WKUP_IOPAD(0x0068, PIN_OUTPUT, 0) /* (M4) MCU_RGMII1_TD1 */ + AM65X_WKUP_IOPAD(0x006c, PIN_OUTPUT, 0) /* (M5) MCU_RGMII1_TD0 */ + AM65X_WKUP_IOPAD(0x0078, PIN_INPUT, 0) /* (L2) MCU_RGMII1_RD3 */ + AM65X_WKUP_IOPAD(0x007c, PIN_INPUT, 0) /* (L5) MCU_RGMII1_RD2 */ + AM65X_WKUP_IOPAD(0x0080, PIN_INPUT, 0) /* (M6) MCU_RGMII1_RD1 */ + AM65X_WKUP_IOPAD(0x0084, PIN_INPUT, 0) /* (L6) MCU_RGMII1_RD0 */ + AM65X_WKUP_IOPAD(0x0070, PIN_INPUT, 0) /* (N1) MCU_RGMII1_TXC */ + AM65X_WKUP_IOPAD(0x0074, PIN_INPUT, 0) /* (M1) MCU_RGMII1_RXC */ + >; + }; + mcu_mdio_pins_default: mcu_mdio1_pins_default { + pinctrl-single,pins = < + AM65X_WKUP_IOPAD(0x008c, PIN_OUTPUT, 0) /* (L1) MCU_MDIO0_MDC */ + AM65X_WKUP_IOPAD(0x0088, PIN_INPUT, 0) /* (L4) MCU_MDIO0_MDIO */ >; }; }; @@ -419,3 +443,21 @@ data-lanes = <1 2>; }; }; + +&mcu_cpsw { + pinctrl-names = "default"; + pinctrl-0 = <&mcu_cpsw_pins_default &mcu_mdio_pins_default>; +}; + +&davinci_mdio { + phy0: ethernet-phy@0 { + reg = <0>; + ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>; + ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>; + }; +}; + +&cpsw_port1 { + phy-mode = "rgmii-rxid"; + phy-handle = <&phy0>; +}; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts index 7a5c3d4adadd..98e5e17e3ff7 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts @@ -8,6 +8,7 @@ #include "k3-j721e-som-p0.dtsi" #include <dt-bindings/gpio/gpio.h> #include <dt-bindings/input/input.h> +#include <dt-bindings/net/ti-dp83867.h> / { chosen { @@ -128,6 +129,30 @@ J721E_WKUP_IOPAD(0x38, PIN_INPUT, 0) /* (A23) MCU_OSPI1_LBCLKO */ >; }; + + mcu_cpsw_pins_default: mcu_cpsw_pins_default { + pinctrl-single,pins = < + J721E_WKUP_IOPAD(0x0058, PIN_OUTPUT, 0) /* MCU_RGMII1_TX_CTL */ + J721E_WKUP_IOPAD(0x005c, PIN_INPUT, 0) /* MCU_RGMII1_RX_CTL */ + J721E_WKUP_IOPAD(0x0060, PIN_OUTPUT, 0) /* MCU_RGMII1_TD3 */ + J721E_WKUP_IOPAD(0x0064, PIN_OUTPUT, 0) /* MCU_RGMII1_TD2 */ + J721E_WKUP_IOPAD(0x0068, PIN_OUTPUT, 0) /* MCU_RGMII1_TD1 */ + J721E_WKUP_IOPAD(0x006c, PIN_OUTPUT, 0) /* MCU_RGMII1_TD0 */ + J721E_WKUP_IOPAD(0x0078, PIN_INPUT, 0) /* MCU_RGMII1_RD3 */ + J721E_WKUP_IOPAD(0x007c, PIN_INPUT, 0) /* MCU_RGMII1_RD2 */ + J721E_WKUP_IOPAD(0x0080, PIN_INPUT, 0) /* MCU_RGMII1_RD1 */ + J721E_WKUP_IOPAD(0x0084, PIN_INPUT, 0) /* MCU_RGMII1_RD0 */ + J721E_WKUP_IOPAD(0x0070, PIN_INPUT, 0) /* MCU_RGMII1_TXC */ + J721E_WKUP_IOPAD(0x0074, PIN_INPUT, 0) /* MCU_RGMII1_RXC */ + >; + }; + + mcu_mdio_pins_default: mcu_mdio1_pins_default { + pinctrl-single,pins = < + J721E_WKUP_IOPAD(0x008c, PIN_OUTPUT, 0) /* MCU_MDIO0_MDC */ + J721E_WKUP_IOPAD(0x0088, PIN_INPUT, 0) /* MCU_MDIO0_MDIO */ + >; + }; }; &wkup_uart0 { @@ -429,3 +454,21 @@ #gpio-cells = <2>; }; }; + +&mcu_cpsw { + pinctrl-names = "default"; + pinctrl-0 = <&mcu_cpsw_pins_default &mcu_mdio_pins_default>; +}; + +&davinci_mdio { + phy0: ethernet-phy@0 { + reg = <0>; + ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>; + ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>; + }; +}; + +&cpsw_port1 { + phy-mode = "rgmii-rxid"; + phy-handle = <&phy0>; +}; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi index 16c874bfd49a..bfe91f2a52cb 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi @@ -270,4 +270,53 @@ ti,sci-rm-range-rflow = <0x00>; /* GP RFLOW */ }; }; + + mcu_cpsw: ethernet@46000000 { + compatible = "ti,j721e-cpsw-nuss"; + #address-cells = <2>; + #size-cells = <2>; + reg = <0x0 0x46000000 0x0 0x200000>; + reg-names = "cpsw_nuss"; + ranges = <0x0 0x0 0x0 0x46000000 0x0 0x200000>; + dma-coherent; + clocks = <&k3_clks 18 22>; + clock-names = "fck"; + power-domains = <&k3_pds 18 TI_SCI_PD_EXCLUSIVE>; + + dmas = <&mcu_udmap 0xf000>, + <&mcu_udmap 0xf001>, + <&mcu_udmap 0xf002>, + <&mcu_udmap 0xf003>, + <&mcu_udmap 0xf004>, + <&mcu_udmap 0xf005>, + <&mcu_udmap 0xf006>, + <&mcu_udmap 0xf007>, + <&mcu_udmap 0x7000>; + dma-names = "tx0", "tx1", "tx2", "tx3", + "tx4", "tx5", "tx6", "tx7", + "rx"; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + cpsw_port1: port@1 { + reg = <1>; + ti,mac-only; + label = "port1"; + ti,syscon-efuse = <&mcu_conf 0x200>; + phys = <&phy_gmii_sel 1>; + }; + }; + + davinci_mdio: mdio@f00 { + compatible = "ti,cpsw-mdio","ti,davinci_mdio"; + reg = <0x0 0xf00 0x0 0x100>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&k3_clks 18 22>; + clock-names = "fck"; + bus_freq = <1000000>; + }; + }; }; diff --git a/arch/arm64/boot/dts/ti/k3-j721e.dtsi b/arch/arm64/boot/dts/ti/k3-j721e.dtsi index 027bd1febafa..2f9a56d9b114 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e.dtsi @@ -30,6 +30,7 @@ serial9 = &main_uart7; serial10 = &main_uart8; serial11 = &main_uart9; + ethernet0 = &cpsw_port1; }; chosen { }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 0f212889c931..a6c0d02d9928 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 @@ -283,6 +284,7 @@ CONFIG_SMSC911X=y CONFIG_SNI_AVE=y CONFIG_SNI_NETSEC=y CONFIG_STMMAC_ETH=m +CONFIG_TI_K3_AM65_CPSW_NUSS=y CONFIG_MDIO_BUS_MUX_MMIOREG=y CONFIG_MARVELL_PHY=m CONFIG_MARVELL_10G_PHY=m @@ -452,6 +454,7 @@ CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y CONFIG_CPU_THERMAL=y CONFIG_THERMAL_EMULATION=y CONFIG_QORIQ_THERMAL=m +CONFIG_SUN8I_THERMAL=y CONFIG_ROCKCHIP_THERMAL=m CONFIG_RCAR_THERMAL=y CONFIG_RCAR_GEN3_THERMAL=y @@ -547,6 +550,7 @@ CONFIG_ROCKCHIP_DW_MIPI_DSI=y CONFIG_ROCKCHIP_INNO_HDMI=y CONFIG_DRM_RCAR_DU=m CONFIG_DRM_SUN4I=m +CONFIG_DRM_SUN6I_DSI=m CONFIG_DRM_SUN8I_DW_HDMI=m CONFIG_DRM_SUN8I_MIXER=m CONFIG_DRM_MSM=m @@ -681,7 +685,7 @@ CONFIG_RTC_DRV_SNVS=m CONFIG_RTC_DRV_IMX_SC=m CONFIG_RTC_DRV_XGENE=y CONFIG_DMADEVICES=y -CONFIG_DMA_BCM2835=m +CONFIG_DMA_BCM2835=y CONFIG_DMA_SUN6I=m CONFIG_FSL_EDMA=y CONFIG_IMX_SDMA=y @@ -696,6 +700,8 @@ CONFIG_QCOM_HIDMA_MGMT=y CONFIG_QCOM_HIDMA=y CONFIG_RCAR_DMAC=y CONFIG_RENESAS_USB_DMAC=m +CONFIG_TI_K3_UDMA=y +CONFIG_TI_K3_UDMA_GLUE_LAYER=y CONFIG_VFIO=y CONFIG_VFIO_PCI=y CONFIG_VIRTIO_PCI=y @@ -771,7 +777,7 @@ 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/.gitignore b/arch/arm64/crypto/.gitignore index 879df8781ed5..e403b1343328 100644 --- a/arch/arm64/crypto/.gitignore +++ b/arch/arm64/crypto/.gitignore @@ -1,2 +1,3 @@ sha256-core.S sha512-core.S +poly1305-core.S diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S index 45062553467f..1dc5bbbfeed2 100644 --- a/arch/arm64/crypto/aes-ce.S +++ b/arch/arm64/crypto/aes-ce.S @@ -9,8 +9,8 @@ #include <linux/linkage.h> #include <asm/assembler.h> -#define AES_ENTRY(func) SYM_FUNC_START(ce_ ## func) -#define AES_ENDPROC(func) SYM_FUNC_END(ce_ ## func) +#define AES_FUNC_START(func) SYM_FUNC_START(ce_ ## func) +#define AES_FUNC_END(func) SYM_FUNC_END(ce_ ## func) .arch armv8-a+crypto diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index 8a2faa42b57e..cf618d8f6cec 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -51,7 +51,7 @@ SYM_FUNC_END(aes_decrypt_block5x) * int blocks) */ -AES_ENTRY(aes_ecb_encrypt) +AES_FUNC_START(aes_ecb_encrypt) stp x29, x30, [sp, #-16]! mov x29, sp @@ -79,10 +79,10 @@ ST5( st1 {v4.16b}, [x0], #16 ) .Lecbencout: ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_ecb_encrypt) +AES_FUNC_END(aes_ecb_encrypt) -AES_ENTRY(aes_ecb_decrypt) +AES_FUNC_START(aes_ecb_decrypt) stp x29, x30, [sp, #-16]! mov x29, sp @@ -110,7 +110,7 @@ ST5( st1 {v4.16b}, [x0], #16 ) .Lecbdecout: ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_ecb_decrypt) +AES_FUNC_END(aes_ecb_decrypt) /* @@ -126,7 +126,7 @@ AES_ENDPROC(aes_ecb_decrypt) * u32 const rk2[]); */ -AES_ENTRY(aes_essiv_cbc_encrypt) +AES_FUNC_START(aes_essiv_cbc_encrypt) ld1 {v4.16b}, [x5] /* get iv */ mov w8, #14 /* AES-256: 14 rounds */ @@ -135,7 +135,7 @@ AES_ENTRY(aes_essiv_cbc_encrypt) enc_switch_key w3, x2, x6 b .Lcbcencloop4x -AES_ENTRY(aes_cbc_encrypt) +AES_FUNC_START(aes_cbc_encrypt) ld1 {v4.16b}, [x5] /* get iv */ enc_prepare w3, x2, x6 @@ -167,10 +167,10 @@ AES_ENTRY(aes_cbc_encrypt) .Lcbcencout: st1 {v4.16b}, [x5] /* return iv */ ret -AES_ENDPROC(aes_cbc_encrypt) -AES_ENDPROC(aes_essiv_cbc_encrypt) +AES_FUNC_END(aes_cbc_encrypt) +AES_FUNC_END(aes_essiv_cbc_encrypt) -AES_ENTRY(aes_essiv_cbc_decrypt) +AES_FUNC_START(aes_essiv_cbc_decrypt) stp x29, x30, [sp, #-16]! mov x29, sp @@ -181,7 +181,7 @@ AES_ENTRY(aes_essiv_cbc_decrypt) encrypt_block cbciv, w8, x6, x7, w9 b .Lessivcbcdecstart -AES_ENTRY(aes_cbc_decrypt) +AES_FUNC_START(aes_cbc_decrypt) stp x29, x30, [sp, #-16]! mov x29, sp @@ -238,8 +238,8 @@ ST5( st1 {v4.16b}, [x0], #16 ) st1 {cbciv.16b}, [x5] /* return iv */ ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_cbc_decrypt) -AES_ENDPROC(aes_essiv_cbc_decrypt) +AES_FUNC_END(aes_cbc_decrypt) +AES_FUNC_END(aes_essiv_cbc_decrypt) /* @@ -249,7 +249,7 @@ AES_ENDPROC(aes_essiv_cbc_decrypt) * int rounds, int bytes, u8 const iv[]) */ -AES_ENTRY(aes_cbc_cts_encrypt) +AES_FUNC_START(aes_cbc_cts_encrypt) adr_l x8, .Lcts_permute_table sub x4, x4, #16 add x9, x8, #32 @@ -276,9 +276,9 @@ AES_ENTRY(aes_cbc_cts_encrypt) st1 {v0.16b}, [x4] /* overlapping stores */ st1 {v1.16b}, [x0] ret -AES_ENDPROC(aes_cbc_cts_encrypt) +AES_FUNC_END(aes_cbc_cts_encrypt) -AES_ENTRY(aes_cbc_cts_decrypt) +AES_FUNC_START(aes_cbc_cts_decrypt) adr_l x8, .Lcts_permute_table sub x4, x4, #16 add x9, x8, #32 @@ -305,7 +305,7 @@ AES_ENTRY(aes_cbc_cts_decrypt) st1 {v2.16b}, [x4] /* overlapping stores */ st1 {v0.16b}, [x0] ret -AES_ENDPROC(aes_cbc_cts_decrypt) +AES_FUNC_END(aes_cbc_cts_decrypt) .section ".rodata", "a" .align 6 @@ -324,7 +324,7 @@ AES_ENDPROC(aes_cbc_cts_decrypt) * int blocks, u8 ctr[]) */ -AES_ENTRY(aes_ctr_encrypt) +AES_FUNC_START(aes_ctr_encrypt) stp x29, x30, [sp, #-16]! mov x29, sp @@ -409,7 +409,7 @@ ST5( st1 {v4.16b}, [x0], #16 ) rev x7, x7 ins vctr.d[0], x7 b .Lctrcarrydone -AES_ENDPROC(aes_ctr_encrypt) +AES_FUNC_END(aes_ctr_encrypt) /* @@ -433,7 +433,7 @@ AES_ENDPROC(aes_ctr_encrypt) uzp1 xtsmask.4s, xtsmask.4s, \tmp\().4s .endm -AES_ENTRY(aes_xts_encrypt) +AES_FUNC_START(aes_xts_encrypt) stp x29, x30, [sp, #-16]! mov x29, sp @@ -518,9 +518,9 @@ AES_ENTRY(aes_xts_encrypt) st1 {v2.16b}, [x4] /* overlapping stores */ mov w4, wzr b .Lxtsencctsout -AES_ENDPROC(aes_xts_encrypt) +AES_FUNC_END(aes_xts_encrypt) -AES_ENTRY(aes_xts_decrypt) +AES_FUNC_START(aes_xts_decrypt) stp x29, x30, [sp, #-16]! mov x29, sp @@ -612,13 +612,13 @@ AES_ENTRY(aes_xts_decrypt) st1 {v2.16b}, [x4] /* overlapping stores */ mov w4, wzr b .Lxtsdecctsout -AES_ENDPROC(aes_xts_decrypt) +AES_FUNC_END(aes_xts_decrypt) /* * aes_mac_update(u8 const in[], u32 const rk[], int rounds, * int blocks, u8 dg[], int enc_before, int enc_after) */ -AES_ENTRY(aes_mac_update) +AES_FUNC_START(aes_mac_update) frame_push 6 mov x19, x0 @@ -676,4 +676,4 @@ AES_ENTRY(aes_mac_update) ld1 {v0.16b}, [x23] /* get dg */ enc_prepare w21, x20, x0 b .Lmacloop4x -AES_ENDPROC(aes_mac_update) +AES_FUNC_END(aes_mac_update) diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S index 247d34ddaab0..e47d3ec2cfb4 100644 --- a/arch/arm64/crypto/aes-neon.S +++ b/arch/arm64/crypto/aes-neon.S @@ -8,8 +8,8 @@ #include <linux/linkage.h> #include <asm/assembler.h> -#define AES_ENTRY(func) SYM_FUNC_START(neon_ ## func) -#define AES_ENDPROC(func) SYM_FUNC_END(neon_ ## func) +#define AES_FUNC_START(func) SYM_FUNC_START(neon_ ## func) +#define AES_FUNC_END(func) SYM_FUNC_END(neon_ ## func) xtsmask .req v7 cbciv .req v7 diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index e3e27349a9fe..fb507d569922 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -151,6 +151,7 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key, kernel_neon_begin(); aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds); kernel_neon_end(); + memzero_explicit(&rk, sizeof(rk)); return 0; } 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/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index 084c6a30b03a..6b958dcdf136 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -587,20 +587,20 @@ CPU_LE( rev w8, w8 ) * struct ghash_key const *k, u64 dg[], u8 ctr[], * int rounds, u8 tag) */ -ENTRY(pmull_gcm_encrypt) +SYM_FUNC_START(pmull_gcm_encrypt) pmull_gcm_do_crypt 1 -ENDPROC(pmull_gcm_encrypt) +SYM_FUNC_END(pmull_gcm_encrypt) /* * void pmull_gcm_decrypt(int blocks, u8 dst[], const u8 src[], * struct ghash_key const *k, u64 dg[], u8 ctr[], * int rounds, u8 tag) */ -ENTRY(pmull_gcm_decrypt) +SYM_FUNC_START(pmull_gcm_decrypt) pmull_gcm_do_crypt 0 -ENDPROC(pmull_gcm_decrypt) +SYM_FUNC_END(pmull_gcm_decrypt) -pmull_gcm_ghash_4x: +SYM_FUNC_START_LOCAL(pmull_gcm_ghash_4x) movi MASK.16b, #0xe1 shl MASK.2d, MASK.2d, #57 @@ -681,9 +681,9 @@ pmull_gcm_ghash_4x: eor XL.16b, XL.16b, T2.16b ret -ENDPROC(pmull_gcm_ghash_4x) +SYM_FUNC_END(pmull_gcm_ghash_4x) -pmull_gcm_enc_4x: +SYM_FUNC_START_LOCAL(pmull_gcm_enc_4x) ld1 {KS0.16b}, [x5] // load upper counter sub w10, w8, #4 sub w11, w8, #3 @@ -746,7 +746,7 @@ pmull_gcm_enc_4x: eor INP3.16b, INP3.16b, KS3.16b ret -ENDPROC(pmull_gcm_enc_4x) +SYM_FUNC_END(pmull_gcm_enc_4x) .section ".rodata", "a" .align 6 diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index 63c875d3314b..565ef604ca04 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -91,12 +91,32 @@ static int sha1_ce_final(struct shash_desc *desc, u8 *out) return sha1_base_finish(desc, out); } +static int sha1_ce_export(struct shash_desc *desc, void *out) +{ + struct sha1_ce_state *sctx = shash_desc_ctx(desc); + + memcpy(out, &sctx->sst, sizeof(struct sha1_state)); + return 0; +} + +static int sha1_ce_import(struct shash_desc *desc, const void *in) +{ + struct sha1_ce_state *sctx = shash_desc_ctx(desc); + + memcpy(&sctx->sst, in, sizeof(struct sha1_state)); + sctx->finalize = 0; + return 0; +} + static struct shash_alg alg = { .init = sha1_base_init, .update = sha1_ce_update, .final = sha1_ce_final, .finup = sha1_ce_finup, + .import = sha1_ce_import, + .export = sha1_ce_export, .descsize = sizeof(struct sha1_ce_state), + .statesize = sizeof(struct sha1_state), .digestsize = SHA1_DIGEST_SIZE, .base = { .cra_name = "sha1", diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index a8e67bafba3d..9450d19b9e6e 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -109,12 +109,32 @@ static int sha256_ce_final(struct shash_desc *desc, u8 *out) return sha256_base_finish(desc, out); } +static int sha256_ce_export(struct shash_desc *desc, void *out) +{ + struct sha256_ce_state *sctx = shash_desc_ctx(desc); + + memcpy(out, &sctx->sst, sizeof(struct sha256_state)); + return 0; +} + +static int sha256_ce_import(struct shash_desc *desc, const void *in) +{ + struct sha256_ce_state *sctx = shash_desc_ctx(desc); + + memcpy(&sctx->sst, in, sizeof(struct sha256_state)); + sctx->finalize = 0; + return 0; +} + static struct shash_alg algs[] = { { .init = sha224_base_init, .update = sha256_ce_update, .final = sha256_ce_final, .finup = sha256_ce_finup, + .export = sha256_ce_export, + .import = sha256_ce_import, .descsize = sizeof(struct sha256_ce_state), + .statesize = sizeof(struct sha256_state), .digestsize = SHA224_DIGEST_SIZE, .base = { .cra_name = "sha224", @@ -128,7 +148,10 @@ static struct shash_alg algs[] = { { .update = sha256_ce_update, .final = sha256_ce_final, .finup = sha256_ce_finup, + .export = sha256_ce_export, + .import = sha256_ce_import, .descsize = sizeof(struct sha256_ce_state), + .statesize = sizeof(struct sha256_state), .digestsize = SHA256_DIGEST_SIZE, .base = { .cra_name = "sha256", diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index d3077c991962..ff9cbb631212 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -1,26 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += bugs.h -generic-y += delay.h -generic-y += div64.h -generic-y += dma.h -generic-y += dma-mapping.h generic-y += early_ioremap.h -generic-y += emergency-restart.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h generic-y += qrwlock.h generic-y += qspinlock.h -generic-y += serial.h generic-y += set_memory.h -generic-y += switch_to.h -generic-y += trace_clock.h -generic-y += unaligned.h generic-y += user.h -generic-y += vga.h 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/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h new file mode 100644 index 000000000000..ce2a8486992b --- /dev/null +++ b/arch/arm64/include/asm/asm_pointer_auth.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_ASM_POINTER_AUTH_H +#define __ASM_ASM_POINTER_AUTH_H + +#include <asm/alternative.h> +#include <asm/asm-offsets.h> +#include <asm/cpufeature.h> +#include <asm/sysreg.h> + +#ifdef CONFIG_ARM64_PTR_AUTH +/* + * thread.keys_user.ap* as offset exceeds the #imm offset range + * so use the base value of ldp as thread.keys_user and offset as + * thread.keys_user.ap*. + */ + .macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3 + mov \tmp1, #THREAD_KEYS_USER + add \tmp1, \tsk, \tmp1 +alternative_if_not ARM64_HAS_ADDRESS_AUTH + b .Laddr_auth_skip_\@ +alternative_else_nop_endif + ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA] + msr_s SYS_APIAKEYLO_EL1, \tmp2 + msr_s SYS_APIAKEYHI_EL1, \tmp3 + ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIB] + msr_s SYS_APIBKEYLO_EL1, \tmp2 + msr_s SYS_APIBKEYHI_EL1, \tmp3 + ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDA] + msr_s SYS_APDAKEYLO_EL1, \tmp2 + msr_s SYS_APDAKEYHI_EL1, \tmp3 + ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDB] + msr_s SYS_APDBKEYLO_EL1, \tmp2 + msr_s SYS_APDBKEYHI_EL1, \tmp3 +.Laddr_auth_skip_\@: +alternative_if ARM64_HAS_GENERIC_AUTH + ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APGA] + msr_s SYS_APGAKEYLO_EL1, \tmp2 + msr_s SYS_APGAKEYHI_EL1, \tmp3 +alternative_else_nop_endif + .endm + + .macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3 +alternative_if ARM64_HAS_ADDRESS_AUTH + mov \tmp1, #THREAD_KEYS_KERNEL + add \tmp1, \tsk, \tmp1 + ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_KERNEL_KEY_APIA] + msr_s SYS_APIAKEYLO_EL1, \tmp2 + msr_s SYS_APIAKEYHI_EL1, \tmp3 + .if \sync == 1 + isb + .endif +alternative_else_nop_endif + .endm + +#else /* CONFIG_ARM64_PTR_AUTH */ + + .macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3 + .endm + + .macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3 + .endm + +#endif /* CONFIG_ARM64_PTR_AUTH */ + +#endif /* __ASM_ASM_POINTER_AUTH_H */ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index aca337d79d12..0bff325117b4 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -257,12 +257,6 @@ alternative_endif .endm /* - * mmid - get context id from mm pointer (mm->context.id) - */ - .macro mmid, rd, rn - ldr \rd, [\rn, #MM_CONTEXT_ID] - .endm -/* * read_ctr - read CTR_EL0. If the system has mismatched register fields, * provide the system wide safe value from arm64_ftr_reg_ctrel0.sys_val */ @@ -431,6 +425,16 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU .endm /* + * reset_amuserenr_el0 - reset AMUSERENR_EL0 if AMUv1 present + */ + .macro reset_amuserenr_el0, tmpreg + mrs \tmpreg, id_aa64pfr0_el1 // Check ID_AA64PFR0_EL1 + ubfx \tmpreg, \tmpreg, #ID_AA64PFR0_AMU_SHIFT, #4 + cbz \tmpreg, .Lskip_\@ // Skip if no AMU present + msr_s SYS_AMUSERENR_EL0, xzr // Disable AMU access from EL0 +.Lskip_\@: + .endm +/* * copy_page - copy src to dest using temp registers t1-t8 */ .macro copy_page dest:req src:req t1:req t2:req t3:req t4:req t5:req t6:req t7:req t8:req 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/checksum.h b/arch/arm64/include/asm/checksum.h index 8d2a7de39744..b6f7bc6da5fb 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -5,7 +5,12 @@ #ifndef __ASM_CHECKSUM_H #define __ASM_CHECKSUM_H -#include <linux/types.h> +#include <linux/in6.h> + +#define _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum); static inline __sum16 csum_fold(__wsum csum) { diff --git a/arch/arm64/include/asm/clocksource.h b/arch/arm64/include/asm/clocksource.h index 0ece64a26c8c..482185566b0c 100644 --- a/arch/arm64/include/asm/clocksource.h +++ b/arch/arm64/include/asm/clocksource.h @@ -2,8 +2,6 @@ #ifndef _ASM_CLOCKSOURCE_H #define _ASM_CLOCKSOURCE_H -struct arch_clocksource_data { - bool vdso_direct; /* Usable for direct VDSO access? */ -}; +#include <asm/vdso/clocksource.h> #endif diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h new file mode 100644 index 000000000000..eece20d2c55f --- /dev/null +++ b/arch/arm64/include/asm/compiler.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_COMPILER_H +#define __ASM_COMPILER_H + +#if defined(CONFIG_ARM64_PTR_AUTH) + +/* + * The EL0/EL1 pointer bits used by a pointer authentication code. + * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply. + */ +#define ptrauth_user_pac_mask() GENMASK_ULL(54, vabits_actual) +#define ptrauth_kernel_pac_mask() GENMASK_ULL(63, vabits_actual) + +/* Valid for EL0 TTBR0 and EL1 TTBR1 instruction pointers */ +#define ptrauth_clear_pac(ptr) \ + ((ptr & BIT_ULL(55)) ? (ptr | ptrauth_kernel_pac_mask()) : \ + (ptr & ~ptrauth_user_pac_mask())) + +#define __builtin_return_address(val) \ + (void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val))) + +#endif /* CONFIG_ARM64_PTR_AUTH */ + +#endif /* __ASM_COMPILER_H */ diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h index 86aabf1e0199..d28e8f37d3b4 100644 --- a/arch/arm64/include/asm/cpu_ops.h +++ b/arch/arm64/include/asm/cpu_ops.h @@ -55,12 +55,12 @@ struct cpu_operations { #endif }; -extern const struct cpu_operations *cpu_ops[NR_CPUS]; -int __init cpu_read_ops(int cpu); +int __init init_cpu_ops(int cpu); +extern const struct cpu_operations *get_cpu_ops(int cpu); -static inline void __init cpu_read_bootcpu_ops(void) +static inline void __init init_bootcpu_ops(void) { - cpu_read_ops(0); + init_cpu_ops(0); } #endif /* ifndef __ASM_CPU_OPS_H */ diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 865e0253fc1e..8eb5a088ae65 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -58,7 +58,10 @@ #define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE 48 #define ARM64_HAS_E0PD 49 #define ARM64_HAS_RNG 50 +#define ARM64_HAS_AMU_EXTN 51 +#define ARM64_HAS_ADDRESS_AUTH 52 +#define ARM64_HAS_GENERIC_AUTH 53 -#define ARM64_NCAPS 51 +#define ARM64_NCAPS 54 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 92ef9539874a..afe08251ff95 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -208,6 +208,10 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; * In some non-typical cases either both (a) and (b), or neither, * should be permitted. This can be described by including neither * or both flags in the capability's type field. + * + * In case of a conflict, the CPU is prevented from booting. If the + * ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability, + * then a kernel panic is triggered. */ @@ -240,6 +244,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; #define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4)) /* Is it safe for a late CPU to miss this capability when system has it */ #define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5)) +/* Panic when a conflict is detected */ +#define ARM64_CPUCAP_PANIC_ON_CONFLICT ((u16)BIT(6)) /* * CPU errata workarounds that need to be enabled at boot time if one or @@ -279,9 +285,20 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU feature used early in the boot based on the boot CPU. All secondary - * CPUs must match the state of the capability as detected by the boot CPU. + * CPUs must match the state of the capability as detected by the boot CPU. In + * case of a conflict, a kernel panic is triggered. + */ +#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE \ + (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT) + +/* + * CPU feature used early in the boot based on the boot CPU. It is safe for a + * late CPU to have this feature even though the boot CPU hasn't enabled it, + * although the feature will not be used by Linux in this case. If the boot CPU + * has enabled this feature already, then every late CPU must have it. */ -#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE ARM64_CPUCAP_SCOPE_BOOT_CPU +#define ARM64_CPUCAP_BOOT_CPU_FEATURE \ + (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) struct arm64_cpu_capabilities { const char *desc; @@ -340,18 +357,6 @@ static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) return cap->type & ARM64_CPUCAP_SCOPE_MASK; } -static inline bool -cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) -{ - return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU); -} - -static inline bool -cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap) -{ - return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU); -} - /* * Generic helper for handling capabilties with multiple (match,enable) pairs * of call backs, sharing the same capability bit. @@ -390,14 +395,16 @@ unsigned long cpu_get_elf_hwcap2(void); #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name)) #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name)) -/* System capability check for constant caps */ -static __always_inline bool __cpus_have_const_cap(int num) +static __always_inline bool system_capabilities_finalized(void) { - if (num >= ARM64_NCAPS) - return false; - return static_branch_unlikely(&cpu_hwcap_keys[num]); + return static_branch_likely(&arm64_const_caps_ready); } +/* + * Test for a capability with a runtime check. + * + * Before the capability is detected, this returns false. + */ static inline bool cpus_have_cap(unsigned int num) { if (num >= ARM64_NCAPS) @@ -405,14 +412,53 @@ static inline bool cpus_have_cap(unsigned int num) return test_bit(num, cpu_hwcaps); } +/* + * Test for a capability without a runtime check. + * + * Before capabilities are finalized, this returns false. + * After capabilities are finalized, this is patched to avoid a runtime check. + * + * @num must be a compile-time constant. + */ +static __always_inline bool __cpus_have_const_cap(int num) +{ + if (num >= ARM64_NCAPS) + return false; + return static_branch_unlikely(&cpu_hwcap_keys[num]); +} + +/* + * Test for a capability, possibly with a runtime check. + * + * Before capabilities are finalized, this behaves as cpus_have_cap(). + * After capabilities are finalized, this is patched to avoid a runtime check. + * + * @num must be a compile-time constant. + */ static __always_inline bool cpus_have_const_cap(int num) { - if (static_branch_likely(&arm64_const_caps_ready)) + if (system_capabilities_finalized()) return __cpus_have_const_cap(num); else return cpus_have_cap(num); } +/* + * Test for a capability without a runtime check. + * + * Before capabilities are finalized, this will BUG(). + * After capabilities are finalized, this is patched to avoid a runtime check. + * + * @num must be a compile-time constant. + */ +static __always_inline bool cpus_have_final_cap(int num) +{ + if (system_capabilities_finalized()) + return __cpus_have_const_cap(num); + else + BUG(); +} + static inline void cpus_set_cap(unsigned int num) { if (num >= ARM64_NCAPS) { @@ -435,18 +481,41 @@ 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); } +/* + * Fields that identify the version of the Performance Monitors Extension do + * not follow the standard ID scheme. See ARM DDI 0487E.a page D13-2825, + * "Alternative ID scheme used for the Performance Monitors Extension version". + */ +static inline u64 __attribute_const__ +cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap) +{ + u64 val = cpuid_feature_extract_unsigned_field(features, field); + u64 mask = GENMASK_ULL(field + 3, field); + + /* Treat IMPLEMENTATION DEFINED functionality as unimplemented */ + if (val == 0xf) + val = 0; + + if (val > cap) { + features &= ~mask; + features |= (cap << field) & mask; + } + + return features; +} + static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp) { return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); @@ -564,7 +633,7 @@ 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 +644,13 @@ 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); @@ -590,15 +659,13 @@ static inline bool system_supports_cnp(void) static inline bool system_supports_address_auth(void) { return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) && - (cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) || - cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF)); + cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH); } static inline bool system_supports_generic_auth(void) { return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) && - (cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_ARCH) || - cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF)); + cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH); } static inline bool system_uses_irq_prio_masking(void) @@ -613,11 +680,6 @@ static inline bool system_has_prio_mask_debugging(void) system_uses_irq_prio_masking(); } -static inline bool system_capabilities_finalized(void) -{ - return static_branch_likely(&arm64_const_caps_ready); -} - #define ARM64_BP_HARDEN_UNKNOWN -1 #define ARM64_BP_HARDEN_WA_NEEDED 0 #define ARM64_BP_HARDEN_NOT_REQUIRED 1 @@ -678,6 +740,11 @@ static inline bool cpu_has_hw_af(void) ID_AA64MMFR1_HADBS_SHIFT); } +#ifdef CONFIG_ARM64_AMU_EXTN +/* Check whether the cpu supports the Activity Monitors Unit (AMU) */ +extern bool cpu_has_amu_feat(int cpu); +#endif + #endif /* __ASSEMBLY__ */ #endif 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/esr.h b/arch/arm64/include/asm/esr.h index cb29253ae86b..6a395a7e6707 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -60,7 +60,7 @@ #define ESR_ELx_EC_BKPT32 (0x38) /* Unallocated EC: 0x39 */ #define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ -/* Unallocted EC: 0x3B */ +/* Unallocated EC: 0x3B */ #define ESR_ELx_EC_BRK64 (0x3C) /* Unallocated EC: 0x3D - 0x3F */ #define ESR_ELx_EC_MAX (0x3F) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index b87c6e276ab1..7a6e81ca23a8 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -33,7 +33,6 @@ static inline u32 disr_to_esr(u64 disr) asmlinkage void enter_from_user_mode(void); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); -void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, @@ -47,7 +46,4 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); void do_cp15instr(unsigned int esr, struct pt_regs *regs); void do_el0_svc(struct pt_regs *regs); void do_el0_svc_compat(struct pt_regs *regs); -void do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, - struct pt_regs *regs); - #endif /* __ASM_EXCEPTION_H */ 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_arm.h b/arch/arm64/include/asm/kvm_arm.h index 6e5d839f42b5..51c1d9918999 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -267,6 +267,7 @@ /* Hyp Coprocessor Trap Register */ #define CPTR_EL2_TCPAC (1 << 31) +#define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) #define CPTR_EL2_TZ (1 << 8) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 44a243754c1b..7c7eeeaab9fa 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -36,6 +36,8 @@ */ #define KVM_VECTOR_PREAMBLE (2 * AARCH64_INSN_SIZE) +#define __SMCCC_WORKAROUND_1_SMC_SZ 36 + #ifndef __ASSEMBLY__ #include <linux/mm.h> @@ -75,6 +77,8 @@ extern void __vgic_v3_init_lrs(void); extern u32 __kvm_get_mdcr_el2(void); +extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; + /* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */ #define __hyp_this_cpu_ptr(sym) \ ({ \ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 688c63412cc2..a30b4eec7cb4 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); } @@ -89,7 +89,8 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 &= ~HCR_TWE; - if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count)) + if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || + vcpu->kvm->arch.vgic.nassgireq) vcpu->arch.hcr_el2 &= ~HCR_TWI; else vcpu->arch.hcr_el2 |= HCR_TWI; @@ -127,7 +128,7 @@ 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 +154,17 @@ 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 +182,13 @@ 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 +265,12 @@ 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 +280,12 @@ 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 +300,7 @@ 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 +320,17 @@ 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 +341,18 @@ 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 +362,17 @@ 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 +391,7 @@ 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 +505,7 @@ 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 +520,7 @@ 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..32c8a675e5a4 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -44,6 +44,7 @@ #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) +#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -626,38 +627,6 @@ 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..30b0e8d6b895 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(); @@ -480,7 +481,7 @@ static inline void *kvm_get_hyp_vector(void) int slot = -1; if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) { - vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start)); + vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); slot = data->hyp_vectors_slot; } @@ -509,14 +510,13 @@ static inline int kvm_map_vectors(void) * HBP + HEL2 -> use hardened vertors and use exec mapping */ if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) { - __kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start); + __kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs); __kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base); } if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) { - phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start); - unsigned long size = (__bp_harden_hyp_vecs_end - - __bp_harden_hyp_vecs_start); + phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs); + unsigned long size = __BP_HARDEN_HYP_VECS_SZ; /* * Always allocate a spare vector slot, as we don't 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..2be67b232499 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -54,6 +54,7 @@ #define MODULES_VADDR (BPF_JIT_REGION_END) #define MODULES_VSIZE (SZ_128M) #define VMEMMAP_START (-VMEMMAP_SIZE - SZ_2M) +#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE) #define PCI_IO_END (VMEMMAP_START - SZ_2M) #define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) #define FIXADDR_TOP (PCI_IO_START - SZ_2M) @@ -213,7 +214,7 @@ 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..68140fdd89d6 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -13,6 +13,7 @@ #define TTBR_ASID_MASK (UL(0xffff) << 48) #define BP_HARDEN_EL2_SLOTS 4 +#define __BP_HARDEN_HYP_VECS_SZ (BP_HARDEN_EL2_SLOTS * SZ_2K) #ifndef __ASSEMBLY__ @@ -23,17 +24,15 @@ typedef struct { } mm_context_t; /* - * This macro is only used by the TLBI code, which cannot race with an - * ASID change and therefore doesn't need to reload the counter using - * atomic64_read. + * This macro is only used by the TLBI and low-level switch_mm() code, + * neither of which can race with an ASID change. We therefore don't + * need to reload the counter using atomic64_read(). */ #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); @@ -45,7 +44,8 @@ struct bp_hardening_data { #if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) || \ defined(CONFIG_HARDEN_EL2_VECTORS)) -extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[]; + +extern char __bp_harden_hyp_vecs[]; extern atomic_t arm64_el2_vector_last_slot; #endif /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */ diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 3827ff4040a3..ab46187c6300 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -46,6 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void) isb(); } +void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm); + static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) { BUG_ON(pgd == swapper_pg_dir); diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index d39ddb258a04..75d6cd23a679 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -21,6 +21,10 @@ extern void __cpu_copy_user_page(void *to, const void *from, extern void copy_page(void *to, const void *from); extern void clear_page(void *to); +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) +#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE + #define clear_user_page(addr,vaddr,pg) __cpu_clear_user_page(addr, vaddr) #define copy_user_page(to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr) diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h index 2bdbc79bbd01..e7765b62c712 100644 --- a/arch/arm64/include/asm/perf_event.h +++ b/arch/arm64/include/asm/perf_event.h @@ -176,9 +176,10 @@ #define ARMV8_PMU_PMCR_X (1 << 4) /* Export to ETM */ #define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ #define ARMV8_PMU_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */ +#define ARMV8_PMU_PMCR_LP (1 << 7) /* Long event counter enable */ #define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */ #define ARMV8_PMU_PMCR_N_MASK 0x1f -#define ARMV8_PMU_PMCR_MASK 0x7f /* Mask for writable bits */ +#define ARMV8_PMU_PMCR_MASK 0xff /* Mask for writable bits */ /* * PMOVSR: counters overflow flag status reg 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/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index 7a24bad1a58b..70c47156e54b 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -22,7 +22,7 @@ struct ptrauth_key { * We give each process its own keys, which are shared by all threads. The keys * are inherited upon fork(), and reinitialised upon exec*(). */ -struct ptrauth_keys { +struct ptrauth_keys_user { struct ptrauth_key apia; struct ptrauth_key apib; struct ptrauth_key apda; @@ -30,7 +30,11 @@ struct ptrauth_keys { struct ptrauth_key apga; }; -static inline void ptrauth_keys_init(struct ptrauth_keys *keys) +struct ptrauth_keys_kernel { + struct ptrauth_key apia; +}; + +static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys) { if (system_supports_address_auth()) { get_random_bytes(&keys->apia, sizeof(keys->apia)); @@ -50,48 +54,38 @@ do { \ write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1); \ } while (0) -static inline void ptrauth_keys_switch(struct ptrauth_keys *keys) +static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys) { - if (system_supports_address_auth()) { - __ptrauth_key_install(APIA, keys->apia); - __ptrauth_key_install(APIB, keys->apib); - __ptrauth_key_install(APDA, keys->apda); - __ptrauth_key_install(APDB, keys->apdb); - } + if (system_supports_address_auth()) + get_random_bytes(&keys->apia, sizeof(keys->apia)); +} - if (system_supports_generic_auth()) - __ptrauth_key_install(APGA, keys->apga); +static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys) +{ + if (system_supports_address_auth()) + __ptrauth_key_install(APIA, keys->apia); } extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg); -/* - * The EL0 pointer bits used by a pointer authentication code. - * This is dependent on TBI0 being enabled, or bits 63:56 would also apply. - */ -#define ptrauth_user_pac_mask() GENMASK(54, vabits_actual) - -/* Only valid for EL0 TTBR0 instruction pointers */ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr) { - return ptr & ~ptrauth_user_pac_mask(); + return ptrauth_clear_pac(ptr); } #define ptrauth_thread_init_user(tsk) \ -do { \ - struct task_struct *__ptiu_tsk = (tsk); \ - ptrauth_keys_init(&__ptiu_tsk->thread.keys_user); \ - ptrauth_keys_switch(&__ptiu_tsk->thread.keys_user); \ -} while (0) - -#define ptrauth_thread_switch(tsk) \ - ptrauth_keys_switch(&(tsk)->thread.keys_user) + ptrauth_keys_init_user(&(tsk)->thread.keys_user) +#define ptrauth_thread_init_kernel(tsk) \ + ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel) +#define ptrauth_thread_switch_kernel(tsk) \ + ptrauth_keys_switch_kernel(&(tsk)->thread.keys_kernel) #else /* CONFIG_ARM64_PTR_AUTH */ #define ptrauth_prctl_reset_keys(tsk, arg) (-EINVAL) #define ptrauth_strip_insn_pac(lr) (lr) #define ptrauth_thread_init_user(tsk) -#define ptrauth_thread_switch(tsk) +#define ptrauth_thread_init_kernel(tsk) +#define ptrauth_thread_switch_kernel(tsk) #endif /* CONFIG_ARM64_PTR_AUTH */ #endif /* __ASM_POINTER_AUTH_H */ diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h index a2ce65a0c1fa..0d5d1f0525eb 100644 --- a/arch/arm64/include/asm/proc-fns.h +++ b/arch/arm64/include/asm/proc-fns.h @@ -13,11 +13,9 @@ #include <asm/page.h> -struct mm_struct; struct cpu_suspend_ctx; extern void cpu_do_idle(void); -extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr); extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5ba63204d078..240fe5e5b720 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -28,6 +28,8 @@ #include <linux/string.h> #include <linux/thread_info.h> +#include <vdso/processor.h> + #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> @@ -146,7 +148,8 @@ struct thread_struct { unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ #ifdef CONFIG_ARM64_PTR_AUTH - struct ptrauth_keys keys_user; + struct ptrauth_keys_user keys_user; + struct ptrauth_keys_kernel keys_kernel; #endif }; @@ -256,11 +259,6 @@ extern void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); -static inline void cpu_relax(void) -{ - asm volatile("yield" ::: "memory"); -} - /* Thread switching */ extern struct task_struct *cpu_switch_to(struct task_struct *prev, struct task_struct *next); diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index a0c8a0b65259..40d5ba029615 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -23,6 +23,14 @@ #define CPU_STUCK_REASON_52_BIT_VA (UL(1) << CPU_STUCK_REASON_SHIFT) #define CPU_STUCK_REASON_NO_GRAN (UL(2) << CPU_STUCK_REASON_SHIFT) +/* Possible options for __cpu_setup */ +/* Option to setup primary cpu */ +#define ARM64_CPU_BOOT_PRIMARY (1) +/* Option to setup secondary cpus */ +#define ARM64_CPU_BOOT_SECONDARY (2) +/* Option to setup cpus for different cpu run time services */ +#define ARM64_CPU_RUNTIME (3) + #ifndef __ASSEMBLY__ #include <asm/percpu.h> @@ -30,6 +38,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/thread_info.h> +#include <asm/pointer_auth.h> DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); @@ -87,6 +96,9 @@ asmlinkage void secondary_start_kernel(void); struct secondary_data { void *stack; struct task_struct *task; +#ifdef CONFIG_ARM64_PTR_AUTH + struct ptrauth_keys_kernel ptrauth_key; +#endif long status; }; diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 102404dc1e13..9083d6992603 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -18,6 +18,10 @@ * See: * https://lore.kernel.org/lkml/20200110100612.GC2827@hirez.programming.kicks-ass.net */ -#define vcpu_is_preempted(cpu) false +#define vcpu_is_preempted vcpu_is_preempted +static inline bool vcpu_is_preempted(int cpu) +{ + return false; +} #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h index 5884a2b02827..7263e0bac680 100644 --- a/arch/arm64/include/asm/stackprotector.h +++ b/arch/arm64/include/asm/stackprotector.h @@ -15,6 +15,7 @@ #include <linux/random.h> #include <linux/version.h> +#include <asm/pointer_auth.h> extern unsigned long __stack_chk_guard; @@ -26,6 +27,7 @@ extern unsigned long __stack_chk_guard; */ static __always_inline void boot_init_stack_canary(void) { +#if defined(CONFIG_STACKPROTECTOR) unsigned long canary; /* Try to get a semi random initial value. */ @@ -36,6 +38,9 @@ static __always_inline void boot_init_stack_canary(void) current->stack_canary = canary; if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK)) __stack_chk_guard = current->stack_canary; +#endif + ptrauth_thread_init_kernel(current); + ptrauth_thread_switch_kernel(current); } #endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index b91570ff9db1..ebc622432831 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -386,6 +386,42 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +/* Definitions for system register interface to AMU for ARMv8.4 onwards */ +#define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2)) +#define SYS_AMCR_EL0 SYS_AM_EL0(2, 0) +#define SYS_AMCFGR_EL0 SYS_AM_EL0(2, 1) +#define SYS_AMCGCR_EL0 SYS_AM_EL0(2, 2) +#define SYS_AMUSERENR_EL0 SYS_AM_EL0(2, 3) +#define SYS_AMCNTENCLR0_EL0 SYS_AM_EL0(2, 4) +#define SYS_AMCNTENSET0_EL0 SYS_AM_EL0(2, 5) +#define SYS_AMCNTENCLR1_EL0 SYS_AM_EL0(3, 0) +#define SYS_AMCNTENSET1_EL0 SYS_AM_EL0(3, 1) + +/* + * Group 0 of activity monitors (architected): + * op0 op1 CRn CRm op2 + * Counter: 11 011 1101 010:n<3> n<2:0> + * Type: 11 011 1101 011:n<3> n<2:0> + * n: 0-15 + * + * Group 1 of activity monitors (auxiliary): + * op0 op1 CRn CRm op2 + * Counter: 11 011 1101 110:n<3> n<2:0> + * Type: 11 011 1101 111:n<3> n<2:0> + * n: 0-15 + */ + +#define SYS_AMEVCNTR0_EL0(n) SYS_AM_EL0(4 + ((n) >> 3), (n) & 7) +#define SYS_AMEVTYPE0_EL0(n) SYS_AM_EL0(6 + ((n) >> 3), (n) & 7) +#define SYS_AMEVCNTR1_EL0(n) SYS_AM_EL0(12 + ((n) >> 3), (n) & 7) +#define SYS_AMEVTYPE1_EL0(n) SYS_AM_EL0(14 + ((n) >> 3), (n) & 7) + +/* AMU v1: Fixed (architecturally defined) activity monitors */ +#define SYS_AMEVCNTR0_CORE_EL0 SYS_AMEVCNTR0_EL0(0) +#define SYS_AMEVCNTR0_CONST_EL0 SYS_AMEVCNTR0_EL0(1) +#define SYS_AMEVCNTR0_INST_RET_EL0 SYS_AMEVCNTR0_EL0(2) +#define SYS_AMEVCNTR0_MEM_STALL SYS_AMEVCNTR0_EL0(3) + #define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0) #define SYS_CNTP_TVAL_EL0 sys_reg(3, 3, 14, 2, 0) @@ -598,6 +634,7 @@ #define ID_AA64PFR0_CSV3_SHIFT 60 #define ID_AA64PFR0_CSV2_SHIFT 56 #define ID_AA64PFR0_DIT_SHIFT 48 +#define ID_AA64PFR0_AMU_SHIFT 44 #define ID_AA64PFR0_SVE_SHIFT 32 #define ID_AA64PFR0_RAS_SHIFT 28 #define ID_AA64PFR0_GIC_SHIFT 24 @@ -608,6 +645,7 @@ #define ID_AA64PFR0_EL1_SHIFT 4 #define ID_AA64PFR0_EL0_SHIFT 0 +#define ID_AA64PFR0_AMU 0x1 #define ID_AA64PFR0_SVE 0x1 #define ID_AA64PFR0_RAS_V1 0x1 #define ID_AA64PFR0_FP_NI 0xf @@ -702,6 +740,16 @@ #define ID_AA64DFR0_TRACEVER_SHIFT 4 #define ID_AA64DFR0_DEBUGVER_SHIFT 0 +#define ID_AA64DFR0_PMUVER_8_0 0x1 +#define ID_AA64DFR0_PMUVER_8_1 0x4 +#define ID_AA64DFR0_PMUVER_8_4 0x5 +#define ID_AA64DFR0_PMUVER_8_5 0x6 +#define ID_AA64DFR0_PMUVER_IMP_DEF 0xf + +#define ID_DFR0_PERFMON_SHIFT 24 + +#define ID_DFR0_PERFMON_8_1 0x4 + #define ID_ISAR5_RDM_SHIFT 24 #define ID_ISAR5_CRC32_SHIFT 16 #define ID_ISAR5_SHA2_SHIFT 12 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..0cc835ddfcd1 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -16,6 +16,15 @@ int pcibus_to_node(struct pci_bus *bus); #include <linux/arch_topology.h> +#ifdef CONFIG_ARM64_AMU_EXTN +/* + * Replace task scheduler's default counter-based + * frequency-invariance scale factor setting. + */ +void topology_scale_freq_tick(void); +#define arch_scale_freq_tick topology_scale_freq_tick +#endif /* CONFIG_ARM64_AMU_EXTN */ + /* Replace task scheduler's default frequency-invariant accounting */ #define arch_scale_freq_capacity topology_get_freq_scale @@ -25,6 +34,9 @@ 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/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h new file mode 100644 index 000000000000..df6ea65c1dec --- /dev/null +++ b/arch/arm64/include/asm/vdso/clocksource.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSOCLOCKSOURCE_H +#define __ASM_VDSOCLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES \ + VDSO_CLOCKMODE_ARCHTIMER + +#endif diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index 537b1e695365..b6907ae78e53 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -8,12 +8,10 @@ #ifndef __ASSEMBLY__ #include <asm/unistd.h> -#include <uapi/linux/time.h> +#include <asm/errno.h> #include <asm/vdso/compat_barrier.h> -#define __VDSO_USE_SYSCALL ULLONG_MAX - #define VDSO_HAS_CLOCK_GETRES 1 #define BUILD_VDSO32 1 @@ -78,10 +76,6 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) register long ret asm ("r0"); register long nr asm("r7") = __NR_compat_clock_getres_time64; - /* The checks below are required for ABI consistency with arm */ - if ((_clkid >= MAX_CLOCKS) && (_ts == NULL)) - return -EINVAL; - asm volatile( " swi #0\n" : "=r" (ret) @@ -99,10 +93,6 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) register long ret asm ("r0"); register long nr asm("r7") = __NR_compat_clock_getres; - /* The checks below are required for ABI consistency with arm */ - if ((_clkid >= MAX_CLOCKS) && (_ts == NULL)) - return -EINVAL; - asm volatile( " swi #0\n" : "=r" (ret) @@ -117,11 +107,12 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) u64 res; /* - * clock_mode == 0 implies that vDSO are enabled otherwise - * fallback on syscall. + * Core checks for mode already, so this raced against a concurrent + * update. Return something. Core will do another round and then + * see the mode change and fallback to the syscall. */ - if (clock_mode) - return __VDSO_USE_SYSCALL; + if (clock_mode == VDSO_CLOCKMODE_NONE) + return 0; /* * This isb() is required to prevent that the counter value diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index b08f476b72b4..afba6ba332f8 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -8,9 +8,6 @@ #ifndef __ASSEMBLY__ #include <asm/unistd.h> -#include <uapi/linux/time.h> - -#define __VDSO_USE_SYSCALL ULLONG_MAX #define VDSO_HAS_CLOCK_GETRES 1 @@ -71,11 +68,12 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) u64 res; /* - * clock_mode == 0 implies that vDSO are enabled otherwise - * fallback on syscall. + * Core checks for mode already, so this raced against a concurrent + * update. Return something. Core will do another round and then + * see the mode change and fallback to the syscall. */ - if (clock_mode) - return __VDSO_USE_SYSCALL; + if (clock_mode == VDSO_CLOCKMODE_NONE) + return 0; /* * This isb() is required to prevent that the counter value diff --git a/arch/arm64/include/asm/vdso/processor.h b/arch/arm64/include/asm/vdso/processor.h new file mode 100644 index 000000000000..ff830b766ad2 --- /dev/null +++ b/arch/arm64/include/asm/vdso/processor.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_VDSO_PROCESSOR_H +#define __ASM_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLY__ + +static inline void cpu_relax(void) +{ + asm volatile("yield" ::: "memory"); +} + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h index 0c20a7c1bee5..f94b1457c117 100644 --- a/arch/arm64/include/asm/vdso/vsyscall.h +++ b/arch/arm64/include/asm/vdso/vsyscall.h @@ -22,15 +22,6 @@ struct vdso_data *__arm64_get_k_vdso_data(void) #define __arch_get_k_vdso_data __arm64_get_k_vdso_data static __always_inline -int __arm64_get_clock_mode(struct timekeeper *tk) -{ - u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct; - - return use_syscall; -} -#define __arch_get_clock_mode __arm64_get_clock_mode - -static __always_inline void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk) { vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK; 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/Makefile b/arch/arm64/kernel/Makefile index fc6488660f64..4e5b8ee31442 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -21,7 +21,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ syscall.o -extra-$(CONFIG_EFI) := efi-entry.o +targets += efi-entry.o OBJCOPYFLAGS := --prefix-symbols=__efistub_ $(obj)/%.stub.o: $(obj)/%.o FORCE diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 7832b3216370..4cc581af2d96 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -630,7 +630,7 @@ static int __init armv8_deprecated_init(void) register_insn_emulation(&cp15_barrier_ops); if (IS_ENABLED(CONFIG_SETEND_EMULATION)) { - if(system_supports_mixed_endian_el0()) + if (system_supports_mixed_endian_el0()) register_insn_emulation(&setend_ops); else pr_info("setend instruction emulation is not supported on this system\n"); diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index a5bdce8af65b..9981a0a5a87f 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -40,6 +40,10 @@ int main(void) #endif BLANK(); DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context)); +#ifdef CONFIG_ARM64_PTR_AUTH + DEFINE(THREAD_KEYS_USER, offsetof(struct task_struct, thread.keys_user)); + DEFINE(THREAD_KEYS_KERNEL, offsetof(struct task_struct, thread.keys_kernel)); +#endif BLANK(); DEFINE(S_X0, offsetof(struct pt_regs, regs[0])); DEFINE(S_X2, offsetof(struct pt_regs, regs[2])); @@ -88,6 +92,9 @@ int main(void) BLANK(); DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task)); +#ifdef CONFIG_ARM64_PTR_AUTH + DEFINE(CPU_BOOT_PTRAUTH_KEY, offsetof(struct secondary_data, ptrauth_key)); +#endif BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); @@ -128,5 +135,14 @@ int main(void) DEFINE(SDEI_EVENT_INTREGS, offsetof(struct sdei_registered_event, interrupted_regs)); DEFINE(SDEI_EVENT_PRIORITY, offsetof(struct sdei_registered_event, priority)); #endif +#ifdef CONFIG_ARM64_PTR_AUTH + DEFINE(PTRAUTH_USER_KEY_APIA, offsetof(struct ptrauth_keys_user, apia)); + DEFINE(PTRAUTH_USER_KEY_APIB, offsetof(struct ptrauth_keys_user, apib)); + DEFINE(PTRAUTH_USER_KEY_APDA, offsetof(struct ptrauth_keys_user, apda)); + DEFINE(PTRAUTH_USER_KEY_APDB, offsetof(struct ptrauth_keys_user, apdb)); + DEFINE(PTRAUTH_USER_KEY_APGA, offsetof(struct ptrauth_keys_user, apga)); + DEFINE(PTRAUTH_KERNEL_KEY_APIA, offsetof(struct ptrauth_keys_kernel, apia)); + BLANK(); +#endif return 0; } diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 32c7bf858dd9..38087b4c0432 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -32,7 +32,7 @@ ENTRY(__cpu_soft_restart) /* Clear sctlr_el1 flags. */ mrs x12, sctlr_el1 - ldr x13, =SCTLR_ELx_FLAGS + mov_q x13, SCTLR_ELx_FLAGS bic x12, x12, x13 pre_disable_mmu_workaround msr sctlr_el1, x12 diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 703ad0a84f99..df56d2295d16 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/cpufeature.h> +#include <asm/kvm_asm.h> #include <asm/smp_plat.h> static bool __maybe_unused @@ -113,13 +114,10 @@ atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1); DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); #ifdef CONFIG_KVM_INDIRECT_VECTORS -extern char __smccc_workaround_1_smc_start[]; -extern char __smccc_workaround_1_smc_end[]; - static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, const char *hyp_vecs_end) { - void *dst = lm_alias(__bp_harden_hyp_vecs_start + slot * SZ_2K); + void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K); int i; for (i = 0; i < SZ_2K; i += 0x80) @@ -163,9 +161,6 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, raw_spin_unlock(&bp_lock); } #else -#define __smccc_workaround_1_smc_start NULL -#define __smccc_workaround_1_smc_end NULL - static void install_bp_hardening_cb(bp_hardening_cb_t fn, const char *hyp_vecs_start, const char *hyp_vecs_end) @@ -176,7 +171,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, #include <linux/arm-smccc.h> -static void call_smc_arch_workaround_1(void) +static void __maybe_unused call_smc_arch_workaround_1(void) { arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } @@ -239,11 +234,14 @@ static int detect_harden_bp_fw(void) smccc_end = NULL; break; +#if IS_ENABLED(CONFIG_KVM_ARM_HOST) case SMCCC_CONDUIT_SMC: cb = call_smc_arch_workaround_1; - smccc_start = __smccc_workaround_1_smc_start; - smccc_end = __smccc_workaround_1_smc_end; + smccc_start = __smccc_workaround_1_smc; + smccc_end = __smccc_workaround_1_smc + + __SMCCC_WORKAROUND_1_SMC_SZ; break; +#endif default: return -1; diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c index 7e07072757af..e133011f64b5 100644 --- a/arch/arm64/kernel/cpu_ops.c +++ b/arch/arm64/kernel/cpu_ops.c @@ -15,10 +15,12 @@ #include <asm/smp_plat.h> extern const struct cpu_operations smp_spin_table_ops; +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL extern const struct cpu_operations acpi_parking_protocol_ops; +#endif extern const struct cpu_operations cpu_psci_ops; -const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; +static const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = { &smp_spin_table_ops, @@ -94,7 +96,7 @@ static const char *__init cpu_read_enable_method(int cpu) /* * Read a cpu's enable method and record it in cpu_ops. */ -int __init cpu_read_ops(int cpu) +int __init init_cpu_ops(int cpu) { const char *enable_method = cpu_read_enable_method(cpu); @@ -109,3 +111,8 @@ int __init cpu_read_ops(int cpu) return 0; } + +const struct cpu_operations *get_cpu_ops(int cpu) +{ + return cpu_ops[cpu]; +} diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0b6715625cf6..9fac745aa7bb 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -116,6 +116,8 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap); +static bool __system_matches_cap(unsigned int n); + /* * NOTE: Any changes to the visibility of features should be kept in * sync with the documentation of the CPU feature register ABI. @@ -163,6 +165,7 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_AMU_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0), @@ -551,7 +554,7 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new) BUG_ON(!reg); - for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { + for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { u64 ftr_mask = arm64_ftr_mask(ftrp); s64 ftr_new = arm64_ftr_value(ftrp, new); @@ -1222,6 +1225,57 @@ static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap, #endif +#ifdef CONFIG_ARM64_AMU_EXTN + +/* + * The "amu_cpus" cpumask only signals that the CPU implementation for the + * flagged CPUs supports the Activity Monitors Unit (AMU) but does not provide + * information regarding all the events that it supports. When a CPU bit is + * set in the cpumask, the user of this feature can only rely on the presence + * of the 4 fixed counters for that CPU. But this does not guarantee that the + * counters are enabled or access to these counters is enabled by code + * executed at higher exception levels (firmware). + */ +static struct cpumask amu_cpus __read_mostly; + +bool cpu_has_amu_feat(int cpu) +{ + return cpumask_test_cpu(cpu, &amu_cpus); +} + +/* Initialize the use of AMU counters for frequency invariance */ +extern void init_cpu_freq_invariance_counters(void); + +static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) +{ + if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) { + pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n", + smp_processor_id()); + cpumask_set_cpu(smp_processor_id(), &amu_cpus); + init_cpu_freq_invariance_counters(); + } +} + +static bool has_amu(const struct arm64_cpu_capabilities *cap, + int __unused) +{ + /* + * The AMU extension is a non-conflicting feature: the kernel can + * safely run a mix of CPUs with and without support for the + * activity monitors extension. Therefore, unconditionally enable + * the capability to allow any late CPU to use the feature. + * + * With this feature unconditionally enabled, the cpu_enable + * function will be called for all CPUs that match the criteria, + * including secondary and hotplugged, marking this feature as + * present on that respective CPU. The enable function will also + * print a detection message. + */ + + return true; +} +#endif + #ifdef CONFIG_ARM64_VHE static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused) { @@ -1316,10 +1370,18 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused) #endif /* CONFIG_ARM64_RAS_EXTN */ #ifdef CONFIG_ARM64_PTR_AUTH -static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap) +static bool has_address_auth(const struct arm64_cpu_capabilities *entry, + int __unused) { - sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | - SCTLR_ELx_ENDA | SCTLR_ELx_ENDB); + return __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) || + __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF); +} + +static bool has_generic_auth(const struct arm64_cpu_capabilities *entry, + int __unused) +{ + return __system_matches_cap(ARM64_HAS_GENERIC_AUTH_ARCH) || + __system_matches_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF); } #endif /* CONFIG_ARM64_PTR_AUTH */ @@ -1347,6 +1409,25 @@ static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry, } #endif +/* Internal helper functions to match cpu capability type */ +static bool +cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU); +} + +static bool +cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU); +} + +static bool +cpucap_panic_on_conflict(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_PANIC_ON_CONFLICT); +} + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", @@ -1499,6 +1580,24 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_clear_disr, }, #endif /* CONFIG_ARM64_RAS_EXTN */ +#ifdef CONFIG_ARM64_AMU_EXTN + { + /* + * The feature is enabled by default if CONFIG_ARM64_AMU_EXTN=y. + * Therefore, don't provide .desc as we don't want the detection + * message to be shown until at least one CPU is detected to + * support the feature. + */ + .capability = ARM64_HAS_AMU_EXTN, + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, + .matches = has_amu, + .sys_reg = SYS_ID_AA64PFR0_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64PFR0_AMU_SHIFT, + .min_field_value = ID_AA64PFR0_AMU, + .cpu_enable = cpu_amu_enable, + }, +#endif /* CONFIG_ARM64_AMU_EXTN */ { .desc = "Data cache clean to the PoU not required for I/D coherence", .capability = ARM64_HAS_CACHE_IDC, @@ -1592,24 +1691,27 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "Address authentication (architected algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_ARCH, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_APA_SHIFT, .min_field_value = ID_AA64ISAR1_APA_ARCHITECTED, .matches = has_cpuid_feature, - .cpu_enable = cpu_enable_address_auth, }, { .desc = "Address authentication (IMP DEF algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_API_SHIFT, .min_field_value = ID_AA64ISAR1_API_IMP_DEF, .matches = has_cpuid_feature, - .cpu_enable = cpu_enable_address_auth, + }, + { + .capability = ARM64_HAS_ADDRESS_AUTH, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .matches = has_address_auth, }, { .desc = "Generic authentication (architected algorithm)", @@ -1631,6 +1733,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .min_field_value = ID_AA64ISAR1_GPI_IMP_DEF, .matches = has_cpuid_feature, }, + { + .capability = ARM64_HAS_GENERIC_AUTH, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_generic_auth, + }, #endif /* CONFIG_ARM64_PTR_AUTH */ #ifdef CONFIG_ARM64_PSEUDO_NMI { @@ -1980,10 +2087,8 @@ static void __init enable_cpu_capabilities(u16 scope_mask) * Run through the list of capabilities to check for conflicts. * If the system has already detected a capability, take necessary * action on this CPU. - * - * Returns "false" on conflicts. */ -static bool verify_local_cpu_caps(u16 scope_mask) +static void verify_local_cpu_caps(u16 scope_mask) { int i; bool cpu_has_cap, system_has_cap; @@ -2028,10 +2133,12 @@ static bool verify_local_cpu_caps(u16 scope_mask) pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n", smp_processor_id(), caps->capability, caps->desc, system_has_cap, cpu_has_cap); - return false; - } - return true; + if (cpucap_panic_on_conflict(caps)) + cpu_panic_kernel(); + else + cpu_die_early(); + } } /* @@ -2041,12 +2148,8 @@ static bool verify_local_cpu_caps(u16 scope_mask) static void check_early_cpu_features(void) { verify_cpu_asid_bits(); - /* - * Early features are used by the kernel already. If there - * is a conflict, we cannot proceed further. - */ - if (!verify_local_cpu_caps(SCOPE_BOOT_CPU)) - cpu_panic_kernel(); + + verify_local_cpu_caps(SCOPE_BOOT_CPU); } static void @@ -2094,8 +2197,7 @@ static void verify_local_cpu_capabilities(void) * check_early_cpu_features(), as they need to be verified * on all secondary CPUs. */ - if (!verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU)) - cpu_die_early(); + verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU); verify_local_elf_hwcaps(arm64_elf_hwcaps); @@ -2146,6 +2248,23 @@ bool this_cpu_has_cap(unsigned int n) return false; } +/* + * This helper function is used in a narrow window when, + * - The system wide safe registers are set with all the SMP CPUs and, + * - The SYSTEM_FEATURE cpu_hwcaps may not have been set. + * In all other cases cpus_have_{const_}cap() should be used. + */ +static bool __system_matches_cap(unsigned int n) +{ + if (n < ARM64_NCAPS) { + const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n]; + + if (cap) + return cap->matches(cap, SCOPE_SYSTEM); + } + return false; +} + void cpu_set_feature(unsigned int num) { WARN_ON(num >= MAX_CPU_FEATURES); @@ -2218,7 +2337,7 @@ void __init setup_cpu_features(void) static bool __maybe_unused cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) { - return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO)); + return (__system_matches_cap(ARM64_HAS_PAN) && !__system_matches_cap(ARM64_HAS_UAO)); } static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap) diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index e4d6af2fdec7..b512b5503f6e 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -18,11 +18,11 @@ int arm_cpuidle_init(unsigned int cpu) { + const struct cpu_operations *ops = get_cpu_ops(cpu); int ret = -EOPNOTSUPP; - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_suspend && - cpu_ops[cpu]->cpu_init_idle) - ret = cpu_ops[cpu]->cpu_init_idle(cpu); + if (ops && ops->cpu_suspend && ops->cpu_init_idle) + ret = ops->cpu_init_idle(cpu); return ret; } @@ -37,8 +37,9 @@ int arm_cpuidle_init(unsigned int cpu) int arm_cpuidle_suspend(int index) { int cpu = smp_processor_id(); + const struct cpu_operations *ops = get_cpu_ops(cpu); - return cpu_ops[cpu]->cpu_suspend(index); + return ops->cpu_suspend(index); } #ifdef CONFIG_ACPI 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/entry-common.c b/arch/arm64/kernel/entry-common.c index fde59981445c..c839b5bf1904 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(el0_pc); static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); - local_daif_restore(DAIF_PROCCTX_NOIRQ); + local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(regs->sp, esr, regs); } NOKPROBE_SYMBOL(el0_sp); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 7d02f9966d34..833d48c9acb5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -75,27 +75,27 @@ add x29, sp, #S_STACKFRAME .endm -ENTRY(ftrace_regs_caller) +SYM_CODE_START(ftrace_regs_caller) ftrace_regs_entry 1 b ftrace_common -ENDPROC(ftrace_regs_caller) +SYM_CODE_END(ftrace_regs_caller) -ENTRY(ftrace_caller) +SYM_CODE_START(ftrace_caller) ftrace_regs_entry 0 b ftrace_common -ENDPROC(ftrace_caller) +SYM_CODE_END(ftrace_caller) -ENTRY(ftrace_common) +SYM_CODE_START(ftrace_common) sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) mov x1, x9 // parent_ip (callsite's LR) ldr_l x2, function_trace_op // op mov x3, sp // regs -GLOBAL(ftrace_call) +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) bl ftrace_stub #ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller(); nop // If enabled, this will be replaced // "b ftrace_graph_caller" #endif @@ -122,17 +122,17 @@ ftrace_common_return: add sp, sp, #S_FRAME_SIZE + 16 ret x9 -ENDPROC(ftrace_common) +SYM_CODE_END(ftrace_common) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) +SYM_CODE_START(ftrace_graph_caller) ldr x0, [sp, #S_PC] sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) add x1, sp, #S_LR // parent_ip (callsite's LR) ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) bl prepare_ftrace_return b ftrace_common_return -ENDPROC(ftrace_graph_caller) +SYM_CODE_END(ftrace_graph_caller) #endif #else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ @@ -218,7 +218,7 @@ ENDPROC(ftrace_graph_caller) * - tracer function to probe instrumented function's entry, * - ftrace_graph_caller to set up an exit hook */ -ENTRY(_mcount) +SYM_FUNC_START(_mcount) mcount_enter ldr_l x2, ftrace_trace_function @@ -242,7 +242,7 @@ skip_ftrace_call: // } b.ne ftrace_graph_caller // ftrace_graph_caller(); #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ mcount_exit -ENDPROC(_mcount) +SYM_FUNC_END(_mcount) EXPORT_SYMBOL(_mcount) NOKPROBE(_mcount) @@ -253,9 +253,9 @@ NOKPROBE(_mcount) * and later on, NOP to branch to ftrace_caller() when enabled or branch to * NOP when disabled per-function base. */ -ENTRY(_mcount) +SYM_FUNC_START(_mcount) ret -ENDPROC(_mcount) +SYM_FUNC_END(_mcount) EXPORT_SYMBOL(_mcount) NOKPROBE(_mcount) @@ -268,24 +268,24 @@ NOKPROBE(_mcount) * - tracer function to probe instrumented function's entry, * - ftrace_graph_caller to set up an exit hook */ -ENTRY(ftrace_caller) +SYM_FUNC_START(ftrace_caller) mcount_enter mcount_get_pc0 x0 // function's pc mcount_get_lr x1 // function's lr -GLOBAL(ftrace_call) // tracer(pc, lr); +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) // tracer(pc, lr); nop // This will be replaced with "bl xxx" // where xxx can be any kind of tracer. #ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller(); nop // If enabled, this will be replaced // "b ftrace_graph_caller" #endif mcount_exit -ENDPROC(ftrace_caller) +SYM_FUNC_END(ftrace_caller) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -298,20 +298,20 @@ ENDPROC(ftrace_caller) * the call stack in order to intercept instrumented function's return path * and run return_to_handler() later on its exit. */ -ENTRY(ftrace_graph_caller) +SYM_FUNC_START(ftrace_graph_caller) mcount_get_pc x0 // function's pc mcount_get_lr_addr x1 // pointer to function's saved lr mcount_get_parent_fp x2 // parent's fp bl prepare_ftrace_return // prepare_ftrace_return(pc, &lr, fp) mcount_exit -ENDPROC(ftrace_graph_caller) +SYM_FUNC_END(ftrace_graph_caller) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ -ENTRY(ftrace_stub) +SYM_FUNC_START(ftrace_stub) ret -ENDPROC(ftrace_stub) +SYM_FUNC_END(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -320,7 +320,7 @@ ENDPROC(ftrace_stub) * Run ftrace_return_to_handler() before going back to parent. * @fp is checked against the value passed by ftrace_graph_caller(). */ -ENTRY(return_to_handler) +SYM_CODE_START(return_to_handler) /* save return value regs */ sub sp, sp, #64 stp x0, x1, [sp] @@ -340,5 +340,5 @@ ENTRY(return_to_handler) add sp, sp, #64 ret -END(return_to_handler) +SYM_CODE_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 9461d812ae27..ddcde093c433 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -14,6 +14,7 @@ #include <asm/alternative.h> #include <asm/assembler.h> #include <asm/asm-offsets.h> +#include <asm/asm_pointer_auth.h> #include <asm/cpufeature.h> #include <asm/errno.h> #include <asm/esr.h> @@ -177,6 +178,7 @@ alternative_cb_end apply_ssbd 1, x22, x23 + ptrauth_keys_install_kernel tsk, 1, x20, x22, x23 .else add x21, sp, #S_FRAME_SIZE get_current_task tsk @@ -341,6 +343,9 @@ alternative_else_nop_endif msr cntkctl_el1, x1 4: #endif + /* No kernel C function calls after this as user keys are set. */ + ptrauth_keys_install_user tsk, x0, x1, x2 + apply_ssbd 0, x0, x1 .endif @@ -465,7 +470,7 @@ alternative_endif .pushsection ".entry.text", "ax" .align 11 -ENTRY(vectors) +SYM_CODE_START(vectors) kernel_ventry 1, sync_invalid // Synchronous EL1t kernel_ventry 1, irq_invalid // IRQ EL1t kernel_ventry 1, fiq_invalid // FIQ EL1t @@ -492,7 +497,7 @@ ENTRY(vectors) kernel_ventry 0, fiq_invalid, 32 // FIQ 32-bit EL0 kernel_ventry 0, error_invalid, 32 // Error 32-bit EL0 #endif -END(vectors) +SYM_CODE_END(vectors) #ifdef CONFIG_VMAP_STACK /* @@ -534,57 +539,57 @@ __bad_stack: ASM_BUG() .endm -el0_sync_invalid: +SYM_CODE_START_LOCAL(el0_sync_invalid) inv_entry 0, BAD_SYNC -ENDPROC(el0_sync_invalid) +SYM_CODE_END(el0_sync_invalid) -el0_irq_invalid: +SYM_CODE_START_LOCAL(el0_irq_invalid) inv_entry 0, BAD_IRQ -ENDPROC(el0_irq_invalid) +SYM_CODE_END(el0_irq_invalid) -el0_fiq_invalid: +SYM_CODE_START_LOCAL(el0_fiq_invalid) inv_entry 0, BAD_FIQ -ENDPROC(el0_fiq_invalid) +SYM_CODE_END(el0_fiq_invalid) -el0_error_invalid: +SYM_CODE_START_LOCAL(el0_error_invalid) inv_entry 0, BAD_ERROR -ENDPROC(el0_error_invalid) +SYM_CODE_END(el0_error_invalid) #ifdef CONFIG_COMPAT -el0_fiq_invalid_compat: +SYM_CODE_START_LOCAL(el0_fiq_invalid_compat) inv_entry 0, BAD_FIQ, 32 -ENDPROC(el0_fiq_invalid_compat) +SYM_CODE_END(el0_fiq_invalid_compat) #endif -el1_sync_invalid: +SYM_CODE_START_LOCAL(el1_sync_invalid) inv_entry 1, BAD_SYNC -ENDPROC(el1_sync_invalid) +SYM_CODE_END(el1_sync_invalid) -el1_irq_invalid: +SYM_CODE_START_LOCAL(el1_irq_invalid) inv_entry 1, BAD_IRQ -ENDPROC(el1_irq_invalid) +SYM_CODE_END(el1_irq_invalid) -el1_fiq_invalid: +SYM_CODE_START_LOCAL(el1_fiq_invalid) inv_entry 1, BAD_FIQ -ENDPROC(el1_fiq_invalid) +SYM_CODE_END(el1_fiq_invalid) -el1_error_invalid: +SYM_CODE_START_LOCAL(el1_error_invalid) inv_entry 1, BAD_ERROR -ENDPROC(el1_error_invalid) +SYM_CODE_END(el1_error_invalid) /* * EL1 mode handlers. */ .align 6 -el1_sync: +SYM_CODE_START_LOCAL_NOALIGN(el1_sync) kernel_entry 1 mov x0, sp bl el1_sync_handler kernel_exit 1 -ENDPROC(el1_sync) +SYM_CODE_END(el1_sync) .align 6 -el1_irq: +SYM_CODE_START_LOCAL_NOALIGN(el1_irq) kernel_entry 1 gic_prio_irq_setup pmr=x20, tmp=x1 enable_da_f @@ -639,42 +644,42 @@ alternative_else_nop_endif #endif kernel_exit 1 -ENDPROC(el1_irq) +SYM_CODE_END(el1_irq) /* * EL0 mode handlers. */ .align 6 -el0_sync: +SYM_CODE_START_LOCAL_NOALIGN(el0_sync) kernel_entry 0 mov x0, sp bl el0_sync_handler b ret_to_user -ENDPROC(el0_sync) +SYM_CODE_END(el0_sync) #ifdef CONFIG_COMPAT .align 6 -el0_sync_compat: +SYM_CODE_START_LOCAL_NOALIGN(el0_sync_compat) kernel_entry 0, 32 mov x0, sp bl el0_sync_compat_handler b ret_to_user -ENDPROC(el0_sync_compat) +SYM_CODE_END(el0_sync_compat) .align 6 -el0_irq_compat: +SYM_CODE_START_LOCAL_NOALIGN(el0_irq_compat) kernel_entry 0, 32 b el0_irq_naked -ENDPROC(el0_irq_compat) +SYM_CODE_END(el0_irq_compat) -el0_error_compat: +SYM_CODE_START_LOCAL_NOALIGN(el0_error_compat) kernel_entry 0, 32 b el0_error_naked -ENDPROC(el0_error_compat) +SYM_CODE_END(el0_error_compat) #endif .align 6 -el0_irq: +SYM_CODE_START_LOCAL_NOALIGN(el0_irq) kernel_entry 0 el0_irq_naked: gic_prio_irq_setup pmr=x20, tmp=x0 @@ -696,9 +701,9 @@ el0_irq_naked: bl trace_hardirqs_on #endif b ret_to_user -ENDPROC(el0_irq) +SYM_CODE_END(el0_irq) -el1_error: +SYM_CODE_START_LOCAL(el1_error) kernel_entry 1 mrs x1, esr_el1 gic_prio_kentry_setup tmp=x2 @@ -706,9 +711,9 @@ el1_error: mov x0, sp bl do_serror kernel_exit 1 -ENDPROC(el1_error) +SYM_CODE_END(el1_error) -el0_error: +SYM_CODE_START_LOCAL(el0_error) kernel_entry 0 el0_error_naked: mrs x25, esr_el1 @@ -720,7 +725,7 @@ el0_error_naked: bl do_serror enable_da_f b ret_to_user -ENDPROC(el0_error) +SYM_CODE_END(el0_error) /* * Ok, we need to do extra processing, enter the slow path. @@ -832,7 +837,7 @@ alternative_else_nop_endif .endm .align 11 -ENTRY(tramp_vectors) +SYM_CODE_START_NOALIGN(tramp_vectors) .space 0x400 tramp_ventry @@ -844,24 +849,24 @@ ENTRY(tramp_vectors) tramp_ventry 32 tramp_ventry 32 tramp_ventry 32 -END(tramp_vectors) +SYM_CODE_END(tramp_vectors) -ENTRY(tramp_exit_native) +SYM_CODE_START(tramp_exit_native) tramp_exit -END(tramp_exit_native) +SYM_CODE_END(tramp_exit_native) -ENTRY(tramp_exit_compat) +SYM_CODE_START(tramp_exit_compat) tramp_exit 32 -END(tramp_exit_compat) +SYM_CODE_END(tramp_exit_compat) .ltorg .popsection // .entry.tramp.text #ifdef CONFIG_RANDOMIZE_BASE .pushsection ".rodata", "a" .align PAGE_SHIFT - .globl __entry_tramp_data_start -__entry_tramp_data_start: +SYM_DATA_START(__entry_tramp_data_start) .quad vectors +SYM_DATA_END(__entry_tramp_data_start) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ @@ -874,7 +879,7 @@ __entry_tramp_data_start: * Previous and next are guaranteed not to be the same. * */ -ENTRY(cpu_switch_to) +SYM_FUNC_START(cpu_switch_to) mov x10, #THREAD_CPU_CONTEXT add x8, x0, x10 mov x9, sp @@ -895,21 +900,22 @@ ENTRY(cpu_switch_to) ldr lr, [x8] mov sp, x9 msr sp_el0, x1 + ptrauth_keys_install_kernel x1, 1, x8, x9, x10 ret -ENDPROC(cpu_switch_to) +SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) /* * This is how we return from a fork. */ -ENTRY(ret_from_fork) +SYM_CODE_START(ret_from_fork) bl schedule_tail cbz x19, 1f // not a kernel thread mov x0, x20 blr x19 1: get_current_task tsk b ret_to_user -ENDPROC(ret_from_fork) +SYM_CODE_END(ret_from_fork) NOKPROBE(ret_from_fork) #ifdef CONFIG_ARM_SDE_INTERFACE @@ -938,7 +944,7 @@ NOKPROBE(ret_from_fork) */ .ltorg .pushsection ".entry.tramp.text", "ax" -ENTRY(__sdei_asm_entry_trampoline) +SYM_CODE_START(__sdei_asm_entry_trampoline) mrs x4, ttbr1_el1 tbz x4, #USER_ASID_BIT, 1f @@ -960,7 +966,7 @@ ENTRY(__sdei_asm_entry_trampoline) ldr x4, =__sdei_asm_handler #endif br x4 -ENDPROC(__sdei_asm_entry_trampoline) +SYM_CODE_END(__sdei_asm_entry_trampoline) NOKPROBE(__sdei_asm_entry_trampoline) /* @@ -970,21 +976,22 @@ NOKPROBE(__sdei_asm_entry_trampoline) * x2: exit_mode * x4: struct sdei_registered_event argument from registration time. */ -ENTRY(__sdei_asm_exit_trampoline) +SYM_CODE_START(__sdei_asm_exit_trampoline) ldr x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)] cbnz x4, 1f tramp_unmap_kernel tmp=x4 1: sdei_handler_exit exit_mode=x2 -ENDPROC(__sdei_asm_exit_trampoline) +SYM_CODE_END(__sdei_asm_exit_trampoline) NOKPROBE(__sdei_asm_exit_trampoline) .ltorg .popsection // .entry.tramp.text #ifdef CONFIG_RANDOMIZE_BASE .pushsection ".rodata", "a" -__sdei_asm_trampoline_next_handler: +SYM_DATA_START(__sdei_asm_trampoline_next_handler) .quad __sdei_asm_handler +SYM_DATA_END(__sdei_asm_trampoline_next_handler) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ @@ -1002,7 +1009,7 @@ __sdei_asm_trampoline_next_handler: * follow SMC-CC. We save (or retrieve) all the registers as the handler may * want them. */ -ENTRY(__sdei_asm_handler) +SYM_CODE_START(__sdei_asm_handler) stp x2, x3, [x1, #SDEI_EVENT_INTREGS + S_PC] stp x4, x5, [x1, #SDEI_EVENT_INTREGS + 16 * 2] stp x6, x7, [x1, #SDEI_EVENT_INTREGS + 16 * 3] @@ -1085,6 +1092,6 @@ alternative_else_nop_endif tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline br x5 #endif -ENDPROC(__sdei_asm_handler) +SYM_CODE_END(__sdei_asm_handler) NOKPROBE(__sdei_asm_handler) #endif /* CONFIG_ARM_SDE_INTERFACE */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 989b1944cb71..57a91032b4c2 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -105,7 +105,7 @@ pe_header: * x24 __primary_switch() .. relocate_kernel() * current RELR displacement */ -ENTRY(stext) +SYM_CODE_START(stext) bl preserve_boot_args bl el2_setup // Drop to EL1, w0=cpu_boot_mode adrp x23, __PHYS_OFFSET @@ -118,14 +118,15 @@ ENTRY(stext) * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ + mov x0, #ARM64_CPU_BOOT_PRIMARY bl __cpu_setup // initialise processor b __primary_switch -ENDPROC(stext) +SYM_CODE_END(stext) /* * Preserve the arguments passed by the bootloader in x0 .. x3 */ -preserve_boot_args: +SYM_CODE_START_LOCAL(preserve_boot_args) mov x21, x0 // x21=FDT adr_l x0, boot_args // record the contents of @@ -137,7 +138,7 @@ preserve_boot_args: mov x1, #0x20 // 4 x 8 bytes b __inval_dcache_area // tail call -ENDPROC(preserve_boot_args) +SYM_CODE_END(preserve_boot_args) /* * Macro to create a table entry to the next page. @@ -275,7 +276,7 @@ ENDPROC(preserve_boot_args) * - first few MB of the kernel linear mapping to jump to once the MMU has * been enabled */ -__create_page_tables: +SYM_FUNC_START_LOCAL(__create_page_tables) mov x28, lr /* @@ -403,15 +404,14 @@ __create_page_tables: bl __inval_dcache_area ret x28 -ENDPROC(__create_page_tables) - .ltorg +SYM_FUNC_END(__create_page_tables) /* * The following fragment of code is executed with the MMU enabled. * * x0 = __PHYS_OFFSET */ -__primary_switched: +SYM_FUNC_START_LOCAL(__primary_switched) adrp x4, init_thread_union add sp, x4, #THREAD_SIZE adr_l x5, init_task @@ -456,7 +456,14 @@ __primary_switched: mov x29, #0 mov x30, #0 b start_kernel -ENDPROC(__primary_switched) +SYM_FUNC_END(__primary_switched) + + .pushsection ".rodata", "a" +SYM_DATA_START(kimage_vaddr) + .quad _text - TEXT_OFFSET +SYM_DATA_END(kimage_vaddr) +EXPORT_SYMBOL(kimage_vaddr) + .popsection /* * end early head section, begin head code that is also used for @@ -464,10 +471,6 @@ ENDPROC(__primary_switched) */ .section ".idmap.text","awx" -ENTRY(kimage_vaddr) - .quad _text - TEXT_OFFSET -EXPORT_SYMBOL(kimage_vaddr) - /* * If we're fortunate enough to boot at EL2, ensure that the world is * sane before dropping to EL1. @@ -475,7 +478,7 @@ EXPORT_SYMBOL(kimage_vaddr) * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in w0 if * booted in EL1 or EL2 respectively. */ -ENTRY(el2_setup) +SYM_FUNC_START(el2_setup) msr SPsel, #1 // We want to use SP_EL{1,2} mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 @@ -599,7 +602,7 @@ set_hcr: isb ret -install_el2_stub: +SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL) /* * When VHE is not in use, early init of EL2 and EL1 needs to be * done here. @@ -636,13 +639,13 @@ install_el2_stub: msr elr_el2, lr mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 eret -ENDPROC(el2_setup) +SYM_FUNC_END(el2_setup) /* * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed * in w0. See arch/arm64/include/asm/virt.h for more info. */ -set_cpu_boot_mode_flag: +SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag) adr_l x1, __boot_cpu_mode cmp w0, #BOOT_CPU_MODE_EL2 b.ne 1f @@ -651,7 +654,7 @@ set_cpu_boot_mode_flag: dmb sy dc ivac, x1 // Invalidate potentially stale cache line ret -ENDPROC(set_cpu_boot_mode_flag) +SYM_FUNC_END(set_cpu_boot_mode_flag) /* * These values are written with the MMU off, but read with the MMU on. @@ -667,15 +670,17 @@ ENDPROC(set_cpu_boot_mode_flag) * This is not in .bss, because we set it sufficiently early that the boot-time * zeroing of .bss would clobber it. */ -ENTRY(__boot_cpu_mode) +SYM_DATA_START(__boot_cpu_mode) .long BOOT_CPU_MODE_EL2 .long BOOT_CPU_MODE_EL1 +SYM_DATA_END(__boot_cpu_mode) /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. */ -ENTRY(__early_cpu_boot_status) +SYM_DATA_START(__early_cpu_boot_status) .quad 0 +SYM_DATA_END(__early_cpu_boot_status) .popsection @@ -683,7 +688,7 @@ ENTRY(__early_cpu_boot_status) * This provides a "holding pen" for platforms to hold all secondary * cores are held until we're ready for them to initialise. */ -ENTRY(secondary_holding_pen) +SYM_FUNC_START(secondary_holding_pen) bl el2_setup // Drop to EL1, w0=cpu_boot_mode bl set_cpu_boot_mode_flag mrs x0, mpidr_el1 @@ -695,31 +700,32 @@ pen: ldr x4, [x3] b.eq secondary_startup wfe b pen -ENDPROC(secondary_holding_pen) +SYM_FUNC_END(secondary_holding_pen) /* * Secondary entry point that jumps straight into the kernel. Only to * be used where CPUs are brought online dynamically by the kernel. */ -ENTRY(secondary_entry) +SYM_FUNC_START(secondary_entry) bl el2_setup // Drop to EL1 bl set_cpu_boot_mode_flag b secondary_startup -ENDPROC(secondary_entry) +SYM_FUNC_END(secondary_entry) -secondary_startup: +SYM_FUNC_START_LOCAL(secondary_startup) /* * Common entry point for secondary CPUs. */ bl __cpu_secondary_check52bitva + mov x0, #ARM64_CPU_BOOT_SECONDARY bl __cpu_setup // initialise processor adrp x1, swapper_pg_dir bl __enable_mmu ldr x8, =__secondary_switched br x8 -ENDPROC(secondary_startup) +SYM_FUNC_END(secondary_startup) -__secondary_switched: +SYM_FUNC_START_LOCAL(__secondary_switched) adr_l x5, vectors msr vbar_el1, x5 isb @@ -734,13 +740,13 @@ __secondary_switched: mov x29, #0 mov x30, #0 b secondary_start_kernel -ENDPROC(__secondary_switched) +SYM_FUNC_END(__secondary_switched) -__secondary_too_slow: +SYM_FUNC_START_LOCAL(__secondary_too_slow) wfe wfi b __secondary_too_slow -ENDPROC(__secondary_too_slow) +SYM_FUNC_END(__secondary_too_slow) /* * The booting CPU updates the failed status @__early_cpu_boot_status, @@ -772,7 +778,7 @@ ENDPROC(__secondary_too_slow) * Checks if the selected granule size is supported by the CPU. * If it isn't, park the CPU */ -ENTRY(__enable_mmu) +SYM_FUNC_START(__enable_mmu) mrs x2, ID_AA64MMFR0_EL1 ubfx x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4 cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED @@ -796,9 +802,9 @@ ENTRY(__enable_mmu) dsb nsh isb ret -ENDPROC(__enable_mmu) +SYM_FUNC_END(__enable_mmu) -ENTRY(__cpu_secondary_check52bitva) +SYM_FUNC_START(__cpu_secondary_check52bitva) #ifdef CONFIG_ARM64_VA_BITS_52 ldr_l x0, vabits_actual cmp x0, #52 @@ -816,9 +822,9 @@ ENTRY(__cpu_secondary_check52bitva) #endif 2: ret -ENDPROC(__cpu_secondary_check52bitva) +SYM_FUNC_END(__cpu_secondary_check52bitva) -__no_granule_support: +SYM_FUNC_START_LOCAL(__no_granule_support) /* Indicate that this CPU can't boot and is stuck in the kernel */ update_early_cpu_boot_status \ CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_NO_GRAN, x1, x2 @@ -826,10 +832,10 @@ __no_granule_support: wfe wfi b 1b -ENDPROC(__no_granule_support) +SYM_FUNC_END(__no_granule_support) #ifdef CONFIG_RELOCATABLE -__relocate_kernel: +SYM_FUNC_START_LOCAL(__relocate_kernel) /* * Iterate over each entry in the relocation table, and apply the * relocations in place. @@ -931,10 +937,10 @@ __relocate_kernel: #endif ret -ENDPROC(__relocate_kernel) +SYM_FUNC_END(__relocate_kernel) #endif -__primary_switch: +SYM_FUNC_START_LOCAL(__primary_switch) #ifdef CONFIG_RANDOMIZE_BASE mov x19, x0 // preserve new SCTLR_EL1 value mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value @@ -977,4 +983,4 @@ __primary_switch: ldr x8, =__primary_switched adrp x0, __PHYS_OFFSET br x8 -ENDPROC(__primary_switch) +SYM_FUNC_END(__primary_switch) diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 38bcd4d4e43b..6532105b3e32 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -110,8 +110,6 @@ ENTRY(swsusp_arch_suspend_exit) cbz x24, 3f /* Do we need to re-initialise EL2? */ hvc #0 3: ret - - .ltorg ENDPROC(swsusp_arch_suspend_exit) /* 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/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 73d46070b315..e473ead806ed 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -63,7 +63,7 @@ el1_sync: beq 9f // Nothing to reset! /* Someone called kvm_call_hyp() against the hyp-stub... */ - ldr x0, =HVC_STUB_ERR + mov_q x0, HVC_STUB_ERR eret 9: mov x0, xzr 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/kaslr.c b/arch/arm64/kernel/kaslr.c index 53b8a4ee64ff..91a83104c6e8 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -11,6 +11,7 @@ #include <linux/sched.h> #include <linux/types.h> +#include <asm/archrandom.h> #include <asm/cacheflush.h> #include <asm/fixmap.h> #include <asm/kernel-pgtable.h> diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index dd3ae8081b38..b40c3b0def92 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -121,7 +121,7 @@ static int setup_dtb(struct kimage *image, /* add kaslr-seed */ ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED); - if (ret == -FDT_ERR_NOTFOUND) + if (ret == -FDT_ERR_NOTFOUND) ret = 0; else if (ret) goto out; diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index e40b65645c86..4d7879484cec 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -285,6 +285,17 @@ static struct attribute_group armv8_pmuv3_format_attr_group = { #define ARMV8_IDX_COUNTER_LAST(cpu_pmu) \ (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) + +/* + * We unconditionally enable ARMv8.5-PMU long event counter support + * (64-bit events) where supported. Indicate if this arm_pmu has long + * event counter support. + */ +static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu) +{ + return (cpu_pmu->pmuver >= ID_AA64DFR0_PMUVER_8_5); +} + /* * We must chain two programmable counters for 64 bit events, * except when we have allocated the 64bit cycle counter (for CPU @@ -294,9 +305,11 @@ static struct attribute_group armv8_pmuv3_format_attr_group = { static inline bool armv8pmu_event_is_chained(struct perf_event *event) { int idx = event->hw.idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); return !WARN_ON(idx < 0) && armv8pmu_event_is_64bit(event) && + !armv8pmu_has_long_event(cpu_pmu) && (idx != ARMV8_IDX_CYCLE_COUNTER); } @@ -345,7 +358,7 @@ static inline void armv8pmu_select_counter(int idx) isb(); } -static inline u32 armv8pmu_read_evcntr(int idx) +static inline u64 armv8pmu_read_evcntr(int idx) { armv8pmu_select_counter(idx); return read_sysreg(pmxevcntr_el0); @@ -362,6 +375,44 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event) return val; } +/* + * The cycle counter is always a 64-bit counter. When ARMV8_PMU_PMCR_LP + * is set the event counters also become 64-bit counters. Unless the + * user has requested a long counter (attr.config1) then we want to + * interrupt upon 32-bit overflow - we achieve this by applying a bias. + */ +static bool armv8pmu_event_needs_bias(struct perf_event *event) +{ + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (armv8pmu_event_is_64bit(event)) + return false; + + if (armv8pmu_has_long_event(cpu_pmu) || + idx == ARMV8_IDX_CYCLE_COUNTER) + return true; + + return false; +} + +static u64 armv8pmu_bias_long_counter(struct perf_event *event, u64 value) +{ + if (armv8pmu_event_needs_bias(event)) + value |= GENMASK(63, 32); + + return value; +} + +static u64 armv8pmu_unbias_long_counter(struct perf_event *event, u64 value) +{ + if (armv8pmu_event_needs_bias(event)) + value &= ~GENMASK(63, 32); + + return value; +} + static u64 armv8pmu_read_counter(struct perf_event *event) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); @@ -377,10 +428,10 @@ static u64 armv8pmu_read_counter(struct perf_event *event) else value = armv8pmu_read_hw_counter(event); - return value; + return armv8pmu_unbias_long_counter(event, value); } -static inline void armv8pmu_write_evcntr(int idx, u32 value) +static inline void armv8pmu_write_evcntr(int idx, u64 value) { armv8pmu_select_counter(idx); write_sysreg(value, pmxevcntr_el0); @@ -405,20 +456,14 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value) struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + value = armv8pmu_bias_long_counter(event, value); + if (!armv8pmu_counter_valid(cpu_pmu, idx)) pr_err("CPU%u writing wrong counter %d\n", smp_processor_id(), idx); - else if (idx == ARMV8_IDX_CYCLE_COUNTER) { - /* - * The cycles counter is really a 64-bit counter. - * When treating it as a 32-bit counter, we only count - * the lower 32 bits, and set the upper 32-bits so that - * we get an interrupt upon 32-bit overflow. - */ - if (!armv8pmu_event_is_64bit(event)) - value |= 0xffffffff00000000ULL; + else if (idx == ARMV8_IDX_CYCLE_COUNTER) write_sysreg(value, pmccntr_el0); - } else + else armv8pmu_write_hw_counter(event, value); } @@ -450,86 +495,74 @@ static inline void armv8pmu_write_event_type(struct perf_event *event) } } -static inline int armv8pmu_enable_counter(int idx) +static u32 armv8pmu_event_cnten_mask(struct perf_event *event) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmcntenset_el0); - return idx; + int counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); + u32 mask = BIT(counter); + + if (armv8pmu_event_is_chained(event)) + mask |= BIT(counter - 1); + return mask; +} + +static inline void armv8pmu_enable_counter(u32 mask) +{ + write_sysreg(mask, pmcntenset_el0); } static inline void armv8pmu_enable_event_counter(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; - int idx = event->hw.idx; - u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx)); + u32 mask = armv8pmu_event_cnten_mask(event); - if (armv8pmu_event_is_chained(event)) - counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1)); - - kvm_set_pmu_events(counter_bits, attr); + kvm_set_pmu_events(mask, attr); /* We rely on the hypervisor switch code to enable guest counters */ - if (!kvm_pmu_counter_deferred(attr)) { - armv8pmu_enable_counter(idx); - if (armv8pmu_event_is_chained(event)) - armv8pmu_enable_counter(idx - 1); - } + if (!kvm_pmu_counter_deferred(attr)) + armv8pmu_enable_counter(mask); } -static inline int armv8pmu_disable_counter(int idx) +static inline void armv8pmu_disable_counter(u32 mask) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmcntenclr_el0); - return idx; + write_sysreg(mask, pmcntenclr_el0); } static inline void armv8pmu_disable_event_counter(struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; struct perf_event_attr *attr = &event->attr; - int idx = hwc->idx; - u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx)); - - if (armv8pmu_event_is_chained(event)) - counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1)); + u32 mask = armv8pmu_event_cnten_mask(event); - kvm_clr_pmu_events(counter_bits); + kvm_clr_pmu_events(mask); /* We rely on the hypervisor switch code to disable guest counters */ - if (!kvm_pmu_counter_deferred(attr)) { - if (armv8pmu_event_is_chained(event)) - armv8pmu_disable_counter(idx - 1); - armv8pmu_disable_counter(idx); - } + if (!kvm_pmu_counter_deferred(attr)) + armv8pmu_disable_counter(mask); } -static inline int armv8pmu_enable_intens(int idx) +static inline void armv8pmu_enable_intens(u32 mask) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmintenset_el1); - return idx; + write_sysreg(mask, pmintenset_el1); } -static inline int armv8pmu_enable_event_irq(struct perf_event *event) +static inline void armv8pmu_enable_event_irq(struct perf_event *event) { - return armv8pmu_enable_intens(event->hw.idx); + u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); + armv8pmu_enable_intens(BIT(counter)); } -static inline int armv8pmu_disable_intens(int idx) +static inline void armv8pmu_disable_intens(u32 mask) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmintenclr_el1); + write_sysreg(mask, pmintenclr_el1); isb(); /* Clear the overflow flag in case an interrupt is pending. */ - write_sysreg(BIT(counter), pmovsclr_el0); + write_sysreg(mask, pmovsclr_el0); isb(); - - return idx; } -static inline int armv8pmu_disable_event_irq(struct perf_event *event) +static inline void armv8pmu_disable_event_irq(struct perf_event *event) { - return armv8pmu_disable_intens(event->hw.idx); + u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); + armv8pmu_disable_intens(BIT(counter)); } static inline u32 armv8pmu_getreset_flags(void) @@ -743,7 +776,8 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, /* * Otherwise use events counters */ - if (armv8pmu_event_is_64bit(event)) + if (armv8pmu_event_is_64bit(event) && + !armv8pmu_has_long_event(cpu_pmu)) return armv8pmu_get_chain_idx(cpuc, cpu_pmu); else return armv8pmu_get_single_idx(cpuc, cpu_pmu); @@ -815,13 +849,11 @@ static int armv8pmu_filter_match(struct perf_event *event) static void armv8pmu_reset(void *info) { struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; - u32 idx, nb_cnt = cpu_pmu->num_events; + u32 pmcr; /* The counter and interrupt enable registers are unknown at reset. */ - for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { - armv8pmu_disable_counter(idx); - armv8pmu_disable_intens(idx); - } + armv8pmu_disable_counter(U32_MAX); + armv8pmu_disable_intens(U32_MAX); /* Clear the counters we flip at guest entry/exit */ kvm_clr_pmu_events(U32_MAX); @@ -830,8 +862,13 @@ static void armv8pmu_reset(void *info) * Initialize & Reset PMNC. Request overflow interrupt for * 64 bit cycle counter but cheat in armv8pmu_write_counter(). */ - armv8pmu_pmcr_write(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | - ARMV8_PMU_PMCR_LC); + pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC; + + /* Enable long event counter support where available */ + if (armv8pmu_has_long_event(cpu_pmu)) + pmcr |= ARMV8_PMU_PMCR_LP; + + armv8pmu_pmcr_write(pmcr); } static int __armv8_pmuv3_map_event(struct perf_event *event, @@ -914,6 +951,7 @@ static void __armv8pmu_probe_pmu(void *info) if (pmuver == 0xf || pmuver == 0) return; + cpu_pmu->pmuver = pmuver; probe->present = true; /* Read the nb of CNTx counters supported from PMNC */ @@ -953,7 +991,10 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu) return probe.present ? 0 : -ENODEV; } -static int armv8_pmu_init(struct arm_pmu *cpu_pmu) +static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, + int (*map_event)(struct perf_event *event), + const struct attribute_group *events, + const struct attribute_group *format) { int ret = armv8pmu_probe_pmu(cpu_pmu); if (ret) @@ -972,144 +1013,127 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->set_event_filter = armv8pmu_set_event_filter; cpu_pmu->filter_match = armv8pmu_filter_match; + cpu_pmu->name = name; + cpu_pmu->map_event = map_event; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ? + events : &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ? + format : &armv8_pmuv3_format_attr_group; + return 0; } static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_pmuv3"; - cpu_pmu->map_event = armv8_pmuv3_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_pmuv3", + armv8_pmuv3_map_event, NULL, NULL); +} - return 0; +static int armv8_a34_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a34", + armv8_pmuv3_map_event, NULL, NULL); } static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a35"; - cpu_pmu->map_event = armv8_a53_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; - - return 0; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35", + armv8_a53_map_event, NULL, NULL); } static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a53"; - cpu_pmu->map_event = armv8_a53_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53", + armv8_a53_map_event, NULL, NULL); +} - return 0; +static int armv8_a55_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a55", + armv8_pmuv3_map_event, NULL, NULL); } static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a57"; - cpu_pmu->map_event = armv8_a57_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57", + armv8_a57_map_event, NULL, NULL); +} - return 0; +static int armv8_a65_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a65", + armv8_pmuv3_map_event, NULL, NULL); } static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a72"; - cpu_pmu->map_event = armv8_a57_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; - - return 0; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72", + armv8_a57_map_event, NULL, NULL); } static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a73"; - cpu_pmu->map_event = armv8_a73_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73", + armv8_a73_map_event, NULL, NULL); +} - return 0; +static int armv8_a75_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a75", + armv8_pmuv3_map_event, NULL, NULL); } -static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) +static int armv8_a76_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a76", + armv8_pmuv3_map_event, NULL, NULL); +} - cpu_pmu->name = "armv8_cavium_thunder"; - cpu_pmu->map_event = armv8_thunder_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; +static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a77", + armv8_pmuv3_map_event, NULL, NULL); +} - return 0; +static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_neoverse_e1", + armv8_pmuv3_map_event, NULL, NULL); } -static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) +static int armv8_n1_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; + return armv8_pmu_init(cpu_pmu, "armv8_neoverse_n1", + armv8_pmuv3_map_event, NULL, NULL); +} - cpu_pmu->name = "armv8_brcm_vulcan"; - cpu_pmu->map_event = armv8_vulcan_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; +static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder", + armv8_thunder_map_event, NULL, NULL); +} - return 0; +static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan", + armv8_vulcan_map_event, NULL, NULL); } static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init}, + {.compatible = "arm,cortex-a34-pmu", .data = armv8_a34_pmu_init}, {.compatible = "arm,cortex-a35-pmu", .data = armv8_a35_pmu_init}, {.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init}, + {.compatible = "arm,cortex-a55-pmu", .data = armv8_a55_pmu_init}, {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init}, + {.compatible = "arm,cortex-a65-pmu", .data = armv8_a65_pmu_init}, {.compatible = "arm,cortex-a72-pmu", .data = armv8_a72_pmu_init}, {.compatible = "arm,cortex-a73-pmu", .data = armv8_a73_pmu_init}, + {.compatible = "arm,cortex-a75-pmu", .data = armv8_a75_pmu_init}, + {.compatible = "arm,cortex-a76-pmu", .data = armv8_a76_pmu_init}, + {.compatible = "arm,cortex-a77-pmu", .data = armv8_a77_pmu_init}, + {.compatible = "arm,neoverse-e1-pmu", .data = armv8_e1_pmu_init}, + {.compatible = "arm,neoverse-n1-pmu", .data = armv8_n1_pmu_init}, {.compatible = "cavium,thunder-pmu", .data = armv8_thunder_pmu_init}, {.compatible = "brcm,vulcan-pmu", .data = armv8_vulcan_pmu_init}, {}, diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c index c507b584259d..1e77736a4f66 100644 --- a/arch/arm64/kernel/pointer_auth.c +++ b/arch/arm64/kernel/pointer_auth.c @@ -9,7 +9,7 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg) { - struct ptrauth_keys *keys = &tsk->thread.keys_user; + struct ptrauth_keys_user *keys = &tsk->thread.keys_user; unsigned long addr_key_mask = PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY; unsigned long key_mask = addr_key_mask | PR_PAC_APGAKEY; @@ -18,8 +18,7 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg) return -EINVAL; if (!arg) { - ptrauth_keys_init(keys); - ptrauth_keys_switch(keys); + ptrauth_keys_init_user(keys); return 0; } @@ -41,7 +40,5 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg) if (arg & PR_PAC_APGAKEY) get_random_bytes(&keys->apga, sizeof(keys->apga)); - ptrauth_keys_switch(keys); - return 0; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index bbb0f0c145f6..56be4cbf771f 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); } /* @@ -262,7 +262,7 @@ void __show_regs(struct pt_regs *regs) if (!user_mode(regs)) { printk("pc : %pS\n", (void *)regs->pc); - printk("lr : %pS\n", (void *)lr); + printk("lr : %pS\n", (void *)ptrauth_strip_insn_pac(lr)); } else { printk("pc : %016llx\n", regs->pc); printk("lr : %016llx\n", lr); @@ -376,6 +376,8 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start, */ fpsimd_flush_task_state(p); + ptrauth_thread_init_kernel(p); + if (likely(!(p->flags & PF_KTHREAD))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; @@ -466,6 +468,13 @@ static void ssbs_thread_switch(struct task_struct *next) if (unlikely(next->flags & PF_KTHREAD)) return; + /* + * If all CPUs implement the SSBS extension, then we just need to + * context-switch the PSTATE field. + */ + if (cpu_have_feature(cpu_feature(SSBS))) + return; + /* If the mitigation is enabled, then we leave SSBS clear. */ if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) || test_tsk_thread_flag(next, TIF_SSBD)) @@ -505,7 +514,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, contextidr_thread_switch(next); entry_task_switch(next); uao_thread_switch(next); - ptrauth_thread_switch(next); ssbs_thread_switch(next); /* @@ -608,8 +616,6 @@ long get_tagged_addr_ctrl(void) * only prevents the tagged address ABI enabling via prctl() and does not * disable it for tasks that already opted in to the relaxed ABI. */ -static int zero; -static int one = 1; static struct ctl_table tagged_addr_sysctl_table[] = { { @@ -618,8 +624,8 @@ static struct ctl_table tagged_addr_sysctl_table[] = { .data = &tagged_addr_disabled, .maxlen = sizeof(int), .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { } }; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index cd6e5fa48b9c..b3d3005d9515 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -999,7 +999,7 @@ static struct ptrauth_key pac_key_from_user(__uint128_t ukey) } static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, - const struct ptrauth_keys *keys) + const struct ptrauth_keys_user *keys) { ukeys->apiakey = pac_key_to_user(&keys->apia); ukeys->apibkey = pac_key_to_user(&keys->apib); @@ -1007,7 +1007,7 @@ static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, ukeys->apdbkey = pac_key_to_user(&keys->apdb); } -static void pac_address_keys_from_user(struct ptrauth_keys *keys, +static void pac_address_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_address_keys *ukeys) { keys->apia = pac_key_from_user(ukeys->apiakey); @@ -1021,7 +1021,7 @@ static int pac_address_keys_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; if (!system_supports_address_auth()) @@ -1038,7 +1038,7 @@ static int pac_address_keys_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; int ret; @@ -1056,12 +1056,12 @@ static int pac_address_keys_set(struct task_struct *target, } static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys, - const struct ptrauth_keys *keys) + const struct ptrauth_keys_user *keys) { ukeys->apgakey = pac_key_to_user(&keys->apga); } -static void pac_generic_keys_from_user(struct ptrauth_keys *keys, +static void pac_generic_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_generic_keys *ukeys) { keys->apga = pac_key_from_user(ukeys->apgakey); @@ -1072,7 +1072,7 @@ static int pac_generic_keys_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; if (!system_supports_generic_auth()) @@ -1089,7 +1089,7 @@ static int pac_generic_keys_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; int ret; diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index c1d7db71a726..c40ce496c78b 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -41,7 +41,7 @@ ENTRY(arm64_relocate_new_kernel) cmp x0, #CurrentEL_EL2 b.ne 1f mrs x0, sctlr_el2 - ldr x1, =SCTLR_ELx_FLAGS + mov_q x1, SCTLR_ELx_FLAGS bic x0, x0, x1 pre_disable_mmu_workaround msr sctlr_el2, x0 @@ -113,8 +113,6 @@ ENTRY(arm64_relocate_new_kernel) ENDPROC(arm64_relocate_new_kernel) -.ltorg - .align 3 /* To keep the 64-bit values below naturally aligned. */ .Lcopy_end: diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index a34890bf309f..3fd2c11c09fc 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -344,7 +344,7 @@ void __init setup_arch(char **cmdline_p) else psci_acpi_init(); - cpu_read_bootcpu_ops(); + init_bootcpu_ops(); smp_init_cpus(); smp_build_mpidr_hash(); @@ -371,8 +371,10 @@ void __init setup_arch(char **cmdline_p) static inline bool cpu_can_disable(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable) - return cpu_ops[cpu]->cpu_can_disable(cpu); + const struct cpu_operations *ops = get_cpu_ops(cpu); + + if (ops && ops->cpu_can_disable) + return ops->cpu_can_disable(cpu); #endif return false; } diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index f5b04dd8a710..7b2f2e650c44 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -3,6 +3,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> +#include <asm/smp.h> .text /* @@ -99,6 +100,7 @@ ENDPROC(__cpu_suspend_enter) .pushsection ".idmap.text", "awx" ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly + mov x0, #ARM64_CPU_RUNTIME bl __cpu_setup /* enable the MMU early - so we can access sleep_save_stash by va */ adrp x1, swapper_pg_dir diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d4ed9a19d8fe..061f60fe452f 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -93,8 +93,10 @@ static inline int op_cpu_kill(unsigned int cpu) */ static int boot_secondary(unsigned int cpu, struct task_struct *idle) { - if (cpu_ops[cpu]->cpu_boot) - return cpu_ops[cpu]->cpu_boot(cpu); + const struct cpu_operations *ops = get_cpu_ops(cpu); + + if (ops->cpu_boot) + return ops->cpu_boot(cpu); return -EOPNOTSUPP; } @@ -112,63 +114,66 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) */ secondary_data.task = idle; secondary_data.stack = task_stack_page(idle) + THREAD_SIZE; +#if defined(CONFIG_ARM64_PTR_AUTH) + secondary_data.ptrauth_key.apia.lo = idle->thread.keys_kernel.apia.lo; + secondary_data.ptrauth_key.apia.hi = idle->thread.keys_kernel.apia.hi; +#endif update_cpu_boot_status(CPU_MMU_OFF); __flush_dcache_area(&secondary_data, sizeof(secondary_data)); - /* - * Now bring the CPU into our world. - */ + /* Now bring the CPU into our world */ ret = boot_secondary(cpu, idle); - if (ret == 0) { - /* - * CPU was successfully started, wait for it to come online or - * time out. - */ - wait_for_completion_timeout(&cpu_running, - msecs_to_jiffies(5000)); - - if (!cpu_online(cpu)) { - pr_crit("CPU%u: failed to come online\n", cpu); - ret = -EIO; - } - } else { + if (ret) { pr_err("CPU%u: failed to boot: %d\n", cpu, ret); return ret; } + /* + * CPU was successfully started, wait for it to come online or + * time out. + */ + wait_for_completion_timeout(&cpu_running, + msecs_to_jiffies(5000)); + if (cpu_online(cpu)) + return 0; + + pr_crit("CPU%u: failed to come online\n", cpu); secondary_data.task = NULL; secondary_data.stack = NULL; +#if defined(CONFIG_ARM64_PTR_AUTH) + secondary_data.ptrauth_key.apia.lo = 0; + secondary_data.ptrauth_key.apia.hi = 0; +#endif __flush_dcache_area(&secondary_data, sizeof(secondary_data)); status = READ_ONCE(secondary_data.status); - if (ret && status) { - - if (status == CPU_MMU_OFF) - status = READ_ONCE(__early_cpu_boot_status); + if (status == CPU_MMU_OFF) + status = READ_ONCE(__early_cpu_boot_status); - switch (status & CPU_BOOT_STATUS_MASK) { - default: - pr_err("CPU%u: failed in unknown state : 0x%lx\n", - cpu, status); - cpus_stuck_in_kernel++; - break; - case CPU_KILL_ME: - if (!op_cpu_kill(cpu)) { - pr_crit("CPU%u: died during early boot\n", cpu); - break; - } - pr_crit("CPU%u: may not have shut down cleanly\n", cpu); - /* Fall through */ - case CPU_STUCK_IN_KERNEL: - pr_crit("CPU%u: is stuck in kernel\n", cpu); - if (status & CPU_STUCK_REASON_52_BIT_VA) - pr_crit("CPU%u: does not support 52-bit VAs\n", cpu); - if (status & CPU_STUCK_REASON_NO_GRAN) - pr_crit("CPU%u: does not support %luK granule \n", cpu, PAGE_SIZE / SZ_1K); - cpus_stuck_in_kernel++; + switch (status & CPU_BOOT_STATUS_MASK) { + default: + pr_err("CPU%u: failed in unknown state : 0x%lx\n", + cpu, status); + cpus_stuck_in_kernel++; + break; + case CPU_KILL_ME: + if (!op_cpu_kill(cpu)) { + pr_crit("CPU%u: died during early boot\n", cpu); break; - case CPU_PANIC_KERNEL: - panic("CPU%u detected unsupported configuration\n", cpu); } + pr_crit("CPU%u: may not have shut down cleanly\n", cpu); + /* Fall through */ + case CPU_STUCK_IN_KERNEL: + pr_crit("CPU%u: is stuck in kernel\n", cpu); + if (status & CPU_STUCK_REASON_52_BIT_VA) + pr_crit("CPU%u: does not support 52-bit VAs\n", cpu); + if (status & CPU_STUCK_REASON_NO_GRAN) { + pr_crit("CPU%u: does not support %luK granule\n", + cpu, PAGE_SIZE / SZ_1K); + } + cpus_stuck_in_kernel++; + break; + case CPU_PANIC_KERNEL: + panic("CPU%u detected unsupported configuration\n", cpu); } return ret; @@ -196,6 +201,7 @@ asmlinkage notrace void secondary_start_kernel(void) { u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; struct mm_struct *mm = &init_mm; + const struct cpu_operations *ops; unsigned int cpu; cpu = task_cpu(current); @@ -227,8 +233,9 @@ asmlinkage notrace void secondary_start_kernel(void) */ check_local_cpu_capabilities(); - if (cpu_ops[cpu]->cpu_postboot) - cpu_ops[cpu]->cpu_postboot(); + ops = get_cpu_ops(cpu); + if (ops->cpu_postboot) + ops->cpu_postboot(); /* * Log the CPU info before it is marked online and might get read. @@ -266,19 +273,21 @@ asmlinkage notrace void secondary_start_kernel(void) #ifdef CONFIG_HOTPLUG_CPU static int op_cpu_disable(unsigned int cpu) { + const struct cpu_operations *ops = get_cpu_ops(cpu); + /* * If we don't have a cpu_die method, abort before we reach the point * of no return. CPU0 may not have an cpu_ops, so test for it. */ - if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die) + if (!ops || !ops->cpu_die) return -EOPNOTSUPP; /* * We may need to abort a hot unplug for some other mechanism-specific * reason. */ - if (cpu_ops[cpu]->cpu_disable) - return cpu_ops[cpu]->cpu_disable(cpu); + if (ops->cpu_disable) + return ops->cpu_disable(cpu); return 0; } @@ -314,15 +323,17 @@ int __cpu_disable(void) static int op_cpu_kill(unsigned int cpu) { + const struct cpu_operations *ops = get_cpu_ops(cpu); + /* * If we have no means of synchronising with the dying CPU, then assume * that it is really dead. We can only wait for an arbitrary length of * time and hope that it's dead, so let's skip the wait and just hope. */ - if (!cpu_ops[cpu]->cpu_kill) + if (!ops->cpu_kill) return 0; - return cpu_ops[cpu]->cpu_kill(cpu); + return ops->cpu_kill(cpu); } /* @@ -357,6 +368,7 @@ void __cpu_die(unsigned int cpu) void cpu_die(void) { unsigned int cpu = smp_processor_id(); + const struct cpu_operations *ops = get_cpu_ops(cpu); idle_task_exit(); @@ -370,12 +382,22 @@ void cpu_die(void) * mechanism must perform all required cache maintenance to ensure that * no dirty lines are lost in the process of shutting down the CPU. */ - cpu_ops[cpu]->cpu_die(cpu); + ops->cpu_die(cpu); BUG(); } #endif +static void __cpu_try_die(int cpu) +{ +#ifdef CONFIG_HOTPLUG_CPU + const struct cpu_operations *ops = get_cpu_ops(cpu); + + if (ops && ops->cpu_die) + ops->cpu_die(cpu); +#endif +} + /* * Kill the calling secondary CPU, early in bringup before it is turned * online. @@ -389,12 +411,11 @@ void cpu_die_early(void) /* Mark this CPU absent */ set_cpu_present(cpu, 0); -#ifdef CONFIG_HOTPLUG_CPU - update_cpu_boot_status(CPU_KILL_ME); - /* Check if we can park ourselves */ - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) - cpu_ops[cpu]->cpu_die(cpu); -#endif + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { + update_cpu_boot_status(CPU_KILL_ME); + __cpu_try_die(cpu); + } + update_cpu_boot_status(CPU_STUCK_IN_KERNEL); cpu_park_loop(); @@ -488,10 +509,13 @@ static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid) */ static int __init smp_cpu_setup(int cpu) { - if (cpu_read_ops(cpu)) + const struct cpu_operations *ops; + + if (init_cpu_ops(cpu)) return -ENODEV; - if (cpu_ops[cpu]->cpu_init(cpu)) + ops = get_cpu_ops(cpu); + if (ops->cpu_init(cpu)) return -ENODEV; set_cpu_possible(cpu, true); @@ -714,6 +738,7 @@ void __init smp_init_cpus(void) void __init smp_prepare_cpus(unsigned int max_cpus) { + const struct cpu_operations *ops; int err; unsigned int cpu; unsigned int this_cpu; @@ -744,10 +769,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus) if (cpu == smp_processor_id()) continue; - if (!cpu_ops[cpu]) + ops = get_cpu_ops(cpu); + if (!ops) continue; - err = cpu_ops[cpu]->cpu_prepare(cpu); + err = ops->cpu_prepare(cpu); if (err) continue; @@ -863,10 +889,8 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) local_irq_disable(); sdei_mask_local_cpu(); -#ifdef CONFIG_HOTPLUG_CPU - if (cpu_ops[cpu]->cpu_die) - cpu_ops[cpu]->cpu_die(cpu); -#endif + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) + __cpu_try_die(cpu); /* just in case */ cpu_park_loop(); @@ -958,11 +982,22 @@ 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 +1010,10 @@ 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 +1036,11 @@ 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 +1048,7 @@ 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); @@ -1044,8 +1083,9 @@ static bool have_cpu_die(void) { #ifdef CONFIG_HOTPLUG_CPU int any_cpu = raw_smp_processor_id(); + const struct cpu_operations *ops = get_cpu_ops(any_cpu); - if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die) + if (ops && ops->cpu_die) return true; #endif return false; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index a336cb124320..139679c745bf 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -14,6 +14,7 @@ #include <linux/stacktrace.h> #include <asm/irq.h> +#include <asm/pointer_auth.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> @@ -86,7 +87,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && - (frame->pc == (unsigned long)return_to_handler)) { + (ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) { struct ftrace_ret_stack *ret_stack; /* * This is a case where function graph tracer has @@ -101,6 +102,8 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + frame->pc = ptrauth_strip_insn_pac(frame->pc); + /* * Frames created upon entry from EL0 have NULL FP and PC values, so * don't bother reporting these. Frames created by __noreturn functions diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 73f06d4b3aae..eebbc8d7123e 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -23,7 +23,7 @@ #include <linux/irq.h> #include <linux/delay.h> #include <linux/clocksource.h> -#include <linux/clk-provider.h> +#include <linux/of_clk.h> #include <linux/acpi.h> #include <clocksource/arm_arch_timer.h> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index fa9528dfd0ce..0801a0f3c156 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -14,6 +14,7 @@ #include <linux/acpi.h> #include <linux/arch_topology.h> #include <linux/cacheinfo.h> +#include <linux/cpufreq.h> #include <linux/init.h> #include <linux/percpu.h> @@ -120,4 +121,183 @@ int __init parse_acpi_topology(void) } #endif +#ifdef CONFIG_ARM64_AMU_EXTN +#undef pr_fmt +#define pr_fmt(fmt) "AMU: " fmt + +static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale); +static DEFINE_PER_CPU(u64, arch_const_cycles_prev); +static DEFINE_PER_CPU(u64, arch_core_cycles_prev); +static cpumask_var_t amu_fie_cpus; + +/* Initialize counter reference per-cpu variables for the current CPU */ +void init_cpu_freq_invariance_counters(void) +{ + this_cpu_write(arch_core_cycles_prev, + read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0)); + this_cpu_write(arch_const_cycles_prev, + read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0)); +} + +static int validate_cpu_freq_invariance_counters(int cpu) +{ + u64 max_freq_hz, ratio; + + if (!cpu_has_amu_feat(cpu)) { + pr_debug("CPU%d: counters are not supported.\n", cpu); + return -EINVAL; + } + + if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) || + !per_cpu(arch_core_cycles_prev, cpu))) { + pr_debug("CPU%d: cycle counters are not enabled.\n", cpu); + return -EINVAL; + } + + /* Convert maximum frequency from KHz to Hz and validate */ + max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000; + if (unlikely(!max_freq_hz)) { + pr_debug("CPU%d: invalid maximum frequency.\n", cpu); + return -EINVAL; + } + + /* + * Pre-compute the fixed ratio between the frequency of the constant + * counter and the maximum frequency of the CPU. + * + * const_freq + * arch_max_freq_scale = ---------------- * SCHED_CAPACITY_SCALE² + * cpuinfo_max_freq + * + * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE² + * in order to ensure a good resolution for arch_max_freq_scale for + * very low arch timer frequencies (down to the KHz range which should + * be unlikely). + */ + ratio = (u64)arch_timer_get_rate() << (2 * SCHED_CAPACITY_SHIFT); + ratio = div64_u64(ratio, max_freq_hz); + if (!ratio) { + WARN_ONCE(1, "System timer frequency too low.\n"); + return -EINVAL; + } + + per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio; + + return 0; +} + +static inline bool +enable_policy_freq_counters(int cpu, cpumask_var_t valid_cpus) +{ + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + + if (!policy) { + pr_debug("CPU%d: No cpufreq policy found.\n", cpu); + return false; + } + + if (cpumask_subset(policy->related_cpus, valid_cpus)) + cpumask_or(amu_fie_cpus, policy->related_cpus, + amu_fie_cpus); + + cpufreq_cpu_put(policy); + + return true; +} + +static DEFINE_STATIC_KEY_FALSE(amu_fie_key); +#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key) + +static int __init init_amu_fie(void) +{ + cpumask_var_t valid_cpus; + bool have_policy = false; + int ret = 0; + int cpu; + + if (!zalloc_cpumask_var(&valid_cpus, GFP_KERNEL)) + return -ENOMEM; + + if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) { + ret = -ENOMEM; + goto free_valid_mask; + } + + for_each_present_cpu(cpu) { + if (validate_cpu_freq_invariance_counters(cpu)) + continue; + cpumask_set_cpu(cpu, valid_cpus); + have_policy |= enable_policy_freq_counters(cpu, valid_cpus); + } + + /* + * If we are not restricted by cpufreq policies, we only enable + * the use of the AMU feature for FIE if all CPUs support AMU. + * Otherwise, enable_policy_freq_counters has already enabled + * policy cpus. + */ + if (!have_policy && cpumask_equal(valid_cpus, cpu_present_mask)) + cpumask_or(amu_fie_cpus, amu_fie_cpus, valid_cpus); + + if (!cpumask_empty(amu_fie_cpus)) { + pr_info("CPUs[%*pbl]: counters will be used for FIE.", + cpumask_pr_args(amu_fie_cpus)); + static_branch_enable(&amu_fie_key); + } + +free_valid_mask: + free_cpumask_var(valid_cpus); + + return ret; +} +late_initcall_sync(init_amu_fie); + +bool arch_freq_counters_available(struct cpumask *cpus) +{ + return amu_freq_invariant() && + cpumask_subset(cpus, amu_fie_cpus); +} + +void topology_scale_freq_tick(void) +{ + u64 prev_core_cnt, prev_const_cnt; + u64 core_cnt, const_cnt, scale; + int cpu = smp_processor_id(); + + if (!amu_freq_invariant()) + return; + + if (!cpumask_test_cpu(cpu, amu_fie_cpus)) + return; + + const_cnt = read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0); + core_cnt = read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0); + prev_const_cnt = this_cpu_read(arch_const_cycles_prev); + prev_core_cnt = this_cpu_read(arch_core_cycles_prev); + + if (unlikely(core_cnt <= prev_core_cnt || + const_cnt <= prev_const_cnt)) + goto store_and_exit; + + /* + * /\core arch_max_freq_scale + * scale = ------- * -------------------- + * /\const SCHED_CAPACITY_SCALE + * + * See validate_cpu_freq_invariance_counters() for details on + * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. + */ + scale = core_cnt - prev_core_cnt; + scale *= this_cpu_read(arch_max_freq_scale); + scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, + const_cnt - prev_const_cnt); + + scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); + this_cpu_write(freq_scale, (unsigned long)scale); + +store_and_exit: + this_cpu_write(arch_core_cycles_prev, core_cnt); + this_cpu_write(arch_const_cycles_prev, const_cnt); +} +#endif /* CONFIG_ARM64_AMU_EXTN */ diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S index 0723aa398d6e..12324863d5c2 100644 --- a/arch/arm64/kernel/vdso/sigreturn.S +++ b/arch/arm64/kernel/vdso/sigreturn.S @@ -14,7 +14,7 @@ .text nop -ENTRY(__kernel_rt_sigreturn) +SYM_FUNC_START(__kernel_rt_sigreturn) .cfi_startproc .cfi_signal_frame .cfi_def_cfa x29, 0 @@ -23,4 +23,4 @@ ENTRY(__kernel_rt_sigreturn) mov x8, #__NR_rt_sigreturn svc #0 .cfi_endproc -ENDPROC(__kernel_rt_sigreturn) +SYM_FUNC_END(__kernel_rt_sigreturn) diff --git a/arch/arm64/kernel/vdso/vgettimeofday.c b/arch/arm64/kernel/vdso/vgettimeofday.c index 747635501a14..4236cf34d7d9 100644 --- a/arch/arm64/kernel/vdso/vgettimeofday.c +++ b/arch/arm64/kernel/vdso/vgettimeofday.c @@ -5,8 +5,6 @@ * Copyright (C) 2018 ARM Limited * */ -#include <linux/time.h> -#include <linux/types.h> int __kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 04df57b43cb1..3964738ebbde 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -10,7 +10,18 @@ include $(srctree)/lib/vdso/Makefile # Same as cc-*option, but using CC_COMPAT instead of CC ifeq ($(CONFIG_CC_IS_CLANG), y) +COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit)) +COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..) + +CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%)) +CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR) +CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments +ifneq ($(COMPAT_GCC_TOOLCHAIN),) +CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN) +endif + CC_COMPAT ?= $(CC) +CC_COMPAT += $(CC_COMPAT_CLANG_FLAGS) else CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc endif diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S index 1a81277c2d09..620524969696 100644 --- a/arch/arm64/kernel/vdso32/sigreturn.S +++ b/arch/arm64/kernel/vdso32/sigreturn.S @@ -10,13 +10,6 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> -#define ARM_ENTRY(name) \ - ENTRY(name) - -#define ARM_ENDPROC(name) \ - .type name, %function; \ - END(name) - .text .arm @@ -24,39 +17,39 @@ .save {r0-r15} .pad #COMPAT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_sigreturn_arm) +SYM_FUNC_START(__kernel_sigreturn_arm) mov r7, #__NR_compat_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_sigreturn_arm) +SYM_FUNC_END(__kernel_sigreturn_arm) .fnstart .save {r0-r15} .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_rt_sigreturn_arm) +SYM_FUNC_START(__kernel_rt_sigreturn_arm) mov r7, #__NR_compat_rt_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_rt_sigreturn_arm) +SYM_FUNC_END(__kernel_rt_sigreturn_arm) .thumb .fnstart .save {r0-r15} .pad #COMPAT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_sigreturn_thumb) +SYM_FUNC_START(__kernel_sigreturn_thumb) mov r7, #__NR_compat_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_sigreturn_thumb) +SYM_FUNC_END(__kernel_sigreturn_thumb) .fnstart .save {r0-r15} .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_rt_sigreturn_thumb) +SYM_FUNC_START(__kernel_rt_sigreturn_thumb) mov r7, #__NR_compat_rt_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_rt_sigreturn_thumb) +SYM_FUNC_END(__kernel_rt_sigreturn_thumb) diff --git a/arch/arm64/kernel/vdso32/vgettimeofday.c b/arch/arm64/kernel/vdso32/vgettimeofday.c index 54fc1c2ce93f..5acff29c5991 100644 --- a/arch/arm64/kernel/vdso32/vgettimeofday.c +++ b/arch/arm64/kernel/vdso32/vgettimeofday.c @@ -5,26 +5,16 @@ * Copyright (C) 2018 ARM Limited * */ -#include <linux/time.h> -#include <linux/types.h> int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts) { - /* The checks below are required for ABI consistency with arm */ - if ((u32)ts >= TASK_SIZE_32) - return -EFAULT; - return __cvdso_clock_gettime32(clock, ts); } int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts) { - /* The checks below are required for ABI consistency with arm */ - if ((u32)ts >= TASK_SIZE_32) - return -EFAULT; - return __cvdso_clock_gettime(clock, ts); } @@ -37,10 +27,6 @@ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, int __vdso_clock_getres(clockid_t clock_id, struct old_timespec32 *res) { - /* The checks below are required for ABI consistency with arm */ - if ((u32)res >= TASK_SIZE_32) - return -EFAULT; - return __cvdso_clock_getres_time32(clock_id, res); } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 525010504f9d..e329a36b2bee 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -11,7 +11,6 @@ #include <linux/kvm_host.h> #include <asm/fpsimd.h> #include <asm/kvm_asm.h> -#include <asm/kvm_host.h> #include <asm/kvm_mmu.h> #include <asm/sysreg.h> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 2bd92301d32f..23ebe51410f0 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -25,7 +25,6 @@ #include <asm/kvm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> -#include <asm/kvm_host.h> #include <asm/sigcontext.h> #include "trace.h" diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 160be2b4696d..6e6ed5581eed 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -18,7 +18,7 @@ .align 11 -ENTRY(__kvm_hyp_init) +SYM_CODE_START(__kvm_hyp_init) ventry __invalid // Synchronous EL2t ventry __invalid // IRQ EL2t ventry __invalid // FIQ EL2t @@ -60,7 +60,7 @@ alternative_else_nop_endif msr ttbr0_el2, x4 mrs x4, tcr_el1 - ldr x5, =TCR_EL2_MASK + mov_q x5, TCR_EL2_MASK and x4, x4, x5 mov x5, #TCR_EL2_RES1 orr x4, x4, x5 @@ -102,7 +102,7 @@ alternative_else_nop_endif * as well as the EE bit on BE. Drop the A flag since the compiler * is allowed to generate unaligned accesses. */ - ldr x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A)) + mov_q x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A)) CPU_BE( orr x4, x4, #SCTLR_ELx_EE) msr sctlr_el2, x4 isb @@ -117,9 +117,9 @@ CPU_BE( orr x4, x4, #SCTLR_ELx_EE) /* Hello, World! */ eret -ENDPROC(__kvm_hyp_init) +SYM_CODE_END(__kvm_hyp_init) -ENTRY(__kvm_handle_stub_hvc) +SYM_CODE_START(__kvm_handle_stub_hvc) cmp x0, #HVC_SOFT_RESTART b.ne 1f @@ -142,7 +142,7 @@ reset: * case we coming via HVC_SOFT_RESTART. */ mrs x5, sctlr_el2 - ldr x6, =SCTLR_ELx_FLAGS + mov_q x6, SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc pre_disable_mmu_workaround msr sctlr_el2, x5 @@ -155,11 +155,9 @@ reset: eret 1: /* Bad stub call */ - ldr x0, =HVC_STUB_ERR + mov_q x0, HVC_STUB_ERR eret -ENDPROC(__kvm_handle_stub_hvc) - - .ltorg +SYM_CODE_END(__kvm_handle_stub_hvc) .popsection diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index c0094d520dff..3c79a1124af2 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -28,7 +28,7 @@ * and is used to implement hyp stubs in the same way as in * arch/arm64/kernel/hyp_stub.S. */ -ENTRY(__kvm_call_hyp) +SYM_FUNC_START(__kvm_call_hyp) hvc #0 ret -ENDPROC(__kvm_call_hyp) +SYM_FUNC_END(__kvm_call_hyp) diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S index 78ff53225691..5b8ff517ff10 100644 --- a/arch/arm64/kvm/hyp/fpsimd.S +++ b/arch/arm64/kvm/hyp/fpsimd.S @@ -11,12 +11,12 @@ .text .pushsection .hyp.text, "ax" -ENTRY(__fpsimd_save_state) +SYM_FUNC_START(__fpsimd_save_state) fpsimd_save x0, 1 ret -ENDPROC(__fpsimd_save_state) +SYM_FUNC_END(__fpsimd_save_state) -ENTRY(__fpsimd_restore_state) +SYM_FUNC_START(__fpsimd_restore_state) fpsimd_restore x0, 1 ret -ENDPROC(__fpsimd_restore_state) +SYM_FUNC_END(__fpsimd_restore_state) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index ffa68d5713f1..c2a13ab3c471 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -180,7 +180,7 @@ el2_error: eret sb -ENTRY(__hyp_do_panic) +SYM_FUNC_START(__hyp_do_panic) mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ PSR_MODE_EL1h) msr spsr_el2, lr @@ -188,18 +188,19 @@ ENTRY(__hyp_do_panic) msr elr_el2, lr eret sb -ENDPROC(__hyp_do_panic) +SYM_FUNC_END(__hyp_do_panic) -ENTRY(__hyp_panic) +SYM_CODE_START(__hyp_panic) get_host_ctxt x0, x1 b hyp_panic -ENDPROC(__hyp_panic) +SYM_CODE_END(__hyp_panic) .macro invalid_vector label, target = __hyp_panic .align 2 +SYM_CODE_START(\label) \label: b \target -ENDPROC(\label) +SYM_CODE_END(\label) .endm /* None of these should ever happen */ @@ -246,7 +247,7 @@ check_preamble_length 661b, 662b check_preamble_length 661b, 662b .endm -ENTRY(__kvm_hyp_vector) +SYM_CODE_START(__kvm_hyp_vector) invalid_vect el2t_sync_invalid // Synchronous EL2t invalid_vect el2t_irq_invalid // IRQ EL2t invalid_vect el2t_fiq_invalid // FIQ EL2t @@ -266,7 +267,7 @@ ENTRY(__kvm_hyp_vector) valid_vect el1_irq // IRQ 32-bit EL1 invalid_vect el1_fiq_invalid // FIQ 32-bit EL1 valid_vect el1_error // Error 32-bit EL1 -ENDPROC(__kvm_hyp_vector) +SYM_CODE_END(__kvm_hyp_vector) #ifdef CONFIG_KVM_INDIRECT_VECTORS .macro hyp_ventry @@ -311,15 +312,17 @@ alternative_cb_end .endm .align 11 -ENTRY(__bp_harden_hyp_vecs_start) +SYM_CODE_START(__bp_harden_hyp_vecs) .rept BP_HARDEN_EL2_SLOTS generate_vectors .endr -ENTRY(__bp_harden_hyp_vecs_end) +1: .org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ + .org 1b +SYM_CODE_END(__bp_harden_hyp_vecs) .popsection -ENTRY(__smccc_workaround_1_smc_start) +SYM_CODE_START(__smccc_workaround_1_smc) esb sub sp, sp, #(8 * 4) stp x2, x3, [sp, #(8 * 0)] @@ -329,5 +332,7 @@ ENTRY(__smccc_workaround_1_smc_start) ldp x2, x3, [sp, #(8 * 0)] ldp x0, x1, [sp, #(8 * 2)] add sp, sp, #(8 * 4) -ENTRY(__smccc_workaround_1_smc_end) +1: .org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ + .org 1b +SYM_CODE_END(__smccc_workaround_1_smc) #endif diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index dfe8dd172512..8a1e81a400e0 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -17,7 +17,6 @@ #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_host.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/fpsimd.h> @@ -98,6 +97,18 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; val &= ~CPACR_EL1_ZEN; + + /* + * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to + * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2, + * except for some missing controls, such as TAM. + * In this case, CPTR_EL2.TAM has the same position with or without + * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM + * shift value for trapping the AMU accesses. + */ + + val |= CPTR_EL2_TAM; + if (update_fp_enabled(vcpu)) { if (vcpu_has_sve(vcpu)) val |= CPACR_EL1_ZEN; @@ -119,7 +130,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) __activate_traps_common(vcpu); val = CPTR_EL2_DEFAULT; - val |= CPTR_EL2_TTA | CPTR_EL2_TZ; + val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM; if (!update_fp_enabled(vcpu)) { val |= CPTR_EL2_TFP; __activate_traps_fpsimd32(vcpu); @@ -127,7 +138,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) write_sysreg(val, cptr_el2); - if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; isb(); @@ -146,12 +157,12 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) { u64 hcr = vcpu->arch.hcr_el2; - if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) + if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) hcr |= HCR_TVM; write_sysreg(hcr, hcr_el2); - if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); if (has_vhe()) @@ -181,7 +192,7 @@ static void __hyp_text __deactivate_traps_nvhe(void) { u64 mdcr_el2 = read_sysreg(mdcr_el2); - if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { u64 val; /* @@ -328,7 +339,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) * resolve the IPA using the AT instruction. */ if (!(esr & ESR_ELx_S1PTW) && - (cpus_have_const_cap(ARM64_WORKAROUND_834220) || + (cpus_have_final_cap(ARM64_WORKAROUND_834220) || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { if (!__translate_far_to_hpfar(far, &hpfar)) return false; @@ -498,7 +509,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (*exit_code != ARM_EXCEPTION_TRAP) goto exit; - if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && + if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 && handle_tx2_tvm(vcpu)) return true; @@ -555,7 +566,7 @@ exit: static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu) { - if (!cpus_have_const_cap(ARM64_SSBD)) + if (!cpus_have_final_cap(ARM64_SSBD)) return false; return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG); @@ -625,7 +636,7 @@ 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 +689,42 @@ 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/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 7672a978926c..75b1925763f1 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -71,7 +71,7 @@ static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ct ctxt->gp_regs.regs.pc = read_sysreg_el2(SYS_ELR); ctxt->gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); - if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2); } @@ -118,7 +118,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - if (!cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { + if (!cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); } else if (!ctxt->__hyp_running_vcpu) { @@ -149,7 +149,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); - if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) && + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) && ctxt->__hyp_running_vcpu) { /* * Must only be done for host registers, hence the context @@ -194,7 +194,7 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) write_sysreg_el2(ctxt->gp_regs.regs.pc, SYS_ELR); write_sysreg_el2(pstate, SYS_SPSR); - if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2); } diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 92f560e3e1aa..ceaddbe4279f 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -23,7 +23,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, local_irq_save(cxt->flags); - if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) { /* * For CPUs that are affected by ARM errata 1165522 or 1530923, * we cannot trust stage-1 to be in a correct state at that @@ -63,7 +63,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { - if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { u64 val; /* @@ -103,7 +103,7 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); isb(); - if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) { /* Restore the registers to what they were */ write_sysreg_el1(cxt->tcr, SYS_TCR); write_sysreg_el1(cxt->sctlr, SYS_SCTLR); @@ -117,7 +117,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, { write_sysreg(0, vttbr_el2); - if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { /* Ensure write of the host VMID */ isb(); /* Restore the host's TCR_EL1 */ 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/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 3e909b117f0c..51db934702b6 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -22,7 +22,6 @@ #include <asm/kvm_arm.h> #include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_host.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/perf_event.h> @@ -1003,6 +1002,20 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } +static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + kvm_inject_undefined(vcpu); + + return false; +} + +/* Macro to expand the AMU counter and type registers*/ +#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu } +#define AMU_AMEVTYPE0_EL0(n) { SYS_DESC(SYS_AMEVTYPE0_EL0(n)), access_amu } +#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu } +#define AMU_AMEVTYPE1_EL0(n) { SYS_DESC(SYS_AMEVTYPE1_EL0(n)), access_amu } + static bool trap_ptrauth(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) @@ -1078,13 +1091,25 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); u64 val = raz ? 0 : read_sanitised_ftr_reg(id); - if (id == SYS_ID_AA64PFR0_EL1 && !vcpu_has_sve(vcpu)) { - val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); + if (id == SYS_ID_AA64PFR0_EL1) { + if (!vcpu_has_sve(vcpu)) + val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); + val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT); } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) { val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) | (0xfUL << ID_AA64ISAR1_API_SHIFT) | (0xfUL << ID_AA64ISAR1_GPA_SHIFT) | (0xfUL << ID_AA64ISAR1_GPI_SHIFT)); + } else if (id == SYS_ID_AA64DFR0_EL1) { + /* Limit guests to PMUv3 for ARMv8.1 */ + val = cpuid_feature_cap_perfmon_field(val, + ID_AA64DFR0_PMUVER_SHIFT, + ID_AA64DFR0_PMUVER_8_1); + } else if (id == SYS_ID_DFR0_EL1) { + /* Limit guests to PMUv3 for ARMv8.1 */ + val = cpuid_feature_cap_perfmon_field(val, + ID_DFR0_PERFMON_SHIFT, + ID_DFR0_PERFMON_8_1); } return val; @@ -1565,6 +1590,79 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, + { SYS_DESC(SYS_AMCR_EL0), access_amu }, + { SYS_DESC(SYS_AMCFGR_EL0), access_amu }, + { SYS_DESC(SYS_AMCGCR_EL0), access_amu }, + { SYS_DESC(SYS_AMUSERENR_EL0), access_amu }, + { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu }, + { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu }, + { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu }, + { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu }, + AMU_AMEVCNTR0_EL0(0), + AMU_AMEVCNTR0_EL0(1), + AMU_AMEVCNTR0_EL0(2), + AMU_AMEVCNTR0_EL0(3), + AMU_AMEVCNTR0_EL0(4), + AMU_AMEVCNTR0_EL0(5), + AMU_AMEVCNTR0_EL0(6), + AMU_AMEVCNTR0_EL0(7), + AMU_AMEVCNTR0_EL0(8), + AMU_AMEVCNTR0_EL0(9), + AMU_AMEVCNTR0_EL0(10), + AMU_AMEVCNTR0_EL0(11), + AMU_AMEVCNTR0_EL0(12), + AMU_AMEVCNTR0_EL0(13), + AMU_AMEVCNTR0_EL0(14), + AMU_AMEVCNTR0_EL0(15), + AMU_AMEVTYPE0_EL0(0), + AMU_AMEVTYPE0_EL0(1), + AMU_AMEVTYPE0_EL0(2), + AMU_AMEVTYPE0_EL0(3), + AMU_AMEVTYPE0_EL0(4), + AMU_AMEVTYPE0_EL0(5), + AMU_AMEVTYPE0_EL0(6), + AMU_AMEVTYPE0_EL0(7), + AMU_AMEVTYPE0_EL0(8), + AMU_AMEVTYPE0_EL0(9), + AMU_AMEVTYPE0_EL0(10), + AMU_AMEVTYPE0_EL0(11), + AMU_AMEVTYPE0_EL0(12), + AMU_AMEVTYPE0_EL0(13), + AMU_AMEVTYPE0_EL0(14), + AMU_AMEVTYPE0_EL0(15), + AMU_AMEVCNTR1_EL0(0), + AMU_AMEVCNTR1_EL0(1), + AMU_AMEVCNTR1_EL0(2), + AMU_AMEVCNTR1_EL0(3), + AMU_AMEVCNTR1_EL0(4), + AMU_AMEVCNTR1_EL0(5), + AMU_AMEVCNTR1_EL0(6), + AMU_AMEVCNTR1_EL0(7), + AMU_AMEVCNTR1_EL0(8), + AMU_AMEVCNTR1_EL0(9), + AMU_AMEVCNTR1_EL0(10), + AMU_AMEVCNTR1_EL0(11), + AMU_AMEVCNTR1_EL0(12), + AMU_AMEVCNTR1_EL0(13), + AMU_AMEVCNTR1_EL0(14), + AMU_AMEVCNTR1_EL0(15), + AMU_AMEVTYPE1_EL0(0), + AMU_AMEVTYPE1_EL0(1), + AMU_AMEVTYPE1_EL0(2), + AMU_AMEVTYPE1_EL0(3), + AMU_AMEVTYPE1_EL0(4), + AMU_AMEVTYPE1_EL0(5), + AMU_AMEVTYPE1_EL0(6), + AMU_AMEVTYPE1_EL0(7), + AMU_AMEVTYPE1_EL0(8), + AMU_AMEVTYPE1_EL0(9), + AMU_AMEVTYPE1_EL0(10), + AMU_AMEVTYPE1_EL0(11), + AMU_AMEVTYPE1_EL0(12), + AMU_AMEVTYPE1_EL0(13), + AMU_AMEVTYPE1_EL0(14), + AMU_AMEVTYPE1_EL0(15), + { SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer }, diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c index 2b4a3e2d1b89..9cb6b4c8355a 100644 --- a/arch/arm64/kvm/sys_regs_generic_v8.c +++ b/arch/arm64/kvm/sys_regs_generic_v8.c @@ -12,7 +12,6 @@ #include <asm/cputype.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> -#include <asm/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> #include <asm/sysreg.h> diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c index 1f82c66b32ea..60eccae2abad 100644 --- a/arch/arm64/lib/csum.c +++ b/arch/arm64/lib/csum.c @@ -124,3 +124,30 @@ unsigned int do_csum(const unsigned char *buff, int len) return sum >> 16; } + +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum csum) +{ + __uint128_t src, dst; + u64 sum = (__force u64)csum; + + src = *(const __uint128_t *)saddr->s6_addr; + dst = *(const __uint128_t *)daddr->s6_addr; + + sum += (__force u32)htonl(len); +#ifdef __LITTLE_ENDIAN + sum += (u32)proto << 24; +#else + sum += proto; +#endif + src += (src >> 64) | (src << 64); + dst += (dst >> 64) | (dst << 64); + + sum = accumulate(sum, src >> 64); + sum = accumulate(sum, dst >> 64); + + sum += ((sum >> 32) | (sum << 32)); + return csum_fold((__force __wsum)(sum >> 32)); +} +EXPORT_SYMBOL(csum_ipv6_magic); diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S index 4767540d1b94..4e79566726c8 100644 --- a/arch/arm64/lib/strcmp.S +++ b/arch/arm64/lib/strcmp.S @@ -186,7 +186,7 @@ CPU_LE( rev data2, data2 ) * as carry-propagation can corrupt the upper bits if the trailing * bytes in the string contain 0x01. * However, if there is no NUL byte in the dword, we can generate - * the result directly. We ca not just subtract the bytes as the + * the result directly. We cannot just subtract the bytes as the * MSB might be significant. */ CPU_BE( cbnz has_nul, 1f ) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 8ef73e89d514..9b26f9a88724 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -6,6 +6,7 @@ * Copyright (C) 2012 ARM Ltd. */ +#include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/sched.h> #include <linux/slab.h> @@ -254,20 +255,59 @@ switch_mm_fastpath: /* Errata workaround post TTBRx_EL1 update. */ asmlinkage void post_ttbr_update_workaround(void) { + if (!IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) + return; + asm(ALTERNATIVE("nop; nop; nop", "ic iallu; dsb nsh; isb", - ARM64_WORKAROUND_CAVIUM_27456, - CONFIG_CAVIUM_ERRATUM_27456)); + ARM64_WORKAROUND_CAVIUM_27456)); } -static int asids_init(void) +void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm) { - asid_bits = get_cpu_asid_bits(); + unsigned long ttbr1 = read_sysreg(ttbr1_el1); + unsigned long asid = ASID(mm); + unsigned long ttbr0 = phys_to_ttbr(pgd_phys); + + /* Skip CNP for the reserved ASID */ + if (system_supports_cnp() && asid) + ttbr0 |= TTBR_CNP_BIT; + + /* SW PAN needs a copy of the ASID in TTBR0 for entry */ + if (IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN)) + ttbr0 |= FIELD_PREP(TTBR_ASID_MASK, asid); + + /* Set ASID in TTBR1 since TCR.A1 is set */ + ttbr1 &= ~TTBR_ASID_MASK; + ttbr1 |= FIELD_PREP(TTBR_ASID_MASK, asid); + + write_sysreg(ttbr1, ttbr1_el1); + isb(); + write_sysreg(ttbr0, ttbr0_el1); + isb(); + post_ttbr_update_workaround(); +} + +static int asids_update_limit(void) +{ + 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 +322,6 @@ 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/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 85566d32958f..1027851d469a 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -446,7 +446,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct mm_struct *mm = current->mm; vm_fault_t fault, major = 0; unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; - unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int mm_flags = FAULT_FLAG_DEFAULT; if (kprobe_page_fault(regs, esr)) return 0; @@ -513,25 +513,15 @@ retry: fault = __do_page_fault(mm, addr, mm_flags, vm_flags); major |= fault & VM_FAULT_MAJOR; - if (fault & VM_FAULT_RETRY) { - /* - * If we need to retry but a fatal signal is pending, - * handle the signal first. We do not need to release - * the mmap_sem because it would already be released - * in __lock_page_or_retry in mm/filemap.c. - */ - if (fatal_signal_pending(current)) { - if (!user_mode(regs)) - goto no_context; - return 0; - } + /* Quick path to respond to signals */ + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + goto no_context; + return 0; + } - /* - * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of - * starvation. - */ + if (fault & VM_FAULT_RETRY) { if (mm_flags & FAULT_FLAG_ALLOW_RETRY) { - mm_flags &= ~FAULT_FLAG_ALLOW_RETRY; mm_flags |= FAULT_FLAG_TRIED; goto retry; } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 128f70852bf3..9b08f7c7e6f0 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -17,6 +17,7 @@ #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/memblock.h> +#include <linux/memory.h> #include <linux/fs.h> #include <linux/io.h> #include <linux/mm.h> @@ -724,6 +725,312 @@ int kern_addr_valid(unsigned long addr) return pfn_valid(pte_pfn(pte)); } + +#ifdef CONFIG_MEMORY_HOTPLUG +static void free_hotplug_page_range(struct page *page, size_t size) +{ + WARN_ON(PageReserved(page)); + free_pages((unsigned long)page_address(page), get_order(size)); +} + +static void free_hotplug_pgtable_page(struct page *page) +{ + free_hotplug_page_range(page, PAGE_SIZE); +} + +static bool pgtable_range_aligned(unsigned long start, unsigned long end, + unsigned long floor, unsigned long ceiling, + unsigned long mask) +{ + start &= mask; + if (start < floor) + return false; + + if (ceiling) { + ceiling &= mask; + if (!ceiling) + return false; + } + + if (end - 1 > ceiling - 1) + return false; + return true; +} + +static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr, + unsigned long end, bool free_mapped) +{ + pte_t *ptep, pte; + + do { + ptep = pte_offset_kernel(pmdp, addr); + pte = READ_ONCE(*ptep); + if (pte_none(pte)) + continue; + + WARN_ON(!pte_present(pte)); + pte_clear(&init_mm, addr, ptep); + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + if (free_mapped) + free_hotplug_page_range(pte_page(pte), PAGE_SIZE); + } while (addr += PAGE_SIZE, addr < end); +} + +static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr, + unsigned long end, bool free_mapped) +{ + unsigned long next; + pmd_t *pmdp, pmd; + + do { + next = pmd_addr_end(addr, end); + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) + continue; + + WARN_ON(!pmd_present(pmd)); + if (pmd_sect(pmd)) { + pmd_clear(pmdp); + + /* + * One TLBI should be sufficient here as the PMD_SIZE + * range is mapped with a single block entry. + */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + if (free_mapped) + free_hotplug_page_range(pmd_page(pmd), + PMD_SIZE); + continue; + } + WARN_ON(!pmd_table(pmd)); + unmap_hotplug_pte_range(pmdp, addr, next, free_mapped); + } while (addr = next, addr < end); +} + +static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr, + unsigned long end, bool free_mapped) +{ + unsigned long next; + pud_t *pudp, pud; + + do { + next = pud_addr_end(addr, end); + pudp = pud_offset(p4dp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) + continue; + + WARN_ON(!pud_present(pud)); + if (pud_sect(pud)) { + pud_clear(pudp); + + /* + * One TLBI should be sufficient here as the PUD_SIZE + * range is mapped with a single block entry. + */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + if (free_mapped) + free_hotplug_page_range(pud_page(pud), + PUD_SIZE); + continue; + } + WARN_ON(!pud_table(pud)); + unmap_hotplug_pmd_range(pudp, addr, next, free_mapped); + } while (addr = next, addr < end); +} + +static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr, + unsigned long end, bool free_mapped) +{ + unsigned long next; + p4d_t *p4dp, p4d; + + do { + next = p4d_addr_end(addr, end); + p4dp = p4d_offset(pgdp, addr); + p4d = READ_ONCE(*p4dp); + if (p4d_none(p4d)) + continue; + + WARN_ON(!p4d_present(p4d)); + unmap_hotplug_pud_range(p4dp, addr, next, free_mapped); + } while (addr = next, addr < end); +} + +static void unmap_hotplug_range(unsigned long addr, unsigned long end, + bool free_mapped) +{ + unsigned long next; + pgd_t *pgdp, pgd; + + do { + next = pgd_addr_end(addr, end); + pgdp = pgd_offset_k(addr); + pgd = READ_ONCE(*pgdp); + if (pgd_none(pgd)) + continue; + + WARN_ON(!pgd_present(pgd)); + unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped); + } while (addr = next, addr < end); +} + +static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned long floor, + unsigned long ceiling) +{ + pte_t *ptep, pte; + unsigned long i, start = addr; + + do { + ptep = pte_offset_kernel(pmdp, addr); + pte = READ_ONCE(*ptep); + + /* + * This is just a sanity check here which verifies that + * pte clearing has been done by earlier unmap loops. + */ + WARN_ON(!pte_none(pte)); + } while (addr += PAGE_SIZE, addr < end); + + if (!pgtable_range_aligned(start, end, floor, ceiling, PMD_MASK)) + return; + + /* + * Check whether we can free the pte page if the rest of the + * entries are empty. Overlap with other regions have been + * handled by the floor/ceiling check. + */ + ptep = pte_offset_kernel(pmdp, 0UL); + for (i = 0; i < PTRS_PER_PTE; i++) { + if (!pte_none(READ_ONCE(ptep[i]))) + return; + } + + pmd_clear(pmdp); + __flush_tlb_kernel_pgtable(start); + free_hotplug_pgtable_page(virt_to_page(ptep)); +} + +static void free_empty_pmd_table(pud_t *pudp, unsigned long addr, + unsigned long end, unsigned long floor, + unsigned long ceiling) +{ + pmd_t *pmdp, pmd; + unsigned long i, next, start = addr; + + do { + next = pmd_addr_end(addr, end); + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) + continue; + + WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd)); + free_empty_pte_table(pmdp, addr, next, floor, ceiling); + } while (addr = next, addr < end); + + if (CONFIG_PGTABLE_LEVELS <= 2) + return; + + if (!pgtable_range_aligned(start, end, floor, ceiling, PUD_MASK)) + return; + + /* + * Check whether we can free the pmd page if the rest of the + * entries are empty. Overlap with other regions have been + * handled by the floor/ceiling check. + */ + pmdp = pmd_offset(pudp, 0UL); + for (i = 0; i < PTRS_PER_PMD; i++) { + if (!pmd_none(READ_ONCE(pmdp[i]))) + return; + } + + pud_clear(pudp); + __flush_tlb_kernel_pgtable(start); + free_hotplug_pgtable_page(virt_to_page(pmdp)); +} + +static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr, + unsigned long end, unsigned long floor, + unsigned long ceiling) +{ + pud_t *pudp, pud; + unsigned long i, next, start = addr; + + do { + next = pud_addr_end(addr, end); + pudp = pud_offset(p4dp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) + continue; + + WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud)); + free_empty_pmd_table(pudp, addr, next, floor, ceiling); + } while (addr = next, addr < end); + + if (CONFIG_PGTABLE_LEVELS <= 3) + return; + + if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK)) + return; + + /* + * Check whether we can free the pud page if the rest of the + * entries are empty. Overlap with other regions have been + * handled by the floor/ceiling check. + */ + pudp = pud_offset(p4dp, 0UL); + for (i = 0; i < PTRS_PER_PUD; i++) { + if (!pud_none(READ_ONCE(pudp[i]))) + return; + } + + p4d_clear(p4dp); + __flush_tlb_kernel_pgtable(start); + free_hotplug_pgtable_page(virt_to_page(pudp)); +} + +static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, + unsigned long end, unsigned long floor, + unsigned long ceiling) +{ + unsigned long next; + p4d_t *p4dp, p4d; + + do { + next = p4d_addr_end(addr, end); + p4dp = p4d_offset(pgdp, addr); + p4d = READ_ONCE(*p4dp); + if (p4d_none(p4d)) + continue; + + WARN_ON(!p4d_present(p4d)); + free_empty_pud_table(p4dp, addr, next, floor, ceiling); + } while (addr = next, addr < end); +} + +static void free_empty_tables(unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + unsigned long next; + pgd_t *pgdp, pgd; + + do { + next = pgd_addr_end(addr, end); + pgdp = pgd_offset_k(addr); + pgd = READ_ONCE(*pgdp); + if (pgd_none(pgd)) + continue; + + WARN_ON(!pgd_present(pgd)); + free_empty_p4d_table(pgdp, addr, next, floor, ceiling); + } while (addr = next, addr < end); +} +#endif + #ifdef CONFIG_SPARSEMEM_VMEMMAP #if !ARM64_SWAPPER_USES_SECTION_MAPS int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, @@ -771,6 +1078,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { +#ifdef CONFIG_MEMORY_HOTPLUG + WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); + + unmap_hotplug_range(start, end, true); + free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END); +#endif } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ @@ -1049,10 +1362,21 @@ int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) } #ifdef CONFIG_MEMORY_HOTPLUG +static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) +{ + unsigned long end = start + size; + + WARN_ON(pgdir != init_mm.pgd); + WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END)); + + unmap_hotplug_range(start, end, false); + free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); +} + int arch_add_memory(int nid, u64 start, u64 size, struct mhp_restrictions *restrictions) { - int flags = 0; + int ret, flags = 0; if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; @@ -1062,22 +1386,59 @@ int arch_add_memory(int nid, u64 start, u64 size, memblock_clear_nomap(start, size); - return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, + ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, restrictions); + if (ret) + __remove_pgd_mapping(swapper_pg_dir, + __phys_to_virt(start), size); + return ret; } + void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - /* - * FIXME: Cleanup page tables (also in arch_add_memory() in case - * adding fails). Until then, this function should only be used - * during memory hotplug (adding memory), not for memory - * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be - * unlocked yet. - */ __remove_pages(start_pfn, nr_pages, altmap); + __remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size); +} + +/* + * This memory hotplug notifier helps prevent boot memory from being + * inadvertently removed as it blocks pfn range offlining process in + * __offline_pages(). Hence this prevents both offlining as well as + * removal process for boot memory which is initially always online. + * In future if and when boot memory could be removed, this notifier + * should be dropped and free_hotplug_page_range() should handle any + * reserved pages allocated during boot. + */ +static int prevent_bootmem_remove_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct mem_section *ms; + struct memory_notify *arg = data; + unsigned long end_pfn = arg->start_pfn + arg->nr_pages; + unsigned long pfn = arg->start_pfn; + + if (action != MEM_GOING_OFFLINE) + return NOTIFY_OK; + + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + ms = __pfn_to_section(pfn); + if (early_section(ms)) + return NOTIFY_BAD; + } + return NOTIFY_OK; +} + +static struct notifier_block prevent_bootmem_remove_nb = { + .notifier_call = prevent_bootmem_remove_notifier, +}; + +static int __init prevent_bootmem_remove_init(void) +{ + return register_memory_notifier(&prevent_bootmem_remove_nb); } +device_initcall(prevent_bootmem_remove_init); #endif diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index aafed6902411..197a9ba2d5ea 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -11,11 +11,13 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/asm-offsets.h> +#include <asm/asm_pointer_auth.h> #include <asm/hwcap.h> #include <asm/pgtable.h> #include <asm/pgtable-hwdef.h> #include <asm/cpufeature.h> #include <asm/alternative.h> +#include <asm/smp.h> #ifdef CONFIG_ARM64_64K_PAGES #define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K @@ -131,45 +133,19 @@ alternative_endif ubfx x11, x11, #1, #1 msr oslar_el1, x11 reset_pmuserenr_el0 x0 // Disable PMU access from EL0 + reset_amuserenr_el0 x0 // Disable AMU access from EL0 alternative_if ARM64_HAS_RAS_EXTN msr_s SYS_DISR_EL1, xzr alternative_else_nop_endif + ptrauth_keys_install_kernel x14, 0, x1, x2, x3 isb ret SYM_FUNC_END(cpu_do_resume) .popsection #endif -/* - * cpu_do_switch_mm(pgd_phys, tsk) - * - * Set the translation table base pointer to be pgd_phys. - * - * - pgd_phys - physical address of new TTB - */ -SYM_FUNC_START(cpu_do_switch_mm) - mrs x2, ttbr1_el1 - mmid x1, x1 // get mm->context.id - phys_to_ttbr x3, x0 - -alternative_if ARM64_HAS_CNP - cbz x1, 1f // skip CNP for reserved ASID - orr x3, x3, #TTBR_CNP_BIT -1: -alternative_else_nop_endif -#ifdef CONFIG_ARM64_SW_TTBR0_PAN - bfi x3, x1, #48, #16 // set the ASID field in TTBR0 -#endif - bfi x2, x1, #48, #16 // set the ASID - msr ttbr1_el1, x2 // in TTBR1 (since TCR.A1 is set) - isb - msr ttbr0_el1, x3 // now update TTBR0 - isb - b post_ttbr_update_workaround // Back to C code... -SYM_FUNC_END(cpu_do_switch_mm) - .pushsection ".idmap.text", "awx" .macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 @@ -408,35 +384,37 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings) /* * __cpu_setup * - * Initialise the processor for turning the MMU on. Return in x0 the - * value of the SCTLR_EL1 register. + * Initialise the processor for turning the MMU on. + * + * Input: + * x0 with a flag ARM64_CPU_BOOT_PRIMARY/ARM64_CPU_BOOT_SECONDARY/ARM64_CPU_RUNTIME. + * Output: + * Return in x0 the value of the SCTLR_EL1 register. */ .pushsection ".idmap.text", "awx" SYM_FUNC_START(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh - mov x0, #3 << 20 - msr cpacr_el1, x0 // Enable FP/ASIMD - mov x0, #1 << 12 // Reset mdscr_el1 and disable - msr mdscr_el1, x0 // access to the DCC from EL0 + mov x1, #3 << 20 + msr cpacr_el1, x1 // Enable FP/ASIMD + mov x1, #1 << 12 // Reset mdscr_el1 and disable + msr mdscr_el1, x1 // access to the DCC from EL0 isb // Unmask debug exceptions now, enable_dbg // since this is per-cpu - reset_pmuserenr_el0 x0 // Disable PMU access from EL0 + reset_pmuserenr_el0 x1 // Disable PMU access from EL0 + reset_amuserenr_el0 x1 // Disable AMU access from EL0 + /* * Memory region attributes */ mov_q x5, MAIR_EL1_SET msr mair_el1, x5 /* - * Prepare SCTLR - */ - mov_q x0, SCTLR_EL1_SET - /* * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for * both user and kernel. */ - ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ + mov_q x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS tcr_clear_errata_bits x10, x9, x5 @@ -468,5 +446,51 @@ SYM_FUNC_START(__cpu_setup) 1: #endif /* CONFIG_ARM64_HW_AFDBM */ msr tcr_el1, x10 + mov x1, x0 + /* + * Prepare SCTLR + */ + mov_q x0, SCTLR_EL1_SET + +#ifdef CONFIG_ARM64_PTR_AUTH + /* No ptrauth setup for run time cpus */ + cmp x1, #ARM64_CPU_RUNTIME + b.eq 3f + + /* Check if the CPU supports ptrauth */ + mrs x2, id_aa64isar1_el1 + ubfx x2, x2, #ID_AA64ISAR1_APA_SHIFT, #8 + cbz x2, 3f + + /* + * The primary cpu keys are reset here and can be + * re-initialised with some proper values later. + */ + msr_s SYS_APIAKEYLO_EL1, xzr + msr_s SYS_APIAKEYHI_EL1, xzr + + /* Just enable ptrauth for primary cpu */ + cmp x1, #ARM64_CPU_BOOT_PRIMARY + b.eq 2f + + /* if !system_supports_address_auth() then skip enable */ +alternative_if_not ARM64_HAS_ADDRESS_AUTH + b 3f +alternative_else_nop_endif + + /* Install ptrauth key for secondary cpus */ + adr_l x2, secondary_data + ldr x3, [x2, #CPU_BOOT_TASK] // get secondary_data.task + cbz x3, 2f // check for slow booting cpus + ldp x3, x4, [x2, #CPU_BOOT_PTRAUTH_KEY] + msr_s SYS_APIAKEYLO_EL1, x3 + msr_s SYS_APIAKEYHI_EL1, x4 + +2: /* Enable ptrauth instructions */ + ldr x2, =SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \ + SCTLR_ELx_ENDA | SCTLR_ELx_ENDB + orr x0, x0, x2 +3: +#endif ret // return to head.S SYM_FUNC_END(__cpu_setup) diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c index 1f2eae3e988b..d29d722ec3ec 100644 --- a/arch/arm64/mm/ptdump_debugfs.c +++ b/arch/arm64/mm/ptdump_debugfs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> +#include <linux/memory_hotplug.h> #include <linux/seq_file.h> #include <asm/ptdump.h> @@ -7,7 +8,10 @@ static int ptdump_show(struct seq_file *m, void *v) { struct ptdump_info *info = m->private; + + get_online_mems(); ptdump_walk(m, info); + put_online_mems(); return 0; } DEFINE_SHOW_ATTRIBUTE(ptdump); diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index a036e05fc3c6..a4ef93a1f7ae 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -1,42 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += atomic.h -generic-y += barrier.h -generic-y += bugs.h -generic-y += compat.h -generic-y += current.h -generic-y += device.h -generic-y += div64.h -generic-y += dma.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += fb.h -generic-y += futex.h -generic-y += hw_irq.h -generic-y += io.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += local.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += mmu.h -generic-y += mmu_context.h -generic-y += pci.h -generic-y += percpu.h -generic-y += pgalloc.h -generic-y += preempt.h -generic-y += serial.h -generic-y += shmparam.h -generic-y += tlbflush.h -generic-y += topology.h -generic-y += trace_clock.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h diff --git a/arch/c6x/include/asm/unaligned.h b/arch/c6x/include/asm/unaligned.h index b56ba7110f5a..d628cc170564 100644 --- a/arch/c6x/include/asm/unaligned.h +++ b/arch/c6x/include/asm/unaligned.h @@ -10,6 +10,7 @@ #define _ASM_C6X_UNALIGNED_H #include <linux/swab.h> +#include <linux/unaligned/generic.h> /* * The C64x+ can do unaligned word and dword accesses in hardware @@ -100,68 +101,4 @@ static inline void put_unaligned64(u64 val, const void *p) #endif -/* - * Cause a link-time error if we try an unaligned access other than - * 1,2,4 or 8 bytes long - */ -extern int __bad_unaligned_access_size(void); - -#define __get_unaligned_le(ptr) (typeof(*(ptr)))({ \ - sizeof(*(ptr)) == 1 ? *(ptr) : \ - (sizeof(*(ptr)) == 2 ? get_unaligned_le16((ptr)) : \ - (sizeof(*(ptr)) == 4 ? get_unaligned_le32((ptr)) : \ - (sizeof(*(ptr)) == 8 ? get_unaligned_le64((ptr)) : \ - __bad_unaligned_access_size()))); \ - }) - -#define __get_unaligned_be(ptr) (__force typeof(*(ptr)))({ \ - sizeof(*(ptr)) == 1 ? *(ptr) : \ - (sizeof(*(ptr)) == 2 ? get_unaligned_be16((ptr)) : \ - (sizeof(*(ptr)) == 4 ? get_unaligned_be32((ptr)) : \ - (sizeof(*(ptr)) == 8 ? get_unaligned_be64((ptr)) : \ - __bad_unaligned_access_size()))); \ - }) - -#define __put_unaligned_le(val, ptr) ({ \ - void *__gu_p = (ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - *(u8 *)__gu_p = (__force u8)(val); \ - break; \ - case 2: \ - put_unaligned_le16((__force u16)(val), __gu_p); \ - break; \ - case 4: \ - put_unaligned_le32((__force u32)(val), __gu_p); \ - break; \ - case 8: \ - put_unaligned_le64((__force u64)(val), __gu_p); \ - break; \ - default: \ - __bad_unaligned_access_size(); \ - break; \ - } \ - (void)0; }) - -#define __put_unaligned_be(val, ptr) ({ \ - void *__gu_p = (ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - *(u8 *)__gu_p = (__force u8)(val); \ - break; \ - case 2: \ - put_unaligned_be16((__force u16)(val), __gu_p); \ - break; \ - case 4: \ - put_unaligned_be32((__force u32)(val), __gu_p); \ - break; \ - case 8: \ - put_unaligned_be64((__force u64)(val), __gu_p); \ - break; \ - default: \ - __bad_unaligned_access_size(); \ - break; \ - } \ - (void)0; }) - #endif /* _ASM_C6X_UNALIGNED_H */ 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..93372255984d 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -1,45 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += asm-offsets.h -generic-y += bugs.h -generic-y += compat.h -generic-y += current.h -generic-y += delay.h -generic-y += device.h -generic-y += div64.h -generic-y += dma.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h -generic-y += fb.h -generic-y += futex.h generic-y += gpio.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += linkage.h -generic-y += local.h 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 -generic-y += sections.h -generic-y += serial.h -generic-y += timex.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += unaligned.h generic-y += user.h -generic-y += vga.h generic-y += vmlinux.lds.h -generic-y += word-at-a-time.h -generic-y += xor.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/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 7f618190e1a9..ddf04f32b546 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -1,54 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += asm-offsets.h -generic-y += barrier.h -generic-y += bugs.h -generic-y += cacheflush.h -generic-y += checksum.h -generic-y += compat.h -generic-y += current.h -generic-y += delay.h -generic-y += device.h -generic-y += div64.h -generic-y += dma.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += fb.h -generic-y += ftrace.h -generic-y += futex.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += linkage.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += mmu.h -generic-y += mmu_context.h -generic-y += module.h generic-y += parport.h -generic-y += pci.h -generic-y += percpu.h -generic-y += pgalloc.h -generic-y += preempt.h -generic-y += sections.h -generic-y += serial.h -generic-y += shmparam.h generic-y += spinlock.h -generic-y += timex.h -generic-y += tlbflush.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += uaccess.h -generic-y += unaligned.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 84bb1ed1b931..373964bb177e 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -1,39 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += barrier.h -generic-y += bug.h -generic-y += bugs.h -generic-y += compat.h -generic-y += current.h -generic-y += device.h -generic-y += div64.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h generic-y += extable.h -generic-y += fb.h -generic-y += ftrace.h -generic-y += hardirq.h -generic-y += hw_irq.h generic-y += iomap.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += pci.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += sections.h -generic-y += serial.h -generic-y += shmparam.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += unaligned.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h 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/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index b3bc71680ae4..72334b26317a 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -41,7 +41,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) int si_code = SEGV_MAPERR; vm_fault_t fault; const struct exception_table_entry *fixup; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; /* * If we're in an interrupt or have no user context, @@ -91,7 +91,7 @@ good_area: fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; /* The most common case -- we are done. */ @@ -102,7 +102,6 @@ good_area: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; goto retry; } diff --git a/arch/ia64/configs/zx1_defconfig b/arch/ia64/configs/zx1_defconfig index 8c92e095f8bb..d42f79a33e91 100644 --- a/arch/ia64/configs/zx1_defconfig +++ b/arch/ia64/configs/zx1_defconfig @@ -35,7 +35,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_CHR_DEV_OSST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 390393667d3b..f994c1daf9d4 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -1,12 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h -generic-y += compat.h -generic-y += exec.h -generic-y += irq_work.h generic-y += kvm_para.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += preempt.h -generic-y += trace_clock.h generic-y += vtime.h -generic-y += word-at-a-time.h 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/hw_irq.h b/arch/ia64/include/asm/hw_irq.h index e6385c7bdeb0..f6ff95b4ecb1 100644 --- a/arch/ia64/include/asm/hw_irq.h +++ b/arch/ia64/include/asm/hw_irq.h @@ -113,7 +113,6 @@ extern struct irq_chip irq_type_ia64_lsapic; /* CPU-internal interrupt controlle #define ia64_register_ipi ia64_native_register_ipi #define assign_irq_vector ia64_native_assign_irq_vector #define free_irq_vector ia64_native_free_irq_vector -#define register_percpu_irq ia64_native_register_percpu_irq #define ia64_resend_irq ia64_native_resend_irq extern void ia64_native_register_ipi(void); @@ -123,7 +122,6 @@ extern void ia64_native_free_irq_vector (int vector); extern int reserve_irq_vector (int vector); extern void __setup_vector_irq(int cpu); extern void ia64_send_ipi (int cpu, int vector, int delivery_mode, int redirect); -extern void ia64_native_register_percpu_irq (ia64_vector vec, struct irqaction *action); extern void destroy_and_reserve_irq (unsigned int irq); #ifdef CONFIG_SMP 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/irq.h b/arch/ia64/kernel/irq.h new file mode 100644 index 000000000000..4d16f3cbeb1d --- /dev/null +++ b/arch/ia64/kernel/irq.h @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +extern void register_percpu_irq(ia64_vector vec, irq_handler_t handler, + unsigned long flags, const char *name); diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 8e91c86e8072..e7862e4cb1e7 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -351,11 +351,6 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction irq_move_irqaction = { - .handler = smp_irq_move_cleanup_interrupt, - .name = "irq_move" -}; - static int __init parse_vector_domain(char *arg) { if (!arg) @@ -586,28 +581,15 @@ static irqreturn_t dummy_handler (int irq, void *dev_id) return IRQ_NONE; } -static struct irqaction ipi_irqaction = { - .handler = handle_IPI, - .name = "IPI" -}; - /* * KVM uses this interrupt to force a cpu out of guest mode */ -static struct irqaction resched_irqaction = { - .handler = dummy_handler, - .name = "resched" -}; - -static struct irqaction tlb_irqaction = { - .handler = dummy_handler, - .name = "tlb_flush" -}; #endif void -ia64_native_register_percpu_irq (ia64_vector vec, struct irqaction *action) +register_percpu_irq(ia64_vector vec, irq_handler_t handler, unsigned long flags, + const char *name) { unsigned int irq; @@ -615,8 +597,9 @@ ia64_native_register_percpu_irq (ia64_vector vec, struct irqaction *action) BUG_ON(bind_irq_vector(irq, vec, CPU_MASK_ALL)); irq_set_status_flags(irq, IRQ_PER_CPU); irq_set_chip(irq, &irq_type_ia64_lsapic); - if (action) - setup_irq(irq, action); + if (handler) + if (request_irq(irq, handler, flags, name, NULL)) + pr_err("Failed to request irq %u (%s)\n", irq, name); irq_set_handler(irq, handle_percpu_irq); } @@ -624,9 +607,10 @@ void __init ia64_native_register_ipi(void) { #ifdef CONFIG_SMP - register_percpu_irq(IA64_IPI_VECTOR, &ipi_irqaction); - register_percpu_irq(IA64_IPI_RESCHEDULE, &resched_irqaction); - register_percpu_irq(IA64_IPI_LOCAL_TLB_FLUSH, &tlb_irqaction); + register_percpu_irq(IA64_IPI_VECTOR, handle_IPI, 0, "IPI"); + register_percpu_irq(IA64_IPI_RESCHEDULE, dummy_handler, 0, "resched"); + register_percpu_irq(IA64_IPI_LOCAL_TLB_FLUSH, dummy_handler, 0, + "tlb_flush"); #endif } @@ -635,10 +619,13 @@ init_IRQ (void) { acpi_boot_init(); ia64_register_ipi(); - register_percpu_irq(IA64_SPURIOUS_INT_VECTOR, NULL); + register_percpu_irq(IA64_SPURIOUS_INT_VECTOR, NULL, 0, NULL); #ifdef CONFIG_SMP - if (vector_domain_type != VECTOR_DOMAIN_NONE) - register_percpu_irq(IA64_IRQ_MOVE_VECTOR, &irq_move_irqaction); + if (vector_domain_type != VECTOR_DOMAIN_NONE) { + register_percpu_irq(IA64_IRQ_MOVE_VECTOR, + smp_irq_move_cleanup_interrupt, 0, + "irq_move"); + } #endif #ifdef CONFIG_PERFMON pfm_init_percpu(); diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index bf2cb9294795..6fb54dfa1350 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -104,6 +104,7 @@ #include "mca_drv.h" #include "entry.h" +#include "irq.h" #if defined(IA64_MCA_DEBUG_INFO) # define IA64_MCA_DEBUG(fmt...) printk(fmt) @@ -1766,36 +1767,6 @@ ia64_mca_disable_cpe_polling(char *str) __setup("disable_cpe_poll", ia64_mca_disable_cpe_polling); -static struct irqaction cmci_irqaction = { - .handler = ia64_mca_cmc_int_handler, - .name = "cmc_hndlr" -}; - -static struct irqaction cmcp_irqaction = { - .handler = ia64_mca_cmc_int_caller, - .name = "cmc_poll" -}; - -static struct irqaction mca_rdzv_irqaction = { - .handler = ia64_mca_rendez_int_handler, - .name = "mca_rdzv" -}; - -static struct irqaction mca_wkup_irqaction = { - .handler = ia64_mca_wakeup_int_handler, - .name = "mca_wkup" -}; - -static struct irqaction mca_cpe_irqaction = { - .handler = ia64_mca_cpe_int_handler, - .name = "cpe_hndlr" -}; - -static struct irqaction mca_cpep_irqaction = { - .handler = ia64_mca_cpe_int_caller, - .name = "cpe_poll" -}; - /* Minimal format of the MCA/INIT stacks. The pseudo processes that run on * these stacks can never sleep, they cannot return from the kernel to user * space, they do not appear in a normal ps listing. So there is no need to @@ -2056,18 +2027,23 @@ void __init ia64_mca_irq_init(void) * Configure the CMCI/P vector and handler. Interrupts for CMC are * per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c). */ - register_percpu_irq(IA64_CMC_VECTOR, &cmci_irqaction); - register_percpu_irq(IA64_CMCP_VECTOR, &cmcp_irqaction); + register_percpu_irq(IA64_CMC_VECTOR, ia64_mca_cmc_int_handler, 0, + "cmc_hndlr"); + register_percpu_irq(IA64_CMCP_VECTOR, ia64_mca_cmc_int_caller, 0, + "cmc_poll"); ia64_mca_cmc_vector_setup(); /* Setup vector on BSP */ /* Setup the MCA rendezvous interrupt vector */ - register_percpu_irq(IA64_MCA_RENDEZ_VECTOR, &mca_rdzv_irqaction); + register_percpu_irq(IA64_MCA_RENDEZ_VECTOR, ia64_mca_rendez_int_handler, + 0, "mca_rdzv"); /* Setup the MCA wakeup interrupt vector */ - register_percpu_irq(IA64_MCA_WAKEUP_VECTOR, &mca_wkup_irqaction); + register_percpu_irq(IA64_MCA_WAKEUP_VECTOR, ia64_mca_wakeup_int_handler, + 0, "mca_wkup"); /* Setup the CPEI/P handler */ - register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction); + register_percpu_irq(IA64_CPEP_VECTOR, ia64_mca_cpe_int_caller, 0, + "cpe_poll"); } /* @@ -2108,7 +2084,9 @@ ia64_mca_late_init(void) if (irq > 0) { cpe_poll_enabled = 0; irq_set_status_flags(irq, IRQ_PER_CPU); - setup_irq(irq, &mca_cpe_irqaction); + if (request_irq(irq, ia64_mca_cpe_int_handler, + 0, "cpe_hndlr", NULL)) + pr_err("Failed to register cpe_hndlr interrupt\n"); ia64_cpe_irq = irq; ia64_mca_register_cpev(cpe_vector); IA64_MCA_DEBUG("%s: CPEI/P setup and enabled.\n", diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index a23c3938a1c4..df257002950e 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -57,6 +57,8 @@ #include <linux/uaccess.h> #include <asm/delay.h> +#include "irq.h" + #ifdef CONFIG_PERFMON /* * perfmon context state @@ -6313,11 +6315,6 @@ pfm_flush_pmds(struct task_struct *task, pfm_context_t *ctx) } } -static struct irqaction perfmon_irqaction = { - .handler = pfm_interrupt_handler, - .name = "perfmon" -}; - static void pfm_alt_save_pmu_state(void *data) { @@ -6591,7 +6588,8 @@ pfm_init_percpu (void) pfm_unfreeze_pmu(); if (first_time) { - register_percpu_irq(IA64_PERFMON_VECTOR, &perfmon_irqaction); + register_percpu_irq(IA64_PERFMON_VECTOR, pfm_interrupt_handler, + 0, "perfmon"); first_time=0; } 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/kernel/time.c b/arch/ia64/kernel/time.c index 91b4024c9351..7abc5f37bfaf 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -32,6 +32,7 @@ #include <asm/sections.h> #include "fsyscall_gtod_data.h" +#include "irq.h" static u64 itc_get_cycles(struct clocksource *cs); @@ -380,13 +381,6 @@ static u64 itc_get_cycles(struct clocksource *cs) return now; } - -static struct irqaction timer_irqaction = { - .handler = timer_interrupt, - .flags = IRQF_IRQPOLL, - .name = "timer" -}; - void read_persistent_clock64(struct timespec64 *ts) { efi_gettimeofday(ts); @@ -395,7 +389,8 @@ void read_persistent_clock64(struct timespec64 *ts) void __init time_init (void) { - register_percpu_irq(IA64_TIMER_VECTOR, &timer_irqaction); + register_percpu_irq(IA64_TIMER_VECTOR, timer_interrupt, IRQF_IRQPOLL, + "timer"); ia64_init_itm(); } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index c2f299fe9e04..30d0c1fca99e 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -65,7 +65,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re struct mm_struct *mm = current->mm; unsigned long mask; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT)); @@ -141,7 +141,7 @@ retry: */ fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -167,7 +167,6 @@ retry: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would 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/Kconfig.bus b/arch/m68k/Kconfig.bus index 9d0a3a23d50e..f1be832e2b74 100644 --- a/arch/m68k/Kconfig.bus +++ b/arch/m68k/Kconfig.bus @@ -66,6 +66,6 @@ endif if !MMU config ISA_DMA_API - def_bool !M5272 + def_bool !M5272 endif diff --git a/arch/m68k/Kconfig.debug b/arch/m68k/Kconfig.debug index f43643111eaf..11b306bdd788 100644 --- a/arch/m68k/Kconfig.debug +++ b/arch/m68k/Kconfig.debug @@ -12,16 +12,16 @@ config EARLY_PRINTK bool "Early printk" depends on !(SUN3 || M68000 || COLDFIRE) help - Write kernel log output directly to a serial port. - Where implemented, output goes to the framebuffer as well. - PROM console functionality on Sun 3x is not affected by this option. + Write kernel log output directly to a serial port. + Where implemented, output goes to the framebuffer as well. + PROM console functionality on Sun 3x is not affected by this option. - Pass "earlyprintk" on the kernel command line to get a - boot console. + Pass "earlyprintk" on the kernel command line to get a + boot console. - This is useful for kernel debugging when your machine crashes very - early, i.e. before the normal console driver is loaded. - You should normally say N here, unless you want to debug such a crash. + This is useful for kernel debugging when your machine crashes very + early, i.e. before the normal console driver is loaded. + You should normally say N here, unless you want to debug such a crash. if !MMU diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index c01e103492fd..b23a66bac77f 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -269,10 +269,10 @@ config AMCORE Support for the Sysam AMCORE open-hardware generic board. config STMARK2 - bool "Sysam stmark2 board support" - depends on M5441x - help - Support for the Sysam stmark2 open-hardware generic board. + bool "Sysam stmark2 board support" + depends on M5441x + help + Support for the Sysam stmark2 open-hardware generic board. config FIREBEE bool "FireBee board support" diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index e1134c3e0b69..5b3a273ae3da 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -173,7 +173,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -334,7 +333,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -369,6 +367,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -613,9 +612,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 484cb1643df1..0bf0907a7c80 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -169,7 +169,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -319,7 +318,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -348,6 +346,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -569,9 +568,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index eb6a46b6d135..876e69292294 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -176,7 +176,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -334,7 +333,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -364,6 +362,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -591,9 +590,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index bee9263a409c..aa59c242e715 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -166,7 +166,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -316,7 +315,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -346,6 +344,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -562,9 +561,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index c8847a8bcbd6..308cd93929a9 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -168,7 +168,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -318,7 +317,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -347,6 +345,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -571,9 +570,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 303ffafd9cad..0bc210ace870 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -167,7 +167,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -325,7 +324,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -363,6 +361,7 @@ CONFIG_INPUT_ADBHID=y CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -593,9 +592,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 89a704226cd9..3b3b832dee80 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -187,7 +187,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -358,7 +357,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -407,6 +405,7 @@ CONFIG_INPUT_ADBHID=y CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -679,9 +678,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index f62c1f4d03a0..e3633c66926f 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -165,7 +165,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -315,7 +314,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -345,6 +343,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -561,9 +560,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 58dcad26a751..88b3f7f9f146 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -166,7 +166,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -316,7 +315,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -346,6 +344,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -562,9 +561,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 5d3c28d1d545..3dd5b536921e 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -167,7 +167,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -324,7 +323,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -353,6 +351,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -580,9 +579,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 5ef9e17dcd51..715e015ed270 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -163,7 +163,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -313,7 +312,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -343,6 +341,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -564,9 +563,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 22e1accc60a3..f9ff129ac7c2 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -163,7 +163,6 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -313,7 +312,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m @@ -343,6 +341,7 @@ CONFIG_TCM_FILEIO=m CONFIG_TCM_PSCSI=m CONFIG_NETDEVICES=y CONFIG_DUMMY=m +CONFIG_WIREGUARD=m CONFIG_EQUALIZER=m CONFIG_NET_TEAM=m CONFIG_NET_TEAM_MODE_BROADCAST=m @@ -563,9 +562,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m 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/Kbuild b/arch/m68k/include/asm/Kbuild index 591d53b763b7..a0765aa60ea9 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,31 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h -generic-y += barrier.h -generic-y += compat.h -generic-y += device.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += futex.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h +generic-y += hardirq.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += sections.h -generic-y += shmparam.h generic-y += spinlock.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += word-at-a-time.h -generic-y += xor.h diff --git a/arch/m68k/include/asm/hardirq.h b/arch/m68k/include/asm/hardirq.h deleted file mode 100644 index 11793165445d..000000000000 --- a/arch/m68k/include/asm/hardirq.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __M68K_HARDIRQ_H -#define __M68K_HARDIRQ_H - -#include <linux/threads.h> -#include <linux/cache.h> -#include <asm/irq.h> - -#ifdef CONFIG_MMU - -static inline void ack_bad_irq(unsigned int irq) -{ - pr_crit("unexpected IRQ trap at vector %02x\n", irq); -} - -/* entry.S is sensitive to the offsets of these fields */ -typedef struct { - unsigned int __softirq_pending; -} ____cacheline_aligned irq_cpustat_t; - -#include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */ - -#else - -#include <asm-generic/hardirq.h> - -#endif /* !CONFIG_MMU */ - -#endif diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index 82ec54c2eaa4..bc1228e00518 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -28,21 +28,22 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address) return (pmd_t *) pgd; } -#define pmd_populate(mm, pmd, page) (pmd_val(*pmd) = \ - (unsigned long)(page_address(page))) +#define pmd_populate(mm, pmd, pte) (pmd_val(*pmd) = (unsigned long)(pte)) -#define pmd_populate_kernel(mm, pmd, pte) (pmd_val(*pmd) = (unsigned long)(pte)) +#define pmd_populate_kernel pmd_populate -#define pmd_pgtable(pmd) pmd_page(pmd) +#define pmd_pgtable(pmd) pfn_to_virt(pmd_val(pmd) >> PAGE_SHIFT) -static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page, +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable, unsigned long address) { + struct page *page = virt_to_page(pgtable); + pgtable_pte_page_dtor(page); __free_page(page); } -static inline struct page *pte_alloc_one(struct mm_struct *mm) +static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { struct page *page = alloc_pages(GFP_DMA, 0); pte_t *pte; @@ -54,20 +55,16 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm) return NULL; } - pte = kmap(page); - if (pte) { - clear_page(pte); - __flush_page_to_ram(pte); - flush_tlb_kernel_page(pte); - nocache_page(pte); - } - kunmap(page); + pte = page_address(page); + clear_page(pte); - return page; + return pte; } -static inline void pte_free(struct mm_struct *mm, struct page *page) +static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable) { + struct page *page = virt_to_page(pgtable); + pgtable_pte_page_dtor(page); __free_page(page); } @@ -90,7 +87,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) new_pgd = (pgd_t *)__get_free_page(GFP_DMA | __GFP_NOWARN); if (!new_pgd) return NULL; - memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE); + memcpy(new_pgd, swapper_pg_dir, PTRS_PER_PGD * sizeof(pgd_t)); memset(new_pgd, 0, PAGE_OFFSET >> PGDIR_SHIFT); return new_pgd; } diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index ff9cc401ffd1..c66e42917912 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -5,93 +5,71 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> -extern pmd_t *get_pointer_table(void); -extern int free_pointer_table(pmd_t *); +extern void mmu_page_ctor(void *page); +extern void mmu_page_dtor(void *page); -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte; +enum m68k_table_types { + TABLE_PGD = 0, + TABLE_PMD = 0, /* same size as PGD */ + TABLE_PTE = 1, +}; - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - if (pte) { - __flush_page_to_ram(pte); - flush_tlb_kernel_page(pte); - nocache_page(pte); - } +extern void init_pointer_table(void *table, int type); +extern void *get_pointer_table(int type); +extern int free_pointer_table(void *table, int type); - return pte; +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) +{ + return get_pointer_table(TABLE_PTE); } static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - cache_page(pte); - free_page((unsigned long) pte); + free_pointer_table(pte, TABLE_PTE); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { - struct page *page; - pte_t *pte; - - page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); - if(!page) - return NULL; - if (!pgtable_pte_page_ctor(page)) { - __free_page(page); - return NULL; - } - - pte = kmap(page); - __flush_page_to_ram(pte); - flush_tlb_kernel_page(pte); - nocache_page(pte); - kunmap(page); - return page; + return get_pointer_table(TABLE_PTE); } -static inline void pte_free(struct mm_struct *mm, pgtable_t page) +static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable) { - pgtable_pte_page_dtor(page); - cache_page(kmap(page)); - kunmap(page); - __free_page(page); + free_pointer_table(pgtable, TABLE_PTE); } -static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page, +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable, unsigned long address) { - pgtable_pte_page_dtor(page); - cache_page(kmap(page)); - kunmap(page); - __free_page(page); + free_pointer_table(pgtable, TABLE_PTE); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - return get_pointer_table(); + return get_pointer_table(TABLE_PMD); } static inline int pmd_free(struct mm_struct *mm, pmd_t *pmd) { - return free_pointer_table(pmd); + return free_pointer_table(pmd, TABLE_PMD); } static inline int __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { - return free_pointer_table(pmd); + return free_pointer_table(pmd, TABLE_PMD); } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - pmd_free(mm, (pmd_t *)pgd); + free_pointer_table(pgd, TABLE_PGD); } static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - return (pgd_t *)get_pointer_table(); + return get_pointer_table(TABLE_PGD); } @@ -102,9 +80,9 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t * static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page) { - pmd_set(pmd, page_address(page)); + pmd_set(pmd, page); } -#define pmd_pgtable(pmd) pmd_page(pmd) +#define pmd_pgtable(pmd) ((pgtable_t)__pmd_page(pmd)) static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h index 62bedc61f110..4b91a470ad58 100644 --- a/arch/m68k/include/asm/motorola_pgtable.h +++ b/arch/m68k/include/asm/motorola_pgtable.h @@ -23,7 +23,18 @@ #define _DESCTYPE_MASK 0x003 #define _CACHEMASK040 (~0x060) -#define _TABLE_MASK (0xfffffe00) + +/* + * Currently set to the minimum alignment of table pointers (256 bytes). + * The hardware only uses the low 4 bits for state: + * + * 3 - Used + * 2 - Write Protected + * 0,1 - Descriptor Type + * + * and has the rest of the bits reserved. + */ +#define _TABLE_MASK (0xffffff00) #define _PAGE_TABLE (_PAGE_SHORT) #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_NOCACHE) @@ -108,13 +119,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) { - unsigned long ptbl = virt_to_phys(ptep) | _PAGE_TABLE | _PAGE_ACCESSED; - unsigned long *ptr = pmdp->pmd; - short i = 16; - while (--i >= 0) { - *ptr++ = ptbl; - ptbl += (sizeof(pte_t)*PTRS_PER_PTE/16); - } + pmd_val(*pmdp) = virt_to_phys(ptep) | _PAGE_TABLE | _PAGE_ACCESSED; } static inline void pud_set(pud_t *pudp, pmd_t *pmdp) @@ -138,13 +143,14 @@ static inline void pud_set(pud_t *pudp, pmd_t *pmdp) #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) ((pmd_val(pmd) & _DESCTYPE_MASK) != _PAGE_TABLE) #define pmd_present(pmd) (pmd_val(pmd) & _PAGE_TABLE) -#define pmd_clear(pmdp) ({ \ - unsigned long *__ptr = pmdp->pmd; \ - short __i = 16; \ - while (--__i >= 0) \ - *__ptr++ = 0; \ -}) -#define pmd_page(pmd) virt_to_page(__va(pmd_val(pmd))) +#define pmd_clear(pmdp) ({ pmd_val(*pmdp) = 0; }) + +/* + * m68k does not have huge pages (020/030 actually could), but generic code + * expects pmd_page() to exists, only to then DCE it all. Provide a dummy to + * make the compiler happy. + */ +#define pmd_page(pmd) NULL #define pud_none(pud) (!pud_val(pud)) diff --git a/arch/m68k/include/asm/page.h b/arch/m68k/include/asm/page.h index 05e1e1e77a9a..da546487e177 100644 --- a/arch/m68k/include/asm/page.h +++ b/arch/m68k/include/asm/page.h @@ -22,15 +22,25 @@ * These are used to make use of C type-checking.. */ #if !defined(CONFIG_MMU) || CONFIG_PGTABLE_LEVELS == 3 -typedef struct { unsigned long pmd[16]; } pmd_t; -#define pmd_val(x) ((&x)->pmd[0]) -#define __pmd(x) ((pmd_t) { { (x) }, }) +typedef struct { unsigned long pmd; } pmd_t; +#define pmd_val(x) ((&x)->pmd) +#define __pmd(x) ((pmd_t) { (x) } ) #endif typedef struct { unsigned long pte; } pte_t; typedef struct { unsigned long pgd; } pgd_t; typedef struct { unsigned long pgprot; } pgprot_t; + +#if defined(CONFIG_SUN3) +/* + * Sun3 still uses the asm-generic/pgalloc.h code and thus needs this + * definition. It would be possible to unify Sun3 and ColdFire pgalloc and have + * all of m68k use the same type. + */ typedef struct page *pgtable_t; +#else +typedef pte_t *pgtable_t; +#endif #define pte_val(x) ((x).pte) #define pgd_val(x) ((x).pgd) diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index 2bf5c3501e78..f0e5167de834 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -36,7 +36,7 @@ /* PMD_SHIFT determines the size of the area a second-level page table can map */ #if CONFIG_PGTABLE_LEVELS == 3 -#define PMD_SHIFT 22 +#define PMD_SHIFT 18 #endif #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) @@ -67,8 +67,8 @@ #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 1024 #else -#define PTRS_PER_PTE 1024 -#define PTRS_PER_PMD 8 +#define PTRS_PER_PTE 64 +#define PTRS_PER_PMD 128 #define PTRS_PER_PGD 128 #endif #define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) @@ -76,8 +76,8 @@ /* Virtual address region for use by kernel_map() */ #ifdef CONFIG_SUN3 -#define KMAP_START 0x0DC00000 -#define KMAP_END 0x0E000000 +#define KMAP_START 0x0dc00000 +#define KMAP_END 0x0e000000 #elif defined(CONFIG_COLDFIRE) #define KMAP_START 0xe0000000 #define KMAP_END 0xf0000000 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/m68k/mm/fault.c b/arch/m68k/mm/fault.c index e9b1d7585b43..f7afb9897966 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -71,7 +71,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, struct mm_struct *mm = current->mm; struct vm_area_struct * vma; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; pr_debug("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n", regs->sr, regs->pc, address, error_code, mm ? mm->pgd : NULL); @@ -138,7 +138,7 @@ good_area: fault = handle_mm_fault(vma, address, flags); pr_debug("handle_mm_fault returns %x\n", fault); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return 0; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -162,9 +162,6 @@ good_area: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk - * of starvation. */ - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 27c453f4fffe..b88d510d4fe3 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -40,11 +40,6 @@ void *empty_zero_page; EXPORT_SYMBOL(empty_zero_page); -#if !defined(CONFIG_SUN3) && !defined(CONFIG_COLDFIRE) -extern void init_pointer_table(unsigned long ptable); -extern pmd_t *zero_pgtable; -#endif - #ifdef CONFIG_MMU pg_data_t pg_data_map[MAX_NUMNODES]; @@ -125,20 +120,31 @@ void free_initmem(void) static inline void init_pointer_tables(void) { #if defined(CONFIG_MMU) && !defined(CONFIG_SUN3) && !defined(CONFIG_COLDFIRE) - int i; + int i, j; /* insert pointer tables allocated so far into the tablelist */ - init_pointer_table((unsigned long)kernel_pg_dir); + init_pointer_table(kernel_pg_dir, TABLE_PGD); for (i = 0; i < PTRS_PER_PGD; i++) { - pud_t *pud = (pud_t *)(&kernel_pg_dir[i]); + pud_t *pud = (pud_t *)&kernel_pg_dir[i]; + pmd_t *pmd_dir; - if (pud_present(*pud)) - init_pointer_table(pgd_page_vaddr(kernel_pg_dir[i])); - } + if (!pud_present(*pud)) + continue; + + pmd_dir = (pmd_t *)pgd_page_vaddr(kernel_pg_dir[i]); + init_pointer_table(pmd_dir, TABLE_PMD); - /* insert also pointer table that we used to unmap the zero page */ - if (zero_pgtable) - init_pointer_table((unsigned long)zero_pgtable); + for (j = 0; j < PTRS_PER_PMD; j++) { + pmd_t *pmd = &pmd_dir[j]; + pte_t *pte_dir; + + if (!pmd_present(*pmd)) + continue; + + pte_dir = (pte_t *)__pmd_page(*pmd); + init_pointer_table(pte_dir, TABLE_PTE); + } + } #endif } diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c index 120030ad8dc4..14d31d216cef 100644 --- a/arch/m68k/mm/kmap.c +++ b/arch/m68k/mm/kmap.c @@ -24,8 +24,6 @@ #undef DEBUG -#define PTRTREESIZE (256*1024) - /* * For 040/060 we can use the virtual memory area like other architectures, * but for 020/030 we want to use early termination page descriptors and we @@ -50,7 +48,7 @@ static inline void free_io_area(void *addr) #else -#define IO_SIZE (256*1024) +#define IO_SIZE PMD_SIZE static struct vm_struct *iolist; @@ -81,14 +79,13 @@ static void __free_io_area(void *addr, unsigned long size) #if CONFIG_PGTABLE_LEVELS == 3 if (CPU_IS_020_OR_030) { - int pmd_off = (virtaddr/PTRTREESIZE) & 15; - int pmd_type = pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK; + int pmd_type = pmd_val(*pmd_dir) & _DESCTYPE_MASK; if (pmd_type == _PAGE_PRESENT) { - pmd_dir->pmd[pmd_off] = 0; - virtaddr += PTRTREESIZE; - size -= PTRTREESIZE; - continue; + pmd_clear(pmd_dir); + virtaddr += PMD_SIZE; + size -= PMD_SIZE; + } else if (pmd_type == 0) continue; } @@ -249,7 +246,7 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla while ((long)size > 0) { #ifdef DEBUG - if (!(virtaddr & (PTRTREESIZE-1))) + if (!(virtaddr & (PMD_SIZE-1))) printk ("\npa=%#lx va=%#lx ", physaddr, virtaddr); #endif pgd_dir = pgd_offset_k(virtaddr); @@ -263,10 +260,10 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla #if CONFIG_PGTABLE_LEVELS == 3 if (CPU_IS_020_OR_030) { - pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr; - physaddr += PTRTREESIZE; - virtaddr += PTRTREESIZE; - size -= PTRTREESIZE; + pmd_val(*pmd_dir) = physaddr; + physaddr += PMD_SIZE; + virtaddr += PMD_SIZE; + size -= PMD_SIZE; } else #endif { @@ -367,13 +364,12 @@ void kernel_set_cachemode(void *addr, unsigned long size, int cmode) #if CONFIG_PGTABLE_LEVELS == 3 if (CPU_IS_020_OR_030) { - int pmd_off = (virtaddr/PTRTREESIZE) & 15; + unsigned long pmd = pmd_val(*pmd_dir); - if ((pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK) == _PAGE_PRESENT) { - pmd_dir->pmd[pmd_off] = (pmd_dir->pmd[pmd_off] & - _CACHEMASK040) | cmode; - virtaddr += PTRTREESIZE; - size -= PTRTREESIZE; + if ((pmd & _DESCTYPE_MASK) == _PAGE_PRESENT) { + *pmd_dir = __pmd((pmd & _CACHEMASK040) | cmode); + virtaddr += PMD_SIZE; + size -= PMD_SIZE; continue; } } diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c index 227c04fe60d2..65e0c4071912 100644 --- a/arch/m68k/mm/memory.c +++ b/arch/m68k/mm/memory.c @@ -22,109 +22,6 @@ #include <asm/machdep.h> -/* ++andreas: {get,free}_pointer_table rewritten to use unused fields from - struct page instead of separately kmalloced struct. Stolen from - arch/sparc/mm/srmmu.c ... */ - -typedef struct list_head ptable_desc; -static LIST_HEAD(ptable_list); - -#define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page(page)->lru)) -#define PD_PAGE(ptable) (list_entry(ptable, struct page, lru)) -#define PD_MARKBITS(dp) (*(unsigned char *)&PD_PAGE(dp)->index) - -#define PTABLE_SIZE (PTRS_PER_PMD * sizeof(pmd_t)) - -void __init init_pointer_table(unsigned long ptable) -{ - ptable_desc *dp; - unsigned long page = ptable & PAGE_MASK; - unsigned char mask = 1 << ((ptable - page)/PTABLE_SIZE); - - dp = PD_PTABLE(page); - if (!(PD_MARKBITS(dp) & mask)) { - PD_MARKBITS(dp) = 0xff; - list_add(dp, &ptable_list); - } - - PD_MARKBITS(dp) &= ~mask; - pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp)); - - /* unreserve the page so it's possible to free that page */ - __ClearPageReserved(PD_PAGE(dp)); - init_page_count(PD_PAGE(dp)); - - return; -} - -pmd_t *get_pointer_table (void) -{ - ptable_desc *dp = ptable_list.next; - unsigned char mask = PD_MARKBITS (dp); - unsigned char tmp; - unsigned int off; - - /* - * For a pointer table for a user process address space, a - * table is taken from a page allocated for the purpose. Each - * page can hold 8 pointer tables. The page is remapped in - * virtual address space to be noncacheable. - */ - if (mask == 0) { - void *page; - ptable_desc *new; - - if (!(page = (void *)get_zeroed_page(GFP_KERNEL))) - return NULL; - - flush_tlb_kernel_page(page); - nocache_page(page); - - new = PD_PTABLE(page); - PD_MARKBITS(new) = 0xfe; - list_add_tail(new, dp); - - return (pmd_t *)page; - } - - for (tmp = 1, off = 0; (mask & tmp) == 0; tmp <<= 1, off += PTABLE_SIZE) - ; - PD_MARKBITS(dp) = mask & ~tmp; - if (!PD_MARKBITS(dp)) { - /* move to end of list */ - list_move_tail(dp, &ptable_list); - } - return (pmd_t *) (page_address(PD_PAGE(dp)) + off); -} - -int free_pointer_table (pmd_t *ptable) -{ - ptable_desc *dp; - unsigned long page = (unsigned long)ptable & PAGE_MASK; - unsigned char mask = 1 << (((unsigned long)ptable - page)/PTABLE_SIZE); - - dp = PD_PTABLE(page); - if (PD_MARKBITS (dp) & mask) - panic ("table already free!"); - - PD_MARKBITS (dp) |= mask; - - if (PD_MARKBITS(dp) == 0xff) { - /* all tables in page are free, free page */ - list_del(dp); - cache_page((void *)page); - free_page (page); - return 1; - } else if (ptable_list.next != dp) { - /* - * move this descriptor to the front of the list, since - * it has one or more free tables. - */ - list_move(dp, &ptable_list); - } - return 0; -} - /* invalidate page in both caches */ static inline void clear040(unsigned long paddr) { diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 4857985b8080..fc16190ec2d6 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -45,34 +45,185 @@ unsigned long mm_cachebits; EXPORT_SYMBOL(mm_cachebits); #endif + +/* + * Motorola 680x0 user's manual recommends using uncached memory for address + * translation tables. + * + * Seeing how the MMU can be external on (some of) these chips, that seems like + * a very important recommendation to follow. Provide some helpers to combat + * 'variation' amongst the users of this. + */ + +void mmu_page_ctor(void *page) +{ + __flush_page_to_ram(page); + flush_tlb_kernel_page(page); + nocache_page(page); +} + +void mmu_page_dtor(void *page) +{ + cache_page(page); +} + +/* ++andreas: {get,free}_pointer_table rewritten to use unused fields from + struct page instead of separately kmalloced struct. Stolen from + arch/sparc/mm/srmmu.c ... */ + +typedef struct list_head ptable_desc; + +static struct list_head ptable_list[2] = { + LIST_HEAD_INIT(ptable_list[0]), + LIST_HEAD_INIT(ptable_list[1]), +}; + +#define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page(page)->lru)) +#define PD_PAGE(ptable) (list_entry(ptable, struct page, lru)) +#define PD_MARKBITS(dp) (*(unsigned int *)&PD_PAGE(dp)->index) + +static const int ptable_shift[2] = { + 7+2, /* PGD, PMD */ + 6+2, /* PTE */ +}; + +#define ptable_size(type) (1U << ptable_shift[type]) +#define ptable_mask(type) ((1U << (PAGE_SIZE / ptable_size(type))) - 1) + +void __init init_pointer_table(void *table, int type) +{ + ptable_desc *dp; + unsigned long ptable = (unsigned long)table; + unsigned long page = ptable & PAGE_MASK; + unsigned int mask = 1U << ((ptable - page)/ptable_size(type)); + + dp = PD_PTABLE(page); + if (!(PD_MARKBITS(dp) & mask)) { + PD_MARKBITS(dp) = ptable_mask(type); + list_add(dp, &ptable_list[type]); + } + + PD_MARKBITS(dp) &= ~mask; + pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp)); + + /* unreserve the page so it's possible to free that page */ + __ClearPageReserved(PD_PAGE(dp)); + init_page_count(PD_PAGE(dp)); + + return; +} + +void *get_pointer_table(int type) +{ + ptable_desc *dp = ptable_list[type].next; + unsigned int mask = list_empty(&ptable_list[type]) ? 0 : PD_MARKBITS(dp); + unsigned int tmp, off; + + /* + * For a pointer table for a user process address space, a + * table is taken from a page allocated for the purpose. Each + * page can hold 8 pointer tables. The page is remapped in + * virtual address space to be noncacheable. + */ + if (mask == 0) { + void *page; + ptable_desc *new; + + if (!(page = (void *)get_zeroed_page(GFP_KERNEL))) + return NULL; + + if (type == TABLE_PTE) { + /* + * m68k doesn't have SPLIT_PTE_PTLOCKS for not having + * SMP. + */ + pgtable_pte_page_ctor(virt_to_page(page)); + } + + mmu_page_ctor(page); + + new = PD_PTABLE(page); + PD_MARKBITS(new) = ptable_mask(type) - 1; + list_add_tail(new, dp); + + return (pmd_t *)page; + } + + for (tmp = 1, off = 0; (mask & tmp) == 0; tmp <<= 1, off += ptable_size(type)) + ; + PD_MARKBITS(dp) = mask & ~tmp; + if (!PD_MARKBITS(dp)) { + /* move to end of list */ + list_move_tail(dp, &ptable_list[type]); + } + return page_address(PD_PAGE(dp)) + off; +} + +int free_pointer_table(void *table, int type) +{ + ptable_desc *dp; + unsigned long ptable = (unsigned long)table; + unsigned long page = ptable & PAGE_MASK; + unsigned int mask = 1U << ((ptable - page)/ptable_size(type)); + + dp = PD_PTABLE(page); + if (PD_MARKBITS (dp) & mask) + panic ("table already free!"); + + PD_MARKBITS (dp) |= mask; + + if (PD_MARKBITS(dp) == ptable_mask(type)) { + /* all tables in page are free, free page */ + list_del(dp); + mmu_page_dtor((void *)page); + if (type == TABLE_PTE) + pgtable_pte_page_dtor(virt_to_page(page)); + free_page (page); + return 1; + } else if (ptable_list[type].next != dp) { + /* + * move this descriptor to the front of the list, since + * it has one or more free tables. + */ + list_move(dp, &ptable_list[type]); + } + return 0; +} + /* size of memory already mapped in head.S */ extern __initdata unsigned long m68k_init_mapped_size; extern unsigned long availmem; +static pte_t *last_pte_table __initdata = NULL; + static pte_t * __init kernel_page_table(void) { - pte_t *ptablep; + pte_t *pte_table = last_pte_table; - ptablep = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); - if (!ptablep) - panic("%s: Failed to allocate %lu bytes align=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + if (((unsigned long)last_pte_table & ~PAGE_MASK) == 0) { + pte_table = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); + if (!pte_table) { + panic("%s: Failed to allocate %lu bytes align=%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); + } - clear_page(ptablep); - __flush_page_to_ram(ptablep); - flush_tlb_kernel_page(ptablep); - nocache_page(ptablep); + clear_page(pte_table); + mmu_page_ctor(pte_table); - return ptablep; + last_pte_table = pte_table; + } + + last_pte_table += PTRS_PER_PTE; + + return pte_table; } -static pmd_t *last_pgtable __initdata = NULL; -pmd_t *zero_pgtable __initdata = NULL; +static pmd_t *last_pmd_table __initdata = NULL; static pmd_t * __init kernel_ptr_table(void) { - if (!last_pgtable) { + if (!last_pmd_table) { unsigned long pmd, last; int i; @@ -91,33 +242,29 @@ static pmd_t * __init kernel_ptr_table(void) last = pmd; } - last_pgtable = (pmd_t *)last; + last_pmd_table = (pmd_t *)last; #ifdef DEBUG - printk("kernel_ptr_init: %p\n", last_pgtable); + printk("kernel_ptr_init: %p\n", last_pmd_table); #endif } - last_pgtable += PTRS_PER_PMD; - if (((unsigned long)last_pgtable & ~PAGE_MASK) == 0) { - last_pgtable = (pmd_t *)memblock_alloc_low(PAGE_SIZE, + last_pmd_table += PTRS_PER_PMD; + if (((unsigned long)last_pmd_table & ~PAGE_MASK) == 0) { + last_pmd_table = (pmd_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); - if (!last_pgtable) + if (!last_pmd_table) panic("%s: Failed to allocate %lu bytes align=%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); - clear_page(last_pgtable); - __flush_page_to_ram(last_pgtable); - flush_tlb_kernel_page(last_pgtable); - nocache_page(last_pgtable); + clear_page(last_pmd_table); + mmu_page_ctor(last_pmd_table); } - return last_pgtable; + return last_pmd_table; } static void __init map_node(int node) { -#define PTRTREESIZE (256*1024) -#define ROOTTREESIZE (32*1024*1024) unsigned long physaddr, virtaddr, size; pgd_t *pgd_dir; p4d_t *p4d_dir; @@ -135,21 +282,21 @@ static void __init map_node(int node) while (size > 0) { #ifdef DEBUG - if (!(virtaddr & (PTRTREESIZE-1))) + if (!(virtaddr & (PMD_SIZE-1))) printk ("\npa=%#lx va=%#lx ", physaddr & PAGE_MASK, virtaddr); #endif pgd_dir = pgd_offset_k(virtaddr); if (virtaddr && CPU_IS_020_OR_030) { - if (!(virtaddr & (ROOTTREESIZE-1)) && - size >= ROOTTREESIZE) { + if (!(virtaddr & (PGDIR_SIZE-1)) && + size >= PGDIR_SIZE) { #ifdef DEBUG printk ("[very early term]"); #endif pgd_val(*pgd_dir) = physaddr; - size -= ROOTTREESIZE; - virtaddr += ROOTTREESIZE; - physaddr += ROOTTREESIZE; + size -= PGDIR_SIZE; + virtaddr += PGDIR_SIZE; + physaddr += PGDIR_SIZE; continue; } } @@ -169,24 +316,23 @@ static void __init map_node(int node) #ifdef DEBUG printk ("[early term]"); #endif - pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr; - physaddr += PTRTREESIZE; + pmd_val(*pmd_dir) = physaddr; + physaddr += PMD_SIZE; } else { int i; #ifdef DEBUG printk ("[zero map]"); #endif - zero_pgtable = kernel_ptr_table(); - pte_dir = (pte_t *)zero_pgtable; - pmd_dir->pmd[0] = virt_to_phys(pte_dir) | - _PAGE_TABLE | _PAGE_ACCESSED; + pte_dir = kernel_page_table(); + pmd_set(pmd_dir, pte_dir); + pte_val(*pte_dir++) = 0; physaddr += PAGE_SIZE; - for (i = 1; i < 64; physaddr += PAGE_SIZE, i++) + for (i = 1; i < PTRS_PER_PTE; physaddr += PAGE_SIZE, i++) pte_val(*pte_dir++) = physaddr; } - size -= PTRTREESIZE; - virtaddr += PTRTREESIZE; + size -= PMD_SIZE; + virtaddr += PMD_SIZE; } else { if (!pmd_present(*pmd_dir)) { #ifdef DEBUG 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/Kbuild b/arch/microblaze/include/asm/Kbuild index e5c9170a07fc..2e87a9b6d312 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,38 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h -generic-y += barrier.h -generic-y += bitops.h -generic-y += bug.h -generic-y += bugs.h -generic-y += compat.h -generic-y += device.h -generic-y += div64.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += fb.h -generic-y += hardirq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h +generic-y += hw_irq.h generic-y += kvm_para.h -generic-y += linkage.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h generic-y += parport.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += serial.h -generic-y += shmparam.h generic-y += syscalls.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h +generic-y += tlb.h +generic-y += user.h diff --git a/arch/microblaze/include/asm/barrier.h b/arch/microblaze/include/asm/barrier.h new file mode 100644 index 000000000000..70b0a017781b --- /dev/null +++ b/arch/microblaze/include/asm/barrier.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2015 - 2020 Xilinx, Inc. All rights reserved. + */ + +#ifndef _ASM_MICROBLAZE_BARRIER_H +#define _ASM_MICROBLAZE_BARRIER_H + +#define mb() __asm__ __volatile__ ("mbar 1" : : : "memory") + +#include <asm-generic/barrier.h> + +#endif /* _ASM_MICROBLAZE_BARRIER_H */ diff --git a/arch/microblaze/include/asm/cache.h b/arch/microblaze/include/asm/cache.h index 4efe96a036f7..a149b3e711ec 100644 --- a/arch/microblaze/include/asm/cache.h +++ b/arch/microblaze/include/asm/cache.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Cache operations * * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2007-2009 PetaLogix * Copyright (C) 2003 John Williams <jwilliams@itee.uq.edu.au> - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. */ #ifndef _ASM_MICROBLAZE_CACHE_H diff --git a/arch/microblaze/include/asm/cacheflush.h b/arch/microblaze/include/asm/cacheflush.h index b091de77b15b..11f56c85056b 100644 --- a/arch/microblaze/include/asm/cacheflush.h +++ b/arch/microblaze/include/asm/cacheflush.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2007-2009 PetaLogix @@ -5,11 +6,6 @@ * based on v850 version which was * Copyright (C) 2001,02,03 NEC Electronics Corporation * Copyright (C) 2001,02,03 Miles Bader <miles@gnu.org> - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. - * */ #ifndef _ASM_MICROBLAZE_CACHEFLUSH_H diff --git a/arch/microblaze/include/asm/checksum.h b/arch/microblaze/include/asm/checksum.h index adeecebbb0d1..2e5ebd599943 100644 --- a/arch/microblaze/include/asm/checksum.h +++ b/arch/microblaze/include/asm/checksum.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008 Michal Simek <monstr@monstr.eu> * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_CHECKSUM_H diff --git a/arch/microblaze/include/asm/cmpxchg.h b/arch/microblaze/include/asm/cmpxchg.h index 596300c74509..3523b51aab36 100644 --- a/arch/microblaze/include/asm/cmpxchg.h +++ b/arch/microblaze/include/asm/cmpxchg.h @@ -2,42 +2,8 @@ #ifndef _ASM_MICROBLAZE_CMPXCHG_H #define _ASM_MICROBLAZE_CMPXCHG_H -#include <linux/irqflags.h> - -void __bad_xchg(volatile void *ptr, int size); - -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, - int size) -{ - unsigned long ret; - unsigned long flags; - - switch (size) { - case 1: - local_irq_save(flags); - ret = *(volatile unsigned char *)ptr; - *(volatile unsigned char *)ptr = x; - local_irq_restore(flags); - break; - - case 4: - local_irq_save(flags); - ret = *(volatile unsigned long *)ptr; - *(volatile unsigned long *)ptr = x; - local_irq_restore(flags); - break; - default: - __bad_xchg(ptr, size), ret = 0; - break; - } - - return ret; -} - -#define xchg(ptr, x) \ - ((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) - -#include <asm-generic/cmpxchg.h> -#include <asm-generic/cmpxchg-local.h> +#ifndef CONFIG_SMP +# include <asm-generic/cmpxchg.h> +#endif #endif /* _ASM_MICROBLAZE_CMPXCHG_H */ diff --git a/arch/microblaze/include/asm/cpuinfo.h b/arch/microblaze/include/asm/cpuinfo.h index 8f4996730552..786ffa669bf1 100644 --- a/arch/microblaze/include/asm/cpuinfo.h +++ b/arch/microblaze/include/asm/cpuinfo.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Generic support for queying CPU info * * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2007-2009 PetaLogix * Copyright (C) 2007 John Williams <jwilliams@itee.uq.edu.au> - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. */ #ifndef _ASM_MICROBLAZE_CPUINFO_H diff --git a/arch/microblaze/include/asm/cputable.h b/arch/microblaze/include/asm/cputable.h deleted file mode 100644 index 8b137891791f..000000000000 --- a/arch/microblaze/include/asm/cputable.h +++ /dev/null @@ -1 +0,0 @@ - diff --git a/arch/microblaze/include/asm/current.h b/arch/microblaze/include/asm/current.h index 29303ed825cc..a4bb45be30e6 100644 --- a/arch/microblaze/include/asm/current.h +++ b/arch/microblaze/include/asm/current.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_CURRENT_H diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h index ea2a9cd9b159..05fe9e3e0039 100644 --- a/arch/microblaze/include/asm/delay.h +++ b/arch/microblaze/include/asm/delay.h @@ -1,10 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * include/asm-microblaze/delay.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * * Copyright (C) 2008 Michal Simek * Copyright (C) 2007 John Williams * Copyright (C) 2006 Atmark Techno, Inc. diff --git a/arch/microblaze/include/asm/dma.h b/arch/microblaze/include/asm/dma.h index 0d73d0c6de37..e6cb6d0725af 100644 --- a/arch/microblaze/include/asm/dma.h +++ b/arch/microblaze/include/asm/dma.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_DMA_H diff --git a/arch/microblaze/include/asm/elf.h b/arch/microblaze/include/asm/elf.h index 659024449064..5331a8473a46 100644 --- a/arch/microblaze/include/asm/elf.h +++ b/arch/microblaze/include/asm/elf.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_ELF_H #define _ASM_MICROBLAZE_ELF_H diff --git a/arch/microblaze/include/asm/entry.h b/arch/microblaze/include/asm/entry.h index 596e485ae707..6c42bed41166 100644 --- a/arch/microblaze/include/asm/entry.h +++ b/arch/microblaze/include/asm/entry.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions used by low-level trap handlers * * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2007-2009 PetaLogix * Copyright (C) 2007 John Williams <john.williams@petalogix.com> - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. */ #ifndef _ASM_MICROBLAZE_ENTRY_H diff --git a/arch/microblaze/include/asm/exceptions.h b/arch/microblaze/include/asm/exceptions.h index e6a8ddea1dca..d67e65b72215 100644 --- a/arch/microblaze/include/asm/exceptions.h +++ b/arch/microblaze/include/asm/exceptions.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Preliminary support for HW exception handing for Microblaze * * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2005 John Williams <jwilliams@itee.uq.edu.au> - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. */ #ifndef _ASM_MICROBLAZE_EXCEPTIONS_H diff --git a/arch/microblaze/include/asm/fixmap.h b/arch/microblaze/include/asm/fixmap.h index 06c0e2b1883f..0379ce5229e3 100644 --- a/arch/microblaze/include/asm/fixmap.h +++ b/arch/microblaze/include/asm/fixmap.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * fixmap.h: compile-time virtual memory allocation * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * * Copyright (C) 1998 Ingo Molnar * * Copyright 2008 Freescale Semiconductor Inc. diff --git a/arch/microblaze/include/asm/flat.h b/arch/microblaze/include/asm/flat.h index 1ab86770eaee..79a749f4ad04 100644 --- a/arch/microblaze/include/asm/flat.h +++ b/arch/microblaze/include/asm/flat.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * uClinux flat-format executables * * Copyright (C) 2005 John Williams <jwilliams@itee.uq.edu.au> - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. */ #ifndef _ASM_MICROBLAZE_FLAT_H 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/hw_irq.h b/arch/microblaze/include/asm/hw_irq.h deleted file mode 100644 index 8b137891791f..000000000000 --- a/arch/microblaze/include/asm/hw_irq.h +++ /dev/null @@ -1 +0,0 @@ - diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h index d33c61737b8b..1dd6fae41897 100644 --- a/arch/microblaze/include/asm/io.h +++ b/arch/microblaze/include/asm/io.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2007-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_IO_H diff --git a/arch/microblaze/include/asm/irq.h b/arch/microblaze/include/asm/irq.h index eac2fb4b3fb9..cb6ab55d1d01 100644 --- a/arch/microblaze/include/asm/irq.h +++ b/arch/microblaze/include/asm/irq.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_IRQ_H @@ -14,7 +11,4 @@ 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/irqflags.h b/arch/microblaze/include/asm/irqflags.h index c9a6262832c4..818c6c9f550d 100644 --- a/arch/microblaze/include/asm/irqflags.h +++ b/arch/microblaze/include/asm/irqflags.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_IRQFLAGS_H diff --git a/arch/microblaze/include/asm/mmu.h b/arch/microblaze/include/asm/mmu.h index 1f9edddf7f4b..97f1243101cc 100644 --- a/arch/microblaze/include/asm/mmu.h +++ b/arch/microblaze/include/asm/mmu.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_MMU_H diff --git a/arch/microblaze/include/asm/mmu_context_mm.h b/arch/microblaze/include/asm/mmu_context_mm.h index 97559fe0b953..a1c7dd48454c 100644 --- a/arch/microblaze/include/asm/mmu_context_mm.h +++ b/arch/microblaze/include/asm/mmu_context_mm.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_MMU_CONTEXT_H diff --git a/arch/microblaze/include/asm/module.h b/arch/microblaze/include/asm/module.h index 7be1347fce42..eda1c183b6c7 100644 --- a/arch/microblaze/include/asm/module.h +++ b/arch/microblaze/include/asm/module.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_MODULE_H diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h index f4b44b24b02e..ae7215c94706 100644 --- a/arch/microblaze/include/asm/page.h +++ b/arch/microblaze/include/asm/page.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * VM ops * @@ -6,10 +7,6 @@ * Copyright (C) 2006 Atmark Techno, Inc. * Changes for MMU support: * Copyright (C) 2007 Xilinx, Inc. All rights reserved. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_PAGE_H diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index fcf1e23f2e0a..1d7a91252d03 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_PGALLOC_H diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index 2def331f9e2c..45b30878fc17 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_PGTABLE_H diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 66b537b8d138..1ff5a82b76b6 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_PROCESSOR_H diff --git a/arch/microblaze/include/asm/ptrace.h b/arch/microblaze/include/asm/ptrace.h index 5b18ec124e51..bfcb89df5e26 100644 --- a/arch/microblaze/include/asm/ptrace.h +++ b/arch/microblaze/include/asm/ptrace.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_PTRACE_H #define _ASM_MICROBLAZE_PTRACE_H diff --git a/arch/microblaze/include/asm/pvr.h b/arch/microblaze/include/asm/pvr.h index 4bbdb4c03b57..186ee8c3c818 100644 --- a/arch/microblaze/include/asm/pvr.h +++ b/arch/microblaze/include/asm/pvr.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Support for the MicroBlaze PVR (Processor Version Register) * * Copyright (C) 2009 - 2011 Michal Simek <monstr@monstr.eu> * Copyright (C) 2007 John Williams <john.williams@petalogix.com> * Copyright (C) 2007 - 2011 PetaLogix - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. */ #ifndef _ASM_MICROBLAZE_PVR_H diff --git a/arch/microblaze/include/asm/registers.h b/arch/microblaze/include/asm/registers.h index 68c3afb73877..ee81e1cba008 100644 --- a/arch/microblaze/include/asm/registers.h +++ b/arch/microblaze/include/asm/registers.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_REGISTERS_H diff --git a/arch/microblaze/include/asm/sections.h b/arch/microblaze/include/asm/sections.h index 1b281d3ea734..a9311ad84a67 100644 --- a/arch/microblaze/include/asm/sections.h +++ b/arch/microblaze/include/asm/sections.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_SECTIONS_H diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h index ce9b7b786156..be10da9d87cb 100644 --- a/arch/microblaze/include/asm/setup.h +++ b/arch/microblaze/include/asm/setup.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2007-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_SETUP_H #define _ASM_MICROBLAZE_SETUP_H @@ -13,8 +10,6 @@ #include <uapi/asm/setup.h> # ifndef __ASSEMBLY__ -extern unsigned int boot_cpuid; /* move to smp.h */ - extern char cmd_line[COMMAND_LINE_SIZE]; extern char *klimit; diff --git a/arch/microblaze/include/asm/string.h b/arch/microblaze/include/asm/string.h index aec2f59298b8..34071a848b6a 100644 --- a/arch/microblaze/include/asm/string.h +++ b/arch/microblaze/include/asm/string.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_STRING_H diff --git a/arch/microblaze/include/asm/switch_to.h b/arch/microblaze/include/asm/switch_to.h index f45baa2c5e09..5afd6d9977b2 100644 --- a/arch/microblaze/include/asm/switch_to.h +++ b/arch/microblaze/include/asm/switch_to.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_SWITCH_TO_H diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h index 9afe4b5bd6c8..ad8e8fcb90d3 100644 --- a/arch/microblaze/include/asm/thread_info.h +++ b/arch/microblaze/include/asm/thread_info.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_THREAD_INFO_H diff --git a/arch/microblaze/include/asm/timex.h b/arch/microblaze/include/asm/timex.h index befcf3de5532..e99cc29cbe57 100644 --- a/arch/microblaze/include/asm/timex.h +++ b/arch/microblaze/include/asm/timex.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_TIMEX_H diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h deleted file mode 100644 index 628a78ee0a72..000000000000 --- a/arch/microblaze/include/asm/tlb.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> - * Copyright (C) 2008-2009 PetaLogix - * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#ifndef _ASM_MICROBLAZE_TLB_H -#define _ASM_MICROBLAZE_TLB_H - -#include <linux/pagemap.h> -#include <asm-generic/tlb.h> - -#endif /* _ASM_MICROBLAZE_TLB_H */ diff --git a/arch/microblaze/include/asm/tlbflush.h b/arch/microblaze/include/asm/tlbflush.h index 2e1353c2d18d..6f8f5c77a050 100644 --- a/arch/microblaze/include/asm/tlbflush.h +++ b/arch/microblaze/include/asm/tlbflush.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_TLBFLUSH_H diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h index a1f206b90753..070ba6139a62 100644 --- a/arch/microblaze/include/asm/uaccess.h +++ b/arch/microblaze/include/asm/uaccess.h @@ -1,18 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> * Copyright (C) 2008-2009 PetaLogix * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_UACCESS_H #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/include/asm/unaligned.h b/arch/microblaze/include/asm/unaligned.h index b162ed880495..448299beab69 100644 --- a/arch/microblaze/include/asm/unaligned.h +++ b/arch/microblaze/include/asm/unaligned.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008 Michal Simek <monstr@monstr.eu> * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_UNALIGNED_H diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h index d79d35ac6253..cfe3f888b432 100644 --- a/arch/microblaze/include/asm/unistd.h +++ b/arch/microblaze/include/asm/unistd.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2007-2008 Michal Simek <monstr@monstr.eu> * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef _ASM_MICROBLAZE_UNISTD_H #define _ASM_MICROBLAZE_UNISTD_H diff --git a/arch/microblaze/include/asm/unwind.h b/arch/microblaze/include/asm/unwind.h index d248b7de4b13..c327d673622a 100644 --- a/arch/microblaze/include/asm/unwind.h +++ b/arch/microblaze/include/asm/unwind.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Backtrace support for Microblaze * * Copyright (C) 2010 Digital Design Corporation - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ #ifndef __MICROBLAZE_UNWIND_H diff --git a/arch/microblaze/include/asm/user.h b/arch/microblaze/include/asm/user.h deleted file mode 100644 index 8b137891791f..000000000000 --- a/arch/microblaze/include/asm/user.h +++ /dev/null @@ -1 +0,0 @@ - diff --git a/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c b/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c index a32daec96c12..c7ee51b0900e 100644 --- a/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c +++ b/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c @@ -22,13 +22,8 @@ #define CI(c, p) { ci->c = PVR_##p(pvr); } -#if defined(CONFIG_EARLY_PRINTK) && defined(CONFIG_SERIAL_UARTLITE_CONSOLE) #define err_printk(x) \ - early_printk("ERROR: Microblaze " x "-different for PVR and DTS\n"); -#else -#define err_printk(x) \ - pr_info("ERROR: Microblaze " x "-different for PVR and DTS\n"); -#endif + pr_err("ERROR: Microblaze " x "-different for PVR and DTS\n"); void set_cpuinfo_pvr_full(struct cpuinfo *ci, struct device_node *cpu) { diff --git a/arch/microblaze/kernel/cpu/pvr.c b/arch/microblaze/kernel/cpu/pvr.c index 8d0dc6db48cf..f139052a39bd 100644 --- a/arch/microblaze/kernel/cpu/pvr.c +++ b/arch/microblaze/kernel/cpu/pvr.c @@ -14,6 +14,7 @@ #include <linux/compiler.h> #include <asm/exceptions.h> #include <asm/pvr.h> +#include <linux/irqflags.h> /* * Until we get an assembler that knows about the pvr registers, diff --git a/arch/microblaze/kernel/entry.S b/arch/microblaze/kernel/entry.S index f6ded356394a..b179f8f6d287 100644 --- a/arch/microblaze/kernel/entry.S +++ b/arch/microblaze/kernel/entry.S @@ -958,6 +958,7 @@ ENTRY(_switch_to) nop ENTRY(_reset) + VM_OFF brai 0; /* Jump to reset vector */ /* These are compiled and loaded into high memory, then 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/microblaze/kernel/misc.S b/arch/microblaze/kernel/misc.S index 6759af688451..1228a09d8109 100644 --- a/arch/microblaze/kernel/misc.S +++ b/arch/microblaze/kernel/misc.S @@ -39,7 +39,7 @@ _tlbia_1: rsubi r11, r12, MICROBLAZE_TLB_SIZE - 1 bneid r11, _tlbia_1 /* loop for all entries */ addik r12, r12, 1 - /* sync */ + mbar 1 /* sync */ rtsd r15, 8 nop .size _tlbia, . - _tlbia @@ -58,6 +58,7 @@ _tlbie: blti r12, _tlbie_1 /* Check if found */ mts rtlbhi, r0 /* flush: ensure V is clear */ nop + mbar 1 /* sync */ _tlbie_1: rtsd r15, 8 nop diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index 511c1ab7f57f..dd121e33b8e3 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -41,7 +41,6 @@ DEFINE_PER_CPU(unsigned int, ENTRY_SP); /* Saved SP on kernel entry */ DEFINE_PER_CPU(unsigned int, R11_SAVE); /* Temp variable for entry */ DEFINE_PER_CPU(unsigned int, CURRENT_SAVE); /* Saved current pointer */ -unsigned int boot_cpuid; /* * Placed cmd_line to .data section because can be initialized from * ASM code. Default position is BSS section which is cleared @@ -54,7 +53,6 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; setup_memory(); - parse_early_param(); console_verbose(); diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c index a6683484b3a1..f8832cf49384 100644 --- a/arch/microblaze/kernel/timer.c +++ b/arch/microblaze/kernel/timer.c @@ -161,13 +161,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction timer_irqaction = { - .handler = timer_interrupt, - .flags = IRQF_TIMER, - .name = "timer", - .dev_id = &clockevent_xilinx_timer, -}; - static __init int xilinx_clockevent_init(void) { clockevent_xilinx_timer.mult = @@ -309,7 +302,8 @@ static int __init xilinx_timer_init(struct device_node *timer) freq_div_hz = timer_clock_freq / HZ; - ret = setup_irq(irq, &timer_irqaction); + ret = request_irq(irq, timer_interrupt, IRQF_TIMER, "timer", + &clockevent_xilinx_timer); if (ret) { pr_err("Failed to setup IRQ"); return ret; diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S index 2c09fa3a8a01..df07b3d06cd6 100644 --- a/arch/microblaze/kernel/vmlinux.lds.S +++ b/arch/microblaze/kernel/vmlinux.lds.S @@ -13,6 +13,7 @@ ENTRY(microblaze_start) #define RO_EXCEPTION_TABLE_ALIGN 16 +#include <asm/cache.h> #include <asm/page.h> #include <asm-generic/vmlinux.lds.h> #include <asm/thread_info.h> @@ -89,6 +90,8 @@ SECTIONS { _KERNEL_SDA_BASE_ = _ssro + (_ssro_size / 2) ; } + PERCPU_SECTION(L1_CACHE_BYTES) + . = ALIGN(PAGE_SIZE); __init_begin = .; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index e6a810b0c7ad..3248141f8ed5 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -91,7 +91,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, int code = SEGV_MAPERR; int is_write = error_code & ESR_S; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; regs->ear = address; regs->esr = error_code; @@ -217,7 +217,7 @@ good_area: */ fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -236,7 +236,6 @@ good_area: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 1056f1674065..1ffbfa96b9b8 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -201,18 +201,6 @@ void __init mem_init(void) #endif mem_init_print_info(NULL); -#ifdef CONFIG_MMU - pr_info("Kernel virtual memory layout:\n"); - pr_info(" * 0x%08lx..0x%08lx : fixmap\n", FIXADDR_START, FIXADDR_TOP); -#ifdef CONFIG_HIGHMEM - pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n", - PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP)); -#endif /* CONFIG_HIGHMEM */ - pr_info(" * 0x%08lx..0x%08lx : early ioremap\n", - ioremap_bot, ioremap_base); - pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n", - (unsigned long)VMALLOC_START, VMALLOC_END); -#endif mem_init_done = 1; } @@ -347,6 +335,8 @@ asmlinkage void __init mmu_init(void) * inside 768MB limit */ memblock_set_current_limit(memory_start + lowmem_size - 1); + parse_early_param(); + /* CMA initialization */ dma_contiguous_reserve(memory_start + lowmem_size - 1); } diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 797d7f1ad5fe..f8f3dbdd7ad5 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -4,7 +4,6 @@ config MIPS default y select ARCH_32BIT_OFF_T if !64BIT select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT - select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KCOV select ARCH_HAS_PTE_SPECIAL if !(32BIT && CPU_HAS_RIXI) @@ -51,6 +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 @@ -486,9 +486,11 @@ config MACH_LOONGSON64 select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_ZBOOT - select LOONGSON_MC146818 select ZONE_DMA32 select NUMA + select COMMON_CLK + select USE_OF + select BUILTIN_DTB help This enables the support of Loongson-2/3 family of machines. @@ -973,6 +975,9 @@ config CAVIUM_OCTEON_SOC select SYS_HAS_EARLY_PRINTK select SYS_HAS_CPU_CAVIUM_OCTEON select HAVE_PCI + select HAVE_PLAT_DELAY + select HAVE_PLAT_FW_INIT_CMDLINE + select HAVE_PLAT_MEMCPY select ZONE_DMA32 select HOLES_IN_ZONE select GPIOLIB @@ -1229,6 +1234,15 @@ config GENERIC_ISA_DMA_SUPPORT_BROKEN bool select GENERIC_ISA_DMA +config HAVE_PLAT_DELAY + bool + +config HAVE_PLAT_FW_INIT_CMDLINE + bool + +config HAVE_PLAT_MEMCPY + bool + config ISA_DMA_API bool @@ -2676,7 +2690,7 @@ config NUMA Say Y to compile the kernel to support NUMA (Non-Uniform Memory Access). This option improves performance on systems with more than two nodes; on two node systems it is generally better to - leave it disabled; on single node systems disable this option + leave it disabled; on single node systems leave this option disabled. config SYS_SUPPORTS_NUMA @@ -2758,6 +2772,17 @@ config HW_PERF_EVENTS Enable hardware performance counter support for perf events. If disabled, perf events will use software events only. +config DMI + bool "Enable DMI scanning" + depends on MACH_LOONGSON64 + select DMI_SCAN_MACHINE_NON_EFI_FALLBACK + default y + help + Enabled scanning of DMI to identify machine quirks. Say Y + here unless you have verified that your setup is not + affected by entries in the DMI blacklist. Required by PNP + BIOS code. + config SMP bool "Multi-Processing support" depends on SYS_SUPPORTS_SMP @@ -3070,7 +3095,7 @@ endchoice choice prompt "Kernel command line type" if !CMDLINE_OVERRIDE default MIPS_CMDLINE_FROM_DTB if USE_OF && !ATH79 && !MACH_INGENIC && \ - !MIPS_MALTA && \ + !MACH_LOONGSON64 && !MIPS_MALTA && \ !CAVIUM_OCTEON_SOC default MIPS_CMDLINE_FROM_BOOTLOADER diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c index 3a21a6a18da7..d794ffb67412 100644 --- a/arch/mips/alchemy/common/time.c +++ b/arch/mips/alchemy/common/time.c @@ -72,13 +72,6 @@ static struct clock_event_device au1x_rtcmatch2_clockdev = { .cpumask = cpu_possible_mask, }; -static struct irqaction au1x_rtcmatch2_irqaction = { - .handler = au1x_rtcmatch2_irq, - .flags = IRQF_TIMER, - .name = "timer", - .dev_id = &au1x_rtcmatch2_clockdev, -}; - static int __init alchemy_time_init(unsigned int m2int) { struct clock_event_device *cd = &au1x_rtcmatch2_clockdev; @@ -130,7 +123,9 @@ static int __init alchemy_time_init(unsigned int m2int) cd->min_delta_ns = clockevent_delta2ns(9, cd); cd->min_delta_ticks = 9; /* ~0.28ms */ clockevents_register_device(cd); - setup_irq(m2int, &au1x_rtcmatch2_irqaction); + if (request_irq(m2int, au1x_rtcmatch2_irq, IRQF_TIMER, "timer", + &au1x_rtcmatch2_clockdev)) + pr_err("Failed to register timer interrupt\n"); printk(KERN_INFO "Alchemy clocksource installed\n"); diff --git a/arch/mips/ar7/irq.c b/arch/mips/ar7/irq.c index 93a331fe0641..f0a7942d393e 100644 --- a/arch/mips/ar7/irq.c +++ b/arch/mips/ar7/irq.c @@ -83,12 +83,6 @@ static struct irq_chip ar7_sec_irq_type = { .irq_ack = ar7_ack_sec_irq, }; -static struct irqaction ar7_cascade_action = { - .handler = no_action, - .name = "AR7 cascade interrupt", - .flags = IRQF_NO_THREAD, -}; - static void __init ar7_irq_init(int base) { int i; @@ -116,8 +110,14 @@ static void __init ar7_irq_init(int base) handle_level_irq); } - setup_irq(2, &ar7_cascade_action); - setup_irq(ar7_irq_base, &ar7_cascade_action); + if (request_irq(2, no_action, IRQF_NO_THREAD, "AR7 cascade interrupt", + NULL)) + pr_err("Failed to request irq 2 (AR7 cascade interrupt)\n"); + if (request_irq(ar7_irq_base, no_action, IRQF_NO_THREAD, + "AR7 cascade interrupt", NULL)) { + pr_err("Failed to request irq %d (AR7 cascade interrupt)\n", + ar7_irq_base); + } set_c0_status(IE_IRQ0); } diff --git a/arch/mips/ath25/ar2315.c b/arch/mips/ath25/ar2315.c index 24f619199ee7..e7b53e3960c8 100644 --- a/arch/mips/ath25/ar2315.c +++ b/arch/mips/ath25/ar2315.c @@ -64,11 +64,6 @@ static irqreturn_t ar2315_ahb_err_handler(int cpl, void *dev_id) return IRQ_HANDLED; } -static struct irqaction ar2315_ahb_err_interrupt = { - .handler = ar2315_ahb_err_handler, - .name = "ar2315-ahb-error", -}; - static void ar2315_misc_irq_handler(struct irq_desc *desc) { u32 pending = ar2315_rst_reg_read(AR2315_ISR) & @@ -159,7 +154,9 @@ void __init ar2315_arch_init_irq(void) panic("Failed to add IRQ domain"); irq = irq_create_mapping(domain, AR2315_MISC_IRQ_AHB); - setup_irq(irq, &ar2315_ahb_err_interrupt); + if (request_irq(irq, ar2315_ahb_err_handler, 0, "ar2315-ahb-error", + NULL)) + pr_err("Failed to register ar2315-ahb-error interrupt\n"); irq_set_chained_handler_and_data(AR2315_IRQ_MISC, ar2315_misc_irq_handler, domain); diff --git a/arch/mips/ath25/ar5312.c b/arch/mips/ath25/ar5312.c index 47f3e98974fc..42bf2afb4765 100644 --- a/arch/mips/ath25/ar5312.c +++ b/arch/mips/ath25/ar5312.c @@ -68,11 +68,6 @@ static irqreturn_t ar5312_ahb_err_handler(int cpl, void *dev_id) return IRQ_HANDLED; } -static struct irqaction ar5312_ahb_err_interrupt = { - .handler = ar5312_ahb_err_handler, - .name = "ar5312-ahb-error", -}; - static void ar5312_misc_irq_handler(struct irq_desc *desc) { u32 pending = ar5312_rst_reg_read(AR5312_ISR) & @@ -154,7 +149,9 @@ void __init ar5312_arch_init_irq(void) panic("Failed to add IRQ domain"); irq = irq_create_mapping(domain, AR5312_MISC_IRQ_AHB_PROC); - setup_irq(irq, &ar5312_ahb_err_interrupt); + if (request_irq(irq, ar5312_ahb_err_handler, 0, "ar5312-ahb-error", + NULL)) + pr_err("Failed to register ar5312-ahb-error interrupt\n"); irq_set_chained_handler_and_data(AR5312_IRQ_MISC, ar5312_misc_irq_handler, domain); diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 484ee28922a9..acb4fd647a30 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -15,7 +15,7 @@ #include <linux/memblock.h> #include <linux/err.h> #include <linux/clk.h> -#include <linux/clk-provider.h> +#include <linux/of_clk.h> #include <linux/of_fdt.h> #include <linux/irqchip.h> diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c index ec694b9628c0..2548013442f6 100644 --- a/arch/mips/bcm63xx/irq.c +++ b/arch/mips/bcm63xx/irq.c @@ -399,26 +399,6 @@ static struct irq_chip bcm63xx_external_irq_chip = { .irq_set_type = bcm63xx_external_irq_set_type, }; -static struct irqaction cpu_ip2_cascade_action = { - .handler = no_action, - .name = "cascade_ip2", - .flags = IRQF_NO_THREAD, -}; - -#ifdef CONFIG_SMP -static struct irqaction cpu_ip3_cascade_action = { - .handler = no_action, - .name = "cascade_ip3", - .flags = IRQF_NO_THREAD, -}; -#endif - -static struct irqaction cpu_ext_cascade_action = { - .handler = no_action, - .name = "cascade_extirq", - .flags = IRQF_NO_THREAD, -}; - static void bcm63xx_init_irq(void) { int irq_bits; @@ -531,7 +511,7 @@ static void bcm63xx_init_irq(void) void __init arch_init_irq(void) { - int i; + int i, irq; bcm63xx_init_irq(); mips_cpu_irq_init(); @@ -544,14 +524,25 @@ void __init arch_init_irq(void) handle_edge_irq); if (!is_ext_irq_cascaded) { - for (i = 3; i < 3 + ext_irq_count; ++i) - setup_irq(MIPS_CPU_IRQ_BASE + i, &cpu_ext_cascade_action); + for (i = 3; i < 3 + ext_irq_count; ++i) { + irq = MIPS_CPU_IRQ_BASE + i; + if (request_irq(irq, no_action, IRQF_NO_THREAD, + "cascade_extirq", NULL)) { + pr_err("Failed to request irq %d (cascade_extirq)\n", + irq); + } + } } - setup_irq(MIPS_CPU_IRQ_BASE + 2, &cpu_ip2_cascade_action); + irq = MIPS_CPU_IRQ_BASE + 2; + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade_ip2", NULL)) + pr_err("Failed to request irq %d (cascade_ip2)\n", irq); #ifdef CONFIG_SMP if (is_ext_irq_cascaded) { - setup_irq(MIPS_CPU_IRQ_BASE + 3, &cpu_ip3_cascade_action); + irq = MIPS_CPU_IRQ_BASE + 3; + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade_ip3", + NULL)) + pr_err("Failed to request irq %d (cascade_ip3)\n", irq); bcm63xx_internal_irq_chip.irq_set_affinity = bcm63xx_internal_set_affinity; diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index 2f81a94c71a6..19308df5f577 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -10,11 +10,11 @@ #include <linux/init.h> #include <linux/bitops.h> #include <linux/memblock.h> -#include <linux/clk-provider.h> #include <linux/ioport.h> #include <linux/kernel.h> #include <linux/io.h> #include <linux/of.h> +#include <linux/of_clk.h> #include <linux/of_fdt.h> #include <linux/of_platform.h> #include <linux/libfdt.h> diff --git a/arch/mips/boot/dts/Makefile b/arch/mips/boot/dts/Makefile index 1e79cab8e269..d429a69bfe30 100644 --- a/arch/mips/boot/dts/Makefile +++ b/arch/mips/boot/dts/Makefile @@ -4,6 +4,7 @@ subdir-y += cavium-octeon subdir-y += img subdir-y += ingenic subdir-y += lantiq +subdir-y += loongson subdir-y += mscc subdir-y += mti subdir-y += netlogic diff --git a/arch/mips/boot/dts/brcm/bcm7425.dtsi b/arch/mips/boot/dts/brcm/bcm7425.dtsi index 410e61ebaf9e..aa0b2d39c902 100644 --- a/arch/mips/boot/dts/brcm/bcm7425.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7425.dtsi @@ -403,8 +403,8 @@ compatible = "brcm,brcmnand-v5.0", "brcm,brcmnand"; #address-cells = <1>; #size-cells = <0>; - reg-names = "nand"; - reg = <0x41b800 0x400>; + reg-names = "nand", "flash-edu"; + reg = <0x41b800 0x400>, <0x41bc00 0x24>; interrupt-parent = <&hif_l2_intc>; interrupts = <24>; status = "disabled"; diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 37b93166bf22..db0ca250bd1a 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -4,6 +4,9 @@ #include "jz4780.dtsi" #include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/input/input.h> +#include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/regulator/active-semi,8865-regulator.h> / { compatible = "img,ci20", "ingenic,jz4780"; @@ -25,6 +28,17 @@ 0x30000000 0x30000000>; }; + gpio-keys { + compatible = "gpio-keys"; + + sw1 { + label = "ci20:sw1"; + linux,code = <KEY_F13>; + gpios = <&gpd 17 GPIO_ACTIVE_HIGH>; + wakeup-source; + }; + }; + leds { compatible = "gpio-leds"; @@ -56,10 +70,17 @@ eth0_power: fixedregulator@0 { compatible = "regulator-fixed"; regulator-name = "eth0_power"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; gpio = <&gpb 25 GPIO_ACTIVE_LOW>; enable-active-high; }; + ir: ir { + compatible = "gpio-ir-receiver"; + gpios = <&gpe 3 GPIO_ACTIVE_LOW>; + }; + wlan0_power: fixedregulator@1 { compatible = "regulator-fixed"; regulator-name = "wlan0_power"; @@ -163,63 +184,71 @@ 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 +290,9 @@ 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/boot/dts/loongson/Makefile b/arch/mips/boot/dts/loongson/Makefile new file mode 100644 index 000000000000..56d379471262 --- /dev/null +++ b/arch/mips/boot/dts/loongson/Makefile @@ -0,0 +1,4 @@ +# SPDX_License_Identifier: GPL_2.0 +dtb-$(CONFIG_MACH_LOONGSON64) += loongson3_4core_rs780e.dtb loongson3_8core_rs780e.dtb + +obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/loongson/loongson3-package.dtsi b/arch/mips/boot/dts/loongson/loongson3-package.dtsi new file mode 100644 index 000000000000..5bb876a4de52 --- /dev/null +++ b/arch/mips/boot/dts/loongson/loongson3-package.dtsi @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <dt-bindings/interrupt-controller/irq.h> + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpuintc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + compatible = "mti,cpu-interrupt-controller"; + }; + + package0: bus@1fe00000 { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0x1fe00000 0 0x1fe00000 0x100000 + 0 0x3ff00000 0 0x3ff00000 0x100000 + /* 3A HT Config Space */ + 0xefd 0xfb000000 0xefd 0xfb000000 0x10000000 + /* 3B HT Config Space */ + 0x1efd 0xfb000000 0x1efd 0xfb000000 0x10000000>; + + liointc: interrupt-controller@3ff01400 { + compatible = "loongson,liointc-1.0"; + reg = <0 0x3ff01400 0x64>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&cpuintc>; + interrupts = <2>, <3>; + interrupt-names = "int0", "int1"; + + loongson,parent_int_map = <0xf0ffffff>, /* int0 */ + <0x0f000000>, /* int1 */ + <0x00000000>, /* int2 */ + <0x00000000>; /* int3 */ + + }; + + cpu_uart0: serial@1fe001e0 { + compatible = "ns16550a"; + reg = <0 0x1fe001e0 0x8>; + clock-frequency = <33000000>; + interrupt-parent = <&liointc>; + interrupts = <10 IRQ_TYPE_LEVEL_HIGH>; + no-loopback-test; + }; + + cpu_uart1: serial@1fe001e8 { + status = "disabled"; + compatible = "ns16550a"; + reg = <0 0x1fe001e8 0x8>; + clock-frequency = <33000000>; + interrupts = <10 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&liointc>; + no-loopback-test; + }; + }; +}; diff --git a/arch/mips/boot/dts/loongson/loongson3_4core_rs780e.dts b/arch/mips/boot/dts/loongson/loongson3_4core_rs780e.dts new file mode 100644 index 000000000000..6b5694ca0f95 --- /dev/null +++ b/arch/mips/boot/dts/loongson/loongson3_4core_rs780e.dts @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +/dts-v1/; + +#include "loongson3-package.dtsi" +#include "rs780e-pch.dtsi" + +/ { + compatible = "loongson,loongson3-4core-rs780e"; +}; + +&package0 { + htpic: interrupt-controller@efdfb000080 { + compatible = "loongson,htpic-1.0"; + reg = <0xefd 0xfb000080 0x40>; + interrupt-controller; + #interrupt-cells = <1>; + + interrupt-parent = <&liointc>; + interrupts = <24 IRQ_TYPE_LEVEL_HIGH>, + <25 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>; + }; +}; diff --git a/arch/mips/boot/dts/loongson/loongson3_8core_rs780e.dts b/arch/mips/boot/dts/loongson/loongson3_8core_rs780e.dts new file mode 100644 index 000000000000..ffefa2f829b0 --- /dev/null +++ b/arch/mips/boot/dts/loongson/loongson3_8core_rs780e.dts @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +/dts-v1/; + +#include "loongson3-package.dtsi" +#include "rs780e-pch.dtsi" + +/ { + compatible = "loongson,loongson3-8core-rs780e"; +}; + +&package0 { + htpic: interrupt-controller@1efdfb000080 { + compatible = "loongson,htpic-1.0"; + reg = <0x1efd 0xfb000080 0x40>; + interrupt-controller; + #interrupt-cells = <1>; + + interrupt-parent = <&liointc>; + interrupts = <24 IRQ_TYPE_LEVEL_HIGH>, + <25 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>; + }; +}; diff --git a/arch/mips/boot/dts/loongson/rs780e-pch.dtsi b/arch/mips/boot/dts/loongson/rs780e-pch.dtsi new file mode 100644 index 000000000000..45c54d555fa4 --- /dev/null +++ b/arch/mips/boot/dts/loongson/rs780e-pch.dtsi @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +/ { + bus@10000000 { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0 0x10000000 0 0x10000000 0 0x10000000 + 0 0x40000000 0 0x40000000 0 0x40000000 + 0xfd 0xfe000000 0xfd 0xfe000000 0 0x2000000 /* PCI Config Space */>; + + isa { + compatible = "isa"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <1 0 0 0 0x1000>; + + rtc0: rtc@70 { + compatible = "motorola,mc146818"; + reg = <1 0x70 0x8>; + interrupts = <8>; + interrupt-parent = <&htpic>; + }; + }; + }; +}; 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/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 6bd1e97effdf..6501a842c41a 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2199,6 +2199,9 @@ static int octeon_irq_cib_map(struct irq_domain *d, } cd = kzalloc(sizeof(*cd), GFP_KERNEL); + if (!cd) + return -ENOMEM; + cd->host_data = host_data; cd->bit = hw; diff --git a/arch/mips/cobalt/irq.c b/arch/mips/cobalt/irq.c index 965c777d3561..ead5ae41378d 100644 --- a/arch/mips/cobalt/irq.c +++ b/arch/mips/cobalt/irq.c @@ -45,18 +45,20 @@ asmlinkage void plat_irq_dispatch(void) spurious_interrupt(); } -static struct irqaction cascade = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - void __init arch_init_irq(void) { mips_cpu_irq_init(); gt641xx_irq_init(); init_i8259_irqs(); - setup_irq(GT641XX_CASCADE_IRQ, &cascade); - setup_irq(I8259_CASCADE_IRQ, &cascade); + if (request_irq(GT641XX_CASCADE_IRQ, no_action, IRQF_NO_THREAD, + "cascade", NULL)) { + pr_err("Failed to request irq %d (cascade)\n", + GT641XX_CASCADE_IRQ); + } + if (request_irq(I8259_CASCADE_IRQ, no_action, IRQF_NO_THREAD, + "cascade", NULL)) { + pr_err("Failed to request irq %d (cascade)\n", + I8259_CASCADE_IRQ); + } } diff --git a/arch/mips/configs/ar7_defconfig b/arch/mips/configs/ar7_defconfig index cef2754bd408..cf9c6329b807 100644 --- a/arch/mips/configs/ar7_defconfig +++ b/arch/mips/configs/ar7_defconfig @@ -21,7 +21,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_BSD_DISKLABEL=y -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/mips/configs/ath25_defconfig b/arch/mips/configs/ath25_defconfig index c35add2fd716..7143441f5476 100644 --- a/arch/mips/configs/ath25_defconfig +++ b/arch/mips/configs/ath25_defconfig @@ -22,7 +22,6 @@ CONFIG_HZ_100=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig index 4ffc59cab436..3d14d67dc746 100644 --- a/arch/mips/configs/ath79_defconfig +++ b/arch/mips/configs/ath79_defconfig @@ -23,7 +23,6 @@ CONFIG_PCI=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/mips/configs/bcm63xx_defconfig b/arch/mips/configs/bcm63xx_defconfig index 54e2f9a659fb..861f680184b9 100644 --- a/arch/mips/configs/bcm63xx_defconfig +++ b/arch/mips/configs/bcm63xx_defconfig @@ -21,8 +21,6 @@ CONFIG_PCI=y CONFIG_PCCARD=y CONFIG_PCMCIA_BCM63XX=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_UNIX=y CONFIG_INET=y diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig index f14ad0538f4e..eea9b613bb74 100644 --- a/arch/mips/configs/bigsur_defconfig +++ b/arch/mips/configs/bigsur_defconfig @@ -112,7 +112,6 @@ CONFIG_BLK_DEV_TC86C001=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_CHR_DEV_SCH=m CONFIG_ATA=y diff --git a/arch/mips/configs/bmips_be_defconfig b/arch/mips/configs/bmips_be_defconfig index f669a40e085b..032bb51defe8 100644 --- a/arch/mips/configs/bmips_be_defconfig +++ b/arch/mips/configs/bmips_be_defconfig @@ -12,8 +12,6 @@ CONFIG_NR_CPUS=4 # CONFIG_SECCOMP is not set CONFIG_MIPS_O32_FP64_SUPPORT=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=y diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig index a0b775893dba..625bd2d7e685 100644 --- a/arch/mips/configs/bmips_stb_defconfig +++ b/arch/mips/configs/bmips_stb_defconfig @@ -21,8 +21,6 @@ CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y CONFIG_BMIPS_CPUFREQ=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=y diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig index be41df2a81fb..0db0088bbc1c 100644 --- a/arch/mips/configs/ci20_defconfig +++ b/arch/mips/configs/ci20_defconfig @@ -1,4 +1,5 @@ # CONFIG_LOCALVERSION_AUTO is not set +CONFIG_MODULES=y CONFIG_KERNEL_XZ=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -88,12 +89,14 @@ CONFIG_I2C_JZ4780=y CONFIG_SPI=y CONFIG_SPI_GPIO=y CONFIG_GPIO_SYSFS=y +CONFIG_KEYBOARD_GPIO=m # CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_JZ4740_WDT=y CONFIG_REGULATOR=y CONFIG_REGULATOR_DEBUG=y CONFIG_REGULATOR_FIXED_VOLTAGE=y +CONFIG_REGULATOR_ACT8865=y # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set @@ -166,3 +169,21 @@ CONFIG_STACKTRACE=y # CONFIG_FTRACE is not set CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon console=ttyS4,115200 clk_ignore_unused" +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_TRIGGERS=y +CONFIG_LEDS_TRIGGER_MTD=y +CONFIG_LEDS_TRIGGER_TIMER=y +CONFIG_LEDS_TRIGGER_ONESHOT=y +CONFIG_LEDS_TRIGGER_ONESHOT=y +CONFIG_LEDS_TRIGGER_HEARTBEAT=y +CONFIG_LEDS_TRIGGER_BACKLIGHT=m +CONFIG_LEDS_TRIGGER_CPU=y +CONFIG_LEDS_TRIGGER_DEFAULT_ON=y +CONFIG_LEDS_TRIGGER_TRANSIENT=y +CONFIG_LEDS_TRIGGER_CAMERA=m +CONFIG_LIRC=y +CONFIG_MEDIA_SUPPORT=m +CONFIG_RC_DEVICES=y +CONFIG_IR_GPIO_CIR=m +CONFIG_IR_GPIO_TX=m diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig index bc9b6ae046b2..e6f3e8e3da39 100644 --- a/arch/mips/configs/db1xxx_defconfig +++ b/arch/mips/configs/db1xxx_defconfig @@ -28,7 +28,6 @@ CONFIG_PCMCIA_ALCHEMY_DEVBOARD=y CONFIG_FIRMWARE_MEMMAP=y CONFIG_BLK_DEV_BSGLIB=y CONFIG_PARTITION_ADVANCED=y -CONFIG_DEFAULT_NOOP=y CONFIG_CMA=y CONFIG_CMA_DEBUG=y CONFIG_NET=y diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig index 1788ae23bff9..6466e83067b4 100644 --- a/arch/mips/configs/fuloong2e_defconfig +++ b/arch/mips/configs/fuloong2e_defconfig @@ -99,7 +99,6 @@ CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y # CONFIG_SCSI_LOWLEVEL is not set diff --git a/arch/mips/configs/generic/board-ni169445.config b/arch/mips/configs/generic/board-ni169445.config index 1ed0d3e8715e..fc3580e4e6bc 100644 --- a/arch/mips/configs/generic/board-ni169445.config +++ b/arch/mips/configs/generic/board-ni169445.config @@ -19,7 +19,6 @@ CONFIG_MTD_NAND_ECC_SW_HAMMING=y CONFIG_MTD_NAND_ECC_SW_BCH=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_GPIO=y -CONFIG_MTD_NAND_IDS=y CONFIG_MTD_UBI=y CONFIG_MTD_UBI_BLOCK=y diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index 82d942a6026e..638d7cf5ef01 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -99,7 +99,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_CONSTANTS=y diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig index 370884018aad..7b1fab518317 100644 --- a/arch/mips/configs/ip32_defconfig +++ b/arch/mips/configs/ip32_defconfig @@ -50,7 +50,6 @@ CONFIG_RAID_ATTRS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig index 328d4dfeb4cb..8c223035921f 100644 --- a/arch/mips/configs/jazz_defconfig +++ b/arch/mips/configs/jazz_defconfig @@ -1,15 +1,17 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_BSD_PROCESS_ACCT=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_EXPERT=y CONFIG_SLAB=y CONFIG_MACH_JAZZ=y CONFIG_OLIVETTI_M700=y +CONFIG_MIPS_MAGNUM_4000=y +CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y @@ -18,168 +20,17 @@ CONFIG_BINFMT_MISC=m CONFIG_NET=y CONFIG_PACKET=m CONFIG_UNIX=y -CONFIG_NET_KEY=m -CONFIG_NET_KEY_MIGRATE=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_NET_IPIP=m -CONFIG_IP_MROUTE=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_TCP_MD5SIG=y -CONFIG_IPV6_ROUTER_PREF=y -CONFIG_IPV6_ROUTE_INFO=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_TUNNEL=m -CONFIG_NETWORK_SECMARK=y -CONFIG_NETFILTER=y -CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_SECMARK=y -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CONNTRACK_AMANDA=m -CONFIG_NF_CONNTRACK_FTP=m -CONFIG_NF_CONNTRACK_H323=m -CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_PPTP=m -CONFIG_NF_CONNTRACK_SANE=m -CONFIG_NF_CONNTRACK_SIP=m -CONFIG_NF_CONNTRACK_TFTP=m -CONFIG_NF_CT_NETLINK=m -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m -CONFIG_NETFILTER_XT_TARGET_CONNMARK=m -CONFIG_NETFILTER_XT_TARGET_MARK=m -CONFIG_NETFILTER_XT_TARGET_NFLOG=m -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_SECMARK=m -CONFIG_NETFILTER_XT_TARGET_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_COMMENT=m -CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m -CONFIG_NETFILTER_XT_MATCH_CONNMARK=m -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m -CONFIG_NETFILTER_XT_MATCH_ESP=m -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m -CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_MATCH_LIMIT=m -CONFIG_NETFILTER_XT_MATCH_MAC=m -CONFIG_NETFILTER_XT_MATCH_MARK=m -CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m -CONFIG_NETFILTER_XT_MATCH_QUOTA=m -CONFIG_NETFILTER_XT_MATCH_REALM=m -CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NETFILTER_XT_MATCH_STATISTIC=m -CONFIG_NETFILTER_XT_MATCH_STRING=m -CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_AH=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_AH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_MH=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_DECNET_NF_GRABULATOR=m -CONFIG_BRIDGE_NF_EBTABLES=m -CONFIG_BRIDGE_EBT_BROUTE=m -CONFIG_BRIDGE_EBT_T_FILTER=m -CONFIG_BRIDGE_EBT_T_NAT=m -CONFIG_BRIDGE_EBT_802_3=m -CONFIG_BRIDGE_EBT_AMONG=m -CONFIG_BRIDGE_EBT_ARP=m -CONFIG_BRIDGE_EBT_IP=m -CONFIG_BRIDGE_EBT_LIMIT=m -CONFIG_BRIDGE_EBT_MARK=m -CONFIG_BRIDGE_EBT_PKTTYPE=m -CONFIG_BRIDGE_EBT_STP=m -CONFIG_BRIDGE_EBT_VLAN=m -CONFIG_BRIDGE_EBT_ARPREPLY=m -CONFIG_BRIDGE_EBT_DNAT=m -CONFIG_BRIDGE_EBT_MARK_T=m -CONFIG_BRIDGE_EBT_REDIRECT=m -CONFIG_BRIDGE_EBT_SNAT=m -CONFIG_BRIDGE_EBT_LOG=m -CONFIG_BRIDGE=m -CONFIG_DECNET=m -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CBQ=m -CONFIG_NET_SCH_HTB=m -CONFIG_NET_SCH_HFSC=m -CONFIG_NET_SCH_PRIO=m -CONFIG_NET_SCH_RED=m -CONFIG_NET_SCH_SFQ=m -CONFIG_NET_SCH_TEQL=m -CONFIG_NET_SCH_TBF=m -CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m -CONFIG_NET_SCH_NETEM=m -CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m -CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_FW=m -CONFIG_NET_CLS_U32=m -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m -CONFIG_HAMRADIO=y -CONFIG_AX25=m -CONFIG_NETROM=m -CONFIG_ROSE=m -CONFIG_MKISS=m -CONFIG_6PACK=m -CONFIG_BPQETHER=m -CONFIG_CONNECTOR=m CONFIG_PARPORT=m CONFIG_PARPORT_PC=m CONFIG_PARPORT_1284=y +CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_FD=m -CONFIG_PARIDE=m -CONFIG_PARIDE_PD=m -CONFIG_PARIDE_PCD=m -CONFIG_PARIDE_PF=m -CONFIG_PARIDE_PT=m -CONFIG_PARIDE_PG=m -CONFIG_PARIDE_ATEN=m -CONFIG_PARIDE_BPCK=m -CONFIG_PARIDE_BPCK6=m -CONFIG_PARIDE_COMM=m -CONFIG_PARIDE_DSTR=m -CONFIG_PARIDE_FIT2=m -CONFIG_PARIDE_FIT3=m -CONFIG_PARIDE_EPAT=m -CONFIG_PARIDE_EPIA=m -CONFIG_PARIDE_FRIQ=m -CONFIG_PARIDE_FRPW=m -CONFIG_PARIDE_KBIC=m -CONFIG_PARIDE_KTTI=m -CONFIG_PARIDE_ON20=m -CONFIG_PARIDE_ON26=m CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_NBD=m @@ -191,29 +42,14 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y -CONFIG_SCSI_FC_ATTRS=y -CONFIG_SCSI_SAS_ATTRS=m CONFIG_ISCSI_TCP=m CONFIG_SCSI_PPA=m CONFIG_SCSI_IMM=m CONFIG_JAZZ_ESP=y -CONFIG_MD=y -CONFIG_BLK_DEV_MD=m -CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m -CONFIG_MD_RAID1=m -CONFIG_MD_RAID10=m -CONFIG_MD_RAID456=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m -CONFIG_BLK_DEV_DM=m -CONFIG_DM_SNAPSHOT=m -CONFIG_DM_MIRROR=m -CONFIG_DM_ZERO=m -CONFIG_DM_MULTIPATH=m +CONFIG_ATA=y +CONFIG_PATA_LEGACY=y CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -221,28 +57,18 @@ CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_MIPS_JAZZ_SONIC=y CONFIG_NE2000=m -CONFIG_PHYLIB=m -CONFIG_CICADA_PHY=m -CONFIG_DAVICOM_PHY=m -CONFIG_LXT_PHY=m -CONFIG_MARVELL_PHY=m -CONFIG_QSEMI_PHY=m -CONFIG_SMSC_PHY=m -CONFIG_VITESSE_PHY=m -CONFIG_PLIP=m -CONFIG_INPUT_FF_MEMLESS=m CONFIG_SERIO_PARKBD=m CONFIG_SERIO_RAW=m CONFIG_VT_HW_CONSOLE_BINDING=y -CONFIG_SERIAL_8250=m +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y -CONFIG_PRINTER=m -CONFIG_PPDEV=m -# CONFIG_HW_RANDOM is not set -CONFIG_W1=m +CONFIG_FB=y +CONFIG_FB_G364=y +CONFIG_FRAMEBUFFER_CONSOLE=y # CONFIG_HWMON is not set CONFIG_EXT2_FS=m CONFIG_EXT3_FS=y @@ -263,78 +89,8 @@ CONFIG_VFAT_FS=m CONFIG_NTFS_FS=m CONFIG_PROC_KCORE=y CONFIG_TMPFS=y -CONFIG_ADFS_FS=m -CONFIG_AFFS_FS=m -CONFIG_HFS_FS=m -CONFIG_BEFS_FS=m -CONFIG_BFS_FS=m -CONFIG_EFS_FS=m -CONFIG_CRAMFS=m -CONFIG_VXFS_FS=m -CONFIG_MINIX_FS=m -CONFIG_HPFS_FS=m -CONFIG_QNX4FS_FS=m -CONFIG_ROMFS_FS=m -CONFIG_SYSV_FS=m CONFIG_UFS_FS=m CONFIG_NFS_FS=m CONFIG_NFSD=m CONFIG_NFSD_V3=y CONFIG_CIFS=m -CONFIG_CODA_FS=m -CONFIG_AFS_FS=m -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRC_CCITT=m diff --git a/arch/mips/configs/lasat_defconfig b/arch/mips/configs/lasat_defconfig index c66ca3785655..00cf461db971 100644 --- a/arch/mips/configs/lasat_defconfig +++ b/arch/mips/configs/lasat_defconfig @@ -16,8 +16,6 @@ CONFIG_HZ_1000=y # CONFIG_SECCOMP is not set CONFIG_PCI=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index f9f93427c9bd..8254d7d1396f 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -26,7 +26,7 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_BLK_DEV_INTEGRITY=y -CONFIG_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_BINFMT_MISC=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index 360c6b2d397a..51675f5000d6 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -38,8 +38,9 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_PARTITION_ADVANCED=y -CONFIG_IOSCHED_DEADLINE=m -CONFIG_CFQ_GROUP_IOSCHED=y +CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_IOSCHED_BFQ=y +CONFIG_BFQ_GROUP_IOSCHED=y CONFIG_BINFMT_MISC=m CONFIG_KSM=y CONFIG_NET=y diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig index 59eedf55419d..211bd3d6e6cb 100644 --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@ -239,7 +239,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig index 8ef612552a19..62b1969b4f55 100644 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@ -247,7 +247,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig index d2a008c9907c..9185e0a0aa45 100644 --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@ -245,7 +245,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig index 970df6d42728..636311d67a53 100644 --- a/arch/mips/configs/maltaup_xpa_defconfig +++ b/arch/mips/configs/maltaup_xpa_defconfig @@ -245,7 +245,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/mips/configs/msp71xx_defconfig b/arch/mips/configs/msp71xx_defconfig index 0fdc03fda12e..6ad1a2381226 100644 --- a/arch/mips/configs/msp71xx_defconfig +++ b/arch/mips/configs/msp71xx_defconfig @@ -14,8 +14,6 @@ CONFIG_PCI=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_UNIX=y CONFIG_XFRM_USER=y diff --git a/arch/mips/configs/pnx8335_stb225_defconfig b/arch/mips/configs/pnx8335_stb225_defconfig index 738ba3b1374b..d06db6b87959 100644 --- a/arch/mips/configs/pnx8335_stb225_defconfig +++ b/arch/mips/configs/pnx8335_stb225_defconfig @@ -14,8 +14,6 @@ CONFIG_HZ_128=y CONFIG_MODULES=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_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig index 5b947183852b..252d472387aa 100644 --- a/arch/mips/configs/rb532_defconfig +++ b/arch/mips/configs/rb532_defconfig @@ -23,7 +23,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_PARTITION_ADVANCED=y CONFIG_MAC_PARTITION=y CONFIG_BSD_DISKLABEL=y -# CONFIG_IOSCHED_CFQ is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index 2c7adea7638f..30d7c3db884e 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -203,7 +203,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig index 110948bc6b39..8c2ead53007a 100644 --- a/arch/mips/configs/rt305x_defconfig +++ b/arch/mips/configs/rt305x_defconfig @@ -21,7 +21,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set # CONFIG_COREDUMP is not set # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig index 49b5ea6eff62..9abbc0debc2a 100644 --- a/arch/mips/configs/xway_defconfig +++ b/arch/mips/configs/xway_defconfig @@ -23,7 +23,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y -# CONFIG_IOSCHED_CFQ is not set # CONFIG_COREDUMP is not set # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index 61a0bf13e308..d4e868b828e5 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -103,28 +103,8 @@ int_ptr asic_mask_nr_tbl[DEC_MAX_ASIC_INTS][2] = { int cpu_fpu_mask = DEC_CPU_IRQ_MASK(DEC_CPU_INR_FPU); int *fpu_kstat_irq; -static struct irqaction ioirq = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; -static struct irqaction fpuirq = { - .handler = no_action, - .name = "fpu", - .flags = IRQF_NO_THREAD, -}; - -static struct irqaction busirq = { - .name = "bus error", - .flags = IRQF_NO_THREAD, -}; - -static struct irqaction haltirq = { - .handler = dec_intr_halt, - .name = "halt", - .flags = IRQF_NO_THREAD, -}; - +static irq_handler_t busirq_handler; +static unsigned int busirq_flags = IRQF_NO_THREAD; /* * Bus error (DBE/IBE exceptions and bus interrupts) handling setup. @@ -134,21 +114,21 @@ static void __init dec_be_init(void) switch (mips_machtype) { case MACH_DS23100: /* DS2100/DS3100 Pmin/Pmax */ board_be_handler = dec_kn01_be_handler; - busirq.handler = dec_kn01_be_interrupt; - busirq.flags |= IRQF_SHARED; + busirq_handler = dec_kn01_be_interrupt; + busirq_flags |= IRQF_SHARED; dec_kn01_be_init(); break; case MACH_DS5000_1XX: /* DS5000/1xx 3min */ case MACH_DS5000_XX: /* DS5000/xx Maxine */ board_be_handler = dec_kn02xa_be_handler; - busirq.handler = dec_kn02xa_be_interrupt; + busirq_handler = dec_kn02xa_be_interrupt; dec_kn02xa_be_init(); break; case MACH_DS5000_200: /* DS5000/200 3max */ case MACH_DS5000_2X0: /* DS5000/240 3max+ */ case MACH_DS5900: /* DS5900 bigmax */ board_be_handler = dec_ecc_be_handler; - busirq.handler = dec_ecc_be_interrupt; + busirq_handler = dec_ecc_be_interrupt; dec_ecc_be_init(); break; } @@ -764,20 +744,29 @@ void __init arch_init_irq(void) int irq_fpu; irq_fpu = dec_interrupt[DEC_IRQ_FPU]; - setup_irq(irq_fpu, &fpuirq); + if (request_irq(irq_fpu, no_action, IRQF_NO_THREAD, "fpu", + NULL)) + pr_err("Failed to register fpu interrupt\n"); desc_fpu = irq_to_desc(irq_fpu); fpu_kstat_irq = this_cpu_ptr(desc_fpu->kstat_irqs); } - if (dec_interrupt[DEC_IRQ_CASCADE] >= 0) - setup_irq(dec_interrupt[DEC_IRQ_CASCADE], &ioirq); - + if (dec_interrupt[DEC_IRQ_CASCADE] >= 0) { + if (request_irq(dec_interrupt[DEC_IRQ_CASCADE], no_action, + IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to register cascade interrupt\n"); + } /* Register the bus error interrupt. */ - if (dec_interrupt[DEC_IRQ_BUS] >= 0 && busirq.handler) - setup_irq(dec_interrupt[DEC_IRQ_BUS], &busirq); - + if (dec_interrupt[DEC_IRQ_BUS] >= 0 && busirq_handler) { + if (request_irq(dec_interrupt[DEC_IRQ_BUS], busirq_handler, + busirq_flags, "bus error", busirq_handler)) + pr_err("Failed to register bus error interrupt\n"); + } /* Register the HALT interrupt. */ - if (dec_interrupt[DEC_IRQ_HALT] >= 0) - setup_irq(dec_interrupt[DEC_IRQ_HALT], &haltirq); + if (dec_interrupt[DEC_IRQ_HALT] >= 0) { + if (request_irq(dec_interrupt[DEC_IRQ_HALT], dec_intr_halt, + IRQF_NO_THREAD, "halt", NULL)) + pr_err("Failed to register halt interrupt\n"); + } } asmlinkage unsigned int dec_irq_dispatch(unsigned int irq) diff --git a/arch/mips/emma/markeins/irq.c b/arch/mips/emma/markeins/irq.c index 09427a49e7ae..4aebf559be2e 100644 --- a/arch/mips/emma/markeins/irq.c +++ b/arch/mips/emma/markeins/irq.c @@ -153,14 +153,6 @@ void emma2rh_gpio_irq_init(void) handle_edge_irq, "edge"); } -static struct irqaction irq_cascade = { - .handler = no_action, - .flags = IRQF_NO_THREAD, - .name = "cascade", - .dev_id = NULL, - .next = NULL, -}; - /* * the first level int-handler will jump here if it is a emma2rh irq */ @@ -236,6 +228,7 @@ void emma2rh_irq_dispatch(void) void __init arch_init_irq(void) { u32 reg; + int irq; /* by default, interrupts are disabled. */ emma2rh_out32(EMMA2RH_BHIF_INT_EN_0, 0); @@ -272,9 +265,15 @@ void __init arch_init_irq(void) mips_cpu_irq_init(); /* setup cascade interrupts */ - setup_irq(EMMA2RH_IRQ_BASE + EMMA2RH_SW_CASCADE, &irq_cascade); - setup_irq(EMMA2RH_IRQ_BASE + EMMA2RH_GPIO_CASCADE, &irq_cascade); - setup_irq(MIPS_CPU_IRQ_BASE + 2, &irq_cascade); + irq = EMMA2RH_IRQ_BASE + EMMA2RH_SW_CASCADE; + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", irq); + irq = EMMA2RH_IRQ_BASE + EMMA2RH_GPIO_CASCADE; + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", irq); + irq = MIPS_CPU_IRQ_BASE + 2; + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", irq); } asmlinkage void plat_irq_dispatch(void) diff --git a/arch/mips/fw/lib/cmdline.c b/arch/mips/fw/lib/cmdline.c index 6ecda64ad184..f24cbb4a39b5 100644 --- a/arch/mips/fw/lib/cmdline.c +++ b/arch/mips/fw/lib/cmdline.c @@ -16,6 +16,7 @@ int fw_argc; int *_fw_argv; int *_fw_envp; +#ifndef CONFIG_HAVE_PLAT_FW_INIT_CMDLINE void __init fw_init_cmdline(void) { int i; @@ -41,6 +42,7 @@ void __init fw_init_cmdline(void) strlcat(arcs_cmdline, " ", COMMAND_LINE_SIZE); } } +#endif char * __init fw_getcmdline(void) { diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index 1de215b283d6..805d0135a9f4 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -5,10 +5,10 @@ */ #include <linux/clk.h> -#include <linux/clk-provider.h> #include <linux/clocksource.h> #include <linux/init.h> #include <linux/irqchip.h> +#include <linux/of_clk.h> #include <linux/of_fdt.h> #include <asm/bootinfo.h> diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 4ebd8ce254ce..8643d313890e 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -4,23 +4,10 @@ generated-y += syscall_table_32_o32.h generated-y += syscall_table_64_n32.h generated-y += syscall_table_64_n64.h generated-y += syscall_table_64_o32.h -generic-y += current.h -generic-y += device.h -generic-y += emergency-restart.h generic-y += export.h -generic-y += irq_work.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h generic-y += parport.h -generic-y += percpu.h -generic-y += preempt.h generic-y += qrwlock.h generic-y += qspinlock.h -generic-y += sections.h -generic-y += serial.h -generic-y += trace_clock.h -generic-y += unaligned.h generic-y += user.h -generic-y += word-at-a-time.h -generic-y += xor.h diff --git a/arch/mips/include/asm/clocksource.h b/arch/mips/include/asm/clocksource.h index cab9ae9f1e14..2f1ebbea3d72 100644 --- a/arch/mips/include/asm/clocksource.h +++ b/arch/mips/include/asm/clocksource.h @@ -3,23 +3,9 @@ * Copyright (C) 2015 Imagination Technologies * Author: Alex Smith <alex.smith@imgtec.com> */ - #ifndef __ASM_CLOCKSOURCE_H #define __ASM_CLOCKSOURCE_H -#include <linux/types.h> - -/* VDSO clocksources. */ -#define VDSO_CLOCK_NONE 0 /* No suitable clocksource. */ -#define VDSO_CLOCK_R4K 1 /* Use the coprocessor 0 count. */ -#define VDSO_CLOCK_GIC 2 /* Use the GIC. */ - -/** - * struct arch_clocksource_data - Architecture-specific clocksource information. - * @vdso_clock_mode: Method the VDSO should use to access the clocksource. - */ -struct arch_clocksource_data { - u8 vdso_clock_mode; -}; +#include <asm/vdso/clocksource.h> #endif /* __ASM_CLOCKSOURCE_H */ diff --git a/arch/mips/include/asm/dmi.h b/arch/mips/include/asm/dmi.h new file mode 100644 index 000000000000..27415a288adf --- /dev/null +++ b/arch/mips/include/asm/dmi.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_DMI_H +#define _ASM_DMI_H + +#include <linux/io.h> +#include <linux/memblock.h> + +#define dmi_early_remap(x, l) ioremap_cache(x, l) +#define dmi_early_unmap(x, l) iounmap(x) +#define dmi_remap(x, l) ioremap_cache(x, l) +#define dmi_unmap(x) iounmap(x) + +/* MIPS initialize DMI scan before SLAB is ready, so we use memblock here */ +#define dmi_alloc(l) memblock_alloc_low(l, PAGE_SIZE) + +#if defined(CONFIG_MACH_LOONGSON64) +#define SMBIOS_ENTRY_POINT_SCAN_START 0xFFFE000 +#endif + +#endif /* _ASM_DMI_H */ diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index f8f44b1a6cbb..5aa29ced6970 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -445,6 +445,9 @@ extern unsigned int elf_hwcap; #define ELF_PLATFORM __elf_platform extern const char *__elf_platform; +#define ELF_BASE_PLATFORM __elf_base_platform +extern const char *__elf_base_platform; + /* * See comments in asm-alpha/elf.h, this is the same thing * on the MIPS. 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/i8259.h b/arch/mips/include/asm/i8259.h index 97a5e41ed1ab..a54b9649de22 100644 --- a/arch/mips/include/asm/i8259.h +++ b/arch/mips/include/asm/i8259.h @@ -36,6 +36,7 @@ extern raw_spinlock_t i8259A_lock; extern void make_8259A_irq(unsigned int irq); extern void init_i8259_irqs(void); +extern struct irq_domain *__init_i8259_irqs(struct device_node *node); /** * i8159_set_poll() - Override the i8259 polling function diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 41204a49cf95..2c343c346b79 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -1133,7 +1133,7 @@ extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm); static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, - struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} + struct kvm_memory_slot *slot) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} diff --git a/arch/mips/include/asm/mach-ar7/irq.h b/arch/mips/include/asm/mach-ar7/irq.h index 7ad10e379e2b..46bb730ea970 100644 --- a/arch/mips/include/asm/mach-ar7/irq.h +++ b/arch/mips/include/asm/mach-ar7/irq.h @@ -11,6 +11,6 @@ #define NR_IRQS 256 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __ASM_AR7_IRQ_H */ diff --git a/arch/mips/include/asm/mach-ath79/irq.h b/arch/mips/include/asm/mach-ath79/irq.h index 2df1abf9e5af..882534be0715 100644 --- a/arch/mips/include/asm/mach-ath79/irq.h +++ b/arch/mips/include/asm/mach-ath79/irq.h @@ -27,6 +27,6 @@ #define ATH79_IP3_IRQ_COUNT 3 #define ATH79_IP3_IRQ(_x) (ATH79_IP3_IRQ_BASE + (_x)) -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __ASM_MACH_ATH79_IRQ_H */ diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_ide.h b/arch/mips/include/asm/mach-au1x00/au1xxx_ide.h deleted file mode 100644 index bb91b8923a49..000000000000 --- a/arch/mips/include/asm/mach-au1x00/au1xxx_ide.h +++ /dev/null @@ -1,178 +0,0 @@ -/* - * include/asm-mips/mach-au1x00/au1xxx_ide.h version 01.30.00 Aug. 02 2005 - * - * BRIEF MODULE DESCRIPTION - * AMD Alchemy Au1xxx IDE interface routines over the Static Bus - * - * Copyright (c) 2003-2005 AMD, Personal Connectivity Solutions - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License as published by the Free Software - * Foundation; either version 2 of the License, or (at your option) any later - * version. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, - * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND - * FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR - * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - * - * Note: for more information, please refer "AMD Alchemy Au1200/Au1550 IDE - * Interface and Linux Device Driver" Application Note. - */ - -#ifdef CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA -#define DMA_WAIT_TIMEOUT 100 -#define NUM_DESCRIPTORS PRD_ENTRIES -#else /* CONFIG_BLK_DEV_IDE_AU1XXX_PIO_DBDMA */ -#define NUM_DESCRIPTORS 2 -#endif - -#ifndef AU1XXX_ATA_RQSIZE -#define AU1XXX_ATA_RQSIZE 128 -#endif - -/* Disable Burstable-Support for DBDMA */ -#ifndef CONFIG_BLK_DEV_IDE_AU1XXX_BURSTABLE_ON -#define CONFIG_BLK_DEV_IDE_AU1XXX_BURSTABLE_ON 0 -#endif - -typedef struct { - u32 tx_dev_id, rx_dev_id, target_dev_id; - u32 tx_chan, rx_chan; - void *tx_desc_head, *rx_desc_head; - ide_hwif_t *hwif; -#ifdef CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA - ide_drive_t *drive; - struct dbdma_cmd *dma_table_cpu; - dma_addr_t dma_table_dma; -#endif - int irq; - u32 regbase; - int ddma_id; -} _auide_hwif; - -/******************************************************************************/ -/* PIO Mode timing calculation : */ -/* */ -/* Static Bus Spec ATA Spec */ -/* Tcsoe = t1 */ -/* Toecs = t9 */ -/* Twcs = t9 */ -/* Tcsh = t2i | t2 */ -/* Tcsoff = t2i | t2 */ -/* Twp = t2 */ -/* Tcsw = t1 */ -/* Tpm = 0 */ -/* Ta = t1+t2 */ -/******************************************************************************/ - -#define TCSOE_MASK (0x07 << 29) -#define TOECS_MASK (0x07 << 26) -#define TWCS_MASK (0x07 << 28) -#define TCSH_MASK (0x0F << 24) -#define TCSOFF_MASK (0x07 << 20) -#define TWP_MASK (0x3F << 14) -#define TCSW_MASK (0x0F << 10) -#define TPM_MASK (0x0F << 6) -#define TA_MASK (0x3F << 0) -#define TS_MASK (1 << 8) - -/* Timing parameters PIO mode 0 */ -#define SBC_IDE_PIO0_TCSOE (0x04 << 29) -#define SBC_IDE_PIO0_TOECS (0x01 << 26) -#define SBC_IDE_PIO0_TWCS (0x02 << 28) -#define SBC_IDE_PIO0_TCSH (0x08 << 24) -#define SBC_IDE_PIO0_TCSOFF (0x07 << 20) -#define SBC_IDE_PIO0_TWP (0x10 << 14) -#define SBC_IDE_PIO0_TCSW (0x04 << 10) -#define SBC_IDE_PIO0_TPM (0x00 << 6) -#define SBC_IDE_PIO0_TA (0x15 << 0) -/* Timing parameters PIO mode 1 */ -#define SBC_IDE_PIO1_TCSOE (0x03 << 29) -#define SBC_IDE_PIO1_TOECS (0x01 << 26) -#define SBC_IDE_PIO1_TWCS (0x01 << 28) -#define SBC_IDE_PIO1_TCSH (0x06 << 24) -#define SBC_IDE_PIO1_TCSOFF (0x06 << 20) -#define SBC_IDE_PIO1_TWP (0x08 << 14) -#define SBC_IDE_PIO1_TCSW (0x03 << 10) -#define SBC_IDE_PIO1_TPM (0x00 << 6) -#define SBC_IDE_PIO1_TA (0x0B << 0) -/* Timing parameters PIO mode 2 */ -#define SBC_IDE_PIO2_TCSOE (0x05 << 29) -#define SBC_IDE_PIO2_TOECS (0x01 << 26) -#define SBC_IDE_PIO2_TWCS (0x01 << 28) -#define SBC_IDE_PIO2_TCSH (0x07 << 24) -#define SBC_IDE_PIO2_TCSOFF (0x07 << 20) -#define SBC_IDE_PIO2_TWP (0x1F << 14) -#define SBC_IDE_PIO2_TCSW (0x05 << 10) -#define SBC_IDE_PIO2_TPM (0x00 << 6) -#define SBC_IDE_PIO2_TA (0x22 << 0) -/* Timing parameters PIO mode 3 */ -#define SBC_IDE_PIO3_TCSOE (0x05 << 29) -#define SBC_IDE_PIO3_TOECS (0x01 << 26) -#define SBC_IDE_PIO3_TWCS (0x01 << 28) -#define SBC_IDE_PIO3_TCSH (0x0D << 24) -#define SBC_IDE_PIO3_TCSOFF (0x0D << 20) -#define SBC_IDE_PIO3_TWP (0x15 << 14) -#define SBC_IDE_PIO3_TCSW (0x05 << 10) -#define SBC_IDE_PIO3_TPM (0x00 << 6) -#define SBC_IDE_PIO3_TA (0x1A << 0) -/* Timing parameters PIO mode 4 */ -#define SBC_IDE_PIO4_TCSOE (0x04 << 29) -#define SBC_IDE_PIO4_TOECS (0x01 << 26) -#define SBC_IDE_PIO4_TWCS (0x01 << 28) -#define SBC_IDE_PIO4_TCSH (0x04 << 24) -#define SBC_IDE_PIO4_TCSOFF (0x04 << 20) -#define SBC_IDE_PIO4_TWP (0x0D << 14) -#define SBC_IDE_PIO4_TCSW (0x03 << 10) -#define SBC_IDE_PIO4_TPM (0x00 << 6) -#define SBC_IDE_PIO4_TA (0x12 << 0) -/* Timing parameters MDMA mode 0 */ -#define SBC_IDE_MDMA0_TCSOE (0x03 << 29) -#define SBC_IDE_MDMA0_TOECS (0x01 << 26) -#define SBC_IDE_MDMA0_TWCS (0x01 << 28) -#define SBC_IDE_MDMA0_TCSH (0x07 << 24) -#define SBC_IDE_MDMA0_TCSOFF (0x07 << 20) -#define SBC_IDE_MDMA0_TWP (0x0C << 14) -#define SBC_IDE_MDMA0_TCSW (0x03 << 10) -#define SBC_IDE_MDMA0_TPM (0x00 << 6) -#define SBC_IDE_MDMA0_TA (0x0F << 0) -/* Timing parameters MDMA mode 1 */ -#define SBC_IDE_MDMA1_TCSOE (0x05 << 29) -#define SBC_IDE_MDMA1_TOECS (0x01 << 26) -#define SBC_IDE_MDMA1_TWCS (0x01 << 28) -#define SBC_IDE_MDMA1_TCSH (0x05 << 24) -#define SBC_IDE_MDMA1_TCSOFF (0x05 << 20) -#define SBC_IDE_MDMA1_TWP (0x0F << 14) -#define SBC_IDE_MDMA1_TCSW (0x05 << 10) -#define SBC_IDE_MDMA1_TPM (0x00 << 6) -#define SBC_IDE_MDMA1_TA (0x15 << 0) -/* Timing parameters MDMA mode 2 */ -#define SBC_IDE_MDMA2_TCSOE (0x04 << 29) -#define SBC_IDE_MDMA2_TOECS (0x01 << 26) -#define SBC_IDE_MDMA2_TWCS (0x01 << 28) -#define SBC_IDE_MDMA2_TCSH (0x04 << 24) -#define SBC_IDE_MDMA2_TCSOFF (0x04 << 20) -#define SBC_IDE_MDMA2_TWP (0x0D << 14) -#define SBC_IDE_MDMA2_TCSW (0x04 << 10) -#define SBC_IDE_MDMA2_TPM (0x00 << 6) -#define SBC_IDE_MDMA2_TA (0x12 << 0) - -#define SBC_IDE_TIMING(mode) \ - (SBC_IDE_##mode##_TWCS | \ - SBC_IDE_##mode##_TCSH | \ - SBC_IDE_##mode##_TCSOFF | \ - SBC_IDE_##mode##_TWP | \ - SBC_IDE_##mode##_TCSW | \ - SBC_IDE_##mode##_TPM | \ - SBC_IDE_##mode##_TA) diff --git a/arch/mips/include/asm/mach-emma2rh/irq.h b/arch/mips/include/asm/mach-emma2rh/irq.h index 2f7155dade29..d32736736bb3 100644 --- a/arch/mips/include/asm/mach-emma2rh/irq.h +++ b/arch/mips/include/asm/mach-emma2rh/irq.h @@ -10,6 +10,6 @@ #define NR_IRQS 256 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __ASM_MACH_EMMA2RH_IRQ_H */ diff --git a/arch/mips/include/asm/mach-ip27/irq.h b/arch/mips/include/asm/mach-ip27/irq.h index fd91c58aaf7d..f45d7999fd73 100644 --- a/arch/mips/include/asm/mach-ip27/irq.h +++ b/arch/mips/include/asm/mach-ip27/irq.h @@ -12,7 +12,7 @@ #define NR_IRQS 256 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #define IP27_HUB_PEND0_IRQ (MIPS_CPU_IRQ_BASE + 2) #define IP27_HUB_PEND1_IRQ (MIPS_CPU_IRQ_BASE + 3) diff --git a/arch/mips/include/asm/mach-ip30/irq.h b/arch/mips/include/asm/mach-ip30/irq.h index e5c3dd965266..27ba899c95be 100644 --- a/arch/mips/include/asm/mach-ip30/irq.h +++ b/arch/mips/include/asm/mach-ip30/irq.h @@ -76,7 +76,7 @@ extern void __init ip30_install_ipi(void); */ #define IP30_POWER_IRQ HEART_L2_INT_POWER_BTN -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #define IP30_HEART_L0_IRQ (MIPS_CPU_IRQ_BASE + 2) #define IP30_HEART_L1_IRQ (MIPS_CPU_IRQ_BASE + 3) diff --git a/arch/mips/include/asm/mach-lantiq/falcon/irq.h b/arch/mips/include/asm/mach-lantiq/falcon/irq.h index 91d2bc03c9fa..c14312fb0574 100644 --- a/arch/mips/include/asm/mach-lantiq/falcon/irq.h +++ b/arch/mips/include/asm/mach-lantiq/falcon/irq.h @@ -11,6 +11,6 @@ #define NR_IRQS 328 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif diff --git a/arch/mips/include/asm/mach-lantiq/xway/irq.h b/arch/mips/include/asm/mach-lantiq/xway/irq.h index 76ebbf6c50ef..2980e7771f83 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/irq.h +++ b/arch/mips/include/asm/mach-lantiq/xway/irq.h @@ -11,6 +11,6 @@ #define NR_IRQS 256 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif diff --git a/arch/mips/include/asm/mach-lasat/irq.h b/arch/mips/include/asm/mach-lasat/irq.h index d79cbe075084..e8994921779e 100644 --- a/arch/mips/include/asm/mach-lasat/irq.h +++ b/arch/mips/include/asm/mach-lasat/irq.h @@ -9,6 +9,6 @@ #define NR_IRQS 24 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* _ASM_MACH_LASAT_IRQ_H */ diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index 8c286bedff3e..2ed483e32d8c 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -2,6 +2,8 @@ #ifndef __ASM_MACH_LOONGSON64_BOOT_PARAM_H_ #define __ASM_MACH_LOONGSON64_BOOT_PARAM_H_ +#include <linux/types.h> + #define SYSTEM_RAM_LOW 1 #define SYSTEM_RAM_HIGH 2 #define SYSTEM_RAM_RESERVED 3 diff --git a/arch/mips/include/asm/mach-loongson64/builtin_dtbs.h b/arch/mips/include/asm/mach-loongson64/builtin_dtbs.h new file mode 100644 index 000000000000..853c6d80887b --- /dev/null +++ b/arch/mips/include/asm/mach-loongson64/builtin_dtbs.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2019 Jiaxun Yang <jiaxun.yang@flygoat.com> + * + * Built-in Generic dtbs for MACH_LOONGSON64 + */ + +#ifndef __ASM_MACH_LOONGSON64_BUILTIN_DTBS_H_ +#define __ASM_MACH_LOONGSON64_BUILTIN_DTBS_H_ + +extern u32 __dtb_loongson3_4core_rs780e_begin[]; +extern u32 __dtb_loongson3_8core_rs780e_begin[]; +#endif diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index 73a89913dc38..d41dc4a76e6d 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -7,34 +7,6 @@ /* cpu core interrupt numbers */ #define MIPS_CPU_IRQ_BASE 56 -#define LOONGSON_UART_IRQ (MIPS_CPU_IRQ_BASE + 2) /* UART */ -#define LOONGSON_BRIDGE_IRQ (MIPS_CPU_IRQ_BASE + 3) /* CASCADE */ -#define LOONGSON_TIMER_IRQ (MIPS_CPU_IRQ_BASE + 7) /* CPU Timer */ +#include <asm/mach-generic/irq.h> -#define LOONGSON_HT1_CFG_BASE loongson_sysconf.ht_control_base -#define LOONGSON_HT1_INT_VECTOR_BASE (LOONGSON_HT1_CFG_BASE + 0x80) -#define LOONGSON_HT1_INT_EN_BASE (LOONGSON_HT1_CFG_BASE + 0xa0) -#define LOONGSON_HT1_INT_VECTOR(n) \ - LOONGSON3_REG32(LOONGSON_HT1_INT_VECTOR_BASE, 4 * (n)) -#define LOONGSON_HT1_INTN_EN(n) \ - LOONGSON3_REG32(LOONGSON_HT1_INT_EN_BASE, 4 * (n)) - -#define LOONGSON_INT_ROUTER_OFFSET 0x1400 -#define LOONGSON_INT_ROUTER_INTEN \ - LOONGSON3_REG32(LOONGSON3_REG_BASE, LOONGSON_INT_ROUTER_OFFSET + 0x24) -#define LOONGSON_INT_ROUTER_INTENSET \ - LOONGSON3_REG32(LOONGSON3_REG_BASE, LOONGSON_INT_ROUTER_OFFSET + 0x28) -#define LOONGSON_INT_ROUTER_INTENCLR \ - LOONGSON3_REG32(LOONGSON3_REG_BASE, LOONGSON_INT_ROUTER_OFFSET + 0x2c) -#define LOONGSON_INT_ROUTER_ENTRY(n) \ - LOONGSON3_REG8(LOONGSON3_REG_BASE, LOONGSON_INT_ROUTER_OFFSET + n) -#define LOONGSON_INT_ROUTER_LPC LOONGSON_INT_ROUTER_ENTRY(0x0a) -#define LOONGSON_INT_ROUTER_HT1(n) LOONGSON_INT_ROUTER_ENTRY(n + 0x18) - -#define LOONGSON_INT_COREx_INTy(x, y) (1<<(x) | 1<<(y+4)) /* route to int y of core x */ - -extern void fixup_irqs(void); -extern void loongson3_ipi_interrupt(struct pt_regs *regs); - -#include_next <irq.h> #endif /* __ASM_MACH_LOONGSON64_IRQ_H_ */ diff --git a/arch/mips/include/asm/mach-loongson64/loongson.h b/arch/mips/include/asm/mach-loongson64/loongson.h index a8fce112a9b0..fde1b75c45ea 100644 --- a/arch/mips/include/asm/mach-loongson64/loongson.h +++ b/arch/mips/include/asm/mach-loongson64/loongson.h @@ -25,6 +25,7 @@ extern const struct plat_smp_ops loongson3_smp_ops; /* loongson-specific command line, env and memory initialization */ extern void __init prom_init_memory(void); extern void __init prom_init_env(void); +extern void *loongson_fdt_blob; /* irq operation functions */ extern void mach_irq_dispatch(unsigned int pending); diff --git a/arch/mips/include/asm/mach-malta/irq.h b/arch/mips/include/asm/mach-malta/irq.h index af9eeea250ed..e1bd4298b606 100644 --- a/arch/mips/include/asm/mach-malta/irq.h +++ b/arch/mips/include/asm/mach-malta/irq.h @@ -5,6 +5,6 @@ #define NR_IRQS 256 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __ASM_MACH_MIPS_IRQ_H */ diff --git a/arch/mips/include/asm/mach-pic32/irq.h b/arch/mips/include/asm/mach-pic32/irq.h index d2396941ed2a..ddaf999bc650 100644 --- a/arch/mips/include/asm/mach-pic32/irq.h +++ b/arch/mips/include/asm/mach-pic32/irq.h @@ -9,6 +9,6 @@ #define NR_IRQS 256 #define MIPS_CPU_IRQ_BASE 0 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __ASM_MACH_PIC32_IRQ_H */ diff --git a/arch/mips/include/asm/mach-pistachio/irq.h b/arch/mips/include/asm/mach-pistachio/irq.h index 93bc380f9536..74ac016503ad 100644 --- a/arch/mips/include/asm/mach-pistachio/irq.h +++ b/arch/mips/include/asm/mach-pistachio/irq.h @@ -10,6 +10,6 @@ #define NR_IRQS 256 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __ASM_MACH_PISTACHIO_IRQ_H */ diff --git a/arch/mips/include/asm/mach-ralink/irq.h b/arch/mips/include/asm/mach-ralink/irq.h index 86473e3999aa..2262243d19c9 100644 --- a/arch/mips/include/asm/mach-ralink/irq.h +++ b/arch/mips/include/asm/mach-ralink/irq.h @@ -5,6 +5,6 @@ #define GIC_NUM_INTRS 64 #define NR_IRQS 256 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif diff --git a/arch/mips/include/asm/mach-rm/mc146818rtc.h b/arch/mips/include/asm/mach-rm/mc146818rtc.h index 145bce096fe9..a074f4f84f75 100644 --- a/arch/mips/include/asm/mach-rm/mc146818rtc.h +++ b/arch/mips/include/asm/mach-rm/mc146818rtc.h @@ -16,6 +16,6 @@ #define mc146818_decode_year(year) ((year) + 1980) #endif -#include_next <mc146818rtc.h> +#include <asm/mach-generic/mc146818rtc.h> #endif /* __ASM_MACH_RM_MC146818RTC_H */ diff --git a/arch/mips/include/asm/mach-vr41xx/irq.h b/arch/mips/include/asm/mach-vr41xx/irq.h index 3d63afae37a8..4281b2b9344d 100644 --- a/arch/mips/include/asm/mach-vr41xx/irq.h +++ b/arch/mips/include/asm/mach-vr41xx/irq.h @@ -4,6 +4,6 @@ #include <asm/vr41xx/irq.h> /* for MIPS_CPU_IRQ_BASE */ -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __ASM_MACH_VR41XX_IRQ_H */ diff --git a/arch/mips/include/asm/mach-xilfpga/irq.h b/arch/mips/include/asm/mach-xilfpga/irq.h index b8e93fa8adcf..15ad29ec1dee 100644 --- a/arch/mips/include/asm/mach-xilfpga/irq.h +++ b/arch/mips/include/asm/mach-xilfpga/irq.h @@ -9,6 +9,6 @@ #define NR_IRQS 32 -#include_next <irq.h> +#include <asm/mach-generic/irq.h> #endif /* __MIPS_ASM_MACH_XILFPGA_IRQ_H__ */ 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/processor.h b/arch/mips/include/asm/processor.h index 7619ad319400..856e12f6063d 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -22,6 +22,7 @@ #include <asm/dsemul.h> #include <asm/mipsregs.h> #include <asm/prefetch.h> +#include <asm/vdso/processor.h> /* * System setup and hardware flags.. @@ -253,13 +254,13 @@ struct thread_struct { #ifdef CONFIG_MIPS_FP_SUPPORT /* Saved fpu/fpu emulator stuff. */ struct mips_fpu_struct fpu FPU_ALIGN; -#endif /* Assigned branch delay slot 'emulation' frame */ atomic_t bd_emu_frame; /* PC of the branch from a branch delay slot 'emulation' */ unsigned long bd_emu_branch_pc; /* PC to continue from following a branch delay slot 'emulation' */ unsigned long bd_emu_cont_pc; +#endif #ifdef CONFIG_MIPS_MT_FPAFF /* Emulated instruction count */ unsigned long emulated_fp; @@ -302,7 +303,11 @@ struct thread_struct { .fpr = {{{0,},},}, \ .fcr31 = 0, \ .msacsr = 0, \ - }, + }, \ + /* Delay slot emulation */ \ + .bd_emu_frame = ATOMIC_INIT(BD_EMUFRAME_NONE), \ + .bd_emu_branch_pc = 0, \ + .bd_emu_cont_pc = 0, #else # define FPU_INIT #endif @@ -334,10 +339,6 @@ struct thread_struct { * FPU affinity state (null if not FPAFF) \ */ \ FPAFF_INIT \ - /* Delay slot emulation */ \ - .bd_emu_frame = ATOMIC_INIT(BD_EMUFRAME_NONE), \ - .bd_emu_branch_pc = 0, \ - .bd_emu_cont_pc = 0, \ /* \ * Saved DSP stuff \ */ \ @@ -385,21 +386,6 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29]) #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status) -#ifdef CONFIG_CPU_LOONGSON64 -/* - * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a - * tight read loop is executed, because reads take priority over writes & the - * hardware (incorrectly) doesn't ensure that writes will eventually occur. - * - * Since spin loops of any kind should have a cpu_relax() in them, force an SFB - * flush from cpu_relax() such that any pending writes will become visible as - * expected. - */ -#define cpu_relax() smp_mb() -#else -#define cpu_relax() barrier() -#endif - /* * Return_address is a replacement for __builtin_return_address(count) * which on certain architectures cannot reasonably be implemented in GCC diff --git a/arch/mips/include/asm/sni.h b/arch/mips/include/asm/sni.h index a107201a2e1e..7dfa297ce597 100644 --- a/arch/mips/include/asm/sni.h +++ b/arch/mips/include/asm/sni.h @@ -11,6 +11,8 @@ #ifndef __ASM_SNI_H #define __ASM_SNI_H +#include <linux/irqreturn.h> + extern unsigned int sni_brd_type; #define SNI_BRD_10 2 @@ -239,6 +241,6 @@ static inline int sni_eisa_root_init(void) /* common irq stuff */ extern void (*sni_hwint)(void); -extern struct irqaction sni_isa_irq; +extern irqreturn_t sni_isa_irq_handler(int dummy, void *p); #endif /* __ASM_SNI_H */ 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/include/asm/vdso/clocksource.h b/arch/mips/include/asm/vdso/clocksource.h new file mode 100644 index 000000000000..510e1671d898 --- /dev/null +++ b/arch/mips/include/asm/vdso/clocksource.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef __ASM_VDSOCLOCKSOURCE_H +#define __ASM_VDSOCLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES \ + VDSO_CLOCKMODE_R4K, \ + VDSO_CLOCKMODE_GIC + +#endif /* __ASM_VDSOCLOCKSOURCE_H */ diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h index a58687e26c5d..c63ddcaea54c 100644 --- a/arch/mips/include/asm/vdso/gettimeofday.h +++ b/arch/mips/include/asm/vdso/gettimeofday.h @@ -13,19 +13,13 @@ #ifndef __ASSEMBLY__ -#include <linux/compiler.h> -#include <linux/time.h> - #include <asm/vdso/vdso.h> #include <asm/clocksource.h> -#include <asm/io.h> #include <asm/unistd.h> #include <asm/vdso.h> #define VDSO_HAS_CLOCK_GETRES 1 -#define __VDSO_USE_SYSCALL ULLONG_MAX - static __always_inline long gettimeofday_fallback( struct __kernel_old_timeval *_tv, struct timezone *_tz) @@ -175,29 +169,28 @@ static __always_inline u64 read_gic_count(const struct vdso_data *data) static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) { -#ifdef CONFIG_CLKSRC_MIPS_GIC - const struct vdso_data *data = get_vdso_data(); -#endif - u64 cycle_now; - - switch (clock_mode) { #ifdef CONFIG_CSRC_R4K - case VDSO_CLOCK_R4K: - cycle_now = read_r4k_count(); - break; + if (clock_mode == VDSO_CLOCKMODE_R4K) + return read_r4k_count(); #endif #ifdef CONFIG_CLKSRC_MIPS_GIC - case VDSO_CLOCK_GIC: - cycle_now = read_gic_count(data); - break; + if (clock_mode == VDSO_CLOCKMODE_GIC) + return read_gic_count(get_vdso_data()); #endif - default: - cycle_now = __VDSO_USE_SYSCALL; - break; - } + /* + * Core checks mode already. So this raced against a concurrent + * update. Return something. Core will do another round see the + * change and fallback to syscall. + */ + return 0; +} - return cycle_now; +static inline bool mips_vdso_hres_capable(void) +{ + return IS_ENABLED(CONFIG_CSRC_R4K) || + IS_ENABLED(CONFIG_CLKSRC_MIPS_GIC); } +#define __arch_vdso_hres_capable mips_vdso_hres_capable static __always_inline const struct vdso_data *__arch_get_vdso_data(void) { diff --git a/arch/mips/include/asm/vdso/processor.h b/arch/mips/include/asm/vdso/processor.h new file mode 100644 index 000000000000..511c95d735e6 --- /dev/null +++ b/arch/mips/include/asm/vdso/processor.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_VDSO_PROCESSOR_H +#define __ASM_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_CPU_LOONGSON64 +/* + * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a + * tight read loop is executed, because reads take priority over writes & the + * hardware (incorrectly) doesn't ensure that writes will eventually occur. + * + * Since spin loops of any kind should have a cpu_relax() in them, force an SFB + * flush from cpu_relax() such that any pending writes will become visible as + * expected. + */ +#define cpu_relax() smp_mb() +#else +#define cpu_relax() barrier() +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h index 00d41b94ba31..47168aaf1eff 100644 --- a/arch/mips/include/asm/vdso/vsyscall.h +++ b/arch/mips/include/asm/vdso/vsyscall.h @@ -19,15 +19,6 @@ struct vdso_data *__mips_get_k_vdso_data(void) } #define __arch_get_k_vdso_data __mips_get_k_vdso_data -static __always_inline -int __mips_get_clock_mode(struct timekeeper *tk) -{ - u32 clock_mode = tk->tkr_mono.clock->archdata.vdso_clock_mode; - - return clock_mode; -} -#define __arch_get_clock_mode __mips_get_clock_mode - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/mips/jazz/irq.c b/arch/mips/jazz/irq.c index 5d6828b2a750..04b9c4068493 100644 --- a/arch/mips/jazz/irq.c +++ b/arch/mips/jazz/irq.c @@ -125,24 +125,18 @@ static irqreturn_t r4030_timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction r4030_timer_irqaction = { - .handler = r4030_timer_interrupt, - .flags = IRQF_TIMER, - .name = "R4030 timer", -}; - void __init plat_time_init(void) { struct clock_event_device *cd = &r4030_clockevent; - struct irqaction *action = &r4030_timer_irqaction; unsigned int cpu = smp_processor_id(); BUG_ON(HZ != 100); cd->cpumask = cpumask_of(cpu); clockevents_register_device(cd); - action->dev_id = cd; - setup_irq(JAZZ_TIMER_IRQ, action); + if (request_irq(JAZZ_TIMER_IRQ, r4030_timer_interrupt, IRQF_TIMER, + "R4030 timer", cd)) + pr_err("Failed to register R4030 timer interrupt\n"); /* * Set clock to 100Hz. diff --git a/arch/mips/jz4740/time.c b/arch/mips/jz4740/time.c index 5476899f0882..605a84a250bf 100644 --- a/arch/mips/jz4740/time.c +++ b/arch/mips/jz4740/time.c @@ -4,8 +4,8 @@ * JZ4740 platform time support */ -#include <linux/clk-provider.h> #include <linux/clocksource.h> +#include <linux/of_clk.h> #include <asm/mach-jz4740/timer.h> diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c index b3e8c11a8fa5..d39a2963b451 100644 --- a/arch/mips/kernel/cevt-bcm1480.c +++ b/arch/mips/kernel/cevt-bcm1480.c @@ -91,16 +91,15 @@ static irqreturn_t sibyte_counter_handler(int irq, void *dev_id) } static DEFINE_PER_CPU(struct clock_event_device, sibyte_hpt_clockevent); -static DEFINE_PER_CPU(struct irqaction, sibyte_hpt_irqaction); static DEFINE_PER_CPU(char [18], sibyte_hpt_name); void sb1480_clockevent_init(void) { unsigned int cpu = smp_processor_id(); unsigned int irq = K_BCM1480_INT_TIMER_0 + cpu; - struct irqaction *action = &per_cpu(sibyte_hpt_irqaction, cpu); struct clock_event_device *cd = &per_cpu(sibyte_hpt_clockevent, cpu); unsigned char *name = per_cpu(sibyte_hpt_name, cpu); + unsigned long flags = IRQF_PERCPU | IRQF_TIMER; BUG_ON(cpu > 3); /* Only have 4 general purpose timers */ @@ -133,11 +132,7 @@ void sb1480_clockevent_init(void) bcm1480_unmask_irq(cpu, irq); - action->handler = sibyte_counter_handler; - action->flags = IRQF_PERCPU | IRQF_TIMER; - action->name = name; - action->dev_id = cd; - irq_set_affinity(irq, cpumask_of(cpu)); - setup_irq(irq, action); + if (request_irq(irq, sibyte_counter_handler, flags, name, cd)) + pr_err("Failed to request irq %d (%s)\n", irq, name); } diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c index 1e1edab4a63f..9a47fbcd4638 100644 --- a/arch/mips/kernel/cevt-ds1287.c +++ b/arch/mips/kernel/cevt-ds1287.c @@ -100,14 +100,9 @@ static irqreturn_t ds1287_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction ds1287_irqaction = { - .handler = ds1287_interrupt, - .flags = IRQF_PERCPU | IRQF_TIMER, - .name = "ds1287", -}; - int __init ds1287_clockevent_init(int irq) { + unsigned long flags = IRQF_PERCPU | IRQF_TIMER; struct clock_event_device *cd; cd = &ds1287_clockevent; @@ -122,5 +117,5 @@ int __init ds1287_clockevent_init(int irq) clockevents_register_device(&ds1287_clockevent); - return setup_irq(irq, &ds1287_irqaction); + return request_irq(irq, ds1287_interrupt, flags, "ds1287", NULL); } diff --git a/arch/mips/kernel/cevt-gt641xx.c b/arch/mips/kernel/cevt-gt641xx.c index eb53548d2538..5b132e8c51da 100644 --- a/arch/mips/kernel/cevt-gt641xx.c +++ b/arch/mips/kernel/cevt-gt641xx.c @@ -120,12 +120,6 @@ static irqreturn_t gt641xx_timer0_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction gt641xx_timer0_irqaction = { - .handler = gt641xx_timer0_interrupt, - .flags = IRQF_PERCPU | IRQF_TIMER, - .name = "gt641xx_timer0", -}; - static int __init gt641xx_timer0_clockevent_init(void) { struct clock_event_device *cd; @@ -146,6 +140,7 @@ static int __init gt641xx_timer0_clockevent_init(void) clockevents_register_device(>641xx_timer0_clockevent); - return setup_irq(GT641XX_TIMER0_IRQ, >641xx_timer0_irqaction); + return request_irq(GT641XX_TIMER0_IRQ, gt641xx_timer0_interrupt, + IRQF_PERCPU | IRQF_TIMER, "gt641xx_timer0", NULL); } arch_initcall(gt641xx_timer0_clockevent_init); diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index dd6a18bc10ab..17a9cbb8b3df 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -252,6 +252,7 @@ unsigned int __weak get_c0_compare_int(void) int r4k_clockevent_init(void) { + unsigned long flags = IRQF_PERCPU | IRQF_TIMER | IRQF_SHARED; unsigned int cpu = smp_processor_id(); struct clock_event_device *cd; unsigned int irq, min_delta; @@ -291,7 +292,9 @@ int r4k_clockevent_init(void) cp0_timer_irq_installed = 1; - setup_irq(irq, &c0_compare_irqaction); + if (request_irq(irq, c0_compare_interrupt, flags, "timer", + c0_compare_interrupt)) + pr_err("Failed to request irq %d (timer)\n", irq); return 0; } diff --git a/arch/mips/kernel/cevt-sb1250.c b/arch/mips/kernel/cevt-sb1250.c index e1a08606c27e..0451273fab9f 100644 --- a/arch/mips/kernel/cevt-sb1250.c +++ b/arch/mips/kernel/cevt-sb1250.c @@ -90,16 +90,15 @@ static irqreturn_t sibyte_counter_handler(int irq, void *dev_id) } static DEFINE_PER_CPU(struct clock_event_device, sibyte_hpt_clockevent); -static DEFINE_PER_CPU(struct irqaction, sibyte_hpt_irqaction); static DEFINE_PER_CPU(char [18], sibyte_hpt_name); void sb1250_clockevent_init(void) { unsigned int cpu = smp_processor_id(); unsigned int irq = K_INT_TIMER_0 + cpu; - struct irqaction *action = &per_cpu(sibyte_hpt_irqaction, cpu); struct clock_event_device *cd = &per_cpu(sibyte_hpt_clockevent, cpu); unsigned char *name = per_cpu(sibyte_hpt_name, cpu); + unsigned long flags = IRQF_PERCPU | IRQF_TIMER; /* Only have 4 general purpose timers, and we use last one as hpt */ BUG_ON(cpu > 2); @@ -133,11 +132,7 @@ void sb1250_clockevent_init(void) sb1250_unmask_irq(cpu, irq); - action->handler = sibyte_counter_handler; - action->flags = IRQF_PERCPU | IRQF_TIMER; - action->name = name; - action->dev_id = cd; - irq_set_affinity(irq, cpumask_of(cpu)); - setup_irq(irq, action); + if (request_irq(irq, sibyte_counter_handler, flags, name, cd)) + pr_err("Failed to request irq %d (%s)\n", irq, name); } diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c index 7b17c8f5009d..5709469c21ff 100644 --- a/arch/mips/kernel/cevt-txx9.c +++ b/arch/mips/kernel/cevt-txx9.c @@ -174,13 +174,6 @@ static irqreturn_t txx9tmr_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction txx9tmr_irq = { - .handler = txx9tmr_interrupt, - .flags = IRQF_PERCPU | IRQF_TIMER, - .name = "txx9tmr", - .dev_id = &txx9_clock_event_device, -}; - void __init txx9_clockevent_init(unsigned long baseaddr, int irq, unsigned int imbusclk) { @@ -202,7 +195,9 @@ void __init txx9_clockevent_init(unsigned long baseaddr, int irq, cd->irq = irq; cd->cpumask = cpumask_of(0), clockevents_register_device(cd); - setup_irq(irq, &txx9tmr_irq); + if (request_irq(irq, txx9tmr_interrupt, IRQF_PERCPU | IRQF_TIMER, + "txx9tmr", &txx9_clock_event_device)) + pr_err("Failed to request irq %d (txx9tmr)\n", irq); printk(KERN_INFO "TXx9: clockevent device at 0x%lx, irq %d\n", baseaddr, irq); } diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6ab6b03d35ba..f21a2304401f 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -513,6 +513,13 @@ static inline void set_elf_platform(int cpu, const char *plat) __elf_platform = plat; } +static inline void set_elf_base_platform(const char *plat) +{ + if (__elf_base_platform == NULL) { + __elf_base_platform = plat; + } +} + static inline void cpu_probe_vmbits(struct cpuinfo_mips *c) { #ifdef __NEED_VMBITS_PROBE @@ -527,36 +534,46 @@ static void set_isa(struct cpuinfo_mips *c, unsigned int isa) switch (isa) { case MIPS_CPU_ISA_M64R2: c->isa_level |= MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2; + set_elf_base_platform("mips64r2"); /* fall through */ case MIPS_CPU_ISA_M64R1: c->isa_level |= MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1; + set_elf_base_platform("mips64"); /* fall through */ case MIPS_CPU_ISA_V: c->isa_level |= MIPS_CPU_ISA_V; + set_elf_base_platform("mips5"); /* fall through */ case MIPS_CPU_ISA_IV: c->isa_level |= MIPS_CPU_ISA_IV; + set_elf_base_platform("mips4"); /* fall through */ case MIPS_CPU_ISA_III: c->isa_level |= MIPS_CPU_ISA_II | MIPS_CPU_ISA_III; + set_elf_base_platform("mips3"); break; /* R6 incompatible with everything else */ case MIPS_CPU_ISA_M64R6: c->isa_level |= MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6; + set_elf_base_platform("mips64r6"); /* fall through */ case MIPS_CPU_ISA_M32R6: c->isa_level |= MIPS_CPU_ISA_M32R6; + set_elf_base_platform("mips32r6"); /* Break here so we don't add incompatible ISAs */ break; case MIPS_CPU_ISA_M32R2: c->isa_level |= MIPS_CPU_ISA_M32R2; + set_elf_base_platform("mips32r2"); /* fall through */ case MIPS_CPU_ISA_M32R1: c->isa_level |= MIPS_CPU_ISA_M32R1; + set_elf_base_platform("mips32"); /* fall through */ case MIPS_CPU_ISA_II: c->isa_level |= MIPS_CPU_ISA_II; + set_elf_base_platform("mips2"); break; } } @@ -2113,6 +2130,7 @@ EXPORT_SYMBOL(__ua_limit); const char *__cpu_name[NR_CPUS]; const char *__elf_platform; +const char *__elf_base_platform; void cpu_probe(void) { diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c index eed099f35bf1..437dda64fd7a 100644 --- a/arch/mips/kernel/csrc-r4k.c +++ b/arch/mips/kernel/csrc-r4k.c @@ -78,7 +78,7 @@ int __init init_r4k_clocksource(void) * by the VDSO (HWREna is configured by configure_hwrena()). */ if (cpu_has_mips_r2_r6 && rdhwr_count_usable()) - clocksource_mips.archdata.vdso_clock_mode = VDSO_CLOCK_R4K; + clocksource_mips.vdso_clock_mode = VDSO_CLOCKMODE_R4K; clocksource_register_hz(&clocksource_mips, mips_hpt_frequency); diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index df7ddd246eaa..ca21210e06b5 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -18,16 +18,13 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_NOBALANCING | IRQF_TIMER, - .name = "timer" -}; - void __init setup_pit_timer(void) { + unsigned long flags = IRQF_NOBALANCING | IRQF_TIMER; + clockevent_i8253_init(true); - setup_irq(0, &irq0); + if (request_irq(0, timer_interrupt, flags, "timer", NULL)) + pr_err("Failed to request irq 0 (timer)\n"); } static int __init init_pit_clocksource(void) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 339870ed92f7..b2a797557825 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -75,7 +75,9 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) lose_fpu(0); clear_thread_flag(TIF_MSA_CTX_LIVE); clear_used_math(); +#ifdef CONFIG_MIPS_FP_SUPPORT atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE); +#endif init_dsp(); regs->cp0_epc = pc; regs->regs[29] = sp; @@ -176,7 +178,9 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp, clear_tsk_thread_flag(p, TIF_FPUBOUND); #endif /* CONFIG_MIPS_MT_FPAFF */ +#ifdef CONFIG_MIPS_FP_SUPPORT atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE); +#endif if (clone_flags & CLONE_SETTLS) ti->tp_value = tls; @@ -650,8 +654,10 @@ unsigned long mips_stack_top(void) { unsigned long top = TASK_SIZE & PAGE_MASK; - /* One page for branch delay slot "emulation" */ - top -= PAGE_SIZE; + if (IS_ENABLED(CONFIG_MIPS_FP_SUPPORT)) { + /* One page for branch delay slot "emulation" */ + top -= PAGE_SIZE; + } /* Space for the VDSO, data page & GIC user page */ top -= PAGE_ALIGN(current->thread.abi->vdso->size); diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c index cb95470e2e69..38c6925a1bea 100644 --- a/arch/mips/kernel/rtlx-mt.c +++ b/arch/mips/kernel/rtlx-mt.c @@ -51,11 +51,6 @@ static irqreturn_t rtlx_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction rtlx_irq = { - .handler = rtlx_interrupt, - .name = "RTLX", -}; - static int rtlx_irq_num = MIPS_CPU_IRQ_BASE + MIPS_CPU_RTLX_IRQ; void _interrupt_sp(void) @@ -124,8 +119,7 @@ int __init rtlx_module_init(void) goto out_class; } - rtlx_irq.dev_id = rtlx; - err = setup_irq(rtlx_irq_num, &rtlx_irq); + err = request_irq(rtlx_irq_num, rtlx_interrupt, 0, "RTLX", rtlx); if (err) goto out_class; diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 1ac2752fb791..10bef8f78e7c 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -28,6 +28,7 @@ #include <linux/decompress/generic.h> #include <linux/of_fdt.h> #include <linux/of_reserved_mem.h> +#include <linux/dmi.h> #include <asm/addrspace.h> #include <asm/bootinfo.h> @@ -605,7 +606,8 @@ 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 @@ -798,6 +800,7 @@ void __init setup_arch(char **cmdline_p) #endif arch_mem_init(cmdline_p); + dmi_setup(); resource_init(); plat_smp_setup(); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index f510c00bda88..48d84d5fcc36 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -207,25 +207,13 @@ static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction irq_resched = { - .handler = ipi_resched_interrupt, - .flags = IRQF_PERCPU, - .name = "IPI resched" -}; - -static struct irqaction irq_call = { - .handler = ipi_call_interrupt, - .flags = IRQF_PERCPU, - .name = "IPI call" -}; - -static void smp_ipi_init_one(unsigned int virq, - struct irqaction *action) +static void smp_ipi_init_one(unsigned int virq, const char *name, + irq_handler_t handler) { int ret; irq_set_handler(virq, handle_percpu_irq); - ret = setup_irq(virq, action); + ret = request_irq(virq, handler, IRQF_PERCPU, name, NULL); BUG_ON(ret); } @@ -278,12 +266,15 @@ int mips_smp_ipi_allocate(const struct cpumask *mask) int cpu; for_each_cpu(cpu, mask) { - smp_ipi_init_one(call_virq + cpu, &irq_call); - smp_ipi_init_one(sched_virq + cpu, &irq_resched); + smp_ipi_init_one(call_virq + cpu, "IPI call", + ipi_call_interrupt); + smp_ipi_init_one(sched_virq + cpu, "IPI resched", + ipi_resched_interrupt); } } else { - smp_ipi_init_one(call_virq, &irq_call); - smp_ipi_init_one(sched_virq, &irq_resched); + smp_ipi_init_one(call_virq, "IPI call", ipi_call_interrupt); + smp_ipi_init_one(sched_virq, "IPI resched", + ipi_resched_interrupt); } return 0; @@ -311,8 +302,8 @@ int mips_smp_ipi_free(const struct cpumask *mask) int cpu; for_each_cpu(cpu, mask) { - remove_irq(call_virq + cpu, &irq_call); - remove_irq(sched_virq + cpu, &irq_resched); + free_irq(call_virq + cpu, NULL); + free_irq(sched_virq + cpu, NULL); } } irq_destroy_ipi(call_virq, mask); @@ -696,29 +687,22 @@ 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/vdso.c b/arch/mips/kernel/vdso.c index bc35f8499111..3adb7354bc01 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -71,10 +71,12 @@ subsys_initcall(init_vdso); static unsigned long vdso_base(void) { - unsigned long base; + unsigned long base = STACK_TOP; - /* Skip the delay slot emulation page */ - base = STACK_TOP + PAGE_SIZE; + if (IS_ENABLED(CONFIG_MIPS_FP_SUPPORT)) { + /* Skip the delay slot emulation page */ + base += PAGE_SIZE; + } if (current->flags & PF_RANDOMIZE) { base += get_random_int() & (VDSO_RANDOMIZE_SIZE - 1); @@ -95,14 +97,16 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (down_write_killable(&mm->mmap_sem)) return -EINTR; - /* Map delay slot emulation page */ - base = mmap_region(NULL, STACK_TOP, PAGE_SIZE, - VM_READ | VM_EXEC | - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, - 0, NULL); - if (IS_ERR_VALUE(base)) { - ret = base; - goto out; + if (IS_ENABLED(CONFIG_MIPS_FP_SUPPORT)) { + /* Map delay slot emulation page */ + base = mmap_region(NULL, STACK_TOP, PAGE_SIZE, + VM_READ | VM_EXEC | + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, + 0, NULL); + if (IS_ERR_VALUE(base)) { + ret = base; + goto out; + } } /* 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/kvm/mips.c b/arch/mips/kvm/mips.c index 71244bf87c3a..8f05dd0a0f4e 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -118,12 +118,12 @@ void kvm_arch_hardware_disable(void) kvm_mips_callbacks->hardware_disable(); } -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { return 0; } @@ -188,12 +188,6 @@ long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, return -ENOIOCTLCMD; } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} - void kvm_arch_flush_shadow_all(struct kvm *kvm) { /* Flush whole GPA */ @@ -230,7 +224,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -984,69 +978,16 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, return r; } -/** - * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot - * @kvm: kvm instance - * @log: slot id and address to which we copy the log - * - * Steps 1-4 below provide general overview of dirty page logging. See - * kvm_get_dirty_log_protect() function description for additional details. - * - * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we - * always flush the TLB (step 4) even if previous step failed and the dirty - * bitmap may be corrupt. Regardless of previous outcome the KVM logging API - * does not preclude user space subsequent dirty log read. Flushing TLB ensures - * writes will be marked dirty for next log read. - * - * 1. Take a snapshot of the bit and clear it if needed. - * 2. Write protect the corresponding page. - * 3. Copy the snapshot to the userspace. - * 4. Flush TLB's if needed. - */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - - r = kvm_get_dirty_log_protect(kvm, log, &flush); - - if (flush) { - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - /* Let implementation handle TLB/GVA invalidation */ - kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); - } - - mutex_unlock(&kvm->slots_lock); - return r; } -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) { - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - - r = kvm_clear_dirty_log_protect(kvm, log, &flush); - - if (flush) { - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - - /* Let implementation handle TLB/GVA invalidation */ - kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); - } - - mutex_unlock(&kvm->slots_lock); - return r; + /* Let implementation handle TLB/GVA invalidation */ + kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); } long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) diff --git a/arch/mips/lasat/interrupt.c b/arch/mips/lasat/interrupt.c index 0f3a8975081d..7965bbd0d319 100644 --- a/arch/mips/lasat/interrupt.c +++ b/arch/mips/lasat/interrupt.c @@ -90,14 +90,9 @@ asmlinkage void plat_irq_dispatch(void) } } -static struct irqaction cascade = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - void __init arch_init_irq(void) { + int irq = LASAT_CASCADE_IRQ; int i; if (IS_LASAT_200()) { @@ -119,5 +114,6 @@ void __init arch_init_irq(void) for (i = LASAT_IRQ_BASE; i <= LASAT_IRQ_END; i++) irq_set_chip_and_handler(i, &lasat_irq_type, handle_level_irq); - setup_irq(LASAT_CASCADE_IRQ, &cascade); + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", irq); } diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c index 68c495ed71e3..2e8dfc1d59c8 100644 --- a/arch/mips/lib/delay.c +++ b/arch/mips/lib/delay.c @@ -24,6 +24,8 @@ #define GCC_DADDI_IMM_ASM() "r" #endif +#ifndef CONFIG_HAVE_PLAT_DELAY + void __delay(unsigned long loops) { __asm__ __volatile__ ( @@ -63,3 +65,5 @@ void __ndelay(unsigned long ns) __delay((ns * 0x00000005ull * HZ * lpj) >> 32); } EXPORT_SYMBOL(__ndelay); + +#endif diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S index f7994d936505..88065ee433cd 100644 --- a/arch/mips/lib/memcpy.S +++ b/arch/mips/lib/memcpy.S @@ -598,6 +598,7 @@ SEXC(1) nop .endm +#ifndef CONFIG_HAVE_PLAT_MEMCPY .align 5 LEAF(memmove) EXPORT_SYMBOL(memmove) @@ -665,6 +666,8 @@ EXPORT_SYMBOL(__copy_user) /* Legacy Mode, user <-> user */ __BUILD_COPY_USER LEGACY_MODE USEROP USEROP +#endif + #ifdef CONFIG_EVA /* diff --git a/arch/mips/loongson2ef/common/bonito-irq.c b/arch/mips/loongson2ef/common/bonito-irq.c index 82352cc25e4c..c06ad412ee20 100644 --- a/arch/mips/loongson2ef/common/bonito-irq.c +++ b/arch/mips/loongson2ef/common/bonito-irq.c @@ -30,11 +30,6 @@ static struct irq_chip bonito_irq_type = { .irq_unmask = bonito_irq_enable, }; -static struct irqaction __maybe_unused dma_timeout_irqaction = { - .handler = no_action, - .name = "dma_timeout", -}; - void bonito_irq_init(void) { u32 i; @@ -44,6 +39,8 @@ void bonito_irq_init(void) handle_level_irq); #ifdef CONFIG_CPU_LOONGSON2E - setup_irq(LOONGSON_IRQ_BASE + 10, &dma_timeout_irqaction); + i = LOONGSON_IRQ_BASE + 10; + if (request_irq(i, no_action, 0, "dma_timeout", NULL)) + pr_err("Failed to request irq %d (dma_timeout)\n", i); #endif } diff --git a/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c index 30af1b7c7529..f21a540a1dd2 100644 --- a/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c @@ -100,12 +100,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction irq5 = { - .handler = timer_interrupt, - .flags = IRQF_NOBALANCING | IRQF_TIMER, - .name = "timer" -}; - /* * Initialize the conversion factor and the min/max deltas of the clock event * structure and register the clock event source with the framework. @@ -134,7 +128,9 @@ void __init setup_mfgpt0_timer(void) clockevents_register_device(cd); - setup_irq(CS5536_MFGPT_INTR, &irq5); + if (request_irq(CS5536_MFGPT_INTR, timer_interrupt, + IRQF_NOBALANCING | IRQF_TIMER, "timer", NULL)) + pr_err("Failed to register timer interrupt\n"); } /* diff --git a/arch/mips/loongson2ef/fuloong-2e/irq.c b/arch/mips/loongson2ef/fuloong-2e/irq.c index 32278e7bf85c..305aa2eb74ad 100644 --- a/arch/mips/loongson2ef/fuloong-2e/irq.c +++ b/arch/mips/loongson2ef/fuloong-2e/irq.c @@ -35,14 +35,10 @@ asmlinkage void mach_irq_dispatch(unsigned int pending) spurious_interrupt(); } -static struct irqaction cascade_irqaction = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - void __init mach_init_irq(void) { + int irq; + /* init all controller * 0-15 ------> i8259 interrupt * 16-23 ------> mips cpu interrupt @@ -59,7 +55,11 @@ void __init mach_init_irq(void) bonito_irq_init(); /* bonito irq at IP2 */ - setup_irq(MIPS_CPU_IRQ_BASE + 2, &cascade_irqaction); + irq = MIPS_CPU_IRQ_BASE + 2; + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", irq); /* 8259 irq at IP5 */ - setup_irq(MIPS_CPU_IRQ_BASE + 5, &cascade_irqaction); + irq = MIPS_CPU_IRQ_BASE + 5; + if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", irq); } diff --git a/arch/mips/loongson2ef/lemote-2f/irq.c b/arch/mips/loongson2ef/lemote-2f/irq.c index c58a044c6c07..6f00579971a3 100644 --- a/arch/mips/loongson2ef/lemote-2f/irq.c +++ b/arch/mips/loongson2ef/lemote-2f/irq.c @@ -90,18 +90,6 @@ static irqreturn_t ip6_action(int cpl, void *dev_id) return IRQ_HANDLED; } -static struct irqaction ip6_irqaction = { - .handler = ip6_action, - .name = "cascade", - .flags = IRQF_SHARED | IRQF_NO_THREAD, -}; - -static struct irqaction cascade_irqaction = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD | IRQF_NO_SUSPEND, -}; - void __init mach_init_irq(void) { /* init all controller @@ -120,7 +108,11 @@ void __init mach_init_irq(void) bonito_irq_init(); /* setup north bridge irq (bonito) */ - setup_irq(LOONGSON_NORTH_BRIDGE_IRQ, &ip6_irqaction); + if (request_irq(LOONGSON_NORTH_BRIDGE_IRQ, ip6_action, + IRQF_SHARED | IRQF_NO_THREAD, "cascade", ip6_action)) + pr_err("Failed to register north bridge cascade interrupt\n"); /* setup source bridge irq (i8259) */ - setup_irq(LOONGSON_SOUTH_BRIDGE_IRQ, &cascade_irqaction); + if (request_irq(LOONGSON_SOUTH_BRIDGE_IRQ, no_action, + IRQF_NO_THREAD | IRQF_NO_SUSPEND, "cascade", NULL)) + pr_err("Failed to register south bridge cascade interrupt\n"); } diff --git a/arch/mips/loongson32/common/irq.c b/arch/mips/loongson32/common/irq.c index 168d221d4178..9a50070f74f7 100644 --- a/arch/mips/loongson32/common/irq.c +++ b/arch/mips/loongson32/common/irq.c @@ -149,12 +149,6 @@ asmlinkage void plat_irq_dispatch(void) } -static struct irqaction cascade_irqaction = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - static void __init ls1x_irq_init(int base) { int n; @@ -176,12 +170,17 @@ static void __init ls1x_irq_init(int base) handle_level_irq); } - setup_irq(INT0_IRQ, &cascade_irqaction); - setup_irq(INT1_IRQ, &cascade_irqaction); - setup_irq(INT2_IRQ, &cascade_irqaction); - setup_irq(INT3_IRQ, &cascade_irqaction); + if (request_irq(INT0_IRQ, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", INT0_IRQ); + if (request_irq(INT1_IRQ, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", INT1_IRQ); + if (request_irq(INT2_IRQ, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", INT2_IRQ); + if (request_irq(INT3_IRQ, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", INT3_IRQ); #if defined(CONFIG_LOONGSON1_LS1C) - setup_irq(INT4_IRQ, &cascade_irqaction); + if (request_irq(INT4_IRQ, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to request irq %d (cascade)\n", INT4_IRQ); #endif } diff --git a/arch/mips/loongson32/common/time.c b/arch/mips/loongson32/common/time.c index 4cc73f7ac0d4..459b15c96d3b 100644 --- a/arch/mips/loongson32/common/time.c +++ b/arch/mips/loongson32/common/time.c @@ -176,13 +176,6 @@ static struct clock_event_device ls1x_clockevent = { .tick_resume = ls1x_clockevent_tick_resume, }; -static struct irqaction ls1x_pwmtimer_irqaction = { - .name = "ls1x-pwmtimer", - .handler = ls1x_clockevent_isr, - .dev_id = &ls1x_clockevent, - .flags = IRQF_PERCPU | IRQF_TIMER, -}; - static void __init ls1x_time_init(void) { struct clock_event_device *cd = &ls1x_clockevent; @@ -206,7 +199,10 @@ static void __init ls1x_time_init(void) if (ret) panic(KERN_ERR "Failed to register clocksource: %d\n", ret); - setup_irq(LS1X_TIMER_IRQ, &ls1x_pwmtimer_irqaction); + if (request_irq(LS1X_TIMER_IRQ, ls1x_clockevent_isr, + IRQF_PERCPU | IRQF_TIMER, "ls1x-pwmtimer", + &ls1x_clockevent)) + pr_err("Failed to register ls1x-pwmtimer interrupt\n"); } #endif /* CONFIG_CEVT_CSRC_LS1X */ diff --git a/arch/mips/loongson64/Makefile b/arch/mips/loongson64/Makefile index 7821891bc5d0..b7f40b179c71 100644 --- a/arch/mips/loongson64/Makefile +++ b/arch/mips/loongson64/Makefile @@ -2,7 +2,7 @@ # # Makefile for Loongson-3 family machines # -obj-$(CONFIG_MACH_LOONGSON64) += irq.o cop2-ex.o platform.o acpi_init.o dma.o \ +obj-$(CONFIG_MACH_LOONGSON64) += cop2-ex.o platform.o acpi_init.o dma.o \ setup.o init.o env.o time.o reset.o \ obj-$(CONFIG_SMP) += smp.o diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c index 0daeb7bcf023..2554ef11170d 100644 --- a/arch/mips/loongson64/env.c +++ b/arch/mips/loongson64/env.c @@ -17,6 +17,7 @@ #include <asm/bootinfo.h> #include <loongson.h> #include <boot_param.h> +#include <builtin_dtbs.h> #include <workarounds.h> u32 cpu_clock_freq; @@ -120,6 +121,28 @@ void __init prom_init_env(void) loongson_sysconf.cores_per_node - 1) / loongson_sysconf.cores_per_node; + if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64C) { + switch (read_c0_prid() & PRID_REV_MASK) { + case PRID_REV_LOONGSON3A_R1: + case PRID_REV_LOONGSON3A_R2_0: + case PRID_REV_LOONGSON3A_R2_1: + case PRID_REV_LOONGSON3A_R3_0: + case PRID_REV_LOONGSON3A_R3_1: + loongson_fdt_blob = __dtb_loongson3_4core_rs780e_begin; + break; + case PRID_REV_LOONGSON3B_R1: + case PRID_REV_LOONGSON3B_R2: + loongson_fdt_blob = __dtb_loongson3_8core_rs780e_begin; + break; + default: + break; + } + } + + + if (!loongson_fdt_blob) + pr_err("Failed to determine built-in Loongson64 dtb\n"); + loongson_sysconf.pci_mem_start_addr = eirq_source->pci_mem_start_addr; loongson_sysconf.pci_mem_end_addr = eirq_source->pci_mem_end_addr; loongson_sysconf.pci_io_base = eirq_source->pci_io_start_addr; diff --git a/arch/mips/loongson64/hpet.c b/arch/mips/loongson64/hpet.c index ed15430ad64f..e4282592575b 100644 --- a/arch/mips/loongson64/hpet.c +++ b/arch/mips/loongson64/hpet.c @@ -187,12 +187,6 @@ static irqreturn_t hpet_irq_handler(int irq, void *data) return IRQ_NONE; } -static struct irqaction hpet_irq = { - .handler = hpet_irq_handler, - .flags = IRQF_NOBALANCING | IRQF_TIMER, - .name = "hpet", -}; - /* * hpet address assignation and irq setting should be done in bios. * but pmon don't do this, we just setup here directly. @@ -224,6 +218,7 @@ static void hpet_setup(void) void __init setup_hpet_timer(void) { + unsigned long flags = IRQF_NOBALANCING | IRQF_TIMER; unsigned int cpu = smp_processor_id(); struct clock_event_device *cd; @@ -247,7 +242,8 @@ void __init setup_hpet_timer(void) cd->min_delta_ticks = HPET_MIN_PROG_DELTA; clockevents_register_device(cd); - setup_irq(HPET_T0_IRQ, &hpet_irq); + if (request_irq(HPET_T0_IRQ, hpet_irq_handler, flags, "hpet", NULL)) + pr_err("Failed to request irq %d (hpet)\n", HPET_T0_IRQ); pr_info("hpet clock event device register\n"); } diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index 5ac1a0f35ca4..da38944471f4 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -4,6 +4,7 @@ * Author: Wu Zhangjin, wuzhangjin@gmail.com */ +#include <linux/irqchip.h> #include <linux/memblock.h> #include <asm/bootinfo.h> #include <asm/traps.h> @@ -44,3 +45,8 @@ void __init prom_init(void) void __init prom_free_prom_memory(void) { } + +void __init arch_init_irq(void) +{ + irqchip_init(); +} diff --git a/arch/mips/loongson64/irq.c b/arch/mips/loongson64/irq.c deleted file mode 100644 index 79ad797497e4..000000000000 --- a/arch/mips/loongson64/irq.c +++ /dev/null @@ -1,162 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <loongson.h> -#include <irq.h> -#include <linux/interrupt.h> -#include <linux/init.h> - -#include <asm/irq_cpu.h> -#include <asm/i8259.h> -#include <asm/mipsregs.h> - -#include "smp.h" - -extern void loongson3_send_irq_by_ipi(int cpu, int irqs); - -unsigned int irq_cpu[16] = {[0 ... 15] = -1}; -unsigned int ht_irq[] = {0, 1, 3, 4, 5, 6, 7, 8, 12, 14, 15}; -unsigned int local_irq = 1<<0 | 1<<1 | 1<<2 | 1<<7 | 1<<8 | 1<<12; - -int plat_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, - bool force) -{ - unsigned int cpu; - struct cpumask new_affinity; - - /* I/O devices are connected on package-0 */ - cpumask_copy(&new_affinity, affinity); - for_each_cpu(cpu, affinity) - if (cpu_data[cpu].package > 0) - cpumask_clear_cpu(cpu, &new_affinity); - - if (cpumask_empty(&new_affinity)) - return -EINVAL; - - cpumask_copy(d->common->affinity, &new_affinity); - - return IRQ_SET_MASK_OK_NOCOPY; -} - -static void ht_irqdispatch(void) -{ - unsigned int i, irq; - struct irq_data *irqd; - struct cpumask affinity; - - irq = LOONGSON_HT1_INT_VECTOR(0); - LOONGSON_HT1_INT_VECTOR(0) = irq; /* Acknowledge the IRQs */ - - for (i = 0; i < ARRAY_SIZE(ht_irq); i++) { - if (!(irq & (0x1 << ht_irq[i]))) - continue; - - /* handled by local core */ - if (local_irq & (0x1 << ht_irq[i])) { - do_IRQ(ht_irq[i]); - continue; - } - - irqd = irq_get_irq_data(ht_irq[i]); - cpumask_and(&affinity, irqd->common->affinity, cpu_active_mask); - if (cpumask_empty(&affinity)) { - do_IRQ(ht_irq[i]); - continue; - } - - irq_cpu[ht_irq[i]] = cpumask_next(irq_cpu[ht_irq[i]], &affinity); - if (irq_cpu[ht_irq[i]] >= nr_cpu_ids) - irq_cpu[ht_irq[i]] = cpumask_first(&affinity); - - if (irq_cpu[ht_irq[i]] == 0) { - do_IRQ(ht_irq[i]); - continue; - } - - /* balanced by other cores */ - loongson3_send_irq_by_ipi(irq_cpu[ht_irq[i]], (0x1 << ht_irq[i])); - } -} - -#define UNUSED_IPS (CAUSEF_IP5 | CAUSEF_IP4 | CAUSEF_IP1 | CAUSEF_IP0) - -asmlinkage void plat_irq_dispatch(void) -{ - unsigned int pending; - - pending = read_c0_cause() & read_c0_status() & ST0_IM; - - if (pending & CAUSEF_IP7) - do_IRQ(LOONGSON_TIMER_IRQ); -#if defined(CONFIG_SMP) - if (pending & CAUSEF_IP6) - loongson3_ipi_interrupt(NULL); -#endif - if (pending & CAUSEF_IP3) - ht_irqdispatch(); - if (pending & CAUSEF_IP2) - do_IRQ(LOONGSON_UART_IRQ); - if (pending & UNUSED_IPS) { - pr_err("%s : spurious interrupt\n", __func__); - spurious_interrupt(); - } -} - -static inline void mask_loongson_irq(struct irq_data *d) { } -static inline void unmask_loongson_irq(struct irq_data *d) { } - - /* For MIPS IRQs which shared by all cores */ -static struct irq_chip loongson_irq_chip = { - .name = "Loongson", - .irq_ack = mask_loongson_irq, - .irq_mask = mask_loongson_irq, - .irq_mask_ack = mask_loongson_irq, - .irq_unmask = unmask_loongson_irq, - .irq_eoi = unmask_loongson_irq, -}; - -void irq_router_init(void) -{ - int i; - - /* route LPC int to cpu core0 int 0 */ - LOONGSON_INT_ROUTER_LPC = - LOONGSON_INT_COREx_INTy(loongson_sysconf.boot_cpu_id, 0); - /* route HT1 int0 ~ int7 to cpu core0 INT1*/ - for (i = 0; i < 8; i++) - LOONGSON_INT_ROUTER_HT1(i) = - LOONGSON_INT_COREx_INTy(loongson_sysconf.boot_cpu_id, 1); - /* enable HT1 interrupt */ - LOONGSON_HT1_INTN_EN(0) = 0xffffffff; - /* enable router interrupt intenset */ - LOONGSON_INT_ROUTER_INTENSET = - LOONGSON_INT_ROUTER_INTEN | (0xffff << 16) | 0x1 << 10; -} - -void __init arch_init_irq(void) -{ - struct irq_chip *chip; - - clear_c0_status(ST0_IM | ST0_BEV); - - irq_router_init(); - mips_cpu_irq_init(); - init_i8259_irqs(); - chip = irq_get_chip(I8259A_IRQ_BASE); - chip->irq_set_affinity = plat_set_irq_affinity; - - irq_set_chip_and_handler(LOONGSON_UART_IRQ, - &loongson_irq_chip, handle_percpu_irq); - irq_set_chip_and_handler(LOONGSON_BRIDGE_IRQ, - &loongson_irq_chip, handle_percpu_irq); - - set_c0_status(STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP6); -} - -#ifdef CONFIG_HOTPLUG_CPU - -void fixup_irqs(void) -{ - irq_cpu_offline(); - clear_c0_status(ST0_IM); -} - -#endif diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c index e5b40c5e3296..1ae072df4831 100644 --- a/arch/mips/loongson64/numa.c +++ b/arch/mips/loongson64/numa.c @@ -122,7 +122,7 @@ static unsigned long nid_to_addroffset(unsigned int nid) static void __init szmem(unsigned int node) { u32 i, mem_type; - static unsigned long num_physpages = 0; + static unsigned long num_physpages; u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size; /* Parse memory information and activate */ diff --git a/arch/mips/loongson64/setup.c b/arch/mips/loongson64/setup.c index 4fd27f4f90ed..6fe3ffffcaa6 100644 --- a/arch/mips/loongson64/setup.c +++ b/arch/mips/loongson64/setup.c @@ -8,9 +8,15 @@ #include <asm/wbflush.h> #include <asm/bootinfo.h> +#include <linux/libfdt.h> +#include <linux/of_fdt.h> + +#include <asm/prom.h> #include <loongson.h> +void *loongson_fdt_blob; + static void wbflush_loongson(void) { asm(".set\tpush\n\t" @@ -27,4 +33,14 @@ EXPORT_SYMBOL(__wbflush); void __init plat_mem_setup(void) { + if (loongson_fdt_blob) + __dt_setup_arch(loongson_fdt_blob); +} + +void __init device_tree_init(void) +{ + if (!initial_boot_params) + return; + + unflatten_and_copy_device_tree(); } diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index de8e0741ce2d..e1fe8bbb377d 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -4,6 +4,7 @@ * Author: Chen Huacai, chenhc@lemote.com */ +#include <irq.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/sched.h> @@ -25,6 +26,8 @@ DEFINE_PER_CPU(int, cpu_state); +#define LS_IPI_IRQ (MIPS_CPU_IRQ_BASE + 6) + static void *ipi_set0_regs[16]; static void *ipi_clear0_regs[16]; static void *ipi_status0_regs[16]; @@ -302,20 +305,13 @@ loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action) ipi_write_action(cpu_logical_map(i), (u32)action); } -#define IPI_IRQ_OFFSET 6 - -void loongson3_send_irq_by_ipi(int cpu, int irqs) -{ - ipi_write_action(cpu_logical_map(cpu), irqs << IPI_IRQ_OFFSET); -} -void loongson3_ipi_interrupt(struct pt_regs *regs) +static irqreturn_t loongson3_ipi_interrupt(int irq, void *dev_id) { int i, cpu = smp_processor_id(); - unsigned int action, c0count, irqs; + unsigned int action, c0count; action = ipi_read_clear(cpu); - irqs = action >> IPI_IRQ_OFFSET; if (action & SMP_RESCHEDULE_YOURSELF) scheduler_ipi(); @@ -335,13 +331,7 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) __wbflush(); /* Let others see the result ASAP */ } - if (irqs) { - int irq; - while ((irq = ffs(irqs))) { - do_IRQ(irq-1); - irqs &= ~(1<<(irq-1)); - } - } + return IRQ_HANDLED; } #define MAX_LOOPS 800 @@ -438,6 +428,9 @@ static void __init loongson3_smp_setup(void) static void __init loongson3_prepare_cpus(unsigned int max_cpus) { + if (request_irq(LS_IPI_IRQ, loongson3_ipi_interrupt, + IRQF_PERCPU | IRQF_NO_SUSPEND, "SMP_IPI", NULL)) + pr_err("Failed to request IPI IRQ\n"); init_cpu_present(cpu_possible_mask); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; } @@ -484,7 +477,8 @@ static int loongson3_cpu_disable(void) set_cpu_online(cpu, false); calculate_cpu_foreign_map(); local_irq_save(flags); - fixup_irqs(); + irq_cpu_offline(); + clear_c0_status(ST0_IM); local_irq_restore(flags); local_flush_tlb_all(); diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c index 8064821e9805..4baf965e6fe8 100644 --- a/arch/mips/mm/c-octeon.c +++ b/arch/mips/mm/c-octeon.c @@ -237,17 +237,17 @@ static void probe_octeon(void) c->dcache.sets = dcache_size / (c->dcache.linesz * c->dcache.ways); if (smp_processor_id() == 0) { - pr_notice("Primary instruction cache %ldkB, %s, %d way, " - "%d sets, linesize %d bytes.\n", - icache_size >> 10, - cpu_has_vtag_icache ? + pr_info("Primary instruction cache %ldkB, %s, %d way, " + "%d sets, linesize %d bytes.\n", + icache_size >> 10, + cpu_has_vtag_icache ? "virtually tagged" : "physically tagged", - c->icache.ways, c->icache.sets, c->icache.linesz); + c->icache.ways, c->icache.sets, c->icache.linesz); - pr_notice("Primary data cache %ldkB, %d-way, %d sets, " - "linesize %d bytes.\n", - dcache_size >> 10, c->dcache.ways, - c->dcache.sets, c->dcache.linesz); + pr_info("Primary data cache %ldkB, %d-way, %d sets, " + "linesize %d bytes.\n", + dcache_size >> 10, c->dcache.ways, + c->dcache.sets, c->dcache.linesz); } } diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c index 15bb8cf59828..780dd2a567c1 100644 --- a/arch/mips/mm/c-r3k.c +++ b/arch/mips/mm/c-r3k.c @@ -316,9 +316,9 @@ void r3k_cache_init(void) _dma_cache_wback = r3k_dma_cache_wback_inv; _dma_cache_inv = r3k_dma_cache_wback_inv; - printk("Primary instruction cache %ldkB, linesize %ld bytes.\n", + pr_info("Primary instruction cache %ldkB, linesize %ld bytes.\n", icache_size >> 10, icache_lsize); - printk("Primary data cache %ldkB, linesize %ld bytes.\n", + pr_info("Primary data cache %ldkB, linesize %ld bytes.\n", dcache_size >> 10, dcache_lsize); build_clear_page(); diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 5f3d0103b95d..36a311348739 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -901,6 +901,31 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) __sync(); } +static void prefetch_cache_inv(unsigned long addr, unsigned long size) +{ + unsigned int linesz = cpu_scache_line_size(); + unsigned long addr0 = addr, addr1; + + addr0 &= ~(linesz - 1); + addr1 = (addr0 + size - 1) & ~(linesz - 1); + + protected_writeback_scache_line(addr0); + if (likely(addr1 != addr0)) + protected_writeback_scache_line(addr1); + else + return; + + addr0 += linesz; + if (likely(addr1 != addr0)) + protected_writeback_scache_line(addr0); + else + return; + + addr1 -= linesz; + if (likely(addr1 > addr0)) + protected_writeback_scache_line(addr0); +} + static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) { /* Catch bad driver code */ @@ -908,6 +933,10 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) return; preempt_disable(); + + if (current_cpu_type() == CPU_BMIPS5000) + prefetch_cache_inv(addr, size); + if (cpu_has_inclusive_pcaches) { if (size >= scache_size) { if (current_cpu_type() != CPU_LOONGSON64) @@ -1467,17 +1496,17 @@ static void probe_pcache(void) c->icache.ways = 1; } - printk("Primary instruction cache %ldkB, %s, %s, linesize %d bytes.\n", - icache_size >> 10, - c->icache.flags & MIPS_CACHE_VTAG ? "VIVT" : "VIPT", - way_string[c->icache.ways], c->icache.linesz); + pr_info("Primary instruction cache %ldkB, %s, %s, linesize %d bytes.\n", + icache_size >> 10, + c->icache.flags & MIPS_CACHE_VTAG ? "VIVT" : "VIPT", + way_string[c->icache.ways], c->icache.linesz); - printk("Primary data cache %ldkB, %s, %s, %s, linesize %d bytes\n", - dcache_size >> 10, way_string[c->dcache.ways], - (c->dcache.flags & MIPS_CACHE_PINDEX) ? "PIPT" : "VIPT", - (c->dcache.flags & MIPS_CACHE_ALIASES) ? + pr_info("Primary data cache %ldkB, %s, %s, %s, linesize %d bytes\n", + dcache_size >> 10, way_string[c->dcache.ways], + (c->dcache.flags & MIPS_CACHE_PINDEX) ? "PIPT" : "VIPT", + (c->dcache.flags & MIPS_CACHE_ALIASES) ? "cache aliases" : "no aliases", - c->dcache.linesz); + c->dcache.linesz); } static void probe_vcache(void) diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c index 686867270627..2d479cc7e66b 100644 --- a/arch/mips/mm/c-tx39.c +++ b/arch/mips/mm/c-tx39.c @@ -410,9 +410,9 @@ void tx39_cache_init(void) current_cpu_data.icache.waybit = 0; current_cpu_data.dcache.waybit = 0; - printk("Primary instruction cache %ldkB, linesize %d bytes\n", + pr_info("Primary instruction cache %ldkB, linesize %d bytes\n", icache_size >> 10, current_cpu_data.icache.linesz); - printk("Primary data cache %ldkB, linesize %d bytes\n", + pr_info("Primary data cache %ldkB, linesize %d bytes\n", dcache_size >> 10, current_cpu_data.dcache.linesz); build_clear_page(); diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 1e8d00793784..4a0eafe3d932 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -44,7 +44,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, const int field = sizeof(unsigned long) * 2; int si_code; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); @@ -154,7 +154,7 @@ good_area: */ fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); @@ -178,7 +178,6 @@ good_area: tsk->min_flt++; } if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 344e6e9ea43b..da407cdc2135 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1480,6 +1480,7 @@ static void build_r4000_tlb_refill_handler(void) static void setup_pw(void) { + unsigned int pwctl; unsigned long pgd_i, pgd_w; #ifndef __PAGETABLE_PMD_FOLDED unsigned long pmd_i, pmd_w; @@ -1506,6 +1507,7 @@ static void setup_pw(void) pte_i = ilog2(_PAGE_GLOBAL); pte_w = 0; + pwctl = 1 << 30; /* Set PWDirExt */ #ifndef __PAGETABLE_PMD_FOLDED write_c0_pwfield(pgd_i << 24 | pmd_i << 12 | pt_i << 6 | pte_i); @@ -1516,8 +1518,9 @@ static void setup_pw(void) #endif #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT - write_c0_pwctl(1 << 6 | psn); + pwctl |= (1 << 6 | psn); #endif + write_c0_pwctl(pwctl); write_c0_kpgd((long)swapper_pg_dir); kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */ } diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index a840e0c1642c..03d85b2b3eea 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -144,12 +144,6 @@ static irqreturn_t corehi_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction corehi_irqaction = { - .handler = corehi_handler, - .name = "CoreHi", - .flags = IRQF_NO_THREAD, -}; - static msc_irqmap_t msc_irqmap[] __initdata = { {MSC01C_INT_TMR, MSC01_IRQ_EDGE, 0}, {MSC01C_INT_PCI, MSC01_IRQ_LEVEL, 0}, @@ -223,5 +217,7 @@ void __init arch_init_irq(void) corehi_irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_COREHI; } - setup_irq(corehi_irq, &corehi_irqaction); + if (request_irq(corehi_irq, corehi_handler, IRQF_NO_THREAD, "CoreHi", + NULL)) + pr_err("Failed to request irq %d (CoreHi)\n", corehi_irq); } diff --git a/arch/mips/netlogic/xlr/fmn.c b/arch/mips/netlogic/xlr/fmn.c index d428e8471eec..d7db1533889a 100644 --- a/arch/mips/netlogic/xlr/fmn.c +++ b/arch/mips/netlogic/xlr/fmn.c @@ -110,12 +110,6 @@ static irqreturn_t fmn_message_handler(int irq, void *data) return IRQ_HANDLED; } -struct irqaction fmn_irqaction = { - .handler = fmn_message_handler, - .flags = IRQF_PERCPU, - .name = "fmn", -}; - void xlr_percpu_fmn_init(void) { struct xlr_fmn_info *cpu_fmn_info; @@ -195,8 +189,9 @@ void nlm_setup_fmn_irq(void) { uint32_t flags; - /* setup irq only once */ - setup_irq(IRQ_FMN, &fmn_irqaction); + /* request irq only once */ + if (request_irq(IRQ_FMN, fmn_message_handler, IRQF_PERCPU, "fmn", NULL)) + pr_err("Failed to request irq %d (fmn)\n", IRQ_FMN); flags = nlm_cop2_enable_irqsave(); nlm_fmn_setup_intr(IRQ_FMN, (1 << nlm_threads_per_core) - 1); diff --git a/arch/mips/pic32/pic32mzda/time.c b/arch/mips/pic32/pic32mzda/time.c index 905ec1d86928..7174e9abbb1b 100644 --- a/arch/mips/pic32/pic32mzda/time.c +++ b/arch/mips/pic32/pic32mzda/time.c @@ -3,11 +3,11 @@ * Joshua Henderson <joshua.henderson@microchip.com> * Copyright (C) 2015 Microchip Technology Inc. All rights reserved. */ -#include <linux/clk-provider.h> #include <linux/clocksource.h> #include <linux/init.h> #include <linux/irqdomain.h> #include <linux/of.h> +#include <linux/of_clk.h> #include <linux/of_irq.h> #include <asm/time.h> @@ -23,7 +23,7 @@ static const struct of_device_id pic32_infra_match[] = { static unsigned int pic32_xlate_core_timer_irq(void) { - static struct device_node *node; + struct device_node *node; unsigned int irq; node = of_find_matching_node(NULL, pic32_infra_match); diff --git a/arch/mips/pistachio/time.c b/arch/mips/pistachio/time.c index 3c9235c7710a..de64751dec40 100644 --- a/arch/mips/pistachio/time.c +++ b/arch/mips/pistachio/time.c @@ -6,10 +6,10 @@ */ #include <linux/clk.h> -#include <linux/clk-provider.h> #include <linux/clocksource.h> #include <linux/init.h> #include <linux/of.h> +#include <linux/of_clk.h> #include <asm/mips-cps.h> #include <asm/time.h> diff --git a/arch/mips/pmcs-msp71xx/msp_irq.c b/arch/mips/pmcs-msp71xx/msp_irq.c index 8d53d7a2ed45..d525cc931d89 100644 --- a/arch/mips/pmcs-msp71xx/msp_irq.c +++ b/arch/mips/pmcs-msp71xx/msp_irq.c @@ -107,18 +107,6 @@ asmlinkage void plat_irq_dispatch(void) do_IRQ(MSP_INT_SW1); } -static struct irqaction cic_cascade_msp = { - .handler = no_action, - .name = "MSP CIC cascade", - .flags = IRQF_NO_THREAD, -}; - -static struct irqaction per_cascade_msp = { - .handler = no_action, - .name = "MSP PER cascade", - .flags = IRQF_NO_THREAD, -}; - void __init arch_init_irq(void) { /* assume we'll be using vectored interrupt mode except in UP mode*/ @@ -142,8 +130,12 @@ void __init arch_init_irq(void) #endif /* CONFIG_MIPS_MT_SMP */ #endif /* CONFIG_MIPS_MT */ /* setup the cascaded interrupts */ - setup_irq(MSP_INT_CIC, &cic_cascade_msp); - setup_irq(MSP_INT_PER, &per_cascade_msp); + if (request_irq(MSP_INT_CIC, no_action, IRQF_NO_THREAD, + "MSP CIC cascade", NULL)) + pr_err("Failed to register MSP CIC cascade interrupt\n"); + if (request_irq(MSP_INT_PER, no_action, IRQF_NO_THREAD, + "MSP PER cascade", NULL)) + pr_err("Failed to register MSP PER cascade interrupt\n"); #else /* @@ -153,7 +145,11 @@ void __init arch_init_irq(void) msp_slp_irq_init(); /* setup the cascaded SLP/PER interrupts */ - setup_irq(MSP_INT_SLP, &cic_cascade_msp); - setup_irq(MSP_INT_PER, &per_cascade_msp); + if (request_irq(MSP_INT_SLP, no_action, IRQF_NO_THREAD, + "MSP CIC cascade", NULL)) + pr_err("Failed to register MSP CIC cascade interrupt\n"); + if (request_irq(MSP_INT_PER, no_action, IRQF_NO_THREAD, + "MSP PER cascade", NULL)) + pr_err("Failed to register MSP PER cascade interrupt\n"); #endif } diff --git a/arch/mips/pmcs-msp71xx/msp_smp.c b/arch/mips/pmcs-msp71xx/msp_smp.c index 8f00d26f2a53..00092e2924ec 100644 --- a/arch/mips/pmcs-msp71xx/msp_smp.c +++ b/arch/mips/pmcs-msp71xx/msp_smp.c @@ -38,21 +38,10 @@ static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction irq_resched = { - .handler = ipi_resched_interrupt, - .flags = IRQF_PERCPU, - .name = "IPI_resched" -}; - -static struct irqaction irq_call = { - .handler = ipi_call_interrupt, - .flags = IRQF_PERCPU, - .name = "IPI_call" -}; - -void __init arch_init_ipiirq(int irq, struct irqaction *action) +void __init arch_init_ipiirq(int irq, const char *name, irq_handler_t handler) { - setup_irq(irq, action); + if (request_irq(irq, handler, IRQF_PERCPU, name, NULL)) + pr_err("Failed to request irq %d (%s)\n", irq, name); irq_set_handler(irq, handle_percpu_irq); } @@ -60,7 +49,8 @@ void __init msp_vsmp_int_init(void) { set_vi_handler(MIPS_CPU_IPI_RESCHED_IRQ, ipi_resched_dispatch); set_vi_handler(MIPS_CPU_IPI_CALL_IRQ, ipi_call_dispatch); - arch_init_ipiirq(MIPS_CPU_IPI_RESCHED_IRQ, &irq_resched); - arch_init_ipiirq(MIPS_CPU_IPI_CALL_IRQ, &irq_call); + arch_init_ipiirq(MIPS_CPU_IPI_RESCHED_IRQ, "IPI_resched", + ipi_resched_interrupt); + arch_init_ipiirq(MIPS_CPU_IPI_CALL_IRQ, "IPI_call", ipi_call_interrupt); } #endif /* CONFIG_MIPS_MT_SMP */ diff --git a/arch/mips/pmcs-msp71xx/msp_time.c b/arch/mips/pmcs-msp71xx/msp_time.c index d83de01f00b8..9c629829f447 100644 --- a/arch/mips/pmcs-msp71xx/msp_time.c +++ b/arch/mips/pmcs-msp71xx/msp_time.c @@ -27,7 +27,6 @@ #define get_current_vpe() \ ((read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE) -static struct irqaction timer_vpe1; static int tim_installed; void __init plat_time_init(void) @@ -77,10 +76,13 @@ void __init plat_time_init(void) unsigned int get_c0_compare_int(void) { + unsigned long flags = IRQF_PERCPU | IRQF_TIMER | IRQF_SHARED; + /* MIPS_MT modes may want timer for second VPE */ if ((get_current_vpe()) && !tim_installed) { - memcpy(&timer_vpe1, &c0_compare_irqaction, sizeof(timer_vpe1)); - setup_irq(MSP_INT_VPE1_TIMER, &timer_vpe1); + if (request_irq(MSP_INT_VPE1_TIMER, c0_compare_interrupt, flags, + "timer", c0_compare_interrupt)) + pr_err("Failed to register timer interrupt\n"); tim_installed++; } diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 94e9ce994494..35c2ebd8f094 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -52,6 +52,7 @@ choice select COMMON_CLK select CLKSRC_MIPS_GIC select HAVE_PCI if PCI_MT7621 + select SOC_BUS endchoice choice diff --git a/arch/mips/ralink/cevt-rt3352.c b/arch/mips/ralink/cevt-rt3352.c index 61a08943eb2f..269d4877d120 100644 --- a/arch/mips/ralink/cevt-rt3352.c +++ b/arch/mips/ralink/cevt-rt3352.c @@ -82,12 +82,6 @@ static struct systick_device systick = { }, }; -static struct irqaction systick_irqaction = { - .handler = systick_interrupt, - .flags = IRQF_PERCPU | IRQF_TIMER, - .dev_id = &systick.dev, -}; - static int systick_shutdown(struct clock_event_device *evt) { struct systick_device *sdev; @@ -95,7 +89,7 @@ static int systick_shutdown(struct clock_event_device *evt) sdev = container_of(evt, struct systick_device, dev); if (sdev->irq_requested) - free_irq(systick.dev.irq, &systick_irqaction); + free_irq(systick.dev.irq, &systick.dev); sdev->irq_requested = 0; iowrite32(0, systick.membase + SYSTICK_CONFIG); @@ -104,12 +98,17 @@ static int systick_shutdown(struct clock_event_device *evt) static int systick_set_oneshot(struct clock_event_device *evt) { + const char *name = systick.dev.name; struct systick_device *sdev; + int irq = systick.dev.irq; sdev = container_of(evt, struct systick_device, dev); - if (!sdev->irq_requested) - setup_irq(systick.dev.irq, &systick_irqaction); + if (!sdev->irq_requested) { + if (request_irq(irq, systick_interrupt, + IRQF_PERCPU | IRQF_TIMER, name, &systick.dev)) + pr_err("Failed to request irq %d (%s)\n", irq, name); + } sdev->irq_requested = 1; iowrite32(CFG_EXT_STK_EN | CFG_CNT_EN, systick.membase + SYSTICK_CONFIG); @@ -125,7 +124,6 @@ static int __init ralink_systick_init(struct device_node *np) if (!systick.membase) return -ENXIO; - systick_irqaction.name = np->name; systick.dev.name = np->name; clockevents_calc_mult_shift(&systick.dev, SYSTICK_FREQ, 60); systick.dev.max_delta_ns = clockevent_delta2ns(0x7fff, &systick.dev); diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c index 9415be0d57b8..0accb80db709 100644 --- a/arch/mips/ralink/mt7621.c +++ b/arch/mips/ralink/mt7621.c @@ -7,6 +7,8 @@ #include <linux/kernel.h> #include <linux/init.h> +#include <linux/slab.h> +#include <linux/sys_soc.h> #include <asm/mipsregs.h> #include <asm/smp-ops.h> @@ -160,6 +162,33 @@ void __init ralink_of_remap(void) panic("Failed to remap core resources"); } +static void soc_dev_init(struct ralink_soc_info *soc_info, u32 rev) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return; + + soc_dev_attr->soc_id = "mt7621"; + soc_dev_attr->family = "Ralink"; + + if (((rev >> CHIP_REV_VER_SHIFT) & CHIP_REV_VER_MASK) == 1 && + (rev & CHIP_REV_ECO_MASK) == 1) + soc_dev_attr->revision = "E2"; + else + soc_dev_attr->revision = "E1"; + + soc_dev_attr->data = soc_info; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return; + } +} + void prom_soc_init(struct ralink_soc_info *soc_info) { void __iomem *sysc = (void __iomem *) KSEG1ADDR(MT7621_SYSC_BASE); @@ -214,6 +243,7 @@ void prom_soc_init(struct ralink_soc_info *soc_info) rt2880_pinmux_data = mt7621_pinmux_data; + soc_dev_init(soc_info, rev); if (!register_cps_smp_ops()) return; diff --git a/arch/mips/ralink/timer-gic.c b/arch/mips/ralink/timer-gic.c index 944fbe0fc741..dcf2a44ac51e 100644 --- a/arch/mips/ralink/timer-gic.c +++ b/arch/mips/ralink/timer-gic.c @@ -8,7 +8,7 @@ #include <linux/init.h> #include <linux/of.h> -#include <linux/clk-provider.h> +#include <linux/of_clk.h> #include <linux/clocksource.h> #include "common.h" diff --git a/arch/mips/sgi-ip22/ip22-eisa.c b/arch/mips/sgi-ip22/ip22-eisa.c index a0a79222ce0b..f3b0e90e0135 100644 --- a/arch/mips/sgi-ip22/ip22-eisa.c +++ b/arch/mips/sgi-ip22/ip22-eisa.c @@ -92,11 +92,6 @@ static irqreturn_t ip22_eisa_intr(int irq, void *dev_id) return IRQ_NONE; } -static struct irqaction eisa_action = { - .handler = ip22_eisa_intr, - .name = "EISA", -}; - int __init ip22_eisa_init(void) { int i, c; @@ -136,9 +131,8 @@ int __init ip22_eisa_init(void) init_i8259_irqs(); - /* Cannot use request_irq because of kmalloc not being ready at such - * an early stage. Yes, I've been bitten... */ - setup_irq(SGI_EISA_IRQ, &eisa_action); + if (request_irq(SGI_EISA_IRQ, ip22_eisa_intr, 0, "EISA", NULL)) + pr_err("Failed to request irq %d (EISA)\n", SGI_EISA_IRQ); EISA_bus = 1; return 0; diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c index 3804895fa697..96798a4ab2de 100644 --- a/arch/mips/sgi-ip22/ip22-int.c +++ b/arch/mips/sgi-ip22/ip22-int.c @@ -159,36 +159,7 @@ static void __irq_entry indy_buserror_irq(void) irq_exit(); } -static struct irqaction local0_cascade = { - .handler = no_action, - .flags = IRQF_NO_THREAD, - .name = "local0 cascade", -}; - -static struct irqaction local1_cascade = { - .handler = no_action, - .flags = IRQF_NO_THREAD, - .name = "local1 cascade", -}; - -static struct irqaction buserr = { - .handler = no_action, - .flags = IRQF_NO_THREAD, - .name = "Bus Error", -}; - -static struct irqaction map0_cascade = { - .handler = no_action, - .flags = IRQF_NO_THREAD, - .name = "mapable0 cascade", -}; - #ifdef USE_LIO3_IRQ -static struct irqaction map1_cascade = { - .handler = no_action, - .flags = IRQF_NO_THREAD, - .name = "mapable1 cascade", -}; #define SGI_INTERRUPTS SGINT_END #else #define SGI_INTERRUPTS SGINT_LOCAL3 @@ -322,14 +293,24 @@ void __init arch_init_irq(void) } /* vector handler. this register the IRQ as non-sharable */ - setup_irq(SGI_LOCAL_0_IRQ, &local0_cascade); - setup_irq(SGI_LOCAL_1_IRQ, &local1_cascade); - setup_irq(SGI_BUSERR_IRQ, &buserr); + if (request_irq(SGI_LOCAL_0_IRQ, no_action, IRQF_NO_THREAD, + "local0 cascade", NULL)) + pr_err("Failed to register local0 cascade interrupt\n"); + if (request_irq(SGI_LOCAL_1_IRQ, no_action, IRQF_NO_THREAD, + "local1 cascade", NULL)) + pr_err("Failed to register local1 cascade interrupt\n"); + if (request_irq(SGI_BUSERR_IRQ, no_action, IRQF_NO_THREAD, + "Bus Error", NULL)) + pr_err("Failed to register Bus Error interrupt\n"); /* cascade in cascade. i love Indy ;-) */ - setup_irq(SGI_MAP_0_IRQ, &map0_cascade); + if (request_irq(SGI_MAP_0_IRQ, no_action, IRQF_NO_THREAD, + "mapable0 cascade", NULL)) + pr_err("Failed to register mapable0 cascade interrupt\n"); #ifdef USE_LIO3_IRQ - setup_irq(SGI_MAP_1_IRQ, &map1_cascade); + if (request_irq(SGI_MAP_1_IRQ, no_action, IRQF_NO_THREAD, + "mapable1 cascade", NULL)) + pr_err("Failed to register mapable1 cascade interrupt\n"); #endif #ifdef CONFIG_EISA diff --git a/arch/mips/sgi-ip32/ip32-irq.c b/arch/mips/sgi-ip32/ip32-irq.c index a6a0ff7f5aed..1bbd5bfb5458 100644 --- a/arch/mips/sgi-ip32/ip32-irq.c +++ b/arch/mips/sgi-ip32/ip32-irq.c @@ -111,16 +111,6 @@ static inline void flush_mace_bus(void) extern irqreturn_t crime_memerr_intr(int irq, void *dev_id); extern irqreturn_t crime_cpuerr_intr(int irq, void *dev_id); -static struct irqaction memerr_irq = { - .handler = crime_memerr_intr, - .name = "CRIME memory error", -}; - -static struct irqaction cpuerr_irq = { - .handler = crime_cpuerr_intr, - .name = "CRIME CPU error", -}; - /* * This is for pure CRIME interrupts - ie not MACE. The advantage? * We get to split the register in half and do faster lookups. @@ -497,8 +487,12 @@ void __init arch_init_irq(void) break; } } - setup_irq(CRIME_MEMERR_IRQ, &memerr_irq); - setup_irq(CRIME_CPUERR_IRQ, &cpuerr_irq); + if (request_irq(CRIME_MEMERR_IRQ, crime_memerr_intr, 0, + "CRIME memory error", NULL)) + pr_err("Failed to register CRIME memory error interrupt\n"); + if (request_irq(CRIME_CPUERR_IRQ, crime_cpuerr_intr, 0, + "CRIME CPU error", NULL)) + pr_err("Failed to register CRIME CPU error interrupt\n"); #define ALLINTS (IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5) change_c0_status(ST0_IM, ALLINTS); diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index f9407e170476..0ecffb65fd6d 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -222,7 +222,9 @@ void __init sni_a20r_irq_init(void) irq_set_chip_and_handler(i, &a20r_irq_type, handle_level_irq); sni_hwint = a20r_hwint; change_c0_status(ST0_IM, IE_IRQ0); - setup_irq(SNI_A20R_IRQ_BASE + 3, &sni_isa_irq); + if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, 0, "ISA", + NULL)) + pr_err("Failed to register ISA interrupt\n"); } void sni_a20r_init(void) diff --git a/arch/mips/sni/irq.c b/arch/mips/sni/irq.c index ac61b90bcc66..dec89afc9886 100644 --- a/arch/mips/sni/irq.c +++ b/arch/mips/sni/irq.c @@ -27,7 +27,7 @@ asmlinkage void plat_irq_dispatch(void) } /* ISA irq handler */ -static irqreturn_t sni_isa_irq_handler(int dummy, void *p) +irqreturn_t sni_isa_irq_handler(int dummy, void *p) { int irq; @@ -39,12 +39,6 @@ static irqreturn_t sni_isa_irq_handler(int dummy, void *p) return IRQ_HANDLED; } -struct irqaction sni_isa_irq = { - .handler = sni_isa_irq_handler, - .name = "ISA", - .flags = IRQF_SHARED -}; - /* * On systems with i8259-style interrupt controllers we assume for * driver compatibility reasons interrupts 0 - 15 to be the i8295 diff --git a/arch/mips/sni/pcit.c b/arch/mips/sni/pcit.c index 05bb51676e82..b331fe22c529 100644 --- a/arch/mips/sni/pcit.c +++ b/arch/mips/sni/pcit.c @@ -244,7 +244,9 @@ void __init sni_pcit_irq_init(void) *(volatile u32 *)SNI_PCIT_INT_REG = 0; sni_hwint = sni_pcit_hwint; change_c0_status(ST0_IM, IE_IRQ1); - setup_irq(SNI_PCIT_INT_START + 6, &sni_isa_irq); + if (request_irq(SNI_PCIT_INT_START + 6, sni_isa_irq_handler, 0, "ISA", + NULL)) + pr_err("Failed to register ISA interrupt\n"); } void __init sni_pcit_cplus_irq_init(void) @@ -257,7 +259,9 @@ void __init sni_pcit_cplus_irq_init(void) *(volatile u32 *)SNI_PCIT_INT_REG = 0x40000000; sni_hwint = sni_pcit_hwint_cplus; change_c0_status(ST0_IM, IE_IRQ0); - setup_irq(MIPS_CPU_IRQ_BASE + 3, &sni_isa_irq); + if (request_irq(MIPS_CPU_IRQ_BASE + 3, sni_isa_irq_handler, 0, "ISA", + NULL)) + pr_err("Failed to register ISA interrupt\n"); } void __init sni_pcit_init(void) diff --git a/arch/mips/sni/rm200.c b/arch/mips/sni/rm200.c index f6fa9afcbfd3..d84744ca871d 100644 --- a/arch/mips/sni/rm200.c +++ b/arch/mips/sni/rm200.c @@ -356,11 +356,6 @@ void sni_rm200_init_8259A(void) /* * IRQ2 is cascade interrupt to second interrupt controller */ -static struct irqaction sni_rm200_irq2 = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; static struct resource sni_rm200_pic1_resource = { .name = "onboard ISA pic1", @@ -389,12 +384,6 @@ static irqreturn_t sni_rm200_i8259A_irq_handler(int dummy, void *p) return IRQ_HANDLED; } -struct irqaction sni_rm200_i8259A_irq = { - .handler = sni_rm200_i8259A_irq_handler, - .name = "onboard ISA", - .flags = IRQF_SHARED -}; - void __init sni_rm200_i8259_irqs(void) { int i; @@ -417,7 +406,9 @@ void __init sni_rm200_i8259_irqs(void) irq_set_chip_and_handler(i, &sni_rm200_i8259A_chip, handle_level_irq); - setup_irq(RM200_I8259A_IRQ_BASE + PIC_CASCADE_IR, &sni_rm200_irq2); + if (request_irq(RM200_I8259A_IRQ_BASE + PIC_CASCADE_IR, no_action, + IRQF_NO_THREAD, "cascade", NULL)) + pr_err("Failed to register cascade interrupt\n"); } @@ -481,8 +472,12 @@ void __init sni_rm200_irq_init(void) irq_set_chip_and_handler(i, &rm200_irq_type, handle_level_irq); sni_hwint = sni_rm200_hwint; change_c0_status(ST0_IM, IE_IRQ0); - setup_irq(SNI_RM200_INT_START + 0, &sni_rm200_i8259A_irq); - setup_irq(SNI_RM200_INT_START + 1, &sni_isa_irq); + if (request_irq(SNI_RM200_INT_START + 0, sni_rm200_i8259A_irq_handler, + 0, "onboard ISA", NULL)) + pr_err("Failed to register onboard ISA interrupt\n"); + if (request_irq(SNI_RM200_INT_START + 1, sni_isa_irq_handler, 0, "ISA", + NULL)) + pr_err("Failed to register ISA interrupt\n"); } void __init sni_rm200_init(void) diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c index dbace1f3e1a9..240bb68ec247 100644 --- a/arch/mips/sni/time.c +++ b/arch/mips/sni/time.c @@ -55,12 +55,6 @@ static irqreturn_t a20r_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction a20r_irqaction = { - .handler = a20r_interrupt, - .flags = IRQF_PERCPU | IRQF_TIMER, - .name = "a20r-timer", -}; - /* * a20r platform uses 2 counters to divide the input frequency. * Counter 2 output is connected to Counter 0 & 1 input. @@ -68,13 +62,13 @@ static struct irqaction a20r_irqaction = { static void __init sni_a20r_timer_setup(void) { struct clock_event_device *cd = &a20r_clockevent_device; - struct irqaction *action = &a20r_irqaction; unsigned int cpu = smp_processor_id(); cd->cpumask = cpumask_of(cpu); clockevents_register_device(cd); - action->dev_id = cd; - setup_irq(SNI_A20R_IRQ_TIMER, &a20r_irqaction); + if (request_irq(SNI_A20R_IRQ_TIMER, a20r_interrupt, + IRQF_PERCPU | IRQF_TIMER, "a20r-timer", cd)) + pr_err("Failed to register a20r-timer interrupt\n"); } #define SNI_8254_TICK_RATE 1193182UL 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/mips/vr41xx/common/irq.c b/arch/mips/vr41xx/common/irq.c index 7a826fbf9060..8f68446ff2d9 100644 --- a/arch/mips/vr41xx/common/irq.c +++ b/arch/mips/vr41xx/common/irq.c @@ -17,12 +17,6 @@ typedef struct irq_cascade { static irq_cascade_t irq_cascade[NR_IRQS] __cacheline_aligned; -static struct irqaction cascade_irqaction = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - int cascade_irq(unsigned int irq, int (*get_irq)(unsigned int)) { int retval = 0; @@ -36,7 +30,8 @@ int cascade_irq(unsigned int irq, int (*get_irq)(unsigned int)) irq_cascade[irq].get_irq = get_irq; if (get_irq != NULL) { - retval = setup_irq(irq, &cascade_irqaction); + retval = request_irq(irq, no_action, IRQF_NO_THREAD, + "cascade", NULL); if (retval < 0) irq_cascade[irq].get_irq = NULL; } diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild index 77eae62036b5..ff1e94299317 100644 --- a/arch/nds32/include/asm/Kbuild +++ b/arch/nds32/include/asm/Kbuild @@ -1,46 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += asm-offsets.h -generic-y += atomic.h -generic-y += bitops.h -generic-y += bug.h -generic-y += bugs.h -generic-y += checksum.h generic-y += cmpxchg.h -generic-y += compat.h -generic-y += device.h -generic-y += div64.h -generic-y += dma.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += export.h -generic-y += fb.h generic-y += gpio.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h generic-y += parport.h -generic-y += pci.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += sections.h -generic-y += serial.h -generic-y += switch_to.h -generic-y += timex.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += xor.h -generic-y += unaligned.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h 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/nds32/mm/fault.c b/arch/nds32/mm/fault.c index 906dfb25353c..0cf0c08c7da2 100644 --- a/arch/nds32/mm/fault.c +++ b/arch/nds32/mm/fault.c @@ -80,7 +80,7 @@ void do_page_fault(unsigned long entry, unsigned long addr, int si_code; vm_fault_t fault; unsigned int mask = VM_READ | VM_WRITE | VM_EXEC; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; error_code = error_code & (ITYPE_mskINST | ITYPE_mskETYPE); tsk = current; @@ -214,7 +214,7 @@ good_area: * signal first. We do not need to release the mmap_sem because it * would already be released in __lock_page_or_retry in mm/filemap.c. */ - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { + if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return; @@ -246,7 +246,6 @@ good_area: 1, regs, addr); } if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 68093999bd26..7fe7437555fb 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -1,45 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += atomic.h -generic-y += barrier.h -generic-y += bitops.h -generic-y += bug.h -generic-y += bugs.h generic-y += cmpxchg.h -generic-y += compat.h -generic-y += current.h -generic-y += device.h -generic-y += div64.h -generic-y += dma.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += fb.h -generic-y += ftrace.h -generic-y += futex.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += local.h generic-y += mcs_spinlock.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 += sections.h -generic-y += serial.h generic-y += spinlock.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += unaligned.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 6a2e716b959f..ec9d8a9c426f 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -47,7 +47,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, struct mm_struct *mm = tsk->mm; int code = SEGV_MAPERR; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; cause >>= 2; @@ -133,7 +133,7 @@ good_area: */ fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -157,9 +157,6 @@ good_area: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk - * of starvation. */ - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index e12d6c1735a0..ca5987e11053 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -1,45 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += barrier.h -generic-y += bug.h -generic-y += bugs.h -generic-y += checksum.h -generic-y += compat.h -generic-y += current.h -generic-y += device.h -generic-y += div64.h -generic-y += dma.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += fb.h -generic-y += ftrace.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += local.h generic-y += mcs_spinlock.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 += qspinlock_types.h generic-y += qspinlock.h generic-y += qrwlock_types.h generic-y += qrwlock.h -generic-y += sections.h -generic-y += shmparam.h -generic-y += switch_to.h -generic-y += topology.h -generic-y += trace_clock.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h 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/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 5d4d3a9691d0..8af1cc78c4fb 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -50,7 +50,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, struct vm_area_struct *vma; int si_code; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; @@ -161,7 +161,7 @@ good_area: fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -181,7 +181,6 @@ good_area: else tsk->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would 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/Kbuild b/arch/parisc/include/asm/Kbuild index 9ceedf6393c4..e3ee5c0bfe80 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -2,26 +2,8 @@ generated-y += syscall_table_32.h generated-y += syscall_table_64.h generated-y += syscall_table_c32.h -generic-y += current.h -generic-y += device.h -generic-y += div64.h -generic-y += emergency-restart.h -generic-y += exec.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += percpu.h -generic-y += preempt.h generic-y += seccomp.h -generic-y += trace_clock.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h 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/parisc/mm/fault.c b/arch/parisc/mm/fault.c index adbd5e2144a3..86e8c848f3d7 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -274,7 +274,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (!mm) goto no_context; - flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + flags = FAULT_FLAG_DEFAULT; if (user_mode(regs)) flags |= FAULT_FLAG_USER; @@ -304,7 +304,7 @@ good_area: fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -328,14 +328,12 @@ good_area: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; - /* * No need to up_read(&mm->mmap_sem) as we would * have already released it in __lock_page_or_retry * in mm/filemap.c. */ - + flags |= FAULT_FLAG_TRIED; goto retry; } } diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 497b7d0b2d7e..5fc45364e86e 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 @@ -979,6 +980,7 @@ config PPC_SECURE_BOOT bool depends on PPC_POWERNV depends on IMA_ARCH_POLICY + imply IMA_SECURE_AND_OR_TRUSTED_BOOT help Systems with firmware secure boot enabled need to define security policies to extend secure boot to the OS. This config allows a user diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config index 9575a38c9155..b507df6ac69f 100644 --- a/arch/powerpc/configs/85xx-hw.config +++ b/arch/powerpc/configs/85xx-hw.config @@ -2,7 +2,6 @@ CONFIG_AQUANTIA_PHY=y CONFIG_AT803X_PHY=y CONFIG_ATA=y CONFIG_BLK_DEV_SD=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_BLK_DEV_SR=y CONFIG_BROADCOM_PHY=y CONFIG_C293_PCIE=y diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index f6d140f2d922..200bb1ecb560 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -44,7 +44,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SYM53C8XX_2=y diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index 502a75d49789..a4a805b87469 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -42,7 +42,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SYM53C8XX_2=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index fbfcc85e4dc0..a68c7f3af10e 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -62,7 +62,6 @@ CONFIG_CDROM_PKTCDVD=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig index 2975e64629aa..161351a18517 100644 --- a/arch/powerpc/configs/maple_defconfig +++ b/arch/powerpc/configs/maple_defconfig @@ -41,7 +41,6 @@ CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_IPR=y CONFIG_ATA=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 4b6d31d4474e..08b7f4cef243 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -60,7 +60,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_CHR_DEV_OSST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=y CONFIG_SCSI_CONSTANTS=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index f492e7d35925..05e325ca3fbd 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -117,7 +117,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 71749377d164..df8bdbaa5d8f 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -108,7 +108,6 @@ CONFIG_BLK_DEV_NVME=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 7e68cb222c7b..bae8170d7401 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -110,7 +110,6 @@ CONFIG_VIRTIO_BLK=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 0d746774c2bd..33a01a9e86be 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -60,7 +60,6 @@ CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 3e2f44f38ac5..feb5d47d8d1e 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -368,7 +368,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_ENCLOSURE=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 6b68109e248f..0bea4d3ffb85 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -97,7 +97,6 @@ CONFIG_VIRTIO_BLK=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 1b6bdad36b13..ad6739ac63dc 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -84,7 +84,6 @@ CONFIG_EEPROM_AT24=m # CONFIG_OCXL is not set CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index d0a23d0db863..dadbcf3a0b1e 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -3,12 +3,8 @@ generated-y += syscall_table_32.h generated-y += syscall_table_64.h generated-y += syscall_table_c32.h generated-y += syscall_table_spu.h -generic-y += div64.h -generic-y += dma-mapping.h generic-y += export.h -generic-y += irq_regs.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += preempt.h generic-y += vtime.h generic-y += early_ioremap.h 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/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 635fb154b33f..a3633560493b 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -150,4 +150,7 @@ #define KVM_INST_FETCH_FAILED -1 +/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h index 5a9834e0e2d1..9cb7d8be2366 100644 --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -5,6 +5,7 @@ #ifdef CONFIG_PPC_UV int kvmppc_uvmem_init(void); void kvmppc_uvmem_free(void); +bool kvmppc_uvmem_available(void); int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot); void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot); @@ -30,6 +31,11 @@ static inline int kvmppc_uvmem_init(void) static inline void kvmppc_uvmem_free(void) { } +static inline bool kvmppc_uvmem_available(void) +{ + return false; +} + static inline int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 6e8b8ffd06ad..f99b4333dfba 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -303,6 +303,7 @@ struct kvm_arch { u8 radix; u8 fwnmi_enabled; u8 secure_guest; + u8 svm_enabled; bool threads_indep; bool nested_enable; pgd_t *pgtable; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index bc2494e5710a..94f5a32acaf1 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -107,8 +107,6 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, unsigned int gtlb_idx); extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid); -extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu); -extern int kvmppc_mmu_init(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index, @@ -200,14 +198,11 @@ extern void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, - struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); -extern int kvmppc_core_create_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages); + struct kvm_memory_slot *slot); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, @@ -280,7 +275,8 @@ struct kvmppc_ops { void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change); void (*commit_memory_region)(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, @@ -291,11 +287,7 @@ struct kvmppc_ops { int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end); int (*test_age_hva)(struct kvm *kvm, unsigned long hva); void (*set_spte_hva)(struct kvm *kvm, unsigned long hva, pte_t pte); - void (*mmu_destroy)(struct kvm_vcpu *vcpu); - void (*free_memslot)(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); - int (*create_memslot)(struct kvm_memory_slot *slot, - unsigned long npages); + void (*free_memslot)(struct kvm_memory_slot *slot); int (*init_vm)(struct kvm *kvm); void (*destroy_vm)(struct kvm *kvm); int (*get_smmu_info)(struct kvm *kvm, struct kvm_ppc_smmu_info *info); @@ -321,6 +313,7 @@ struct kvmppc_ops { int size); int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, int size); + int (*enable_svm)(struct kvm *kvm); int (*svm_off)(struct kvm *kvm); }; 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/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.c b/arch/powerpc/kvm/book3s.c index d07a8e12fa15..5690a1f9b976 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -799,21 +799,19 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) return vcpu->kvm->arch.kvm_ops->check_requests(vcpu); } -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - return kvm->arch.kvm_ops->get_dirty_log(kvm, log); + } -void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - kvm->arch.kvm_ops->free_memslot(free, dont); + return kvm->arch.kvm_ops->get_dirty_log(kvm, log); } -int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - return kvm->arch.kvm_ops->create_memslot(slot, npages); + kvm->arch.kvm_ops->free_memslot(slot); } void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) @@ -823,9 +821,11 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { - return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem); + return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem, + change); } void kvmppc_core_commit_memory_region(struct kvm *kvm, @@ -858,11 +858,6 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) return 0; } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) -{ - vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); -} - int kvmppc_core_init_vm(struct kvm *kvm) { diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h index 3a4613985949..eae259ee49af 100644 --- a/arch/powerpc/kvm/book3s.h +++ b/arch/powerpc/kvm/book3s.h @@ -16,6 +16,7 @@ extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte); +extern int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu); extern int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance); diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index f21e73492ce3..3fbd570f9c1e 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -234,7 +234,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, case 2: case 6: pte->may_write = true; - /* fall through */ + fallthrough; case 3: case 5: case 7: diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index d4cb3bcf41b6..e8e7b2c530d1 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -356,7 +356,7 @@ void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu) /* From mm/mmu_context_hash32.c */ #define CTX_TO_VSID(c, id) ((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff) -int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int err; diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 599133256a95..26b8b27a3755 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -311,7 +311,7 @@ do_second: case 2: case 6: gpte->may_write = true; - /* fall through */ + fallthrough; case 3: case 5: case 7: diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index 044dd49eeb9d..e452158a18d7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -384,7 +384,7 @@ void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu) __destroy_context(to_book3s(vcpu)->context_id[0]); } -int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int err; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 6c372f5c61b6..3aecec890d6f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -485,18 +485,18 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, __be64 *hptep; unsigned long mmu_seq, psize, pte_size; unsigned long gpa_base, gfn_base; - unsigned long gpa, gfn, hva, pfn; + unsigned long gpa, gfn, hva, pfn, hpa; struct kvm_memory_slot *memslot; unsigned long *rmap; struct revmap_entry *rev; - struct page *page, *pages[1]; - long index, ret, npages; + struct page *page; + long index, ret; bool is_ci; - unsigned int writing, write_ok; - struct vm_area_struct *vma; + bool writing, write_ok; + unsigned int shift; unsigned long rcbits; long mmio_update; - struct mm_struct *mm; + pte_t pte, *ptep; if (kvm_is_radix(kvm)) return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr); @@ -570,59 +570,62 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, smp_rmb(); ret = -EFAULT; - is_ci = false; - pfn = 0; page = NULL; - mm = kvm->mm; - pte_size = PAGE_SIZE; writing = (dsisr & DSISR_ISSTORE) != 0; /* If writing != 0, then the HPTE must allow writing, if we get here */ write_ok = writing; hva = gfn_to_hva_memslot(memslot, gfn); - npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages); - if (npages < 1) { - /* Check if it's an I/O mapping */ - down_read(&mm->mmap_sem); - vma = find_vma(mm, hva); - if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end && - (vma->vm_flags & VM_PFNMAP)) { - pfn = vma->vm_pgoff + - ((hva - vma->vm_start) >> PAGE_SHIFT); - pte_size = psize; - is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot)))); - write_ok = vma->vm_flags & VM_WRITE; - } - up_read(&mm->mmap_sem); - if (!pfn) - goto out_put; + + /* + * Do a fast check first, since __gfn_to_pfn_memslot doesn't + * do it with !atomic && !async, which is how we call it. + * We always ask for write permission since the common case + * is that the page is writable. + */ + if (__get_user_pages_fast(hva, 1, 1, &page) == 1) { + write_ok = true; } else { - page = pages[0]; - pfn = page_to_pfn(page); - if (PageHuge(page)) { - page = compound_head(page); - pte_size <<= compound_order(page); - } - /* if the guest wants write access, see if that is OK */ - if (!writing && hpte_is_writable(r)) { - pte_t *ptep, pte; - unsigned long flags; - /* - * We need to protect against page table destruction - * hugepage split and collapse. - */ - local_irq_save(flags); - ptep = find_current_mm_pte(mm->pgd, hva, NULL, NULL); - if (ptep) { - pte = kvmppc_read_update_linux_pte(ptep, 1); - if (__pte_write(pte)) - write_ok = 1; - } - local_irq_restore(flags); + /* Call KVM generic code to do the slow-path check */ + pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, + writing, &write_ok); + if (is_error_noslot_pfn(pfn)) + return -EFAULT; + page = NULL; + if (pfn_valid(pfn)) { + page = pfn_to_page(pfn); + if (PageReserved(page)) + page = NULL; } } + /* + * Read the PTE from the process' radix tree and use that + * so we get the shift and attribute bits. + */ + local_irq_disable(); + ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + /* + * If the PTE disappeared temporarily due to a THP + * collapse, just return and let the guest try again. + */ + if (!ptep) { + local_irq_enable(); + if (page) + put_page(page); + return RESUME_GUEST; + } + pte = *ptep; + local_irq_enable(); + hpa = pte_pfn(pte) << PAGE_SHIFT; + pte_size = PAGE_SIZE; + if (shift) + pte_size = 1ul << shift; + is_ci = pte_ci(pte); + if (psize > pte_size) goto out_put; + if (pte_size > psize) + hpa |= hva & (pte_size - psize); /* Check WIMG vs. the actual page we're accessing */ if (!hpte_cache_flags_ok(r, is_ci)) { @@ -636,14 +639,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } /* - * Set the HPTE to point to pfn. - * Since the pfn is at PAGE_SIZE granularity, make sure we + * Set the HPTE to point to hpa. + * Since the hpa is at PAGE_SIZE granularity, make sure we * don't mask out lower-order bits if psize < PAGE_SIZE. */ if (psize < PAGE_SIZE) psize = PAGE_SIZE; - r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) | - ((pfn << PAGE_SHIFT) & ~(psize - 1)); + r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) | hpa; if (hpte_is_writable(r) && !write_ok) r = hpte_make_readonly(r); ret = RESUME_GUEST; @@ -708,20 +710,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, asm volatile("ptesync" : : : "memory"); preempt_enable(); if (page && hpte_is_writable(r)) - SetPageDirty(page); + set_page_dirty_lock(page); out_put: trace_kvm_page_fault_exit(vcpu, hpte, ret); - if (page) { - /* - * We drop pages[0] here, not page because page might - * have been set to the head page of a compound, but - * we have to drop the reference on the correct tail - * page to match the get inside gup() - */ - put_page(pages[0]); - } + if (page) + put_page(page); return ret; out_unlock: diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 803940d79b73..134fbc1f029f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -425,7 +425,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full, unsigned int lpid) { if (full) { - memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE); + memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE); } else { pte_t *p = pte; unsigned long it; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index ee6c103bb7d5..50555ad1db93 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -27,7 +27,6 @@ #include <asm/hvcall.h> #include <asm/synch.h> #include <asm/ppc-opcode.h> -#include <asm/kvm_host.h> #include <asm/udbg.h> #include <asm/iommu.h> #include <asm/tce.h> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index ab6eeb8e753e..6fcaf1fa8e02 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -24,7 +24,6 @@ #include <asm/hvcall.h> #include <asm/synch.h> #include <asm/ppc-opcode.h> -#include <asm/kvm_host.h> #include <asm/udbg.h> #include <asm/iommu.h> #include <asm/tce.h> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 2cefd071b848..fa6e4fc7d0e4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -72,7 +72,6 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/hw_breakpoint.h> -#include <asm/kvm_host.h> #include <asm/kvm_book3s_uvmem.h> #include <asm/ultravisor.h> @@ -1074,25 +1073,35 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_PAGE_IN: - ret = kvmppc_h_svm_page_in(vcpu->kvm, - kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_page_in(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_PAGE_OUT: - ret = kvmppc_h_svm_page_out(vcpu->kvm, - kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_page_out(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_INIT_START: - ret = kvmppc_h_svm_init_start(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_start(vcpu->kvm); break; case H_SVM_INIT_DONE: - ret = kvmppc_h_svm_init_done(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_done(vcpu->kvm); break; case H_SVM_INIT_ABORT: - ret = kvmppc_h_svm_init_abort(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_abort(vcpu->kvm); break; default: @@ -3616,6 +3625,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { kvmppc_nested_cede(vcpu); + kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } } else { @@ -4400,7 +4410,7 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, log->slot); r = -ENOENT; - if (!memslot->dirty_bitmap) + if (!memslot || !memslot->dirty_bitmap) goto out; /* @@ -4447,29 +4457,26 @@ out: return r; } -static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot) { - if (!dont || free->arch.rmap != dont->arch.rmap) { - vfree(free->arch.rmap); - free->arch.rmap = NULL; - } + vfree(slot->arch.rmap); + slot->arch.rmap = NULL; } -static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, - unsigned long npages) +static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, + struct kvm_memory_slot *slot, + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { - slot->arch.rmap = vzalloc(array_size(npages, sizeof(*slot->arch.rmap))); - if (!slot->arch.rmap) - return -ENOMEM; + unsigned long npages = mem->memory_size >> PAGE_SHIFT; - return 0; -} + if (change == KVM_MR_CREATE) { + slot->arch.rmap = vzalloc(array_size(npages, + sizeof(*slot->arch.rmap))); + if (!slot->arch.rmap) + return -ENOMEM; + } -static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) -{ return 0; } @@ -4558,11 +4565,6 @@ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask) } } -static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu) -{ - return; -} - void kvmppc_setup_partition_table(struct kvm *kvm) { unsigned long dw0, dw1; @@ -5427,6 +5429,21 @@ static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa) } /* + * Enable a guest to become a secure VM, or test whether + * that could be enabled. + * Called when the KVM_CAP_PPC_SECURE_GUEST capability is + * tested (kvm == NULL) or enabled (kvm != NULL). + */ +static int kvmhv_enable_svm(struct kvm *kvm) +{ + if (!kvmppc_uvmem_available()) + return -EINVAL; + if (kvm) + kvm->arch.svm_enabled = 1; + return 0; +} + +/* * IOCTL handler to turn off secure mode of guest * * - Release all device pages @@ -5526,9 +5543,7 @@ static struct kvmppc_ops kvm_ops_hv = { .age_hva = kvm_age_hva_hv, .test_age_hva = kvm_test_age_hva_hv, .set_spte_hva = kvm_set_spte_hva_hv, - .mmu_destroy = kvmppc_mmu_destroy_hv, .free_memslot = kvmppc_core_free_memslot_hv, - .create_memslot = kvmppc_core_create_memslot_hv, .init_vm = kvmppc_core_init_vm_hv, .destroy_vm = kvmppc_core_destroy_vm_hv, .get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv, @@ -5548,6 +5563,7 @@ static struct kvmppc_ops kvm_ops_hv = { .enable_nested = kvmhv_enable_nested, .load_from_eaddr = kvmhv_load_from_eaddr, .store_to_eaddr = kvmhv_store_to_eaddr, + .enable_svm = kvmhv_enable_svm, .svm_off = kvmhv_svm_off, }; diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 0db937497169..cc90b8b82329 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -3,6 +3,8 @@ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/kvm_ppc.h> @@ -44,7 +46,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) u64 newmsr, bescr; int ra, rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For treclaim., tsr., and trechkpt. instructions if bit + * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section + * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit + * 31 is an acceptable way to handle these invalid forms that have + * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/ + * bit 31 set) can generate a softpatch interrupt. Hence both forms + * are handled below for these instructions so they behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -105,7 +118,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return RESUME_GUEST; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* check for PR=1 and arch 2.06 bit set in PCR */ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) { /* generate an illegal instruction interrupt */ @@ -140,7 +154,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = msr; return RESUME_GUEST; - case PPC_INST_TRECLAIM: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK): /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { /* generate an illegal instruction interrupt */ @@ -176,7 +191,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST; - case PPC_INST_TRECHKPT: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK): /* XXX do we need to check for PR=0 here? */ /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { @@ -208,6 +224,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) } /* What should we do here? We didn't recognize the instruction */ - WARN_ON_ONCE(1); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr); + return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c index 217246279dfa..fad931f224ef 100644 --- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c @@ -23,7 +23,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) u64 newmsr, msr, bescr; int rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For the tsr. instruction if bit 31 = 0 then it is per + * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid + * Forms, informs specifically that ignoring bit 31 is an acceptable way + * to handle TM-related invalid forms that have bit 31 = 0. Moreover, + * for emulation purposes both forms (w/ and wo/ bit 31 set) can + * generate a softpatch interrupt. Hence both forms are handled below + * for tsr. to make them behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -73,7 +84,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return 1; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* we know the MSR has the TS field = S (0b01) here */ msr = vcpu->arch.shregs.msr; /* check for PR=1 and arch 2.06 bit set in PCR */ diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 79b1202b1c62..76d05c71fb1f 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -113,6 +113,15 @@ struct kvmppc_uvmem_page_pvt { bool skip_page_out; }; +bool kvmppc_uvmem_available(void) +{ + /* + * If kvmppc_uvmem_bitmap != NULL, then there is an ultravisor + * and our data structures have been initialized successfully. + */ + return !!kvmppc_uvmem_bitmap; +} + int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) { struct kvmppc_uvmem_slot *p; @@ -209,6 +218,8 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) int ret = H_SUCCESS; int srcu_idx; + kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START; + if (!kvmppc_uvmem_bitmap) return H_UNSUPPORTED; @@ -216,6 +227,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) if (!kvm_is_radix(kvm)) return H_UNSUPPORTED; + /* NAK the transition to secure if not enabled */ + if (!kvm->arch.svm_enabled) + return H_AUTHORITY; + srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, slots) { @@ -233,7 +248,6 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) goto out; } } - kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_START; out: srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; @@ -563,6 +577,7 @@ kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, mig.end = end; mig.src = &src_pfn; mig.dst = &dst_pfn; + mig.src_owner = &kvmppc_uvmem_pgmap; mutex_lock(&kvm->arch.uvmem_lock); /* The requested page is already paged-out, nothing to do */ @@ -779,6 +794,8 @@ int kvmppc_uvmem_init(void) kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE; kvmppc_uvmem_pgmap.res = *res; kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops; + /* just one global instance: */ + kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap; addr = memremap_pages(&kvmppc_uvmem_pgmap, NUMA_NO_NODE); if (IS_ERR(addr)) { ret = PTR_ERR(addr); @@ -806,6 +823,9 @@ out: void kvmppc_uvmem_free(void) { + if (!kvmppc_uvmem_bitmap) + return; + memunmap_pages(&kvmppc_uvmem_pgmap); release_mem_region(kvmppc_uvmem_pgmap.res.start, resource_size(&kvmppc_uvmem_pgmap.res)); diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 729a0f12a752..a0f6813f4560 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -740,7 +740,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) && ((pte.raddr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)) pte.raddr &= ~SPLIT_HACK_MASK; - /* fall through */ + fallthrough; case MSR_IR: vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); @@ -1795,7 +1795,7 @@ static int kvmppc_core_vcpu_create_pr(struct kvm_vcpu *vcpu) vcpu->arch.shadow_msr = MSR_USER64 & ~MSR_LE; - err = kvmppc_mmu_init(vcpu); + err = kvmppc_mmu_init_pr(vcpu); if (err < 0) goto free_shared_page; @@ -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); @@ -1884,7 +1885,6 @@ out: static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm, struct kvm_dirty_log *log) { - struct kvm_memslots *slots; struct kvm_memory_slot *memslot; struct kvm_vcpu *vcpu; ulong ga, ga_end; @@ -1894,15 +1894,12 @@ static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm, mutex_lock(&kvm->slots_lock); - r = kvm_get_dirty_log(kvm, log, &is_dirty); + r = kvm_get_dirty_log(kvm, log, &is_dirty, &memslot); if (r) goto out; /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - ga = memslot->base_gfn << PAGE_SHIFT; ga_end = ga + (memslot->npages << PAGE_SHIFT); @@ -1927,7 +1924,8 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { return 0; } @@ -1941,19 +1939,11 @@ static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, return; } -static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *slot) { return; } -static int kvmppc_core_create_memslot_pr(struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} - - #ifdef CONFIG_PPC64 static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm, struct kvm_ppc_smmu_info *info) @@ -2097,9 +2087,7 @@ static struct kvmppc_ops kvm_ops_pr = { .age_hva = kvm_age_hva_pr, .test_age_hva = kvm_test_age_hva_pr, .set_spte_hva = kvm_set_spte_hva_pr, - .mmu_destroy = kvmppc_mmu_destroy_pr, .free_memslot = kvmppc_core_free_memslot_pr, - .create_memslot = kvmppc_core_create_memslot_pr, .init_vm = kvmppc_core_init_vm_pr, .destroy_vm = kvmppc_core_destroy_vm_pr, .get_smmu_info = kvm_vm_ioctl_get_smmu_info_pr, diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 7b27604adadf..6c18ea88fd25 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -421,11 +421,11 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, case BOOKE_IRQPRIO_DATA_STORAGE: case BOOKE_IRQPRIO_ALIGNMENT: update_dear = true; - /* fall through */ + fallthrough; case BOOKE_IRQPRIO_INST_STORAGE: case BOOKE_IRQPRIO_PROGRAM: update_esr = true; - /* fall through */ + fallthrough; case BOOKE_IRQPRIO_ITLB_MISS: case BOOKE_IRQPRIO_SYSCALL: case BOOKE_IRQPRIO_FP_UNAVAIL: @@ -459,7 +459,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, case BOOKE_IRQPRIO_DECREMENTER: case BOOKE_IRQPRIO_FIT: keep_irq = true; - /* fall through */ + fallthrough; case BOOKE_IRQPRIO_EXTERNAL: case BOOKE_IRQPRIO_DBELL: allowed = vcpu->arch.shared->msr & MSR_EE; @@ -1766,25 +1766,24 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, return r; } -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - return -ENOTSUPP; + } -void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { + return -ENOTSUPP; } -int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - return 0; } int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { return 0; } @@ -2074,11 +2073,6 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu) kvmppc_clear_dbsr(); } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) -{ - vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); -} - int kvmppc_core_init_vm(struct kvm *kvm) { return kvm->arch.kvm_ops->init_vm(kvm); diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index 9d3169fbce55..65b4d337d337 100644 --- a/arch/powerpc/kvm/booke.h +++ b/arch/powerpc/kvm/booke.h @@ -94,7 +94,6 @@ enum int_class { void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type); -extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu); extern int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance); @@ -102,7 +101,6 @@ extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_val); extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val); -extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu); extern int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance); diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index f2b4feaff6d2..7e8b69015d20 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -490,7 +490,6 @@ static struct kvmppc_ops kvm_ops_e500 = { .vcpu_put = kvmppc_core_vcpu_put_e500, .vcpu_create = kvmppc_core_vcpu_create_e500, .vcpu_free = kvmppc_core_vcpu_free_e500, - .mmu_destroy = kvmppc_mmu_destroy_e500, .init_vm = kvmppc_core_init_vm_e500, .destroy_vm = kvmppc_core_destroy_vm_e500, .emulate_op = kvmppc_core_emulate_op_e500, diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 2d910b87e441..e131fbecdcc4 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -533,10 +533,6 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index, return get_tlb_raddr(gtlbe) | (eaddr & pgmask); } -void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu) -{ -} - /*****************************************/ static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500) diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index e6b06cb2b92c..1c189b5aadcc 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -376,7 +376,6 @@ static struct kvmppc_ops kvm_ops_e500mc = { .vcpu_put = kvmppc_core_vcpu_put_e500mc, .vcpu_create = kvmppc_core_vcpu_create_e500mc, .vcpu_free = kvmppc_core_vcpu_free_e500mc, - .mmu_destroy = kvmppc_mmu_destroy_e500, .init_vm = kvmppc_core_init_vm_e500mc, .destroy_vm = kvmppc_core_destroy_vm_e500mc, .emulate_op = kvmppc_core_emulate_op_e500, diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c index fe312c160d97..23e9c2bd9f27 100644 --- a/arch/powerpc/kvm/mpic.c +++ b/arch/powerpc/kvm/mpic.c @@ -32,7 +32,6 @@ #include <linux/uaccess.h> #include <asm/mpic.h> #include <asm/kvm_para.h> -#include <asm/kvm_host.h> #include <asm/kvm_ppc.h> #include <kvm/iodev.h> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 1af96fb5dc6f..e15166b0a16d 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -32,7 +32,6 @@ #include <asm/plpar_wrappers.h> #endif #include <asm/ultravisor.h> -#include <asm/kvm_host.h> #include "timing.h" #include "irq.h" @@ -416,12 +415,12 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { return kvmppc_core_check_processor_compat(); } @@ -525,7 +524,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: - /* fall through */ case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_OSI: case KVM_CAP_PPC_GET_PVINFO: @@ -671,6 +669,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) (hv_enabled && cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)); break; #endif +#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) + case KVM_CAP_PPC_SECURE_GUEST: + r = hv_enabled && kvmppc_hv_ops->enable_svm && + !kvmppc_hv_ops->enable_svm(NULL); + break; +#endif default: r = 0; break; @@ -685,16 +689,9 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) -{ - kvmppc_core_free_memslot(kvm, free, dont); -} - -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - return kvmppc_core_create_memslot(kvm, slot, npages); + kvmppc_core_free_memslot(kvm, slot); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -702,12 +699,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { - return kvmppc_core_prepare_memory_region(kvm, memslot, mem); + return kvmppc_core_prepare_memory_region(kvm, memslot, mem, change); } void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -759,7 +756,6 @@ 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 +788,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvmppc_core_vcpu_free(vcpu); - kvmppc_mmu_destroy(vcpu); kvmppc_subarch_vcpu_uninit(vcpu); } @@ -2178,6 +2173,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, r = kvm->arch.kvm_ops->enable_nested(kvm); break; #endif +#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) + case KVM_CAP_PPC_SECURE_GUEST: + r = -EINVAL; + if (!is_kvmppc_hv_enabled(kvm) || !kvm->arch.kvm_ops->enable_svm) + break; + r = kvm->arch.kvm_ops->enable_svm(kvm); + break; +#endif default: r = -EINVAL; break; diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h index ace65f9fed30..feef7885ba82 100644 --- a/arch/powerpc/kvm/timing.h +++ b/arch/powerpc/kvm/timing.h @@ -10,7 +10,6 @@ #define __POWERPC_KVM_EXITTIMING_H__ #include <linux/kvm_host.h> -#include <asm/kvm_host.h> #ifdef CONFIG_KVM_EXIT_TIMING void kvmppc_init_timing_stats(struct kvm_vcpu *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/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 59e0ebbd8036..07527f1ed108 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -381,18 +381,6 @@ bool arch_pte_access_permitted(u64 pte, bool write, bool execute) * So do not enforce things if the VMA is not from the current mm, or if we are * in a kernel thread. */ -static inline bool vma_is_foreign(struct vm_area_struct *vma) -{ - if (!current->mm) - return true; - - /* if it is not our ->mm, it has to be foreign */ - if (current->mm != vma->vm_mm) - return true; - - return false; -} - bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 8db0507619e2..d15f0f0ee806 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -434,7 +434,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address, { struct vm_area_struct * vma; struct mm_struct *mm = current->mm; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; int is_exec = TRAP(regs) == 0x400; int is_user = user_mode(regs); int is_write = page_fault_is_write(error_code); @@ -582,28 +582,18 @@ good_area: major |= fault & VM_FAULT_MAJOR; + if (fault_signal_pending(fault, regs)) + return user_mode(regs) ? 0 : SIGBUS; + /* * Handle the retry right now, the mmap_sem has been released in that * case. */ if (unlikely(fault & VM_FAULT_RETRY)) { - /* We retry only once */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - /* - * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk - * of starvation. - */ - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; - if (!fatal_signal_pending(current)) - goto retry; + goto retry; } - - /* - * User mode? Just return to handle the fatal exception otherwise - * return to bad_page_fault - */ - return is_user ? 0 : SIGBUS; } up_read(¤t->mm->mmap_sem); 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/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index a4d40a3ceea3..f3ed1baa6289 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -360,7 +360,7 @@ static bool lmb_is_removable(struct drmem_lmb *lmb) for (i = 0; i < scns_per_block; i++) { pfn = PFN_DOWN(phys_addr); - if (!pfn_present(pfn)) { + if (!pfn_in_present_section(pfn)) { phys_addr += MIN_MEMORY_BLOCK_SIZE; continue; } 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..8672e77a5b7a 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -50,13 +50,12 @@ 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 select ARCH_HAS_MMIOWB select ARCH_HAS_DEBUG_VIRTUAL - select HAVE_EBPF_JIT if 64BIT + select HAVE_EBPF_JIT select EDAC_SUPPORT select ARCH_HAS_GIGANTIC_PAGE select ARCH_WANT_HUGE_PMD_SHARE if 64BIT @@ -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/Kbuild b/arch/riscv/include/asm/Kbuild index ec0ca8c6ab64..3d9410bb4de0 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -1,35 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += bugs.h -generic-y += checksum.h -generic-y += compat.h -generic-y += device.h -generic-y += div64.h generic-y += extable.h generic-y += flat.h -generic-y += dma.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h -generic-y += fb.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h -generic-y += mm-arch-hooks.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += sections.h -generic-y += serial.h -generic-y += shmparam.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += unaligned.h generic-y += user.h -generic-y += vga.h generic-y += vmlinux.lds.h -generic-y += xor.h 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/fault.c b/arch/riscv/mm/fault.c index cf7248e07f43..be84e32adc4c 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -30,7 +30,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs) struct vm_area_struct *vma; struct mm_struct *mm; unsigned long addr, cause; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; int code = SEGV_MAPERR; vm_fault_t fault; @@ -117,7 +117,7 @@ good_area: * signal first. We do not need to release the mmap_sem because it * would already be released in __lock_page_or_retry in mm/filemap.c. */ - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -144,11 +144,6 @@ good_area: 1, regs, addr); } if (fault & VM_FAULT_RETRY) { - /* - * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk - * of starvation. - */ - flags &= ~(FAULT_FLAG_ALLOW_RETRY); flags |= FAULT_FLAG_TRIED; /* 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/riscv/net/Makefile b/arch/riscv/net/Makefile index ec5b14763316..9a1e5f0a94e5 100644 --- a/arch/riscv/net/Makefile +++ b/arch/riscv/net/Makefile @@ -1,2 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o + +obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o + +ifeq ($(CONFIG_ARCH_RV64I),y) + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o +else + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o +endif diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h new file mode 100644 index 000000000000..20e235d06f66 --- /dev/null +++ b/arch/riscv/net/bpf_jit.h @@ -0,0 +1,514 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common functionality for RV32 and RV64 BPF JIT compilers + * + * Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com> + * + */ + +#ifndef _BPF_JIT_H +#define _BPF_JIT_H + +#include <linux/bpf.h> +#include <linux/filter.h> +#include <asm/cacheflush.h> + +enum { + RV_REG_ZERO = 0, /* The constant value 0 */ + RV_REG_RA = 1, /* Return address */ + RV_REG_SP = 2, /* Stack pointer */ + RV_REG_GP = 3, /* Global pointer */ + RV_REG_TP = 4, /* Thread pointer */ + RV_REG_T0 = 5, /* Temporaries */ + RV_REG_T1 = 6, + RV_REG_T2 = 7, + RV_REG_FP = 8, /* Saved register/frame pointer */ + RV_REG_S1 = 9, /* Saved register */ + RV_REG_A0 = 10, /* Function argument/return values */ + RV_REG_A1 = 11, /* Function arguments */ + RV_REG_A2 = 12, + RV_REG_A3 = 13, + RV_REG_A4 = 14, + RV_REG_A5 = 15, + RV_REG_A6 = 16, + RV_REG_A7 = 17, + RV_REG_S2 = 18, /* Saved registers */ + RV_REG_S3 = 19, + RV_REG_S4 = 20, + RV_REG_S5 = 21, + RV_REG_S6 = 22, + RV_REG_S7 = 23, + RV_REG_S8 = 24, + RV_REG_S9 = 25, + RV_REG_S10 = 26, + RV_REG_S11 = 27, + RV_REG_T3 = 28, /* Temporaries */ + RV_REG_T4 = 29, + RV_REG_T5 = 30, + RV_REG_T6 = 31, +}; + +struct rv_jit_context { + struct bpf_prog *prog; + u32 *insns; /* RV insns */ + int ninsns; + int epilogue_offset; + int *offset; /* BPF to RV */ + unsigned long flags; + int stack_size; +}; + +struct rv_jit_data { + struct bpf_binary_header *header; + u8 *image; + struct rv_jit_context ctx; +}; + +static inline void bpf_fill_ill_insns(void *area, unsigned int size) +{ + memset(area, 0, size); +} + +static inline void bpf_flush_icache(void *start, void *end) +{ + flush_icache_range((unsigned long)start, (unsigned long)end); +} + +static inline void emit(const u32 insn, struct rv_jit_context *ctx) +{ + if (ctx->insns) + ctx->insns[ctx->ninsns] = insn; + + ctx->ninsns++; +} + +static inline int epilogue_offset(struct rv_jit_context *ctx) +{ + int to = ctx->epilogue_offset, from = ctx->ninsns; + + return (to - from) << 2; +} + +/* Return -1 or inverted cond. */ +static inline int invert_bpf_cond(u8 cond) +{ + switch (cond) { + case BPF_JEQ: + return BPF_JNE; + case BPF_JGT: + return BPF_JLE; + case BPF_JLT: + return BPF_JGE; + case BPF_JGE: + return BPF_JLT; + case BPF_JLE: + return BPF_JGT; + case BPF_JNE: + return BPF_JEQ; + case BPF_JSGT: + return BPF_JSLE; + case BPF_JSLT: + return BPF_JSGE; + case BPF_JSGE: + return BPF_JSLT; + case BPF_JSLE: + return BPF_JSGT; + } + return -1; +} + +static inline bool is_12b_int(long val) +{ + return -(1L << 11) <= val && val < (1L << 11); +} + +static inline int is_12b_check(int off, int insn) +{ + if (!is_12b_int(off)) { + pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n", + insn, (int)off); + return -1; + } + return 0; +} + +static inline bool is_13b_int(long val) +{ + return -(1L << 12) <= val && val < (1L << 12); +} + +static inline bool is_21b_int(long val) +{ + return -(1L << 20) <= val && val < (1L << 20); +} + +static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) +{ + int from, to; + + off++; /* BPF branch is from PC+1, RV is from PC */ + from = (insn > 0) ? ctx->offset[insn - 1] : 0; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; + return (to - from) << 2; +} + +/* Instruction formats. */ + +static inline u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, + u8 opcode) +{ + return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (rd << 7) | opcode; +} + +static inline u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode) +{ + return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | + opcode; +} + +static inline u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f; + + return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_0 << 7) | opcode; +} + +static inline u32 rv_b_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4); + u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10); + + return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_1 << 7) | opcode; +} + +static inline u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode) +{ + return (imm31_12 << 12) | (rd << 7) | opcode; +} + +static inline u32 rv_j_insn(u32 imm20_1, u8 rd, u8 opcode) +{ + u32 imm; + + imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) | + ((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11); + + return (imm << 12) | (rd << 7) | opcode; +} + +static inline u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1, + u8 funct3, u8 rd, u8 opcode) +{ + u8 funct7 = (funct5 << 2) | (aq << 1) | rl; + + return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode); +} + +/* Instructions shared by both RV32 and RV64. */ + +static inline u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x13); +} + +static inline u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 7, rd, 0x13); +} + +static inline u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x13); +} + +static inline u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x13); +} + +static inline u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x13); +} + +static inline u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x13); +} + +static inline u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13); +} + +static inline u32 rv_lui(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x37); +} + +static inline u32 rv_auipc(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x17); +} + +static inline u32 rv_add(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_sub(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_sltu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 3, rd, 0x33); +} + +static inline u32 rv_and(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 7, rd, 0x33); +} + +static inline u32 rv_or(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 6, rd, 0x33); +} + +static inline u32 rv_xor(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 4, rd, 0x33); +} + +static inline u32 rv_sll(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x33); +} + +static inline u32 rv_srl(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_sra(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_mul(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_mulhu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 3, rd, 0x33); +} + +static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); +} + +static inline u32 rv_jal(u8 rd, u32 imm20_1) +{ + return rv_j_insn(imm20_1, rd, 0x6f); +} + +static inline u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x67); +} + +static inline u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 0, 0x63); +} + +static inline u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 1, 0x63); +} + +static inline u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 6, 0x63); +} + +static inline u32 rv_bgtu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bltu(rs2, rs1, imm12_1); +} + +static inline u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 7, 0x63); +} + +static inline u32 rv_bleu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bgeu(rs2, rs1, imm12_1); +} + +static inline u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 4, 0x63); +} + +static inline u32 rv_bgt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_blt(rs2, rs1, imm12_1); +} + +static inline u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 5, 0x63); +} + +static inline u32 rv_ble(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bge(rs2, rs1, imm12_1); +} + +static inline u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 2, rd, 0x03); +} + +static inline u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x03); +} + +static inline u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x03); +} + +static inline u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23); +} + +static inline u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23); +} + +static inline u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23); +} + +static inline u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +/* + * RV64-only instructions. + * + * These instructions are not available on RV32. Wrap them below a #if to + * ensure that the RV32 JIT doesn't emit any of these instructions. + */ + +#if __riscv_xlen == 64 + +static inline u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b); +} + +static inline u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b); +} + +static inline u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b); +} + +static inline u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b); +} + +static inline u32 rv_addw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_subw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_sllw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b); +} + +static inline u32 rv_srlw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_sraw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); +} + +static inline u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 3, rd, 0x03); +} + +static inline u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x03); +} + +static inline u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23); +} + +static inline u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +#endif /* __riscv_xlen == 64 */ + +void bpf_jit_build_prologue(struct rv_jit_context *ctx); +void bpf_jit_build_epilogue(struct rv_jit_context *ctx); + +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass); + +#endif /* _BPF_JIT_H */ diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c new file mode 100644 index 000000000000..302934177760 --- /dev/null +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -0,0 +1,1310 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * BPF JIT compiler for RV32G + * + * Copyright (c) 2020 Luke Nelson <luke.r.nels@gmail.com> + * Copyright (c) 2020 Xi Wang <xi.wang@gmail.com> + * + * The code is based on the BPF JIT compiler for RV64G by Björn Töpel and + * the BPF JIT compiler for 32-bit ARM by Shubham Bansal and Mircea Gherzan. + */ + +#include <linux/bpf.h> +#include <linux/filter.h> +#include "bpf_jit.h" + +enum { + /* Stack layout - these are offsets from (top of stack - 4). */ + BPF_R6_HI, + BPF_R6_LO, + BPF_R7_HI, + BPF_R7_LO, + BPF_R8_HI, + BPF_R8_LO, + BPF_R9_HI, + BPF_R9_LO, + BPF_AX_HI, + BPF_AX_LO, + /* Stack space for BPF_REG_6 through BPF_REG_9 and BPF_REG_AX. */ + BPF_JIT_SCRATCH_REGS, +}; + +#define STACK_OFFSET(k) (-4 - ((k) * 4)) + +#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) +#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) + +#define RV_REG_TCC RV_REG_T6 +#define RV_REG_TCC_SAVED RV_REG_S7 + +static const s8 bpf2rv32[][2] = { + /* Return value from in-kernel function, and exit value from eBPF. */ + [BPF_REG_0] = {RV_REG_S2, RV_REG_S1}, + /* Arguments from eBPF program to in-kernel function. */ + [BPF_REG_1] = {RV_REG_A1, RV_REG_A0}, + [BPF_REG_2] = {RV_REG_A3, RV_REG_A2}, + [BPF_REG_3] = {RV_REG_A5, RV_REG_A4}, + [BPF_REG_4] = {RV_REG_A7, RV_REG_A6}, + [BPF_REG_5] = {RV_REG_S4, RV_REG_S3}, + /* + * Callee-saved registers that in-kernel function will preserve. + * Stored on the stack. + */ + [BPF_REG_6] = {STACK_OFFSET(BPF_R6_HI), STACK_OFFSET(BPF_R6_LO)}, + [BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)}, + [BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)}, + [BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)}, + /* Read-only frame pointer to access BPF stack. */ + [BPF_REG_FP] = {RV_REG_S6, RV_REG_S5}, + /* Temporary register for blinding constants. Stored on the stack. */ + [BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)}, + /* + * Temporary registers used by the JIT to operate on registers stored + * on the stack. Save t0 and t1 to be used as temporaries in generated + * code. + */ + [TMP_REG_1] = {RV_REG_T3, RV_REG_T2}, + [TMP_REG_2] = {RV_REG_T5, RV_REG_T4}, +}; + +static s8 hi(const s8 *r) +{ + return r[0]; +} + +static s8 lo(const s8 *r) +{ + return r[1]; +} + +static void emit_imm(const s8 rd, s32 imm, struct rv_jit_context *ctx) +{ + u32 upper = (imm + (1 << 11)) >> 12; + u32 lower = imm & 0xfff; + + if (upper) { + emit(rv_lui(rd, upper), ctx); + emit(rv_addi(rd, rd, lower), ctx); + } else { + emit(rv_addi(rd, RV_REG_ZERO, lower), ctx); + } +} + +static void emit_imm32(const s8 *rd, s32 imm, struct rv_jit_context *ctx) +{ + /* Emit immediate into lower bits. */ + emit_imm(lo(rd), imm, ctx); + + /* Sign-extend into upper bits. */ + if (imm >= 0) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + else + emit(rv_addi(hi(rd), RV_REG_ZERO, -1), ctx); +} + +static void emit_imm64(const s8 *rd, s32 imm_hi, s32 imm_lo, + struct rv_jit_context *ctx) +{ + emit_imm(lo(rd), imm_lo, ctx); + emit_imm(hi(rd), imm_hi, ctx); +} + +static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) +{ + int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 4; + const s8 *r0 = bpf2rv32[BPF_REG_0]; + + store_offset -= 4 * BPF_JIT_SCRATCH_REGS; + + /* Set return value if not tail call. */ + if (!is_tail_call) { + emit(rv_addi(RV_REG_A0, lo(r0), 0), ctx); + emit(rv_addi(RV_REG_A1, hi(r0), 0), ctx); + } + + /* Restore callee-saved registers. */ + emit(rv_lw(RV_REG_RA, store_offset - 0, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_FP, store_offset - 4, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S1, store_offset - 8, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S2, store_offset - 12, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S3, store_offset - 16, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S4, store_offset - 20, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S5, store_offset - 24, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S6, store_offset - 28, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S7, store_offset - 32, RV_REG_SP), ctx); + + emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx); + + if (is_tail_call) { + /* + * goto *(t0 + 4); + * Skips first instruction of prologue which initializes tail + * call counter. Assumes t0 contains address of target program, + * see emit_bpf_tail_call. + */ + emit(rv_jalr(RV_REG_ZERO, RV_REG_T0, 4), ctx); + } else { + emit(rv_jalr(RV_REG_ZERO, RV_REG_RA, 0), ctx); + } +} + +static bool is_stacked(s8 reg) +{ + return reg < 0; +} + +static const s8 *bpf_get_reg64(const s8 *reg, const s8 *tmp, + struct rv_jit_context *ctx) +{ + if (is_stacked(hi(reg))) { + emit(rv_lw(hi(tmp), hi(reg), RV_REG_FP), ctx); + emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx); + reg = tmp; + } + return reg; +} + +static void bpf_put_reg64(const s8 *reg, const s8 *src, + struct rv_jit_context *ctx) +{ + if (is_stacked(hi(reg))) { + emit(rv_sw(RV_REG_FP, hi(reg), hi(src)), ctx); + emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx); + } +} + +static const s8 *bpf_get_reg32(const s8 *reg, const s8 *tmp, + struct rv_jit_context *ctx) +{ + if (is_stacked(lo(reg))) { + emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx); + reg = tmp; + } + return reg; +} + +static void bpf_put_reg32(const s8 *reg, const s8 *src, + struct rv_jit_context *ctx) +{ + if (is_stacked(lo(reg))) { + emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_sw(RV_REG_FP, hi(reg), RV_REG_ZERO), ctx); + } else if (!ctx->prog->aux->verifier_zext) { + emit(rv_addi(hi(reg), RV_REG_ZERO, 0), ctx); + } +} + +static void emit_jump_and_link(u8 rd, s32 rvoff, bool force_jalr, + struct rv_jit_context *ctx) +{ + s32 upper, lower; + + if (rvoff && is_21b_int(rvoff) && !force_jalr) { + emit(rv_jal(rd, rvoff >> 1), ctx); + return; + } + + upper = (rvoff + (1 << 11)) >> 12; + lower = rvoff & 0xfff; + emit(rv_auipc(RV_REG_T1, upper), ctx); + emit(rv_jalr(rd, RV_REG_T1, lower), ctx); +} + +static void emit_alu_i64(const s8 *dst, s32 imm, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (op) { + case BPF_MOV: + emit_imm32(rd, imm, ctx); + break; + case BPF_AND: + if (is_12b_int(imm)) { + emit(rv_andi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm >= 0) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_OR: + if (is_12b_int(imm)) { + emit(rv_ori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm < 0) + emit(rv_ori(hi(rd), RV_REG_ZERO, -1), ctx); + break; + case BPF_XOR: + if (is_12b_int(imm)) { + emit(rv_xori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm < 0) + emit(rv_xori(hi(rd), hi(rd), -1), ctx); + break; + case BPF_LSH: + if (imm >= 32) { + emit(rv_slli(hi(rd), lo(rd), imm - 32), ctx); + emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_srli(RV_REG_T0, lo(rd), 32 - imm), ctx); + emit(rv_slli(hi(rd), hi(rd), imm), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_slli(lo(rd), lo(rd), imm), ctx); + } + break; + case BPF_RSH: + if (imm >= 32) { + emit(rv_srli(lo(rd), hi(rd), imm - 32), ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx); + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srli(hi(rd), hi(rd), imm), ctx); + } + break; + case BPF_ARSH: + if (imm >= 32) { + emit(rv_srai(lo(rd), hi(rd), imm - 32), ctx); + emit(rv_srai(hi(rd), hi(rd), 31), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx); + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srai(hi(rd), hi(rd), imm), ctx); + } + break; + } + + bpf_put_reg64(dst, rd, ctx); +} + +static void emit_alu_i32(const s8 *dst, s32 imm, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *rd = bpf_get_reg32(dst, tmp1, ctx); + + switch (op) { + case BPF_MOV: + emit_imm(lo(rd), imm, ctx); + break; + case BPF_ADD: + if (is_12b_int(imm)) { + emit(rv_addi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_add(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_SUB: + if (is_12b_int(-imm)) { + emit(rv_addi(lo(rd), lo(rd), -imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sub(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_AND: + if (is_12b_int(imm)) { + emit(rv_andi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_OR: + if (is_12b_int(imm)) { + emit(rv_ori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_XOR: + if (is_12b_int(imm)) { + emit(rv_xori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_LSH: + if (is_12b_int(imm)) { + emit(rv_slli(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sll(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_RSH: + if (is_12b_int(imm)) { + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_srl(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_ARSH: + if (is_12b_int(imm)) { + emit(rv_srai(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sra(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + } + + bpf_put_reg32(dst, rd, ctx); +} + +static void emit_alu_r64(const s8 *dst, const s8 *src, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + switch (op) { + case BPF_MOV: + emit(rv_addi(lo(rd), lo(rs), 0), ctx); + emit(rv_addi(hi(rd), hi(rs), 0), ctx); + break; + case BPF_ADD: + if (rd == rs) { + emit(rv_srli(RV_REG_T0, lo(rd), 31), ctx); + emit(rv_slli(hi(rd), hi(rd), 1), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_slli(lo(rd), lo(rd), 1), ctx); + } else { + emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), hi(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx); + } + break; + case BPF_SUB: + emit(rv_sub(RV_REG_T1, hi(rd), hi(rs)), ctx); + emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx); + emit(rv_sub(hi(rd), RV_REG_T1, RV_REG_T0), ctx); + emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_AND: + emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_and(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_OR: + emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_XOR: + emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_xor(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_MUL: + emit(rv_mul(RV_REG_T0, hi(rs), lo(rd)), ctx); + emit(rv_mul(hi(rd), hi(rd), lo(rs)), ctx); + emit(rv_mulhu(RV_REG_T1, lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T1), ctx); + break; + case BPF_LSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_sll(hi(rd), lo(rd), RV_REG_T0), ctx); + emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_srli(RV_REG_T0, lo(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_srl(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_sll(hi(rd), hi(rd), lo(rs)), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_RSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_srl(lo(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srl(hi(rd), hi(rd), lo(rs)), ctx); + break; + case BPF_ARSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_sra(lo(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_srai(hi(rd), hi(rd), 31), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_sra(hi(rd), hi(rd), lo(rs)), ctx); + break; + case BPF_NEG: + emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx); + emit(rv_sltu(RV_REG_T0, RV_REG_ZERO, lo(rd)), ctx); + emit(rv_sub(hi(rd), RV_REG_ZERO, hi(rd)), ctx); + emit(rv_sub(hi(rd), hi(rd), RV_REG_T0), ctx); + break; + } + + bpf_put_reg64(dst, rd, ctx); +} + +static void emit_alu_r32(const s8 *dst, const s8 *src, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg32(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg32(src, tmp2, ctx); + + switch (op) { + case BPF_MOV: + emit(rv_addi(lo(rd), lo(rs), 0), ctx); + break; + case BPF_ADD: + emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_SUB: + emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_AND: + emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_OR: + emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_XOR: + emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_MUL: + emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_DIV: + emit(rv_divu(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_MOD: + emit(rv_remu(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_LSH: + emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_RSH: + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_ARSH: + emit(rv_sra(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_NEG: + emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx); + break; + } + + bpf_put_reg32(dst, rd, ctx); +} + +static int emit_branch_r64(const s8 *src1, const s8 *src2, s32 rvoff, + struct rv_jit_context *ctx, const u8 op) +{ + int e, s = ctx->ninsns; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + const s8 *rs1 = bpf_get_reg64(src1, tmp1, ctx); + const s8 *rs2 = bpf_get_reg64(src2, tmp2, ctx); + + /* + * NO_JUMP skips over the rest of the instructions and the + * emit_jump_and_link, meaning the BPF branch is not taken. + * JUMP skips directly to the emit_jump_and_link, meaning + * the BPF branch is taken. + * + * The fallthrough case results in the BPF branch being taken. + */ +#define NO_JUMP(idx) (6 + (2 * (idx))) +#define JUMP(idx) (2 + (2 * (idx))) + + switch (op) { + case BPF_JEQ: + emit(rv_bne(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bne(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JGT: + emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JLT: + emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JGE: + emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JLE: + emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JNE: + emit(rv_bne(hi(rs1), hi(rs2), JUMP(1)), ctx); + emit(rv_beq(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSGT: + emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSLT: + emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSGE: + emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSLE: + emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSET: + emit(rv_and(RV_REG_T0, hi(rs1), hi(rs2)), ctx); + emit(rv_bne(RV_REG_T0, RV_REG_ZERO, JUMP(2)), ctx); + emit(rv_and(RV_REG_T0, lo(rs1), lo(rs2)), ctx); + emit(rv_beq(RV_REG_T0, RV_REG_ZERO, NO_JUMP(0)), ctx); + break; + } + +#undef NO_JUMP +#undef JUMP + + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= (e - s) << 2; + emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + return 0; +} + +static int emit_bcc(u8 op, u8 rd, u8 rs, int rvoff, struct rv_jit_context *ctx) +{ + int e, s = ctx->ninsns; + bool far = false; + int off; + + if (op == BPF_JSET) { + /* + * BPF_JSET is a special case: it has no inverse so we always + * treat it as a far branch. + */ + far = true; + } else if (!is_13b_int(rvoff)) { + op = invert_bpf_cond(op); + far = true; + } + + /* + * For a far branch, the condition is negated and we jump over the + * branch itself, and the two instructions from emit_jump_and_link. + * For a near branch, just use rvoff. + */ + off = far ? 6 : (rvoff >> 1); + + switch (op) { + case BPF_JEQ: + emit(rv_beq(rd, rs, off), ctx); + break; + case BPF_JGT: + emit(rv_bgtu(rd, rs, off), ctx); + break; + case BPF_JLT: + emit(rv_bltu(rd, rs, off), ctx); + break; + case BPF_JGE: + emit(rv_bgeu(rd, rs, off), ctx); + break; + case BPF_JLE: + emit(rv_bleu(rd, rs, off), ctx); + break; + case BPF_JNE: + emit(rv_bne(rd, rs, off), ctx); + break; + case BPF_JSGT: + emit(rv_bgt(rd, rs, off), ctx); + break; + case BPF_JSLT: + emit(rv_blt(rd, rs, off), ctx); + break; + case BPF_JSGE: + emit(rv_bge(rd, rs, off), ctx); + break; + case BPF_JSLE: + emit(rv_ble(rd, rs, off), ctx); + break; + case BPF_JSET: + emit(rv_and(RV_REG_T0, rd, rs), ctx); + emit(rv_beq(RV_REG_T0, RV_REG_ZERO, off), ctx); + break; + } + + if (far) { + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= (e - s) << 2; + emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + } + return 0; +} + +static int emit_branch_r32(const s8 *src1, const s8 *src2, s32 rvoff, + struct rv_jit_context *ctx, const u8 op) +{ + int e, s = ctx->ninsns; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + const s8 *rs1 = bpf_get_reg32(src1, tmp1, ctx); + const s8 *rs2 = bpf_get_reg32(src2, tmp2, ctx); + + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= (e - s) << 2; + + if (emit_bcc(op, lo(rs1), lo(rs2), rvoff, ctx)) + return -1; + + return 0; +} + +static void emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) +{ + const s8 *r0 = bpf2rv32[BPF_REG_0]; + const s8 *r5 = bpf2rv32[BPF_REG_5]; + u32 upper = ((u32)addr + (1 << 11)) >> 12; + u32 lower = addr & 0xfff; + + /* R1-R4 already in correct registers---need to push R5 to stack. */ + emit(rv_addi(RV_REG_SP, RV_REG_SP, -16), ctx); + emit(rv_sw(RV_REG_SP, 0, lo(r5)), ctx); + emit(rv_sw(RV_REG_SP, 4, hi(r5)), ctx); + + /* Backup TCC. */ + emit(rv_addi(RV_REG_TCC_SAVED, RV_REG_TCC, 0), ctx); + + /* + * Use lui/jalr pair to jump to absolute address. Don't use emit_imm as + * the number of emitted instructions should not depend on the value of + * addr. + */ + emit(rv_lui(RV_REG_T1, upper), ctx); + emit(rv_jalr(RV_REG_RA, RV_REG_T1, lower), ctx); + + /* Restore TCC. */ + emit(rv_addi(RV_REG_TCC, RV_REG_TCC_SAVED, 0), ctx); + + /* Set return value and restore stack. */ + emit(rv_addi(lo(r0), RV_REG_A0, 0), ctx); + emit(rv_addi(hi(r0), RV_REG_A1, 0), ctx); + emit(rv_addi(RV_REG_SP, RV_REG_SP, 16), ctx); +} + +static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) +{ + /* + * R1 -> &ctx + * R2 -> &array + * R3 -> index + */ + int tc_ninsn, off, start_insn = ctx->ninsns; + const s8 *arr_reg = bpf2rv32[BPF_REG_2]; + const s8 *idx_reg = bpf2rv32[BPF_REG_3]; + + tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] : + ctx->offset[0]; + + /* max_entries = array->map.max_entries; */ + off = offsetof(struct bpf_array, map.max_entries); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T1, off, lo(arr_reg)), ctx); + + /* + * if (index >= max_entries) + * goto out; + */ + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx); + + /* + * if ((temp_tcc = tcc - 1) < 0) + * goto out; + */ + emit(rv_addi(RV_REG_T1, RV_REG_TCC, -1), ctx); + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + emit_bcc(BPF_JSLT, RV_REG_T1, RV_REG_ZERO, off, ctx); + + /* + * prog = array->ptrs[index]; + * if (!prog) + * goto out; + */ + emit(rv_slli(RV_REG_T0, lo(idx_reg), 2), ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(arr_reg)), ctx); + off = offsetof(struct bpf_array, ptrs); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + emit_bcc(BPF_JEQ, RV_REG_T0, RV_REG_ZERO, off, ctx); + + /* + * tcc = temp_tcc; + * goto *(prog->bpf_func + 4); + */ + off = offsetof(struct bpf_prog, bpf_func); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); + emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx); + /* Epilogue jumps to *(t0 + 4). */ + __build_epilogue(true, ctx); + return 0; +} + +static int emit_load_r64(const s8 *dst, const s8 *src, s16 off, + struct rv_jit_context *ctx, const u8 size) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + emit_imm(RV_REG_T0, off, ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rs)), ctx); + + switch (size) { + case BPF_B: + emit(rv_lbu(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_H: + emit(rv_lhu(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_W: + emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_DW: + emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx); + emit(rv_lw(hi(rd), 4, RV_REG_T0), ctx); + break; + } + + bpf_put_reg64(dst, rd, ctx); + return 0; +} + +static int emit_store_r64(const s8 *dst, const s8 *src, s16 off, + struct rv_jit_context *ctx, const u8 size, + const u8 mode) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + if (mode == BPF_XADD && size != BPF_W) + return -1; + + emit_imm(RV_REG_T0, off, ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rd)), ctx); + + switch (size) { + case BPF_B: + emit(rv_sb(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_H: + emit(rv_sh(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_W: + switch (mode) { + case BPF_MEM: + emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_XADD: + emit(rv_amoadd_w(RV_REG_ZERO, lo(rs), RV_REG_T0, 0, 0), + ctx); + break; + } + break; + case BPF_DW: + emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx); + emit(rv_sw(RV_REG_T0, 4, hi(rs)), ctx); + break; + } + + return 0; +} + +static void emit_rev16(const s8 rd, struct rv_jit_context *ctx) +{ + emit(rv_slli(rd, rd, 16), ctx); + emit(rv_slli(RV_REG_T1, rd, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_add(RV_REG_T1, rd, RV_REG_T1), ctx); + emit(rv_srli(rd, RV_REG_T1, 16), ctx); +} + +static void emit_rev32(const s8 rd, struct rv_jit_context *ctx) +{ + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 0), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_addi(rd, RV_REG_T1, 0), ctx); +} + +static void emit_zext64(const s8 *dst, struct rv_jit_context *ctx) +{ + const s8 *rd; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + + rd = bpf_get_reg64(dst, tmp1, ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + bpf_put_reg64(dst, rd, ctx); +} + +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) +{ + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || + BPF_CLASS(insn->code) == BPF_JMP; + int s, e, rvoff, i = insn - ctx->prog->insnsi; + u8 code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; + + const s8 *dst = bpf2rv32[insn->dst_reg]; + const s8 *src = bpf2rv32[insn->src_reg]; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + switch (code) { + case BPF_ALU64 | BPF_MOV | BPF_X: + + case BPF_ALU64 | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_K: + + case BPF_ALU64 | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_K: + + case BPF_ALU64 | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + + case BPF_ALU64 | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_K: + + case BPF_ALU64 | BPF_LSH | BPF_X: + case BPF_ALU64 | BPF_RSH | BPF_X: + case BPF_ALU64 | BPF_ARSH | BPF_X: + if (BPF_SRC(code) == BPF_K) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + emit_alu_r64(dst, src, ctx, BPF_OP(code)); + break; + + case BPF_ALU64 | BPF_NEG: + emit_alu_r64(dst, tmp2, ctx, BPF_OP(code)); + break; + + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_K: + goto notsupported; + + case BPF_ALU64 | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + emit_alu_i64(dst, imm, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_MOV | BPF_X: + if (imm == 1) { + /* Special mov32 for zext. */ + emit_zext64(dst, ctx); + break; + } + /* Fallthrough. */ + + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_X: + + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_ARSH | BPF_X: + if (BPF_SRC(code) == BPF_K) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + emit_alu_r32(dst, src, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_ARSH | BPF_K: + /* + * mul,div,mod are handled in the BPF_X case since there are + * no RISC-V I-type equivalents. + */ + emit_alu_i32(dst, imm, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_NEG: + /* + * src is ignored---choose tmp2 as a dummy register since it + * is not on the stack. + */ + emit_alu_r32(dst, tmp2, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_END | BPF_FROM_LE: + { + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (imm) { + case 16: + emit(rv_slli(lo(rd), lo(rd), 16), ctx); + emit(rv_srli(lo(rd), lo(rd), 16), ctx); + /* Fallthrough. */ + case 32: + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 64: + /* Do nothing. */ + break; + default: + pr_err("bpf-jit: BPF_END imm %d invalid\n", imm); + return -1; + } + + bpf_put_reg64(dst, rd, ctx); + break; + } + + case BPF_ALU | BPF_END | BPF_FROM_BE: + { + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (imm) { + case 16: + emit_rev16(lo(rd), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 32: + emit_rev32(lo(rd), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 64: + /* Swap upper and lower halves. */ + emit(rv_addi(RV_REG_T0, lo(rd), 0), ctx); + emit(rv_addi(lo(rd), hi(rd), 0), ctx); + emit(rv_addi(hi(rd), RV_REG_T0, 0), ctx); + + /* Swap each half. */ + emit_rev32(lo(rd), ctx); + emit_rev32(hi(rd), ctx); + break; + default: + pr_err("bpf-jit: BPF_END imm %d invalid\n", imm); + return -1; + } + + bpf_put_reg64(dst, rd, ctx); + break; + } + + case BPF_JMP | BPF_JA: + rvoff = rv_offset(i, off, ctx); + emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + break; + + case BPF_JMP | BPF_CALL: + { + bool fixed; + int ret; + u64 addr; + + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, + &fixed); + if (ret < 0) + return ret; + emit_call(fixed, addr, ctx); + break; + } + + case BPF_JMP | BPF_TAIL_CALL: + if (emit_bpf_tail_call(i, ctx)) + return -1; + break; + + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_K: + + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_K: + + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_K: + + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_K: + + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_K: + + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_K: + + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_K: + + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_K: + + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_K: + + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_K: + + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_X: + case BPF_JMP32 | BPF_JSET | BPF_K: + rvoff = rv_offset(i, off, ctx); + if (BPF_SRC(code) == BPF_K) { + s = ctx->ninsns; + emit_imm32(tmp2, imm, ctx); + src = tmp2; + e = ctx->ninsns; + rvoff -= (e - s) << 2; + } + + if (is64) + emit_branch_r64(dst, src, rvoff, ctx, BPF_OP(code)); + else + emit_branch_r32(dst, src, rvoff, ctx, BPF_OP(code)); + break; + + case BPF_JMP | BPF_EXIT: + if (i == ctx->prog->len - 1) + break; + + rvoff = epilogue_offset(ctx); + emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + break; + + case BPF_LD | BPF_IMM | BPF_DW: + { + struct bpf_insn insn1 = insn[1]; + s32 imm_lo = imm; + s32 imm_hi = insn1.imm; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + emit_imm64(rd, imm_hi, imm_lo, ctx); + bpf_put_reg64(dst, rd, ctx); + return 1; + } + + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_DW: + if (emit_load_r64(dst, src, off, ctx, BPF_SIZE(code))) + return -1; + break; + + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_DW: + + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_DW: + case BPF_STX | BPF_XADD | BPF_W: + if (BPF_CLASS(code) == BPF_ST) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + + if (emit_store_r64(dst, src, off, ctx, BPF_SIZE(code), + BPF_MODE(code))) + return -1; + break; + + /* No hardware support for 8-byte atomics in RV32. */ + case BPF_STX | BPF_XADD | BPF_DW: + /* Fallthrough. */ + +notsupported: + pr_info_once("bpf-jit: not supported: opcode %02x ***\n", code); + return -EFAULT; + + default: + pr_err("bpf-jit: unknown opcode %02x\n", code); + return -EINVAL; + } + + return 0; +} + +void bpf_jit_build_prologue(struct rv_jit_context *ctx) +{ + /* Make space to save 9 registers: ra, fp, s1--s7. */ + int stack_adjust = 9 * sizeof(u32), store_offset, bpf_stack_adjust; + const s8 *fp = bpf2rv32[BPF_REG_FP]; + const s8 *r1 = bpf2rv32[BPF_REG_1]; + + bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); + stack_adjust += bpf_stack_adjust; + + store_offset = stack_adjust - 4; + + stack_adjust += 4 * BPF_JIT_SCRATCH_REGS; + + /* + * The first instruction sets the tail-call-counter (TCC) register. + * This instruction is skipped by tail calls. + */ + emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx); + + emit(rv_addi(RV_REG_SP, RV_REG_SP, -stack_adjust), ctx); + + /* Save callee-save registers. */ + emit(rv_sw(RV_REG_SP, store_offset - 0, RV_REG_RA), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 4, RV_REG_FP), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 8, RV_REG_S1), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 12, RV_REG_S2), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 16, RV_REG_S3), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 20, RV_REG_S4), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 24, RV_REG_S5), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 28, RV_REG_S6), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 32, RV_REG_S7), ctx); + + /* Set fp: used as the base address for stacked BPF registers. */ + emit(rv_addi(RV_REG_FP, RV_REG_SP, stack_adjust), ctx); + + /* Set up BPF stack pointer. */ + emit(rv_addi(lo(fp), RV_REG_SP, bpf_stack_adjust), ctx); + emit(rv_addi(hi(fp), RV_REG_ZERO, 0), ctx); + + /* Set up context pointer. */ + emit(rv_addi(lo(r1), RV_REG_A0, 0), ctx); + emit(rv_addi(hi(r1), RV_REG_ZERO, 0), ctx); + + ctx->stack_size = stack_adjust; +} + +void bpf_jit_build_epilogue(struct rv_jit_context *ctx) +{ + __build_epilogue(false, ctx); +} diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp64.c index 483f4ad7f4dc..cc1985d8750a 100644 --- a/arch/riscv/net/bpf_jit_comp.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -7,42 +7,7 @@ #include <linux/bpf.h> #include <linux/filter.h> -#include <asm/cacheflush.h> - -enum { - RV_REG_ZERO = 0, /* The constant value 0 */ - RV_REG_RA = 1, /* Return address */ - RV_REG_SP = 2, /* Stack pointer */ - RV_REG_GP = 3, /* Global pointer */ - RV_REG_TP = 4, /* Thread pointer */ - RV_REG_T0 = 5, /* Temporaries */ - RV_REG_T1 = 6, - RV_REG_T2 = 7, - RV_REG_FP = 8, - RV_REG_S1 = 9, /* Saved registers */ - RV_REG_A0 = 10, /* Function argument/return values */ - RV_REG_A1 = 11, /* Function arguments */ - RV_REG_A2 = 12, - RV_REG_A3 = 13, - RV_REG_A4 = 14, - RV_REG_A5 = 15, - RV_REG_A6 = 16, - RV_REG_A7 = 17, - RV_REG_S2 = 18, /* Saved registers */ - RV_REG_S3 = 19, - RV_REG_S4 = 20, - RV_REG_S5 = 21, - RV_REG_S6 = 22, - RV_REG_S7 = 23, - RV_REG_S8 = 24, - RV_REG_S9 = 25, - RV_REG_S10 = 26, - RV_REG_S11 = 27, - RV_REG_T3 = 28, /* Temporaries */ - RV_REG_T4 = 29, - RV_REG_T5 = 30, - RV_REG_T6 = 31, -}; +#include "bpf_jit.h" #define RV_REG_TCC RV_REG_A6 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ @@ -73,22 +38,6 @@ enum { RV_CTX_F_SEEN_S6 = RV_REG_S6, }; -struct rv_jit_context { - struct bpf_prog *prog; - u32 *insns; /* RV insns */ - int ninsns; - int epilogue_offset; - int *offset; /* BPF to RV */ - unsigned long flags; - int stack_size; -}; - -struct rv_jit_data { - struct bpf_binary_header *header; - u8 *image; - struct rv_jit_context ctx; -}; - static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx) { u8 reg = regmap[bpf_reg]; @@ -156,346 +105,11 @@ static u8 rv_tail_call_reg(struct rv_jit_context *ctx) return RV_REG_A6; } -static void emit(const u32 insn, struct rv_jit_context *ctx) -{ - if (ctx->insns) - ctx->insns[ctx->ninsns] = insn; - - ctx->ninsns++; -} - -static u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, u8 opcode) -{ - return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | - (rd << 7) | opcode; -} - -static u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode) -{ - return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | - opcode; -} - -static u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode) -{ - u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f; - - return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | - (imm4_0 << 7) | opcode; -} - -static u32 rv_sb_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode) -{ - u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4); - u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10); - - return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | - (imm4_1 << 7) | opcode; -} - -static u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode) -{ - return (imm31_12 << 12) | (rd << 7) | opcode; -} - -static u32 rv_uj_insn(u32 imm20_1, u8 rd, u8 opcode) -{ - u32 imm; - - imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) | - ((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11); - - return (imm << 12) | (rd << 7) | opcode; -} - -static u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1, - u8 funct3, u8 rd, u8 opcode) -{ - u8 funct7 = (funct5 << 2) | (aq << 1) | rl; - - return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode); -} - -static u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b); -} - -static u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 0, rd, 0x13); -} - -static u32 rv_addw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b); -} - -static u32 rv_add(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 0, rd, 0x33); -} - -static u32 rv_subw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b); -} - -static u32 rv_sub(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33); -} - -static u32 rv_and(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 7, rd, 0x33); -} - -static u32 rv_or(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 6, rd, 0x33); -} - -static u32 rv_xor(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 4, rd, 0x33); -} - -static u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); -} - -static u32 rv_mul(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 0, rd, 0x33); -} - -static u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); -} - -static u32 rv_divu(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); -} - -static u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); -} - -static u32 rv_remu(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); -} - -static u32 rv_sllw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b); -} - -static u32 rv_sll(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 1, rd, 0x33); -} - -static u32 rv_srlw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b); -} - -static u32 rv_srl(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 5, rd, 0x33); -} - -static u32 rv_sraw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b); -} - -static u32 rv_sra(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33); -} - -static u32 rv_lui(u8 rd, u32 imm31_12) -{ - return rv_u_insn(imm31_12, rd, 0x37); -} - -static u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 1, rd, 0x13); -} - -static u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 7, rd, 0x13); -} - -static u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 6, rd, 0x13); -} - -static u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 4, rd, 0x13); -} - -static u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b); -} - -static u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b); -} - -static u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 5, rd, 0x13); -} - -static u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b); -} - -static u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13); -} - -static u32 rv_jal(u8 rd, u32 imm20_1) -{ - return rv_uj_insn(imm20_1, rd, 0x6f); -} - -static u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 0, rd, 0x67); -} - -static u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 0, 0x63); -} - -static u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 6, 0x63); -} - -static u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 7, 0x63); -} - -static u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 1, 0x63); -} - -static u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 4, 0x63); -} - -static u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 5, 0x63); -} - -static u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23); -} - -static u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23); -} - -static u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23); -} - -static u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23); -} - -static u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 4, rd, 0x03); -} - -static u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 5, rd, 0x03); -} - -static u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 6, rd, 0x03); -} - -static u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 3, rd, 0x03); -} - -static u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) -{ - return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f); -} - -static u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) -{ - return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f); -} - -static u32 rv_auipc(u8 rd, u32 imm31_12) -{ - return rv_u_insn(imm31_12, rd, 0x17); -} - -static bool is_12b_int(s64 val) -{ - return -(1 << 11) <= val && val < (1 << 11); -} - -static bool is_13b_int(s64 val) -{ - return -(1 << 12) <= val && val < (1 << 12); -} - -static bool is_21b_int(s64 val) -{ - return -(1L << 20) <= val && val < (1L << 20); -} - static bool is_32b_int(s64 val) { return -(1L << 31) <= val && val < (1L << 31); } -static int is_12b_check(int off, int insn) -{ - if (!is_12b_int(off)) { - pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n", - insn, (int)off); - return -1; - } - return 0; -} - static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) { /* Note that the immediate from the add is sign-extended, @@ -535,23 +149,6 @@ static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) emit(rv_addi(rd, rd, lower), ctx); } -static int rv_offset(int insn, int off, struct rv_jit_context *ctx) -{ - int from, to; - - off++; /* BPF branch is from PC+1, RV is from PC */ - from = (insn > 0) ? ctx->offset[insn - 1] : 0; - to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; - return (to - from) << 2; -} - -static int epilogue_offset(struct rv_jit_context *ctx) -{ - int to = ctx->epilogue_offset, from = ctx->ninsns; - - return (to - from) << 2; -} - static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) { int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8; @@ -596,34 +193,6 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) ctx); } -/* return -1 or inverted cond */ -static int invert_bpf_cond(u8 cond) -{ - switch (cond) { - case BPF_JEQ: - return BPF_JNE; - case BPF_JGT: - return BPF_JLE; - case BPF_JLT: - return BPF_JGE; - case BPF_JGE: - return BPF_JLT; - case BPF_JLE: - return BPF_JGT; - case BPF_JNE: - return BPF_JEQ; - case BPF_JSGT: - return BPF_JSLE; - case BPF_JSLT: - return BPF_JSGE; - case BPF_JSGE: - return BPF_JSLT; - case BPF_JSLE: - return BPF_JSGT; - } - return -1; -} - static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff, struct rv_jit_context *ctx) { @@ -855,8 +424,8 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) return 0; } -static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, - bool extra_pass) +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || BPF_CLASS(insn->code) == BPF_JMP; @@ -1434,7 +1003,7 @@ out_be: return 0; } -static void build_prologue(struct rv_jit_context *ctx) +void bpf_jit_build_prologue(struct rv_jit_context *ctx) { int stack_adjust = 0, store_offset, bpf_stack_adjust; @@ -1515,175 +1084,11 @@ static void build_prologue(struct rv_jit_context *ctx) ctx->stack_size = stack_adjust; } -static void build_epilogue(struct rv_jit_context *ctx) +void bpf_jit_build_epilogue(struct rv_jit_context *ctx) { __build_epilogue(false, ctx); } -static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) -{ - const struct bpf_prog *prog = ctx->prog; - int i; - - for (i = 0; i < prog->len; i++) { - const struct bpf_insn *insn = &prog->insnsi[i]; - int ret; - - ret = emit_insn(insn, ctx, extra_pass); - if (ret > 0) { - i++; - if (offset) - offset[i] = ctx->ninsns; - continue; - } - if (offset) - offset[i] = ctx->ninsns; - if (ret) - return ret; - } - return 0; -} - -static void bpf_fill_ill_insns(void *area, unsigned int size) -{ - memset(area, 0, size); -} - -static void bpf_flush_icache(void *start, void *end) -{ - flush_icache_range((unsigned long)start, (unsigned long)end); -} - -bool bpf_jit_needs_zext(void) -{ - return true; -} - -struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) -{ - bool tmp_blinded = false, extra_pass = false; - struct bpf_prog *tmp, *orig_prog = prog; - int pass = 0, prev_ninsns = 0, i; - struct rv_jit_data *jit_data; - unsigned int image_size = 0; - struct rv_jit_context *ctx; - - if (!prog->jit_requested) - return orig_prog; - - tmp = bpf_jit_blind_constants(prog); - if (IS_ERR(tmp)) - return orig_prog; - if (tmp != prog) { - tmp_blinded = true; - prog = tmp; - } - - jit_data = prog->aux->jit_data; - if (!jit_data) { - jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); - if (!jit_data) { - prog = orig_prog; - goto out; - } - prog->aux->jit_data = jit_data; - } - - ctx = &jit_data->ctx; - - if (ctx->offset) { - extra_pass = true; - image_size = sizeof(u32) * ctx->ninsns; - goto skip_init_ctx; - } - - ctx->prog = prog; - ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); - if (!ctx->offset) { - prog = orig_prog; - goto out_offset; - } - for (i = 0; i < prog->len; i++) { - prev_ninsns += 32; - ctx->offset[i] = prev_ninsns; - } - - for (i = 0; i < 16; i++) { - pass++; - ctx->ninsns = 0; - if (build_body(ctx, extra_pass, ctx->offset)) { - prog = orig_prog; - goto out_offset; - } - build_prologue(ctx); - ctx->epilogue_offset = ctx->ninsns; - build_epilogue(ctx); - - if (ctx->ninsns == prev_ninsns) { - if (jit_data->header) - break; - - image_size = sizeof(u32) * ctx->ninsns; - jit_data->header = - bpf_jit_binary_alloc(image_size, - &jit_data->image, - sizeof(u32), - bpf_fill_ill_insns); - if (!jit_data->header) { - prog = orig_prog; - goto out_offset; - } - - ctx->insns = (u32 *)jit_data->image; - /* Now, when the image is allocated, the image - * can potentially shrink more (auipc/jalr -> - * jal). - */ - } - prev_ninsns = ctx->ninsns; - } - - if (i == 16) { - pr_err("bpf-jit: image did not converge in <%d passes!\n", i); - bpf_jit_binary_free(jit_data->header); - prog = orig_prog; - goto out_offset; - } - -skip_init_ctx: - pass++; - ctx->ninsns = 0; - - build_prologue(ctx); - if (build_body(ctx, extra_pass, NULL)) { - bpf_jit_binary_free(jit_data->header); - prog = orig_prog; - goto out_offset; - } - build_epilogue(ctx); - - if (bpf_jit_enable > 1) - bpf_jit_dump(prog->len, image_size, pass, ctx->insns); - - prog->bpf_func = (void *)ctx->insns; - prog->jited = 1; - prog->jited_len = image_size; - - bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); - - if (!prog->is_func || extra_pass) { -out_offset: - kfree(ctx->offset); - kfree(jit_data); - prog->aux->jit_data = NULL; - } -out: - if (tmp_blinded) - bpf_jit_prog_release_other(prog, prog == orig_prog ? - tmp : orig_prog); - return prog; -} - void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c new file mode 100644 index 000000000000..709b94ece3ed --- /dev/null +++ b/arch/riscv/net/bpf_jit_core.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common functionality for RV32 and RV64 BPF JIT compilers + * + * Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com> + * + */ + +#include <linux/bpf.h> +#include <linux/filter.h> +#include "bpf_jit.h" + +/* Number of iterations to try until offsets converge. */ +#define NR_JIT_ITERATIONS 16 + +static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) +{ + const struct bpf_prog *prog = ctx->prog; + int i; + + for (i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &prog->insnsi[i]; + int ret; + + ret = bpf_jit_emit_insn(insn, ctx, extra_pass); + /* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */ + if (ret > 0) + i++; + if (offset) + offset[i] = ctx->ninsns; + if (ret < 0) + return ret; + } + return 0; +} + +bool bpf_jit_needs_zext(void) +{ + return true; +} + +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) +{ + bool tmp_blinded = false, extra_pass = false; + struct bpf_prog *tmp, *orig_prog = prog; + int pass = 0, prev_ninsns = 0, i; + struct rv_jit_data *jit_data; + struct rv_jit_context *ctx; + unsigned int image_size = 0; + + if (!prog->jit_requested) + return orig_prog; + + tmp = bpf_jit_blind_constants(prog); + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } + + jit_data = prog->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); + if (!jit_data) { + prog = orig_prog; + goto out; + } + prog->aux->jit_data = jit_data; + } + + ctx = &jit_data->ctx; + + if (ctx->offset) { + extra_pass = true; + image_size = sizeof(u32) * ctx->ninsns; + goto skip_init_ctx; + } + + ctx->prog = prog; + ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); + if (!ctx->offset) { + prog = orig_prog; + goto out_offset; + } + for (i = 0; i < prog->len; i++) { + prev_ninsns += 32; + ctx->offset[i] = prev_ninsns; + } + + for (i = 0; i < NR_JIT_ITERATIONS; i++) { + pass++; + ctx->ninsns = 0; + if (build_body(ctx, extra_pass, ctx->offset)) { + prog = orig_prog; + goto out_offset; + } + bpf_jit_build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; + bpf_jit_build_epilogue(ctx); + + if (ctx->ninsns == prev_ninsns) { + if (jit_data->header) + break; + + image_size = sizeof(u32) * ctx->ninsns; + jit_data->header = + bpf_jit_binary_alloc(image_size, + &jit_data->image, + sizeof(u32), + bpf_fill_ill_insns); + if (!jit_data->header) { + prog = orig_prog; + goto out_offset; + } + + ctx->insns = (u32 *)jit_data->image; + /* + * Now, when the image is allocated, the image can + * potentially shrink more (auipc/jalr -> jal). + */ + } + prev_ninsns = ctx->ninsns; + } + + if (i == NR_JIT_ITERATIONS) { + pr_err("bpf-jit: image did not converge in <%d passes!\n", i); + bpf_jit_binary_free(jit_data->header); + prog = orig_prog; + goto out_offset; + } + +skip_init_ctx: + pass++; + ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx); + if (build_body(ctx, extra_pass, NULL)) { + bpf_jit_binary_free(jit_data->header); + prog = orig_prog; + goto out_offset; + } + bpf_jit_build_epilogue(ctx); + + if (bpf_jit_enable > 1) + bpf_jit_dump(prog->len, image_size, pass, ctx->insns); + + prog->bpf_func = (void *)ctx->insns; + prog->jited = 1; + prog->jited_len = image_size; + + bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); + + if (!prog->is_func || extra_pass) { +out_offset: + kfree(ctx->offset); + kfree(jit_data); + prog->aux->jit_data = NULL; + } +out: + + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); + return prog; +} diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8abe77536d9d..59c216af6264 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -195,6 +195,7 @@ config S390 select ARCH_HAS_FORCE_DMA_UNENCRYPTED select SWIOTLB select GENERIC_ALLOCATOR + imply IMA_SECURE_AND_OR_TRUSTED_BOOT config SCHED_OMIT_FRAME_POINTER 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) $@ bzImage: vmlinux diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index e2c47d3a1c89..45b33b83de08 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -37,7 +37,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o obj-y += version.o pgm_check_info.o ctype.o text_dma.o -obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o +obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o targets := bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y) @@ -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/boot/uv.c b/arch/s390/boot/uv.c index ed007f4a6444..8fde561f1d07 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -3,7 +3,13 @@ #include <asm/facility.h> #include <asm/sections.h> +/* will be used in arch/s390/kernel/uv.c */ +#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST int __bootdata_preserved(prot_virt_guest); +#endif +#if IS_ENABLED(CONFIG_KVM) +struct uv_info __bootdata_preserved(uv_info); +#endif void uv_query_info(void) { @@ -15,10 +21,25 @@ void uv_query_info(void) if (!test_facility(158)) return; - if (uv_call(0, (uint64_t)&uvcb)) + /* rc==0x100 means that there is additional data we do not process */ + if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100) return; + if (IS_ENABLED(CONFIG_KVM)) { + memcpy(uv_info.inst_calls_list, uvcb.inst_calls_list, sizeof(uv_info.inst_calls_list)); + uv_info.uv_base_stor_len = uvcb.uv_base_stor_len; + uv_info.guest_base_stor_len = uvcb.conf_base_phys_stor_len; + uv_info.guest_virt_base_stor_len = uvcb.conf_base_virt_stor_len; + uv_info.guest_virt_var_stor_len = uvcb.conf_virt_var_stor_len; + uv_info.guest_cpu_stor_len = uvcb.cpu_stor_len; + uv_info.max_sec_stor_addr = ALIGN(uvcb.max_guest_stor_addr, PAGE_SIZE); + uv_info.max_num_sec_conf = uvcb.max_num_sec_conf; + uv_info.max_guest_cpus = uvcb.max_guest_cpus; + } + +#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) && test_bit_inv(BIT_UVC_CMD_REMOVE_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list)) prot_virt_guest = 1; +#endif } 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/Kbuild b/arch/s390/include/asm/Kbuild index 1832ae6442ef..83f6e85de7bc 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -5,21 +5,6 @@ generated-y += syscall_table.h generated-y += unistd_nr.h generic-y += asm-offsets.h -generic-y += cacheflush.h -generic-y += device.h -generic-y += dma-mapping.h -generic-y += div64.h -generic-y += emergency-restart.h generic-y += export.h -generic-y += fb.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kmap_types.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += trace_clock.h -generic-y += unaligned.h -generic-y += word-at-a-time.h 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/gmap.h b/arch/s390/include/asm/gmap.h index 37f96b6f0e61..a816fb4734b8 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -9,6 +9,7 @@ #ifndef _ASM_S390_GMAP_H #define _ASM_S390_GMAP_H +#include <linux/radix-tree.h> #include <linux/refcount.h> /* Generic bits for GMAP notification on DAT table entry changes. */ @@ -31,6 +32,7 @@ * @table: pointer to the page directory * @asce: address space control element for gmap page table * @pfault_enabled: defines if pfaults are applicable for the guest + * @guest_handle: protected virtual machine handle for the ultravisor * @host_to_rmap: radix tree with gmap_rmap lists * @children: list of shadow gmap structures * @pt_list: list of all page tables used in the shadow guest address space @@ -54,6 +56,8 @@ struct gmap { unsigned long asce_end; void *private; bool pfault_enabled; + /* only set for protected virtual machines */ + unsigned long guest_handle; /* Additional data for shadow guest address spaces */ struct radix_tree_root host_to_rmap; struct list_head children; @@ -144,4 +148,6 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start, void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); +int gmap_mark_unmergeable(void); +void s390_reset_acc(struct mm_struct *mm); #endif /* _ASM_S390_GMAP_H */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 1726224e7772..d6bcd34f3ec3 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -127,6 +127,12 @@ struct mcck_volatile_info { #define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \ CR14_EXTERNAL_DAMAGE_SUBMASK) +#define SIDAD_SIZE_MASK 0xff +#define sida_origin(sie_block) \ + ((sie_block)->sidad & PAGE_MASK) +#define sida_size(sie_block) \ + ((((sie_block)->sidad & SIDAD_SIZE_MASK) + 1) * PAGE_SIZE) + #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -160,7 +166,13 @@ struct kvm_s390_sie_block { __u8 reserved08[4]; /* 0x0008 */ #define PROG_IN_SIE (1<<0) __u32 prog0c; /* 0x000c */ - __u8 reserved10[16]; /* 0x0010 */ + union { + __u8 reserved10[16]; /* 0x0010 */ + struct { + __u64 pv_handle_cpu; + __u64 pv_handle_config; + }; + }; #define PROG_BLOCK_SIE (1<<0) #define PROG_REQUEST (1<<1) atomic_t prog20; /* 0x0020 */ @@ -209,10 +221,23 @@ struct kvm_s390_sie_block { #define ICPT_PARTEXEC 0x38 #define ICPT_IOINST 0x40 #define ICPT_KSS 0x5c +#define ICPT_MCHKREQ 0x60 +#define ICPT_INT_ENABLE 0x64 +#define ICPT_PV_INSTR 0x68 +#define ICPT_PV_NOTIFY 0x6c +#define ICPT_PV_PREF 0x70 __u8 icptcode; /* 0x0050 */ __u8 icptstatus; /* 0x0051 */ __u16 ihcpu; /* 0x0052 */ - __u8 reserved54[2]; /* 0x0054 */ + __u8 reserved54; /* 0x0054 */ +#define IICTL_CODE_NONE 0x00 +#define IICTL_CODE_MCHK 0x01 +#define IICTL_CODE_EXT 0x02 +#define IICTL_CODE_IO 0x03 +#define IICTL_CODE_RESTART 0x04 +#define IICTL_CODE_SPECIFICATION 0x10 +#define IICTL_CODE_OPERAND 0x11 + __u8 iictl; /* 0x0055 */ __u16 ipa; /* 0x0056 */ __u32 ipb; /* 0x0058 */ __u32 scaoh; /* 0x005c */ @@ -233,7 +258,7 @@ struct kvm_s390_sie_block { #define ECB3_RI 0x01 __u8 ecb3; /* 0x0063 */ __u32 scaol; /* 0x0064 */ - __u8 reserved68; /* 0x0068 */ + __u8 sdf; /* 0x0068 */ __u8 epdx; /* 0x0069 */ __u8 reserved6a[2]; /* 0x006a */ __u32 todpr; /* 0x006c */ @@ -249,31 +274,58 @@ struct kvm_s390_sie_block { #define HPID_KVM 0x4 #define HPID_VSIE 0x5 __u8 hpid; /* 0x00b8 */ - __u8 reservedb9[11]; /* 0x00b9 */ - __u16 extcpuaddr; /* 0x00c4 */ - __u16 eic; /* 0x00c6 */ + __u8 reservedb9[7]; /* 0x00b9 */ + union { + struct { + __u32 eiparams; /* 0x00c0 */ + __u16 extcpuaddr; /* 0x00c4 */ + __u16 eic; /* 0x00c6 */ + }; + __u64 mcic; /* 0x00c0 */ + } __packed; __u32 reservedc8; /* 0x00c8 */ - __u16 pgmilc; /* 0x00cc */ - __u16 iprcc; /* 0x00ce */ - __u32 dxc; /* 0x00d0 */ - __u16 mcn; /* 0x00d4 */ - __u8 perc; /* 0x00d6 */ - __u8 peratmid; /* 0x00d7 */ + union { + struct { + __u16 pgmilc; /* 0x00cc */ + __u16 iprcc; /* 0x00ce */ + }; + __u32 edc; /* 0x00cc */ + } __packed; + union { + struct { + __u32 dxc; /* 0x00d0 */ + __u16 mcn; /* 0x00d4 */ + __u8 perc; /* 0x00d6 */ + __u8 peratmid; /* 0x00d7 */ + }; + __u64 faddr; /* 0x00d0 */ + } __packed; __u64 peraddr; /* 0x00d8 */ __u8 eai; /* 0x00e0 */ __u8 peraid; /* 0x00e1 */ __u8 oai; /* 0x00e2 */ __u8 armid; /* 0x00e3 */ __u8 reservede4[4]; /* 0x00e4 */ - __u64 tecmc; /* 0x00e8 */ - __u8 reservedf0[12]; /* 0x00f0 */ + union { + __u64 tecmc; /* 0x00e8 */ + struct { + __u16 subchannel_id; /* 0x00e8 */ + __u16 subchannel_nr; /* 0x00ea */ + __u32 io_int_parm; /* 0x00ec */ + __u32 io_int_word; /* 0x00f0 */ + }; + } __packed; + __u8 reservedf4[8]; /* 0x00f4 */ #define CRYCB_FORMAT_MASK 0x00000003 #define CRYCB_FORMAT0 0x00000000 #define CRYCB_FORMAT1 0x00000001 #define CRYCB_FORMAT2 0x00000003 __u32 crycbd; /* 0x00fc */ __u64 gcr[16]; /* 0x0100 */ - __u64 gbea; /* 0x0180 */ + union { + __u64 gbea; /* 0x0180 */ + __u64 sidad; + }; __u8 reserved188[8]; /* 0x0188 */ __u64 sdnxo; /* 0x0190 */ __u8 reserved198[8]; /* 0x0198 */ @@ -292,7 +344,7 @@ struct kvm_s390_sie_block { __u64 itdba; /* 0x01e8 */ __u64 riccbd; /* 0x01f0 */ __u64 gvrd; /* 0x01f8 */ -} __attribute__((packed)); +} __packed __aligned(512); struct kvm_s390_itdb { __u8 data[256]; @@ -301,7 +353,9 @@ struct kvm_s390_itdb { struct sie_page { struct kvm_s390_sie_block sie_block; struct mcck_volatile_info mcck_info; /* 0x0200 */ - __u8 reserved218[1000]; /* 0x0218 */ + __u8 reserved218[360]; /* 0x0218 */ + __u64 pv_grregs[16]; /* 0x0380 */ + __u8 reserved400[512]; /* 0x0400 */ struct kvm_s390_itdb itdb; /* 0x0600 */ __u8 reserved700[2304]; /* 0x0700 */ }; @@ -476,6 +530,7 @@ enum irq_types { IRQ_PEND_PFAULT_INIT, IRQ_PEND_EXT_HOST, IRQ_PEND_EXT_SERVICE, + IRQ_PEND_EXT_SERVICE_EV, IRQ_PEND_EXT_TIMING, IRQ_PEND_EXT_CPU_TIMER, IRQ_PEND_EXT_CLOCK_COMP, @@ -520,6 +575,7 @@ enum irq_types { (1UL << IRQ_PEND_EXT_TIMING) | \ (1UL << IRQ_PEND_EXT_HOST) | \ (1UL << IRQ_PEND_EXT_SERVICE) | \ + (1UL << IRQ_PEND_EXT_SERVICE_EV) | \ (1UL << IRQ_PEND_VIRTIO) | \ (1UL << IRQ_PEND_PFAULT_INIT) | \ (1UL << IRQ_PEND_PFAULT_DONE)) @@ -536,6 +592,13 @@ enum irq_types { #define IRQ_PEND_MCHK_MASK ((1UL << IRQ_PEND_MCHK_REP) | \ (1UL << IRQ_PEND_MCHK_EX)) +#define IRQ_PEND_EXT_II_MASK ((1UL << IRQ_PEND_EXT_CPU_TIMER) | \ + (1UL << IRQ_PEND_EXT_CLOCK_COMP) | \ + (1UL << IRQ_PEND_EXT_EMERGENCY) | \ + (1UL << IRQ_PEND_EXT_EXTERNAL) | \ + (1UL << IRQ_PEND_EXT_SERVICE) | \ + (1UL << IRQ_PEND_EXT_SERVICE_EV)) + struct kvm_s390_interrupt_info { struct list_head list; u64 type; @@ -594,6 +657,7 @@ struct kvm_s390_local_interrupt { struct kvm_s390_float_interrupt { unsigned long pending_irqs; + unsigned long masked_irqs; spinlock_t lock; struct list_head lists[FIRQ_LIST_COUNT]; int counters[FIRQ_MAX_COUNT]; @@ -645,6 +709,11 @@ struct kvm_guestdbg_info_arch { unsigned long last_bp; }; +struct kvm_s390_pv_vcpu { + u64 handle; + unsigned long stor_base; +}; + struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; /* if vsie is active, currently executed shadow sie control block */ @@ -673,6 +742,7 @@ struct kvm_vcpu_arch { __u64 cputm_start; bool gs_enabled; bool skey_enabled; + struct kvm_s390_pv_vcpu pv; }; struct kvm_vm_stat { @@ -701,9 +771,6 @@ struct s390_io_adapter { bool masked; bool swap; bool suppressible; - struct rw_semaphore maps_lock; - struct list_head maps; - atomic_t nr_maps; }; #define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8) @@ -846,6 +913,13 @@ struct kvm_s390_gisa_interrupt { DECLARE_BITMAP(kicked_mask, KVM_MAX_VCPUS); }; +struct kvm_s390_pv { + u64 handle; + u64 guest_len; + unsigned long stor_base; + void *stor_var; +}; + struct kvm_arch{ void *sca; int use_esca; @@ -881,6 +955,7 @@ struct kvm_arch{ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS); struct kvm_s390_gisa_interrupt gisa_int; + struct kvm_s390_pv pv; }; #define KVM_HVA_ERR_BAD (-1UL) @@ -921,7 +996,7 @@ static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, - struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} + struct kvm_memory_slot *slot) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index bcfb6371086f..e21b618ad432 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -16,6 +16,8 @@ typedef struct { unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; + /* The mmu context belongs to a secure guest. */ + atomic_t is_protected; /* * The following bitfields need a down_write on the mm * semaphore when they are written to. As they are only diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 8d04e6f3f796..afa836014076 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -23,6 +23,7 @@ static inline int init_new_context(struct task_struct *tsk, INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.flush_count, 0); + atomic_set(&mm->context.is_protected, 0); mm->context.gmap_asce = 0; mm->context.flush_mm = 0; mm->context.compat_mm = test_thread_flag(TIF_31BIT); diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 85e944f04c70..62440a82731a 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); } @@ -153,6 +153,11 @@ static inline int devmem_is_allowed(unsigned long pfn) #define HAVE_ARCH_FREE_PAGE #define HAVE_ARCH_ALLOC_PAGE +#if IS_ENABLED(CONFIG_PGSTE) +int arch_make_page_accessible(struct page *page); +#define HAVE_ARCH_MAKE_PAGE_ACCESSIBLE +#endif + #endif /* !__ASSEMBLY__ */ #define __PAGE_OFFSET 0x0UL diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 137a3920ca36..6076c8c912d2 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -19,6 +19,7 @@ #include <linux/atomic.h> #include <asm/bug.h> #include <asm/page.h> +#include <asm/uv.h> extern pgd_t swapper_pg_dir[]; extern void paging_init(void); @@ -520,6 +521,15 @@ static inline int mm_has_pgste(struct mm_struct *mm) return 0; } +static inline int mm_is_protected(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (unlikely(atomic_read(&mm->context.is_protected))) + return 1; +#endif + return 0; +} + static inline int mm_alloc_pgste(struct mm_struct *mm) { #ifdef CONFIG_PGSTE @@ -752,6 +762,12 @@ 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; @@ -1061,7 +1077,12 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); + pte_t res; + + res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); + if (mm_is_protected(mm) && pte_present(res)) + uv_convert_from_secure(pte_val(res) & PAGE_MASK); + return res; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION @@ -1073,7 +1094,12 @@ void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - return ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID)); + pte_t res; + + res = ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID)); + if (mm_is_protected(vma->vm_mm) && pte_present(res)) + uv_convert_from_secure(pte_val(res) & PAGE_MASK); + return res; } /* @@ -1088,12 +1114,17 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { + pte_t res; + if (full) { - pte_t pte = *ptep; + res = *ptep; *ptep = __pte(_PAGE_INVALID); - return pte; + } else { + res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); } - return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); + if (mm_is_protected(mm) && pte_present(res)) + uv_convert_from_secure(pte_val(res) & PAGE_MASK); + return res; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT 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..e577f8533009 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)); /** @@ -338,7 +338,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * @no_output_qs: number of output queues * @input_handler: handler to be called for input queues * @output_handler: handler to be called for output queues - * @queue_start_poll_array: polling handlers (one per input queue or NULL) + * @irq_poll: Data IRQ polling handler (NULL when not supported) * @scan_threshold: # of in-use buffers that triggers scan on output queue * @int_parm: interruption parameter * @input_sbal_addr_array: address of no_input_qs * 128 pointers @@ -359,8 +359,7 @@ struct qdio_initialize { unsigned int no_output_qs; qdio_handler_t *input_handler; qdio_handler_t *output_handler; - void (**queue_start_poll_array) (struct ccw_device *, int, - unsigned long); + void (*irq_poll)(struct ccw_device *cdev, unsigned long data); unsigned int scan_threshold; unsigned long int_parm; struct qdio_buffer **input_sbal_addr_array; @@ -415,8 +414,8 @@ extern int qdio_activate(struct ccw_device *); extern void qdio_release_aob(struct qaob *); extern int do_QDIO(struct ccw_device *, unsigned int, int, unsigned int, unsigned int); -extern int qdio_start_irq(struct ccw_device *, int); -extern int qdio_stop_irq(struct ccw_device *, int); +extern int qdio_start_irq(struct ccw_device *cdev); +extern int qdio_stop_irq(struct ccw_device *cdev); extern int qdio_get_next_buffers(struct ccw_device *, int, int *, int *); extern int qdio_inspect_queue(struct ccw_device *cdev, unsigned int nr, bool is_input, unsigned int *bufnr, diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 670f14a228e5..6bf3a45ccfec 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -155,7 +155,7 @@ static inline void get_tod_clock_ext(char *clk) static inline unsigned long long get_tod_clock(void) { - unsigned char clk[STORE_CLOCK_EXT_SIZE]; + char clk[STORE_CLOCK_EXT_SIZE]; get_tod_clock_ext(clk); return *((unsigned long long *)&clk[1]); diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 4093a2856929..cff4b4c99b75 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -14,23 +14,62 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/bug.h> +#include <linux/sched.h> #include <asm/page.h> +#include <asm/gmap.h> #define UVC_RC_EXECUTED 0x0001 #define UVC_RC_INV_CMD 0x0002 #define UVC_RC_INV_STATE 0x0003 #define UVC_RC_INV_LEN 0x0005 #define UVC_RC_NO_RESUME 0x0007 +#define UVC_RC_NEED_DESTROY 0x8000 #define UVC_CMD_QUI 0x0001 +#define UVC_CMD_INIT_UV 0x000f +#define UVC_CMD_CREATE_SEC_CONF 0x0100 +#define UVC_CMD_DESTROY_SEC_CONF 0x0101 +#define UVC_CMD_CREATE_SEC_CPU 0x0120 +#define UVC_CMD_DESTROY_SEC_CPU 0x0121 +#define UVC_CMD_CONV_TO_SEC_STOR 0x0200 +#define UVC_CMD_CONV_FROM_SEC_STOR 0x0201 +#define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300 +#define UVC_CMD_UNPACK_IMG 0x0301 +#define UVC_CMD_VERIFY_IMG 0x0302 +#define UVC_CMD_CPU_RESET 0x0310 +#define UVC_CMD_CPU_RESET_INITIAL 0x0311 +#define UVC_CMD_PREPARE_RESET 0x0320 +#define UVC_CMD_CPU_RESET_CLEAR 0x0321 +#define UVC_CMD_CPU_SET_STATE 0x0330 +#define UVC_CMD_SET_UNSHARE_ALL 0x0340 +#define UVC_CMD_PIN_PAGE_SHARED 0x0341 +#define UVC_CMD_UNPIN_PAGE_SHARED 0x0342 #define UVC_CMD_SET_SHARED_ACCESS 0x1000 #define UVC_CMD_REMOVE_SHARED_ACCESS 0x1001 /* Bits in installed uv calls */ enum uv_cmds_inst { BIT_UVC_CMD_QUI = 0, + BIT_UVC_CMD_INIT_UV = 1, + BIT_UVC_CMD_CREATE_SEC_CONF = 2, + BIT_UVC_CMD_DESTROY_SEC_CONF = 3, + BIT_UVC_CMD_CREATE_SEC_CPU = 4, + BIT_UVC_CMD_DESTROY_SEC_CPU = 5, + BIT_UVC_CMD_CONV_TO_SEC_STOR = 6, + BIT_UVC_CMD_CONV_FROM_SEC_STOR = 7, BIT_UVC_CMD_SET_SHARED_ACCESS = 8, BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9, + BIT_UVC_CMD_SET_SEC_PARMS = 11, + BIT_UVC_CMD_UNPACK_IMG = 13, + BIT_UVC_CMD_VERIFY_IMG = 14, + BIT_UVC_CMD_CPU_RESET = 15, + BIT_UVC_CMD_CPU_RESET_INITIAL = 16, + BIT_UVC_CMD_CPU_SET_STATE = 17, + BIT_UVC_CMD_PREPARE_RESET = 18, + BIT_UVC_CMD_CPU_PERFORM_CLEAR_RESET = 19, + BIT_UVC_CMD_UNSHARE_ALL = 20, + BIT_UVC_CMD_PIN_PAGE_SHARED = 21, + BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22, }; struct uv_cb_header { @@ -40,13 +79,127 @@ struct uv_cb_header { u16 rrc; /* Return Reason Code */ } __packed __aligned(8); +/* Query Ultravisor Information */ struct uv_cb_qui { struct uv_cb_header header; u64 reserved08; u64 inst_calls_list[4]; - u64 reserved30[15]; + u64 reserved30[2]; + u64 uv_base_stor_len; + u64 reserved48; + u64 conf_base_phys_stor_len; + u64 conf_base_virt_stor_len; + u64 conf_virt_var_stor_len; + u64 cpu_stor_len; + u32 reserved70[3]; + u32 max_num_sec_conf; + u64 max_guest_stor_addr; + u8 reserved88[158 - 136]; + u16 max_guest_cpus; + u8 reserveda0[200 - 160]; } __packed __aligned(8); +/* Initialize Ultravisor */ +struct uv_cb_init { + struct uv_cb_header header; + u64 reserved08[2]; + u64 stor_origin; + u64 stor_len; + u64 reserved28[4]; +} __packed __aligned(8); + +/* Create Guest Configuration */ +struct uv_cb_cgc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 conf_base_stor_origin; + u64 conf_virt_stor_origin; + u64 reserved30; + u64 guest_stor_origin; + u64 guest_stor_len; + u64 guest_sca; + u64 guest_asce; + u64 reserved58[5]; +} __packed __aligned(8); + +/* Create Secure CPU */ +struct uv_cb_csc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 cpu_handle; + u64 guest_handle; + u64 stor_origin; + u8 reserved30[6]; + u16 num; + u64 state_origin; + u64 reserved40[4]; +} __packed __aligned(8); + +/* Convert to Secure */ +struct uv_cb_cts { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 gaddr; +} __packed __aligned(8); + +/* Convert from Secure / Pin Page Shared */ +struct uv_cb_cfs { + struct uv_cb_header header; + u64 reserved08[2]; + u64 paddr; +} __packed __aligned(8); + +/* Set Secure Config Parameter */ +struct uv_cb_ssc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 sec_header_origin; + u32 sec_header_len; + u32 reserved2c; + u64 reserved30[4]; +} __packed __aligned(8); + +/* Unpack */ +struct uv_cb_unp { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 gaddr; + u64 tweak[2]; + u64 reserved38[3]; +} __packed __aligned(8); + +#define PV_CPU_STATE_OPR 1 +#define PV_CPU_STATE_STP 2 +#define PV_CPU_STATE_CHKSTP 3 +#define PV_CPU_STATE_OPR_LOAD 5 + +struct uv_cb_cpu_set_state { + struct uv_cb_header header; + u64 reserved08[2]; + u64 cpu_handle; + u8 reserved20[7]; + u8 state; + u64 reserved28[5]; +}; + +/* + * A common UV call struct for calls that take no payload + * Examples: + * Destroy cpu/config + * Verify + */ +struct uv_cb_nodata { + struct uv_cb_header header; + u64 reserved08[2]; + u64 handle; + u64 reserved20[4]; +} __packed __aligned(8); + +/* Set Shared Access */ struct uv_cb_share { struct uv_cb_header header; u64 reserved08[3]; @@ -54,21 +207,76 @@ struct uv_cb_share { u64 reserved28; } __packed __aligned(8); -static inline int uv_call(unsigned long r1, unsigned long r2) +static inline int __uv_call(unsigned long r1, unsigned long r2) { int cc; asm volatile( - "0: .insn rrf,0xB9A40000,%[r1],%[r2],0,0\n" - " brc 3,0b\n" - " ipm %[cc]\n" - " srl %[cc],28\n" + " .insn rrf,0xB9A40000,%[r1],%[r2],0,0\n" + " ipm %[cc]\n" + " srl %[cc],28\n" : [cc] "=d" (cc) : [r1] "a" (r1), [r2] "a" (r2) : "memory", "cc"); return cc; } +static inline int uv_call(unsigned long r1, unsigned long r2) +{ + int cc; + + do { + cc = __uv_call(r1, r2); + } while (cc > 1); + return cc; +} + +/* Low level uv_call that avoids stalls for long running busy conditions */ +static inline int uv_call_sched(unsigned long r1, unsigned long r2) +{ + int cc; + + do { + cc = __uv_call(r1, r2); + cond_resched(); + } while (cc > 1); + return cc; +} + +/* + * special variant of uv_call that only transports the cpu or guest + * handle and the command, like destroy or verify. + */ +static inline int uv_cmd_nodata(u64 handle, u16 cmd, u16 *rc, u16 *rrc) +{ + struct uv_cb_nodata uvcb = { + .header.cmd = cmd, + .header.len = sizeof(uvcb), + .handle = handle, + }; + int cc; + + WARN(!handle, "No handle provided to Ultravisor call cmd %x\n", cmd); + cc = uv_call_sched(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + return cc ? -EINVAL : 0; +} + +struct uv_info { + unsigned long inst_calls_list[4]; + unsigned long uv_base_stor_len; + unsigned long guest_base_stor_len; + unsigned long guest_virt_base_stor_len; + unsigned long guest_virt_var_stor_len; + unsigned long guest_cpu_stor_len; + unsigned long max_sec_stor_addr; + unsigned int max_num_sec_conf; + unsigned short max_guest_cpus; +}; + +extern struct uv_info uv_info; + #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST extern int prot_virt_guest; @@ -121,11 +329,40 @@ static inline int uv_remove_shared(unsigned long addr) return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS); } -void uv_query_info(void); #else #define is_prot_virt_guest() 0 static inline int uv_set_shared(unsigned long addr) { return 0; } static inline int uv_remove_shared(unsigned long addr) { return 0; } +#endif + +#if IS_ENABLED(CONFIG_KVM) +extern int prot_virt_host; + +static inline int is_prot_virt_host(void) +{ + return prot_virt_host; +} + +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); +int uv_convert_from_secure(unsigned long paddr); +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); + +void setup_uv(void); +void adjust_to_uv_max(unsigned long *vmax); +#else +#define is_prot_virt_host() 0 +static inline void setup_uv(void) {} +static inline void adjust_to_uv_max(unsigned long *vmax) {} + +static inline int uv_convert_from_secure(unsigned long paddr) +{ + return 0; +} +#endif + +#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM) +void uv_query_info(void); +#else static inline void uv_query_info(void) {} #endif diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 2b1203cf7be6..33d4de233c5b 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -70,7 +70,7 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o -obj-$(CONFIG_IMA) += ima_arch.o +obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_arch.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf_common.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf.o perf_cpum_sf.o @@ -78,6 +78,7 @@ obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_diag.o obj-$(CONFIG_TRACEPOINTS) += trace.o +obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o # vdso obj-y += vdso64/ diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 1d3927e01a5f..faca269d5f27 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -24,6 +24,8 @@ asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); void do_protection_exception(struct pt_regs *regs); void do_dat_exception(struct pt_regs *regs); +void do_secure_storage_access(struct pt_regs *regs); +void do_non_secure_storage_access(struct pt_regs *regs); void addressing_exception(struct pt_regs *regs); void data_exception(struct pt_regs *regs); diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S index eee3a482195a..2c27907a5ffc 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -78,8 +78,8 @@ PGM_CHECK(do_dat_exception) /* 39 */ PGM_CHECK(do_dat_exception) /* 3a */ PGM_CHECK(do_dat_exception) /* 3b */ PGM_CHECK_DEFAULT /* 3c */ -PGM_CHECK_DEFAULT /* 3d */ -PGM_CHECK_DEFAULT /* 3e */ +PGM_CHECK(do_secure_storage_access) /* 3d */ +PGM_CHECK(do_non_secure_storage_access) /* 3e */ PGM_CHECK_DEFAULT /* 3f */ PGM_CHECK(monitor_event_exception) /* 40 */ PGM_CHECK_DEFAULT /* 41 */ diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index b2c2f75860e8..1423090a2259 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -92,10 +92,6 @@ char elf_platform[ELF_PLATFORM_SIZE]; unsigned long int_hwcap = 0; -#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST -int __bootdata_preserved(prot_virt_guest); -#endif - int __bootdata(noexec_disabled); int __bootdata(memory_end_set); unsigned long __bootdata(memory_end); @@ -564,6 +560,9 @@ static void __init setup_memory_end(void) vmax = _REGION1_SIZE; /* 4-level kernel page table */ } + if (is_prot_virt_host()) + adjust_to_uv_max(&vmax); + /* module area is at the end of the kernel address space. */ MODULES_END = vmax; MODULES_VADDR = MODULES_END - MODULES_LEN; @@ -1138,6 +1137,8 @@ void __init setup_arch(char **cmdline_p) */ memblock_trim_memory(1UL << (MAX_ORDER - 1 + PAGE_SHIFT)); + if (is_prot_virt_host()) + setup_uv(); setup_memory_end(); setup_memory(); dma_contiguous_reserve(memory_end); diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c new file mode 100644 index 000000000000..c86d654351d1 --- /dev/null +++ b/arch/s390/kernel/uv.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common Ultravisor functions and initialization + * + * Copyright IBM Corp. 2019, 2020 + */ +#define KMSG_COMPONENT "prot_virt" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/sizes.h> +#include <linux/bitmap.h> +#include <linux/memblock.h> +#include <linux/pagemap.h> +#include <linux/swap.h> +#include <asm/facility.h> +#include <asm/sections.h> +#include <asm/uv.h> + +/* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */ +#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST +int __bootdata_preserved(prot_virt_guest); +#endif + +#if IS_ENABLED(CONFIG_KVM) +int prot_virt_host; +EXPORT_SYMBOL(prot_virt_host); +struct uv_info __bootdata_preserved(uv_info); +EXPORT_SYMBOL(uv_info); + +static int __init prot_virt_setup(char *val) +{ + bool enabled; + int rc; + + rc = kstrtobool(val, &enabled); + if (!rc && enabled) + prot_virt_host = 1; + + if (is_prot_virt_guest() && prot_virt_host) { + prot_virt_host = 0; + pr_warn("Protected virtualization not available in protected guests."); + } + + if (prot_virt_host && !test_facility(158)) { + prot_virt_host = 0; + pr_warn("Protected virtualization not supported by the hardware."); + } + + return rc; +} +early_param("prot_virt", prot_virt_setup); + +static int __init uv_init(unsigned long stor_base, unsigned long stor_len) +{ + struct uv_cb_init uvcb = { + .header.cmd = UVC_CMD_INIT_UV, + .header.len = sizeof(uvcb), + .stor_origin = stor_base, + .stor_len = stor_len, + }; + + if (uv_call(0, (uint64_t)&uvcb)) { + pr_err("Ultravisor init failed with rc: 0x%x rrc: 0%x\n", + uvcb.header.rc, uvcb.header.rrc); + return -1; + } + return 0; +} + +void __init setup_uv(void) +{ + unsigned long uv_stor_base; + + uv_stor_base = (unsigned long)memblock_alloc_try_nid( + uv_info.uv_base_stor_len, SZ_1M, SZ_2G, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); + if (!uv_stor_base) { + pr_warn("Failed to reserve %lu bytes for ultravisor base storage\n", + uv_info.uv_base_stor_len); + goto fail; + } + + if (uv_init(uv_stor_base, uv_info.uv_base_stor_len)) { + memblock_free(uv_stor_base, uv_info.uv_base_stor_len); + goto fail; + } + + pr_info("Reserving %luMB as ultravisor base storage\n", + uv_info.uv_base_stor_len >> 20); + return; +fail: + pr_info("Disabling support for protected virtualization"); + prot_virt_host = 0; +} + +void adjust_to_uv_max(unsigned long *vmax) +{ + *vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr); +} + +/* + * Requests the Ultravisor to pin the page in the shared state. This will + * cause an intercept when the guest attempts to unshare the pinned page. + */ +static int uv_pin_shared(unsigned long paddr) +{ + struct uv_cb_cfs uvcb = { + .header.cmd = UVC_CMD_PIN_PAGE_SHARED, + .header.len = sizeof(uvcb), + .paddr = paddr, + }; + + if (uv_call(0, (u64)&uvcb)) + return -EINVAL; + return 0; +} + +/* + * Requests the Ultravisor to encrypt a guest page and make it + * accessible to the host for paging (export). + * + * @paddr: Absolute host address of page to be exported + */ +int uv_convert_from_secure(unsigned long paddr) +{ + struct uv_cb_cfs uvcb = { + .header.cmd = UVC_CMD_CONV_FROM_SEC_STOR, + .header.len = sizeof(uvcb), + .paddr = paddr + }; + + if (uv_call(0, (u64)&uvcb)) + return -EINVAL; + return 0; +} + +/* + * Calculate the expected ref_count for a page that would otherwise have no + * further pins. This was cribbed from similar functions in other places in + * the kernel, but with some slight modifications. We know that a secure + * page can not be a huge page for example. + */ +static int expected_page_refs(struct page *page) +{ + int res; + + res = page_mapcount(page); + if (PageSwapCache(page)) { + res++; + } else if (page_mapping(page)) { + res++; + if (page_has_private(page)) + res++; + } + return res; +} + +static int make_secure_pte(pte_t *ptep, unsigned long addr, + struct page *exp_page, struct uv_cb_header *uvcb) +{ + pte_t entry = READ_ONCE(*ptep); + struct page *page; + int expected, rc = 0; + + if (!pte_present(entry)) + return -ENXIO; + if (pte_val(entry) & _PAGE_INVALID) + return -ENXIO; + + page = pte_page(entry); + if (page != exp_page) + return -ENXIO; + if (PageWriteback(page)) + return -EAGAIN; + expected = expected_page_refs(page); + if (!page_ref_freeze(page, expected)) + return -EBUSY; + set_bit(PG_arch_1, &page->flags); + rc = uv_call(0, (u64)uvcb); + page_ref_unfreeze(page, expected); + /* Return -ENXIO if the page was not mapped, -EINVAL otherwise */ + if (rc) + rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL; + return rc; +} + +/* + * Requests the Ultravisor to make a page accessible to a guest. + * If it's brought in the first time, it will be cleared. If + * it has been exported before, it will be decrypted and integrity + * checked. + */ +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) +{ + struct vm_area_struct *vma; + bool local_drain = false; + spinlock_t *ptelock; + unsigned long uaddr; + struct page *page; + pte_t *ptep; + int rc; + +again: + rc = -EFAULT; + down_read(&gmap->mm->mmap_sem); + + uaddr = __gmap_translate(gmap, gaddr); + if (IS_ERR_VALUE(uaddr)) + goto out; + vma = find_vma(gmap->mm, uaddr); + if (!vma) + goto out; + /* + * Secure pages cannot be huge and userspace should not combine both. + * In case userspace does it anyway this will result in an -EFAULT for + * the unpack. The guest is thus never reaching secure mode. If + * userspace is playing dirty tricky with mapping huge pages later + * on this will result in a segmentation fault. + */ + if (is_vm_hugetlb_page(vma)) + goto out; + + rc = -ENXIO; + page = follow_page(vma, uaddr, FOLL_WRITE); + if (IS_ERR_OR_NULL(page)) + goto out; + + lock_page(page); + ptep = get_locked_pte(gmap->mm, uaddr, &ptelock); + rc = make_secure_pte(ptep, uaddr, page, uvcb); + pte_unmap_unlock(ptep, ptelock); + unlock_page(page); +out: + up_read(&gmap->mm->mmap_sem); + + if (rc == -EAGAIN) { + wait_on_page_writeback(page); + } else if (rc == -EBUSY) { + /* + * If we have tried a local drain and the page refcount + * still does not match our expected safe value, try with a + * system wide drain. This is needed if the pagevecs holding + * the page are on a different CPU. + */ + if (local_drain) { + lru_add_drain_all(); + /* We give up here, and let the caller try again */ + return -EAGAIN; + } + /* + * We are here if the page refcount does not match the + * expected safe value. The main culprits are usually + * pagevecs. With lru_add_drain() we drain the pagevecs + * on the local CPU so that hopefully the refcount will + * reach the expected safe value. + */ + lru_add_drain(); + local_drain = true; + /* And now we try again immediately after draining */ + goto again; + } else if (rc == -ENXIO) { + if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE)) + return -EFAULT; + return -EAGAIN; + } + return rc; +} +EXPORT_SYMBOL_GPL(gmap_make_secure); + +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) +{ + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_CONV_TO_SEC_STOR, + .header.len = sizeof(uvcb), + .guest_handle = gmap->guest_handle, + .gaddr = gaddr, + }; + + return gmap_make_secure(gmap, gaddr, &uvcb); +} +EXPORT_SYMBOL_GPL(gmap_convert_to_secure); + +/* + * To be called with the page locked or with an extra reference! This will + * prevent gmap_make_secure from touching the page concurrently. Having 2 + * parallel make_page_accessible is fine, as the UV calls will become a + * no-op if the page is already exported. + */ +int arch_make_page_accessible(struct page *page) +{ + int rc = 0; + + /* Hugepage cannot be protected, so nothing to do */ + if (PageHuge(page)) + return 0; + + /* + * PG_arch_1 is used in 3 places: + * 1. for kernel page tables during early boot + * 2. for storage keys of huge pages and KVM + * 3. As an indication that this page might be secure. This can + * overindicate, e.g. we set the bit before calling + * convert_to_secure. + * As secure pages are never huge, all 3 variants can co-exists. + */ + if (!test_bit(PG_arch_1, &page->flags)) + return 0; + + rc = uv_pin_shared(page_to_phys(page)); + if (!rc) { + clear_bit(PG_arch_1, &page->flags); + return 0; + } + + rc = uv_convert_from_secure(page_to_phys(page)); + if (!rc) { + clear_bit(PG_arch_1, &page->flags); + return 0; + } + + return rc; +} +EXPORT_SYMBOL_GPL(arch_make_page_accessible); + +#endif + +#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM) +static ssize_t uv_query_facilities(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n", + uv_info.inst_calls_list[0], + uv_info.inst_calls_list[1], + uv_info.inst_calls_list[2], + uv_info.inst_calls_list[3]); +} + +static struct kobj_attribute uv_query_facilities_attr = + __ATTR(facilities, 0444, uv_query_facilities, NULL); + +static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%d\n", + uv_info.max_guest_cpus); +} + +static struct kobj_attribute uv_query_max_guest_cpus_attr = + __ATTR(max_cpus, 0444, uv_query_max_guest_cpus, NULL); + +static ssize_t uv_query_max_guest_vms(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%d\n", + uv_info.max_num_sec_conf); +} + +static struct kobj_attribute uv_query_max_guest_vms_attr = + __ATTR(max_guests, 0444, uv_query_max_guest_vms, NULL); + +static ssize_t uv_query_max_guest_addr(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%lx\n", + uv_info.max_sec_stor_addr); +} + +static struct kobj_attribute uv_query_max_guest_addr_attr = + __ATTR(max_address, 0444, uv_query_max_guest_addr, NULL); + +static struct attribute *uv_query_attrs[] = { + &uv_query_facilities_attr.attr, + &uv_query_max_guest_cpus_attr.attr, + &uv_query_max_guest_vms_attr.attr, + &uv_query_max_guest_addr_attr.attr, + NULL, +}; + +static struct attribute_group uv_query_attr_group = { + .attrs = uv_query_attrs, +}; + +static struct kset *uv_query_kset; +static struct kobject *uv_kobj; + +static int __init uv_info_init(void) +{ + int rc = -ENOMEM; + + if (!test_facility(158)) + return 0; + + uv_kobj = kobject_create_and_add("uv", firmware_kobj); + if (!uv_kobj) + return -ENOMEM; + + uv_query_kset = kset_create_and_add("query", NULL, uv_kobj); + if (!uv_query_kset) + goto out_kobj; + + rc = sysfs_create_group(&uv_query_kset->kobj, &uv_query_attr_group); + if (!rc) + return 0; + + kset_unregister(uv_query_kset); +out_kobj: + kobject_del(uv_kobj); + kobject_put(uv_kobj); + return rc; +} +device_initcall(uv_info_init); +#endif diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 05ee90a5ea08..12decca22e7c 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -9,6 +9,6 @@ common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqch ccflags-y := -Ivirt/kvm -Iarch/s390/kvm kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-objs += diag.o gaccess.o guestdbg.o vsie.o +kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3fb54ec2cf3e..563429dece03 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -2,7 +2,7 @@ /* * handling diagnose instructions * - * Copyright IBM Corp. 2008, 2011 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -201,6 +201,10 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } + /* + * no need to check the return value of vcpu_stop as it can only have + * an error for protvirt, but protvirt means user cpu state + */ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) kvm_s390_vcpu_stop(vcpu); vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM; diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 07d30ffcfa41..47a67a958107 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -505,7 +505,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, switch (prot) { case PROT_TYPE_IEP: tec->b61 = 1; - /* FALL THROUGH */ + fallthrough; case PROT_TYPE_LA: tec->b56 = 1; break; @@ -514,12 +514,12 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, break; case PROT_TYPE_ALC: tec->b60 = 1; - /* FALL THROUGH */ + fallthrough; case PROT_TYPE_DAT: tec->b61 = 1; break; } - /* FALL THROUGH */ + fallthrough; case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: case PGM_REGION_FIRST_TRANS: @@ -534,7 +534,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, tec->addr = gva >> PAGE_SHIFT; tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH; tec->as = psw_bits(vcpu->arch.sie_block->gpsw).as; - /* FALL THROUGH */ + fallthrough; case PGM_ALEN_TRANSLATION: case PGM_ALE_SEQUENCE: case PGM_ASTE_VALIDITY: @@ -677,7 +677,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rfte.p; ptr = rfte.rto * PAGE_SIZE + vaddr.rsx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_REGION2: { union region2_table_entry rste; @@ -695,7 +695,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rste.p; ptr = rste.rto * PAGE_SIZE + vaddr.rtx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_REGION3: { union region3_table_entry rtte; @@ -723,7 +723,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rtte.fc0.p; ptr = rtte.fc0.sto * PAGE_SIZE + vaddr.sx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; @@ -1050,7 +1050,8 @@ shadow_r2t: rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_REGION2: { union region2_table_entry rste; @@ -1076,7 +1077,8 @@ shadow_r3t: rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_REGION3: { union region3_table_entry rtte; @@ -1111,7 +1113,8 @@ shadow_sgt: rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index a389fa85cca2..e7a7c499a73f 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -2,7 +2,7 @@ /* * in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008, 2014 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -12,10 +12,10 @@ #include <linux/errno.h> #include <linux/pagemap.h> -#include <asm/kvm_host.h> #include <asm/asm-offsets.h> #include <asm/irq.h> #include <asm/sysinfo.h> +#include <asm/uv.h> #include "kvm-s390.h" #include "gaccess.h" @@ -79,6 +79,10 @@ static int handle_stop(struct kvm_vcpu *vcpu) return rc; } + /* + * no need to check the return value of vcpu_stop as it can only have + * an error for protvirt, but protvirt means user cpu state + */ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) kvm_s390_vcpu_stop(vcpu); return -EOPNOTSUPP; @@ -231,6 +235,13 @@ static int handle_prog(struct kvm_vcpu *vcpu) vcpu->stat.exit_program_interruption++; + /* + * Intercept 8 indicates a loop of specification exceptions + * for protected guests. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return -EOPNOTSUPP; + if (guestdbg_enabled(vcpu) && per_event(vcpu)) { rc = kvm_s390_handle_per_event(vcpu); if (rc) @@ -384,7 +395,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu) goto out; } - if (addr & ~PAGE_MASK) + if (!kvm_s390_pv_cpu_is_protected(vcpu) && (addr & ~PAGE_MASK)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); sctns = (void *)get_zeroed_page(GFP_KERNEL); @@ -395,10 +406,15 @@ int handle_sthyi(struct kvm_vcpu *vcpu) out: if (!cc) { - r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE); - if (r) { - free_page((unsigned long)sctns); - return kvm_s390_inject_prog_cond(vcpu, r); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy((void *)(sida_origin(vcpu->arch.sie_block)), + sctns, PAGE_SIZE); + } else { + r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE); + if (r) { + free_page((unsigned long)sctns); + return kvm_s390_inject_prog_cond(vcpu, r); + } } } @@ -444,6 +460,77 @@ static int handle_operexc(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); } +static int handle_pv_spx(struct kvm_vcpu *vcpu) +{ + u32 pref = *(u32 *)vcpu->arch.sie_block->sidad; + + kvm_s390_set_prefix(vcpu, pref); + trace_kvm_s390_handle_prefix(vcpu, 1, pref); + return 0; +} + +static int handle_pv_sclp(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + + spin_lock(&fi->lock); + /* + * 2 cases: + * a: an sccb answering interrupt was already pending or in flight. + * As the sccb value is not known we can simply set some value to + * trigger delivery of a saved SCCB. UV will then use its saved + * copy of the SCCB value. + * b: an error SCCB interrupt needs to be injected so we also inject + * a fake SCCB address. Firmware will use the proper one. + * This makes sure, that both errors and real sccb returns will only + * be delivered after a notification intercept (instruction has + * finished) but not after others. + */ + fi->srv_signal.ext_params |= 0x43000; + set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + clear_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs); + spin_unlock(&fi->lock); + return 0; +} + +static int handle_pv_uvc(struct kvm_vcpu *vcpu) +{ + struct uv_cb_share *guest_uvcb = (void *)vcpu->arch.sie_block->sidad; + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_UNPIN_PAGE_SHARED, + .header.len = sizeof(uvcb), + .guest_handle = kvm_s390_pv_get_handle(vcpu->kvm), + .gaddr = guest_uvcb->paddr, + }; + int rc; + + if (guest_uvcb->header.cmd != UVC_CMD_REMOVE_SHARED_ACCESS) { + WARN_ONCE(1, "Unexpected notification intercept for UVC 0x%x\n", + guest_uvcb->header.cmd); + return 0; + } + rc = gmap_make_secure(vcpu->arch.gmap, uvcb.gaddr, &uvcb); + /* + * If the unpin did not succeed, the guest will exit again for the UVC + * and we will retry the unpin. + */ + if (rc == -EINVAL) + return 0; + return rc; +} + +static int handle_pv_notification(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->ipa == 0xb210) + return handle_pv_spx(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb220) + return handle_pv_sclp(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb9a4) + return handle_pv_uvc(vcpu); + + return handle_instruction(vcpu); +} + int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) { int rc, per_rc = 0; @@ -480,6 +567,28 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) case ICPT_KSS: rc = kvm_s390_skey_check_enable(vcpu); break; + case ICPT_MCHKREQ: + case ICPT_INT_ENABLE: + /* + * PSW bit 13 or a CR (0, 6, 14) changed and we might + * now be able to deliver interrupts. The pre-run code + * will take care of this. + */ + rc = 0; + break; + case ICPT_PV_INSTR: + rc = handle_instruction(vcpu); + break; + case ICPT_PV_NOTIFY: + rc = handle_pv_notification(vcpu); + break; + case ICPT_PV_PREF: + rc = 0; + gmap_convert_to_secure(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu)); + gmap_convert_to_secure(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu) + PAGE_SIZE); + break; default: return -EOPNOTSUPP; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c06c89d370a7..8191106bf7b9 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2,7 +2,7 @@ /* * handling kvm guest interrupts * - * Copyright IBM Corp. 2008, 2015 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> */ @@ -324,8 +324,11 @@ static inline int gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) { - return vcpu->kvm->arch.float_int.pending_irqs | - vcpu->arch.local_int.pending_irqs; + unsigned long pending = vcpu->kvm->arch.float_int.pending_irqs | + vcpu->arch.local_int.pending_irqs; + + pending &= ~vcpu->kvm->arch.float_int.masked_irqs; + return pending; } static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) @@ -383,10 +386,18 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & CR0_CPU_TIMER_SUBMASK)) __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); - if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) + if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) { __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); + __clear_bit(IRQ_PEND_EXT_SERVICE_EV, &active_mask); + } if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; + /* PV guest cpus can have a single interruption injected at a time. */ + if (kvm_s390_pv_cpu_is_protected(vcpu) && + vcpu->arch.sie_block->iictl != IICTL_CODE_NONE) + active_mask &= ~(IRQ_PEND_EXT_II_MASK | + IRQ_PEND_IO_MASK | + IRQ_PEND_MCHK_MASK); /* * Check both floating and local interrupt's cr14 because * bit IRQ_PEND_MCHK_REP could be set in both cases. @@ -479,19 +490,23 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu) static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; vcpu->stat.deliver_cputm++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER, 0, 0); - - rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, - (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_CPU_TIMER; + } else { + rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -499,19 +514,23 @@ static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; vcpu->stat.deliver_ckc++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP, 0, 0); - - rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, - (u16 __user *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_CLK_COMP; + } else { + rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, + (u16 __user *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -553,6 +572,20 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, union mci mci; int rc; + /* + * All other possible payload for a machine check (e.g. the register + * contents in the save area) will be handled by the ultravisor, as + * the hypervisor does not not have the needed information for + * protected guests. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_MCHK; + vcpu->arch.sie_block->mcic = mchk->mcic; + vcpu->arch.sie_block->faddr = mchk->failing_storage_address; + vcpu->arch.sie_block->edc = mchk->ext_damage_code; + return 0; + } + mci.val = mchk->mcic; /* take care of lazy register loading */ save_fpu_regs(); @@ -696,17 +729,21 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart"); vcpu->stat.deliver_restart_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0); - rc = write_guest_lc(vcpu, - offsetof(struct lowcore, restart_old_psw), - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw), - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_RESTART; + } else { + rc = write_guest_lc(vcpu, + offsetof(struct lowcore, restart_old_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_RESTART, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -748,6 +785,12 @@ static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu) vcpu->stat.deliver_emergency_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, cpu_addr, 0); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_EMERGENCY_SIG; + vcpu->arch.sie_block->extcpuaddr = cpu_addr; + return 0; + } rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG, (u16 *)__LC_EXT_INT_CODE); @@ -776,6 +819,12 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL, extcall.code, 0); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_EXTERNAL_CALL; + vcpu->arch.sie_block->extcpuaddr = extcall.code; + return 0; + } rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL, (u16 *)__LC_EXT_INT_CODE); @@ -787,6 +836,21 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +static int __deliver_prog_pv(struct kvm_vcpu *vcpu, u16 code) +{ + switch (code) { + case PGM_SPECIFICATION: + vcpu->arch.sie_block->iictl = IICTL_CODE_SPECIFICATION; + break; + case PGM_OPERAND: + vcpu->arch.sie_block->iictl = IICTL_CODE_OPERAND; + break; + default: + return -EINVAL; + } + return 0; +} + static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -807,6 +871,10 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, pgm_info.code, 0); + /* PER is handled by the ultravisor */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return __deliver_prog_pv(vcpu, pgm_info.code & ~PGM_PER); + switch (pgm_info.code & ~PGM_PER) { case PGM_AFX_TRANSLATION: case PGM_ASX_TRANSLATION: @@ -818,7 +886,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: nullifying = true; - /* fall through */ + fallthrough; case PGM_SPACE_SWITCH: rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); @@ -902,20 +970,49 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +#define SCCB_MASK 0xFFFFFFF8 +#define SCCB_EVENT_PENDING 0x3 + +static int write_sclp(struct kvm_vcpu *vcpu, u32 parm) +{ + int rc; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_SERVICE_SIG; + vcpu->arch.sie_block->eiparams = parm; + return 0; + } + + rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, parm, + (u32 *)__LC_EXT_PARAMS); + + return rc ? -EFAULT : 0; +} + static int __must_check __deliver_service(struct kvm_vcpu *vcpu) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_ext_info ext; - int rc = 0; spin_lock(&fi->lock); - if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs) || + !(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { spin_unlock(&fi->lock); return 0; } ext = fi->srv_signal; memset(&fi->srv_signal, 0, sizeof(ext)); clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + if (kvm_s390_pv_cpu_is_protected(vcpu)) + set_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs); spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x", @@ -924,16 +1021,31 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, ext.ext_params, 0); - rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, ext.ext_params, - (u32 *)__LC_EXT_PARAMS); + return write_sclp(vcpu, ext.ext_params); +} - return rc ? -EFAULT : 0; +static int __must_check __deliver_service_ev(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_ext_info ext; + + spin_lock(&fi->lock); + if (!(test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs))) { + spin_unlock(&fi->lock); + return 0; + } + ext = fi->srv_signal; + /* only clear the event bit */ + fi->srv_signal.ext_params &= ~SCCB_EVENT_PENDING; + clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + spin_unlock(&fi->lock); + + VCPU_EVENT(vcpu, 4, "%s", "deliver: sclp parameter event"); + vcpu->stat.deliver_service_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, + ext.ext_params, 0); + + return write_sclp(vcpu, SCCB_EVENT_PENDING); } static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) @@ -1028,6 +1140,15 @@ static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io) { int rc; + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_IO; + vcpu->arch.sie_block->subchannel_id = io->subchannel_id; + vcpu->arch.sie_block->subchannel_nr = io->subchannel_nr; + vcpu->arch.sie_block->io_int_parm = io->io_int_parm; + vcpu->arch.sie_block->io_int_word = io->io_int_word; + return 0; + } + rc = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID); rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR); rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM); @@ -1329,6 +1450,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) case IRQ_PEND_EXT_SERVICE: rc = __deliver_service(vcpu); break; + case IRQ_PEND_EXT_SERVICE_EV: + rc = __deliver_service_ev(vcpu); + break; case IRQ_PEND_PFAULT_DONE: rc = __deliver_pfault_done(vcpu); break; @@ -1421,7 +1545,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL) return -EINVAL; - if (sclp.has_sigpif) + if (sclp.has_sigpif && !kvm_s390_pv_cpu_get_handle(vcpu)) return sca_inject_ext_call(vcpu, src_id); if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) @@ -1681,9 +1805,6 @@ out: return inti; } -#define SCCB_MASK 0xFFFFFFF8 -#define SCCB_EVENT_PENDING 0x3 - static int __inject_service(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { @@ -1692,6 +1813,11 @@ static int __inject_service(struct kvm *kvm, kvm->stat.inject_service_signal++; spin_lock(&fi->lock); fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING; + + /* We always allow events, track them separately from the sccb ints */ + if (fi->srv_signal.ext_params & SCCB_EVENT_PENDING) + set_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + /* * Early versions of the QEMU s390 bios will inject several * service interrupts after another without handling a @@ -1773,7 +1899,14 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) kvm->stat.inject_io++; isc = int_word_to_isc(inti->io.io_int_word); - if (gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) { + /* + * Do not make use of gisa in protected mode. We do not use the lock + * checking variant as this is just a performance optimization and we + * do not hold the lock here. This is ok as the code will pick + * interrupts from both "lists" for delivery. + */ + if (!kvm_s390_pv_get_handle(kvm) && + gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) { VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc); gisa_set_ipm_gisc(gi->origin, isc); kfree(inti); @@ -1834,7 +1967,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: if (!(type & KVM_S390_INT_IO_AI_MASK && - kvm->arch.gisa_int.origin)) + kvm->arch.gisa_int.origin) || + kvm_s390_pv_cpu_get_handle(dst_vcpu)) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: @@ -2080,6 +2214,10 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; int i; + mutex_lock(&kvm->lock); + if (!kvm_s390_pv_is_protected(kvm)) + fi->masked_irqs = 0; + mutex_unlock(&kvm->lock); spin_lock(&fi->lock); fi->pending_irqs = 0; memset(&fi->srv_signal, 0, sizeof(fi->srv_signal)); @@ -2146,7 +2284,8 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) n++; } } - if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) { + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs) || + test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs)) { if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; @@ -2327,9 +2466,6 @@ static int register_io_adapter(struct kvm_device *dev, if (!adapter) return -ENOMEM; - INIT_LIST_HEAD(&adapter->maps); - init_rwsem(&adapter->maps_lock); - atomic_set(&adapter->nr_maps, 0); adapter->id = adapter_info.id; adapter->isc = adapter_info.isc; adapter->maskable = adapter_info.maskable; @@ -2354,87 +2490,12 @@ int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked) return ret; } -static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr) -{ - struct s390_io_adapter *adapter = get_io_adapter(kvm, id); - struct s390_map_info *map; - int ret; - - if (!adapter || !addr) - return -EINVAL; - - map = kzalloc(sizeof(*map), GFP_KERNEL); - if (!map) { - ret = -ENOMEM; - goto out; - } - INIT_LIST_HEAD(&map->list); - map->guest_addr = addr; - map->addr = gmap_translate(kvm->arch.gmap, addr); - if (map->addr == -EFAULT) { - ret = -EFAULT; - goto out; - } - ret = get_user_pages_fast(map->addr, 1, FOLL_WRITE, &map->page); - if (ret < 0) - goto out; - BUG_ON(ret != 1); - down_write(&adapter->maps_lock); - if (atomic_inc_return(&adapter->nr_maps) < MAX_S390_ADAPTER_MAPS) { - list_add_tail(&map->list, &adapter->maps); - ret = 0; - } else { - put_page(map->page); - ret = -EINVAL; - } - up_write(&adapter->maps_lock); -out: - if (ret) - kfree(map); - return ret; -} - -static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr) -{ - struct s390_io_adapter *adapter = get_io_adapter(kvm, id); - struct s390_map_info *map, *tmp; - int found = 0; - - if (!adapter || !addr) - return -EINVAL; - - down_write(&adapter->maps_lock); - list_for_each_entry_safe(map, tmp, &adapter->maps, list) { - if (map->guest_addr == addr) { - found = 1; - atomic_dec(&adapter->nr_maps); - list_del(&map->list); - put_page(map->page); - kfree(map); - break; - } - } - up_write(&adapter->maps_lock); - - return found ? 0 : -EINVAL; -} - void kvm_s390_destroy_adapters(struct kvm *kvm) { int i; - struct s390_map_info *map, *tmp; - for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) { - if (!kvm->arch.adapters[i]) - continue; - list_for_each_entry_safe(map, tmp, - &kvm->arch.adapters[i]->maps, list) { - list_del(&map->list); - put_page(map->page); - kfree(map); - } + for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) kfree(kvm->arch.adapters[i]); - } } static int modify_io_adapter(struct kvm_device *dev, @@ -2456,11 +2517,14 @@ static int modify_io_adapter(struct kvm_device *dev, if (ret > 0) ret = 0; break; + /* + * The following operations are no longer needed and therefore no-ops. + * The gpa to hva translation is done when an IRQ route is set up. The + * set_irq code uses get_user_pages_remote() to do the actual write. + */ case KVM_S390_IO_ADAPTER_MAP: - ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr); - break; case KVM_S390_IO_ADAPTER_UNMAP: - ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr); + ret = 0; break; default: ret = -EINVAL; @@ -2699,19 +2763,15 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit; } -static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter, - u64 addr) +static struct page *get_map_page(struct kvm *kvm, u64 uaddr) { - struct s390_map_info *map; + struct page *page = NULL; - if (!adapter) - return NULL; - - list_for_each_entry(map, &adapter->maps, list) { - if (map->guest_addr == addr) - return map; - } - return NULL; + down_read(&kvm->mm->mmap_sem); + get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE, + &page, NULL, NULL); + up_read(&kvm->mm->mmap_sem); + return page; } static int adapter_indicators_set(struct kvm *kvm, @@ -2720,30 +2780,35 @@ static int adapter_indicators_set(struct kvm *kvm, { unsigned long bit; int summary_set, idx; - struct s390_map_info *info; + struct page *ind_page, *summary_page; void *map; - info = get_map_info(adapter, adapter_int->ind_addr); - if (!info) + ind_page = get_map_page(kvm, adapter_int->ind_addr); + if (!ind_page) return -1; - map = page_address(info->page); - bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap); - set_bit(bit, map); - idx = srcu_read_lock(&kvm->srcu); - mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); - set_page_dirty_lock(info->page); - info = get_map_info(adapter, adapter_int->summary_addr); - if (!info) { - srcu_read_unlock(&kvm->srcu, idx); + summary_page = get_map_page(kvm, adapter_int->summary_addr); + if (!summary_page) { + put_page(ind_page); return -1; } - map = page_address(info->page); - bit = get_ind_bit(info->addr, adapter_int->summary_offset, - adapter->swap); + + idx = srcu_read_lock(&kvm->srcu); + map = page_address(ind_page); + bit = get_ind_bit(adapter_int->ind_addr, + adapter_int->ind_offset, adapter->swap); + set_bit(bit, map); + mark_page_dirty(kvm, adapter_int->ind_addr >> PAGE_SHIFT); + set_page_dirty_lock(ind_page); + map = page_address(summary_page); + bit = get_ind_bit(adapter_int->summary_addr, + adapter_int->summary_offset, adapter->swap); summary_set = test_and_set_bit(bit, map); - mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); - set_page_dirty_lock(info->page); + mark_page_dirty(kvm, adapter_int->summary_addr >> PAGE_SHIFT); + set_page_dirty_lock(summary_page); srcu_read_unlock(&kvm->srcu, idx); + + put_page(ind_page); + put_page(summary_page); return summary_set ? 0 : 1; } @@ -2765,9 +2830,7 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e, adapter = get_io_adapter(kvm, e->adapter.adapter_id); if (!adapter) return -1; - down_read(&adapter->maps_lock); ret = adapter_indicators_set(kvm, adapter, &e->adapter); - up_read(&adapter->maps_lock); if ((ret > 0) && !adapter->masked) { ret = kvm_s390_inject_airq(kvm, adapter); if (ret == 0) @@ -2818,23 +2881,27 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { - int ret; + u64 uaddr; switch (ue->type) { + /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: e->set = set_adapter_int; - e->adapter.summary_addr = ue->u.adapter.summary_addr; - e->adapter.ind_addr = ue->u.adapter.ind_addr; + uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); + if (uaddr == -EFAULT) + return -EFAULT; + e->adapter.summary_addr = uaddr; + uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr); + if (uaddr == -EFAULT) + return -EFAULT; + e->adapter.ind_addr = uaddr; e->adapter.summary_offset = ue->u.adapter.summary_offset; e->adapter.ind_offset = ue->u.adapter.ind_offset; e->adapter.adapter_id = ue->u.adapter.adapter_id; - ret = 0; - break; + return 0; default: - ret = -EINVAL; + return -EINVAL; } - - return ret; } int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d7ff30e45589..19a81024fe16 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2,7 +2,7 @@ /* * hosting IBM Z kernel virtual machines (s390x) * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -44,6 +44,7 @@ #include <asm/cpacf.h> #include <asm/timex.h> #include <asm/ap.h> +#include <asm/uv.h> #include "kvm-s390.h" #include "gaccess.h" @@ -184,6 +185,11 @@ static u8 halt_poll_max_steal = 10; module_param(halt_poll_max_steal, byte, 0644); MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling"); +/* if set to true, the GISA will be initialized and used if available */ +static bool use_gisa = true; +module_param(use_gisa, bool, 0644); +MODULE_PARM_DESC(use_gisa, "Use the GISA if the host supports it."); + /* * For now we handle at most 16 double words as this is what the s390 base * kernel handles and stores in the prefix page. If we ever need to go beyond @@ -220,6 +226,7 @@ static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc; static struct gmap_notifier gmap_notifier; static struct gmap_notifier vsie_gmap_notifier; debug_info_t *kvm_s390_dbf; +debug_info_t *kvm_s390_dbf_uv; /* Section: not file related */ int kvm_arch_hardware_enable(void) @@ -228,13 +235,15 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { return 0; } +/* forward declarations */ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); +static int sca_switch_to_extended(struct kvm *kvm); static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta) { @@ -293,7 +302,7 @@ static struct notifier_block kvm_clock_notifier = { .notifier_call = kvm_clock_sync, }; -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { gmap_notifier.notifier_call = kvm_gmap_notifier; gmap_register_pte_notifier(&gmap_notifier); @@ -460,7 +469,12 @@ int kvm_arch_init(void *opaque) if (!kvm_s390_dbf) return -ENOMEM; - if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) + kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long)); + if (!kvm_s390_dbf_uv) + goto out; + + if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) || + debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view)) goto out; kvm_s390_cpu_feat_init(); @@ -487,6 +501,7 @@ void kvm_arch_exit(void) { kvm_s390_gib_destroy(); debug_unregister(kvm_s390_dbf); + debug_unregister(kvm_s390_dbf_uv); } /* Section: device related */ @@ -564,14 +579,16 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_BPB: r = test_facility(82); break; + case KVM_CAP_S390_PROTECTED: + r = is_prot_virt_host(); + break; default: r = 0; } return r; } -static void kvm_s390_sync_dirty_log(struct kvm *kvm, - struct kvm_memory_slot *memslot) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { int i; gfn_t cur_gfn, last_gfn; @@ -612,9 +629,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, { int r; unsigned long n; - struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int is_dirty = 0; + int is_dirty; if (kvm_is_ucontrol(kvm)) return -EINVAL; @@ -625,14 +641,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - r = -ENOENT; - if (!memslot->dirty_bitmap) - goto out; - - kvm_s390_sync_dirty_log(kvm, memslot); - r = kvm_get_dirty_log(kvm, log, &is_dirty); + r = kvm_get_dirty_log(kvm, log, &is_dirty, &memslot); if (r) goto out; @@ -1993,6 +2002,9 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *ms; + if (unlikely(!slots->used_slots)) + return 0; + cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); ms = gfn_to_memslot(kvm, cur_gfn); args->count = 0; @@ -2158,6 +2170,194 @@ out: return r; } +static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) +{ + struct kvm_vcpu *vcpu; + u16 rc, rrc; + int ret = 0; + int i; + + /* + * We ignore failures and try to destroy as many CPUs as possible. + * At the same time we must not free the assigned resources when + * this fails, as the ultravisor has still access to that memory. + * So kvm_s390_pv_destroy_cpu can leave a "wanted" memory leak + * behind. + * We want to return the first failure rc and rrc, though. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_lock(&vcpu->mutex); + if (kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc) && !ret) { + *rcp = rc; + *rrcp = rrc; + ret = -EIO; + } + mutex_unlock(&vcpu->mutex); + } + return ret; +} + +static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + int i, r = 0; + u16 dummy; + + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_lock(&vcpu->mutex); + r = kvm_s390_pv_create_cpu(vcpu, rc, rrc); + mutex_unlock(&vcpu->mutex); + if (r) + break; + } + if (r) + kvm_s390_cpus_from_pv(kvm, &dummy, &dummy); + return r; +} + +static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) +{ + int r = 0; + u16 dummy; + void __user *argp = (void __user *)cmd->data; + + switch (cmd->cmd) { + case KVM_PV_ENABLE: { + r = -EINVAL; + if (kvm_s390_pv_is_protected(kvm)) + break; + + /* + * FMT 4 SIE needs esca. As we never switch back to bsca from + * esca, we need no cleanup in the error cases below + */ + r = sca_switch_to_extended(kvm); + if (r) + break; + + down_write(¤t->mm->mmap_sem); + r = gmap_mark_unmergeable(); + up_write(¤t->mm->mmap_sem); + if (r) + break; + + r = kvm_s390_pv_init_vm(kvm, &cmd->rc, &cmd->rrc); + if (r) + break; + + r = kvm_s390_cpus_to_pv(kvm, &cmd->rc, &cmd->rrc); + if (r) + kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); + + /* we need to block service interrupts from now on */ + set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + } + case KVM_PV_DISABLE: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc); + /* + * If a CPU could not be destroyed, destroy VM will also fail. + * There is no point in trying to destroy it. Instead return + * the rc and rrc from the first CPU that failed destroying. + */ + if (r) + break; + r = kvm_s390_pv_deinit_vm(kvm, &cmd->rc, &cmd->rrc); + + /* no need to block service interrupts any more */ + clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + } + case KVM_PV_SET_SEC_PARMS: { + struct kvm_s390_pv_sec_parm parms = {}; + void *hdr; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = -EFAULT; + if (copy_from_user(&parms, argp, sizeof(parms))) + break; + + /* Currently restricted to 8KB */ + r = -EINVAL; + if (parms.length > PAGE_SIZE * 2) + break; + + r = -ENOMEM; + hdr = vmalloc(parms.length); + if (!hdr) + break; + + r = -EFAULT; + if (!copy_from_user(hdr, (void __user *)parms.origin, + parms.length)) + r = kvm_s390_pv_set_sec_parms(kvm, hdr, parms.length, + &cmd->rc, &cmd->rrc); + + vfree(hdr); + break; + } + case KVM_PV_UNPACK: { + struct kvm_s390_pv_unp unp = {}; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = -EFAULT; + if (copy_from_user(&unp, argp, sizeof(unp))) + break; + + r = kvm_s390_pv_unpack(kvm, unp.addr, unp.size, unp.tweak, + &cmd->rc, &cmd->rrc); + break; + } + case KVM_PV_VERIFY: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_VERIFY_IMG, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT VERIFY: rc %x rrc %x", cmd->rc, + cmd->rrc); + break; + } + case KVM_PV_PREP_RESET: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_PREPARE_RESET, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT PREP RESET: rc %x rrc %x", + cmd->rc, cmd->rrc); + break; + } + case KVM_PV_UNSHARE_ALL: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_SET_UNSHARE_ALL, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT UNSHARE: rc %x rrc %x", + cmd->rc, cmd->rrc); + break; + } + default: + r = -ENOTTY; + } + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2255,6 +2455,33 @@ long kvm_arch_vm_ioctl(struct file *filp, mutex_unlock(&kvm->slots_lock); break; } + case KVM_S390_PV_COMMAND: { + struct kvm_pv_cmd args; + + /* protvirt means user sigp */ + kvm->arch.user_cpu_state_ctrl = 1; + r = 0; + if (!is_prot_virt_host()) { + r = -EINVAL; + break; + } + if (copy_from_user(&args, argp, sizeof(args))) { + r = -EFAULT; + break; + } + if (args.flags) { + r = -EINVAL; + break; + } + mutex_lock(&kvm->lock); + r = kvm_s390_handle_pv(kvm, &args); + mutex_unlock(&kvm->lock); + if (copy_to_user(argp, &args, sizeof(args))) { + r = -EFAULT; + break; + } + break; + } default: r = -ENOTTY; } @@ -2504,7 +2731,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.use_skf = sclp.has_skey; spin_lock_init(&kvm->arch.start_stop_lock); kvm_s390_vsie_init(kvm); - kvm_s390_gisa_init(kvm); + if (use_gisa) + kvm_s390_gisa_init(kvm); KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); return 0; @@ -2518,6 +2746,8 @@ out_err: void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { + u16 rc, rrc; + VCPU_EVENT(vcpu, 3, "%s", "free cpu"); trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id); kvm_s390_clear_local_irqs(vcpu); @@ -2530,6 +2760,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.use_cmma) kvm_s390_vcpu_unsetup_cmma(vcpu); + /* We can not hold the vcpu mutex here, we are already dying */ + if (kvm_s390_pv_cpu_get_handle(vcpu)) + kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc); free_page((unsigned long)(vcpu->arch.sie_block)); } @@ -2551,10 +2784,20 @@ static void kvm_free_vcpus(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { + u16 rc, rrc; + kvm_free_vcpus(kvm); sca_dispose(kvm); - debug_unregister(kvm->arch.dbf); kvm_s390_gisa_destroy(kvm); + /* + * We are already at the end of life and kvm->lock is not taken. + * This is ok as the file descriptor is closed by now and nobody + * can mess with the pv state. To avoid lockdep_assert_held from + * complaining we do not use kvm_s390_pv_is_protected. + */ + if (kvm_s390_pv_get_handle(kvm)) + kvm_s390_pv_deinit_vm(kvm, &rc, &rrc); + debug_unregister(kvm->arch.dbf); free_page((unsigned long)kvm->arch.sie_page2); if (!kvm_is_ucontrol(kvm)) gmap_remove(kvm->arch.gmap); @@ -2650,6 +2893,9 @@ static int sca_switch_to_extended(struct kvm *kvm) unsigned int vcpu_idx; u32 scaol, scaoh; + if (kvm->arch.use_esca) + return 0; + new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO); if (!new_sca) return -ENOMEM; @@ -2901,6 +3147,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; + u16 uvrc, uvrrc; atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM | @@ -2968,6 +3215,14 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) kvm_s390_vcpu_crypto_setup(vcpu); + mutex_lock(&vcpu->kvm->lock); + if (kvm_s390_pv_is_protected(vcpu->kvm)) { + rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc); + if (rc) + kvm_s390_vcpu_unsetup_cmma(vcpu); + } + mutex_unlock(&vcpu->kvm->lock); + return rc; } @@ -3268,20 +3523,43 @@ 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); kvm_s390_set_cpu_timer(vcpu, 0); vcpu->arch.sie_block->ckc = 0; - vcpu->arch.sie_block->todpr = 0; 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; - vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + /* + * Do not reset these registers in the protected case, as some of + * them are overlayed and they are not accessible in this case + * anyway. + */ + if (!kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->gbea = 1; + vcpu->arch.sie_block->pp = 0; + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + vcpu->arch.sie_block->todpr = 0; + } } static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) @@ -3471,14 +3749,20 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, switch (mp_state->mp_state) { case KVM_MP_STATE_STOPPED: - kvm_s390_vcpu_stop(vcpu); + rc = kvm_s390_vcpu_stop(vcpu); break; case KVM_MP_STATE_OPERATING: - kvm_s390_vcpu_start(vcpu); + rc = kvm_s390_vcpu_start(vcpu); break; case KVM_MP_STATE_LOAD: + if (!kvm_s390_pv_cpu_is_protected(vcpu)) { + rc = -ENXIO; + break; + } + rc = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR_LOAD); + break; case KVM_MP_STATE_CHECK_STOP: - /* fall through - CHECK_STOP and LOAD are not supported yet */ + fallthrough; /* CHECK_STOP and LOAD are not supported yet */ default: rc = -ENXIO; } @@ -3828,9 +4112,11 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) return vcpu_post_run_fault_in_sie(vcpu); } +#define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK) static int __vcpu_run(struct kvm_vcpu *vcpu) { int rc, exit_reason; + struct sie_page *sie_page = (struct sie_page *)vcpu->arch.sie_block; /* * We try to hold kvm->srcu during most of vcpu_run (except when run- @@ -3852,8 +4138,28 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) guest_enter_irqoff(); __disable_cpu_timer_accounting(vcpu); local_irq_enable(); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy(sie_page->pv_grregs, + vcpu->run->s.regs.gprs, + sizeof(sie_page->pv_grregs)); + } exit_reason = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy(vcpu->run->s.regs.gprs, + sie_page->pv_grregs, + sizeof(sie_page->pv_grregs)); + /* + * We're not allowed to inject interrupts on intercepts + * that leave the guest state in an "in-between" state + * where the next SIE entry will do a continuation. + * Fence interrupts in our "internal" PSW. + */ + if (vcpu->arch.sie_block->icptcode == ICPT_PV_INSTR || + vcpu->arch.sie_block->icptcode == ICPT_PV_PREF) { + vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK; + } + } local_irq_disable(); __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); @@ -3867,7 +4173,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) return rc; } -static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void sync_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct runtime_instr_cb *riccb; struct gs_cb *gscb; @@ -3876,16 +4182,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) gscb = (struct gs_cb *) &kvm_run->s.regs.gscb; vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask; vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr; - if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) - kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix); - if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) { - memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128); - /* some control register changes require a tlb flush */ - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) { - kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm); - vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc; vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr; vcpu->arch.sie_block->pp = kvm_run->s.regs.pp; vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea; @@ -3926,6 +4223,36 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0; } + if (MACHINE_HAS_GS) { + preempt_disable(); + __ctl_set_bit(2, 4); + if (current->thread.gs_cb) { + vcpu->arch.host_gscb = current->thread.gs_cb; + save_gs_cb(vcpu->arch.host_gscb); + } + if (vcpu->arch.gs_enabled) { + current->thread.gs_cb = (struct gs_cb *) + &vcpu->run->s.regs.gscb; + restore_gs_cb(current->thread.gs_cb); + } + preempt_enable(); + } + /* SIE will load etoken directly from SDNX and therefore kvm_run */ +} + +static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) + kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix); + if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) { + memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128); + /* some control register changes require a tlb flush */ + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + } + if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) { + kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm); + vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc; + } save_access_regs(vcpu->arch.host_acrs); restore_access_regs(vcpu->run->s.regs.acrs); /* save host (userspace) fprs/vrs */ @@ -3940,23 +4267,47 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; + + /* Sync fmt2 only data */ + if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) { + sync_regs_fmt2(vcpu, kvm_run); + } else { + /* + * In several places we have to modify our internal view to + * not do things that are disallowed by the ultravisor. For + * example we must not inject interrupts after specific exits + * (e.g. 112 prefix page not secure). We do this by turning + * off the machine check, external and I/O interrupt bits + * of our PSW copy. To avoid getting validity intercepts, we + * do only accept the condition code from userspace. + */ + vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_CC; + vcpu->arch.sie_block->gpsw.mask |= kvm_run->psw_mask & + PSW_MASK_CC; + } + + kvm_run->kvm_dirty_regs = 0; +} + +static void store_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr; + kvm_run->s.regs.pp = vcpu->arch.sie_block->pp; + kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea; + kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; if (MACHINE_HAS_GS) { - preempt_disable(); __ctl_set_bit(2, 4); - if (current->thread.gs_cb) { - vcpu->arch.host_gscb = current->thread.gs_cb; - save_gs_cb(vcpu->arch.host_gscb); - } - if (vcpu->arch.gs_enabled) { - current->thread.gs_cb = (struct gs_cb *) - &vcpu->run->s.regs.gscb; - restore_gs_cb(current->thread.gs_cb); - } + if (vcpu->arch.gs_enabled) + save_gs_cb(current->thread.gs_cb); + preempt_disable(); + current->thread.gs_cb = vcpu->arch.host_gscb; + restore_gs_cb(vcpu->arch.host_gscb); preempt_enable(); + if (!vcpu->arch.host_gscb) + __ctl_clear_bit(2, 4); + vcpu->arch.host_gscb = NULL; } - /* SIE will load etoken directly from SDNX and therefore kvm_run */ - - kvm_run->kvm_dirty_regs = 0; + /* SIE will save etoken directly into SDNX and therefore kvm_run */ } static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -3967,13 +4318,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128); kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu); kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc; - kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr; - kvm_run->s.regs.pp = vcpu->arch.sie_block->pp; - kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea; kvm_run->s.regs.pft = vcpu->arch.pfault_token; kvm_run->s.regs.pfs = vcpu->arch.pfault_select; kvm_run->s.regs.pfc = vcpu->arch.pfault_compare; - kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); /* Save guest register state */ @@ -3982,19 +4329,8 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) /* Restore will be done lazily at return */ current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; - if (MACHINE_HAS_GS) { - __ctl_set_bit(2, 4); - if (vcpu->arch.gs_enabled) - save_gs_cb(current->thread.gs_cb); - preempt_disable(); - current->thread.gs_cb = vcpu->arch.host_gscb; - restore_gs_cb(vcpu->arch.host_gscb); - preempt_enable(); - if (!vcpu->arch.host_gscb) - __ctl_clear_bit(2, 4); - vcpu->arch.host_gscb = NULL; - } - /* SIE will save etoken directly into SDNX and therefore kvm_run */ + if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) + store_regs_fmt2(vcpu, kvm_run); } int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -4018,6 +4354,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_sigset_activate(vcpu); + /* + * no need to check the return value of vcpu_start as it can only have + * an error for protvirt, but protvirt means user cpu state + */ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) { kvm_s390_vcpu_start(vcpu); } else if (is_vcpu_stopped(vcpu)) { @@ -4155,18 +4495,27 @@ static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu) kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu); } -void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) +int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) { - int i, online_vcpus, started_vcpus = 0; + int i, online_vcpus, r = 0, started_vcpus = 0; if (!is_vcpu_stopped(vcpu)) - return; + return 0; trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1); /* Only one cpu at a time may enter/leave the STOPPED state. */ spin_lock(&vcpu->kvm->arch.start_stop_lock); online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + /* Let's tell the UV that we want to change into the operating state */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR); + if (r) { + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return r; + } + } + for (i = 0; i < online_vcpus; i++) { if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) started_vcpus++; @@ -4186,27 +4535,43 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED); /* + * The real PSW might have changed due to a RESTART interpreted by the + * ultravisor. We block all interrupts and let the next sie exit + * refresh our view. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK; + /* * Another VCPU might have used IBS while we were offline. * Let's play safe and flush the VCPU at startup. */ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); spin_unlock(&vcpu->kvm->arch.start_stop_lock); - return; + return 0; } -void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) +int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) { - int i, online_vcpus, started_vcpus = 0; + int i, online_vcpus, r = 0, started_vcpus = 0; struct kvm_vcpu *started_vcpu = NULL; if (is_vcpu_stopped(vcpu)) - return; + return 0; trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0); /* Only one cpu at a time may enter/leave the STOPPED state. */ spin_lock(&vcpu->kvm->arch.start_stop_lock); online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + /* Let's tell the UV that we want to change into the stopped state */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_STP); + if (r) { + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return r; + } + } + /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */ kvm_s390_clear_stop_irq(vcpu); @@ -4229,7 +4594,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) } spin_unlock(&vcpu->kvm->arch.start_stop_lock); - return; + return 0; } static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, @@ -4256,12 +4621,40 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + int r = 0; + + if (mop->flags || !mop->size) + return -EINVAL; + if (mop->size + mop->sida_offset < mop->size) + return -EINVAL; + if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block)) + return -E2BIG; + + switch (mop->op) { + case KVM_S390_MEMOP_SIDA_READ: + if (copy_to_user(uaddr, (void *)(sida_origin(vcpu->arch.sie_block) + + mop->sida_offset), mop->size)) + r = -EFAULT; + + break; + case KVM_S390_MEMOP_SIDA_WRITE: + if (copy_from_user((void *)(sida_origin(vcpu->arch.sie_block) + + mop->sida_offset), uaddr, mop->size)) + r = -EFAULT; + break; + } + return r; +} static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, struct kvm_s390_mem_op *mop) { void __user *uaddr = (void __user *)mop->buf; void *tmpbuf = NULL; - int r, srcu_idx; + int r = 0; const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION | KVM_S390_MEMOP_F_CHECK_ONLY; @@ -4271,14 +4664,15 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return -EINVAL; + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { tmpbuf = vmalloc(mop->size); if (!tmpbuf) return -ENOMEM; } - srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - switch (mop->op) { case KVM_S390_MEMOP_LOGICAL_READ: if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { @@ -4304,12 +4698,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, } r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); break; - default: - r = -EINVAL; } - srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); - if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); @@ -4317,6 +4707,31 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_memsida_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + int r, srcu_idx; + + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + switch (mop->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + case KVM_S390_MEMOP_LOGICAL_WRITE: + r = kvm_s390_guest_mem_op(vcpu, mop); + break; + case KVM_S390_MEMOP_SIDA_READ: + case KVM_S390_MEMOP_SIDA_WRITE: + /* we are locked against sida going away by the vcpu->mutex */ + r = kvm_s390_guest_sida_op(vcpu, mop); + break; + default: + r = -EINVAL; + } + + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + return r; +} + long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4352,6 +4767,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int idx; long r; + u16 rc, rrc; vcpu_load(vcpu); @@ -4373,18 +4789,40 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_S390_CLEAR_RESET: r = 0; kvm_arch_vcpu_ioctl_clear_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET_CLEAR, &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET CLEAR VCPU: rc %x rrc %x", + rc, rrc); + } break; case KVM_S390_INITIAL_RESET: r = 0; kvm_arch_vcpu_ioctl_initial_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET_INITIAL, + &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET INITIAL VCPU: rc %x rrc %x", + rc, rrc); + } break; case KVM_S390_NORMAL_RESET: r = 0; kvm_arch_vcpu_ioctl_normal_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET, &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET NORMAL VCPU: rc %x rrc %x", + rc, rrc); + } break; case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; + r = -EINVAL; + if (kvm_s390_pv_cpu_is_protected(vcpu)) + break; r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) break; @@ -4447,7 +4885,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_s390_mem_op mem_op; if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0) - r = kvm_s390_guest_mem_op(vcpu, &mem_op); + r = kvm_s390_guest_memsida_op(vcpu, &mem_op); else r = -EFAULT; break; @@ -4507,12 +4945,6 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} - /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -4533,12 +4965,15 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) return -EINVAL; + /* When we are protected, we should not change the memory slots */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -4554,7 +4989,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, old->npages * PAGE_SIZE); if (rc) break; - /* FALLTHROUGH */ + fallthrough; case KVM_MR_CREATE: rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, mem->guest_phys_addr, mem->memory_size); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 6d9448dbd052..79dcd647b378 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -2,7 +2,7 @@ /* * definition for kvm on s390 * - * Copyright IBM Corp. 2008, 2009 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -15,6 +15,7 @@ #include <linux/hrtimer.h> #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <linux/lockdep.h> #include <asm/facility.h> #include <asm/processor.h> #include <asm/sclp.h> @@ -25,6 +26,17 @@ #define IS_ITDB_VALID(vcpu) ((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1)) extern debug_info_t *kvm_s390_dbf; +extern debug_info_t *kvm_s390_dbf_uv; + +#define KVM_UV_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ +do { \ + debug_sprintf_event((d_kvm)->arch.dbf, d_loglevel, d_string "\n", \ + d_args); \ + debug_sprintf_event(kvm_s390_dbf_uv, d_loglevel, \ + "%d: " d_string "\n", (d_kvm)->userspace_pid, \ + d_args); \ +} while (0) + #define KVM_EVENT(d_loglevel, d_string, d_args...)\ do { \ debug_sprintf_event(kvm_s390_dbf, d_loglevel, d_string "\n", \ @@ -196,6 +208,39 @@ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) return kvm->arch.user_cpu_state_ctrl != 0; } +/* implemented in pv.c */ +int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); +int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); +int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, + u16 *rrc); +int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, + unsigned long tweak, u16 *rc, u16 *rrc); +int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state); + +static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm) +{ + return kvm->arch.pv.handle; +} + +static inline u64 kvm_s390_pv_cpu_get_handle(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pv.handle; +} + +static inline bool kvm_s390_pv_is_protected(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->lock); + return !!kvm_s390_pv_get_handle(kvm); +} + +static inline bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu) +{ + lockdep_assert_held(&vcpu->mutex); + return !!kvm_s390_pv_cpu_get_handle(vcpu); +} + /* implemented in interrupt.c */ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu); @@ -286,8 +331,8 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); -void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); -void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu); bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ed52ffa8d5d4..69a824f9ef0b 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -2,7 +2,7 @@ /* * handling privileged instructions * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -872,7 +872,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); - if (operand2 & 0xfff) + if (!kvm_s390_pv_cpu_is_protected(vcpu) && (operand2 & 0xfff)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); switch (fc) { @@ -893,8 +893,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu) handle_stsi_3_2_2(vcpu, (void *) mem); break; } - - rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy((void *)sida_origin(vcpu->arch.sie_block), (void *)mem, + PAGE_SIZE); + rc = 0; + } else { + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); + } if (rc) { rc = kvm_s390_inject_prog_cond(vcpu, rc); goto out; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c new file mode 100644 index 000000000000..63e330109b63 --- /dev/null +++ b/arch/s390/kvm/pv.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hosting Protected Virtual Machines + * + * Copyright IBM Corp. 2019, 2020 + * Author(s): Janosch Frank <frankja@linux.ibm.com> + */ +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pagemap.h> +#include <linux/sched/signal.h> +#include <asm/pgalloc.h> +#include <asm/gmap.h> +#include <asm/uv.h> +#include <asm/mman.h> +#include "kvm-s390.h" + +int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) +{ + int cc = 0; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) { + cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_DESTROY_SEC_CPU, rc, rrc); + + KVM_UV_EVENT(vcpu->kvm, 3, + "PROTVIRT DESTROY VCPU %d: rc %x rrc %x", + vcpu->vcpu_id, *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", + *rc, *rrc); + } + /* Intended memory leak for something that should never happen. */ + if (!cc) + free_pages(vcpu->arch.pv.stor_base, + get_order(uv_info.guest_cpu_stor_len)); + + free_page(sida_origin(vcpu->arch.sie_block)); + vcpu->arch.sie_block->pv_handle_cpu = 0; + vcpu->arch.sie_block->pv_handle_config = 0; + memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); + vcpu->arch.sie_block->sdf = 0; + /* + * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0). + * Use the reset value of gbea to avoid leaking the kernel pointer of + * the just freed sida. + */ + vcpu->arch.sie_block->gbea = 1; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + + return cc ? EIO : 0; +} + +int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) +{ + struct uv_cb_csc uvcb = { + .header.cmd = UVC_CMD_CREATE_SEC_CPU, + .header.len = sizeof(uvcb), + }; + int cc; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) + return -EINVAL; + + vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, + get_order(uv_info.guest_cpu_stor_len)); + if (!vcpu->arch.pv.stor_base) + return -ENOMEM; + + /* Input */ + uvcb.guest_handle = kvm_s390_pv_get_handle(vcpu->kvm); + uvcb.num = vcpu->arch.sie_block->icpua; + uvcb.state_origin = (u64)vcpu->arch.sie_block; + uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base; + + /* Alloc Secure Instruction Data Area Designation */ + vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!vcpu->arch.sie_block->sidad) { + free_pages(vcpu->arch.pv.stor_base, + get_order(uv_info.guest_cpu_stor_len)); + return -ENOMEM; + } + + cc = uv_call(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(vcpu->kvm, 3, + "PROTVIRT CREATE VCPU: cpu %d handle %llx rc %x rrc %x", + vcpu->vcpu_id, uvcb.cpu_handle, uvcb.header.rc, + uvcb.header.rrc); + + if (cc) { + u16 dummy; + + kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy); + return -EIO; + } + + /* Output */ + vcpu->arch.pv.handle = uvcb.cpu_handle; + vcpu->arch.sie_block->pv_handle_cpu = uvcb.cpu_handle; + vcpu->arch.sie_block->pv_handle_config = kvm_s390_pv_get_handle(vcpu->kvm); + vcpu->arch.sie_block->sdf = 2; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + return 0; +} + +/* only free resources when the destroy was successful */ +static void kvm_s390_pv_dealloc_vm(struct kvm *kvm) +{ + vfree(kvm->arch.pv.stor_var); + free_pages(kvm->arch.pv.stor_base, + get_order(uv_info.guest_base_stor_len)); + memset(&kvm->arch.pv, 0, sizeof(kvm->arch.pv)); +} + +static int kvm_s390_pv_alloc_vm(struct kvm *kvm) +{ + unsigned long base = uv_info.guest_base_stor_len; + unsigned long virt = uv_info.guest_virt_var_stor_len; + unsigned long npages = 0, vlen = 0; + struct kvm_memory_slot *memslot; + + kvm->arch.pv.stor_var = NULL; + kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, get_order(base)); + if (!kvm->arch.pv.stor_base) + return -ENOMEM; + + /* + * Calculate current guest storage for allocation of the + * variable storage, which is based on the length in MB. + * + * Slots are sorted by GFN + */ + mutex_lock(&kvm->slots_lock); + memslot = kvm_memslots(kvm)->memslots; + npages = memslot->base_gfn + memslot->npages; + mutex_unlock(&kvm->slots_lock); + + kvm->arch.pv.guest_len = npages * PAGE_SIZE; + + /* Allocate variable storage */ + vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); + vlen += uv_info.guest_virt_base_stor_len; + kvm->arch.pv.stor_var = vzalloc(vlen); + if (!kvm->arch.pv.stor_var) + goto out_err; + return 0; + +out_err: + kvm_s390_pv_dealloc_vm(kvm); + return -ENOMEM; +} + +/* this should not fail, but if it does, we must not free the donated memory */ +int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + int cc; + + /* make all pages accessible before destroying the guest */ + s390_reset_acc(kvm->mm); + + cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_DESTROY_SEC_CONF, rc, rrc); + WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); + atomic_set(&kvm->mm->context.is_protected, 0); + KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); + /* Inteded memory leak on "impossible" error */ + if (!cc) + kvm_s390_pv_dealloc_vm(kvm); + return cc ? -EIO : 0; +} + +int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + struct uv_cb_cgc uvcb = { + .header.cmd = UVC_CMD_CREATE_SEC_CONF, + .header.len = sizeof(uvcb) + }; + int cc, ret; + u16 dummy; + + ret = kvm_s390_pv_alloc_vm(kvm); + if (ret) + return ret; + + /* Inputs */ + uvcb.guest_stor_origin = 0; /* MSO is 0 for KVM */ + uvcb.guest_stor_len = kvm->arch.pv.guest_len; + uvcb.guest_asce = kvm->arch.gmap->asce; + uvcb.guest_sca = (unsigned long)kvm->arch.sca; + uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base; + uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var; + + cc = uv_call(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x", + uvcb.guest_handle, uvcb.guest_stor_len, *rc, *rrc); + + /* Outputs */ + kvm->arch.pv.handle = uvcb.guest_handle; + + if (cc) { + if (uvcb.header.rc & UVC_RC_NEED_DESTROY) + kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); + else + kvm_s390_pv_dealloc_vm(kvm); + return -EIO; + } + kvm->arch.gmap->guest_handle = uvcb.guest_handle; + atomic_set(&kvm->mm->context.is_protected, 1); + return 0; +} + +int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, + u16 *rrc) +{ + struct uv_cb_ssc uvcb = { + .header.cmd = UVC_CMD_SET_SEC_CONF_PARAMS, + .header.len = sizeof(uvcb), + .sec_header_origin = (u64)hdr, + .sec_header_len = length, + .guest_handle = kvm_s390_pv_get_handle(kvm), + }; + int cc = uv_call(0, (u64)&uvcb); + + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", + *rc, *rrc); + return cc ? -EINVAL : 0; +} + +static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, + u64 offset, u16 *rc, u16 *rrc) +{ + struct uv_cb_unp uvcb = { + .header.cmd = UVC_CMD_UNPACK_IMG, + .header.len = sizeof(uvcb), + .guest_handle = kvm_s390_pv_get_handle(kvm), + .gaddr = addr, + .tweak[0] = tweak, + .tweak[1] = offset, + }; + int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb); + + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + + if (ret && ret != -EAGAIN) + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", + uvcb.gaddr, *rc, *rrc); + return ret; +} + +int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, + unsigned long tweak, u16 *rc, u16 *rrc) +{ + u64 offset = 0; + int ret = 0; + + if (addr & ~PAGE_MASK || !size || size & ~PAGE_MASK) + return -EINVAL; + + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx", + addr, size); + + while (offset < size) { + ret = unpack_one(kvm, addr, tweak, offset, rc, rrc); + if (ret == -EAGAIN) { + cond_resched(); + if (fatal_signal_pending(current)) + break; + continue; + } + if (ret) + break; + addr += PAGE_SIZE; + offset += PAGE_SIZE; + } + if (!ret) + KVM_UV_EVENT(kvm, 3, "%s", "PROTVIRT VM UNPACK: successful"); + return ret; +} + +int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state) +{ + struct uv_cb_cpu_set_state uvcb = { + .header.cmd = UVC_CMD_CPU_SET_STATE, + .header.len = sizeof(uvcb), + .cpu_handle = kvm_s390_pv_cpu_get_handle(vcpu), + .state = state, + }; + int cc; + + cc = uv_call(0, (u64)&uvcb); + KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT SET CPU %d STATE %d rc %x rrc %x", + vcpu->vcpu_id, state, uvcb.header.rc, uvcb.header.rrc); + if (cc) + return -EINVAL; + return 0; +} diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 7b0bb475c166..09bf7f2121ac 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -38,6 +38,7 @@ #include <asm/irq.h> #include <asm/mmu_context.h> #include <asm/facility.h> +#include <asm/uv.h> #include "../kernel/entry.h" #define __FAIL_ADDR_MASK -4096L @@ -429,7 +430,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) address = trans_exc_code & __FAIL_ADDR_MASK; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + flags = FAULT_FLAG_DEFAULT; if (user_mode(regs)) flags |= FAULT_FLAG_USER; if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) @@ -480,8 +481,7 @@ retry: * the fault. */ fault = handle_mm_fault(vma, address, flags); - /* No reason to continue if interrupted by SIGKILL. */ - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { + if (fault_signal_pending(fault, regs)) { fault = VM_FAULT_SIGNAL; if (flags & FAULT_FLAG_RETRY_NOWAIT) goto out_up; @@ -514,10 +514,7 @@ retry: fault = VM_FAULT_PFAULT; goto out_up; } - /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk - * of starvation. */ - flags &= ~(FAULT_FLAG_ALLOW_RETRY | - FAULT_FLAG_RETRY_NOWAIT); + flags &= ~FAULT_FLAG_RETRY_NOWAIT; flags |= FAULT_FLAG_TRIED; down_read(&mm->mmap_sem); goto retry; @@ -816,3 +813,80 @@ out_extint: early_initcall(pfault_irq_init); #endif /* CONFIG_PFAULT */ + +#if IS_ENABLED(CONFIG_PGSTE) +void do_secure_storage_access(struct pt_regs *regs) +{ + unsigned long addr = regs->int_parm_long & __FAIL_ADDR_MASK; + struct vm_area_struct *vma; + struct mm_struct *mm; + struct page *page; + int rc; + + switch (get_fault_type(regs)) { + case USER_FAULT: + mm = current->mm; + down_read(&mm->mmap_sem); + vma = find_vma(mm, addr); + if (!vma) { + up_read(&mm->mmap_sem); + do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + break; + } + page = follow_page(vma, addr, FOLL_WRITE | FOLL_GET); + if (IS_ERR_OR_NULL(page)) { + up_read(&mm->mmap_sem); + break; + } + if (arch_make_page_accessible(page)) + send_sig(SIGSEGV, current, 0); + put_page(page); + up_read(&mm->mmap_sem); + break; + case KERNEL_FAULT: + page = phys_to_page(addr); + if (unlikely(!try_get_page(page))) + break; + rc = arch_make_page_accessible(page); + put_page(page); + if (rc) + BUG(); + break; + case VDSO_FAULT: + /* fallthrough */ + case GMAP_FAULT: + /* fallthrough */ + default: + do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + WARN_ON_ONCE(1); + } +} +NOKPROBE_SYMBOL(do_secure_storage_access); + +void do_non_secure_storage_access(struct pt_regs *regs) +{ + unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK; + struct gmap *gmap = (struct gmap *)S390_lowcore.gmap; + + if (get_fault_type(regs) != GMAP_FAULT) { + do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + WARN_ON_ONCE(1); + return; + } + + if (gmap_convert_to_secure(gmap, gaddr) == -EINVAL) + send_sig(SIGSEGV, current, 0); +} +NOKPROBE_SYMBOL(do_non_secure_storage_access); + +#else +void do_secure_storage_access(struct pt_regs *regs) +{ + default_trap_handler(regs); +} + +void do_non_secure_storage_access(struct pt_regs *regs) +{ + default_trap_handler(regs); +} +#endif diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index edcdca97e85e..2fbece47ef6f 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -804,7 +804,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, if (*table & _REGION_ENTRY_INVALID) return NULL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); - /* Fallthrough */ + fallthrough; case _ASCE_TYPE_REGION2: table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT; if (level == 3) @@ -812,7 +812,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, if (*table & _REGION_ENTRY_INVALID) return NULL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); - /* Fallthrough */ + fallthrough; case _ASCE_TYPE_REGION3: table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT; if (level == 2) @@ -820,7 +820,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, if (*table & _REGION_ENTRY_INVALID) return NULL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); - /* Fallthrough */ + fallthrough; case _ASCE_TYPE_SEGMENT: table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT; if (level == 1) @@ -2548,6 +2548,23 @@ int s390_enable_sie(void) } EXPORT_SYMBOL_GPL(s390_enable_sie); +int gmap_mark_unmergeable(void) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int ret; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, + MADV_UNMERGEABLE, &vma->vm_flags); + if (ret) + return ret; + } + mm->def_flags &= ~VM_MERGEABLE; + return 0; +} +EXPORT_SYMBOL_GPL(gmap_mark_unmergeable); + /* * Enable storage key handling from now on and initialize the storage * keys with the default key. @@ -2593,7 +2610,6 @@ static const struct mm_walk_ops enable_skey_walk_ops = { int s390_enable_skey(void) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; int rc = 0; down_write(&mm->mmap_sem); @@ -2601,16 +2617,11 @@ int s390_enable_skey(void) goto out_up; mm->context.uses_skeys = 1; - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (ksm_madvise(vma, vma->vm_start, vma->vm_end, - MADV_UNMERGEABLE, &vma->vm_flags)) { - mm->context.uses_skeys = 0; - rc = -ENOMEM; - goto out_up; - } + rc = gmap_mark_unmergeable(); + if (rc) { + mm->context.uses_skeys = 0; + goto out_up; } - mm->def_flags &= ~VM_MERGEABLE; - walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL); out_up: @@ -2640,3 +2651,38 @@ void s390_reset_cmma(struct mm_struct *mm) up_write(&mm->mmap_sem); } EXPORT_SYMBOL_GPL(s390_reset_cmma); + +/* + * make inaccessible pages accessible again + */ +static int __s390_reset_acc(pte_t *ptep, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t pte = READ_ONCE(*ptep); + + if (pte_present(pte)) + WARN_ON_ONCE(uv_convert_from_secure(pte_val(pte) & PAGE_MASK)); + return 0; +} + +static const struct mm_walk_ops reset_acc_walk_ops = { + .pte_entry = __s390_reset_acc, +}; + +#include <linux/sched/mm.h> +void s390_reset_acc(struct mm_struct *mm) +{ + /* + * we might be called during + * reset: we walk the pages and clear + * close of all kvm file descriptors: we walk the pages and clear + * exit of process on fd closure: vma already gone, do nothing + */ + if (!mmget_not_zero(mm)) + return; + down_read(&mm->mmap_sem); + walk_page_range(mm, 0, TASK_SIZE, &reset_acc_walk_ops, NULL); + up_read(&mm->mmap_sem); + mmput(mm); +} +EXPORT_SYMBOL_GPL(s390_reset_acc); 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/Kconfig b/arch/sh/Kconfig index 9ece111b0254..b4f0e37b83eb 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -87,11 +87,6 @@ config SUPERH64 select HAVE_EXIT_THREAD select KALLSYMS -config ARCH_DEFCONFIG - string - default "arch/sh/configs/shx3_defconfig" if SUPERH32 - default "arch/sh/configs/cayman_defconfig" if SUPERH64 - config GENERIC_BUG def_bool y depends on BUG && SUPERH32 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/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index e5beb625ab88..87db9a84b5ec 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -46,7 +46,6 @@ CONFIG_BLK_DEV_IDETAPE=m CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y 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/Kbuild b/arch/sh/include/asm/Kbuild index 51a54df22c11..7435182ef846 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -1,22 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h -generic-y += compat.h -generic-y += current.h -generic-y += delay.h -generic-y += div64.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h -generic-y += irq_regs.h -generic-y += irq_work.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h generic-y += parport.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += serial.h -generic-y += trace_clock.h -generic-y += xor.h 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/sh/include/mach-common/mach/highlander.h b/arch/sh/include/mach-common/mach/highlander.h index 66d3e40fd046..fb44c299d033 100644 --- a/arch/sh/include/mach-common/mach/highlander.h +++ b/arch/sh/include/mach-common/mach/highlander.h @@ -18,7 +18,7 @@ #define PA_IRLPRI4 (PA_BCR+0x000a) /* Interrupt Priorty 4 */ #define PA_RSTCTL (PA_BCR+0x000c) /* Reset Control */ #define PA_PCIBD (PA_BCR+0x000e) /* PCI Board detect control */ -#define PA_PCICD (PA_BCR+0x0010) /* PCI Conector detect control */ +#define PA_PCICD (PA_BCR+0x0010) /* PCI Connector detect control */ #define PA_EXTGIO (PA_BCR+0x0016) /* Extension GPIO Control */ #define PA_IVDRMON (PA_BCR+0x0018) /* iVDR Moniter control */ #define PA_IVDRCTL (PA_BCR+0x001a) /* iVDR control */ @@ -80,7 +80,7 @@ #define PA_SDPOW (PA_BCR+0x0004) /* SD Power control */ #define PA_RSTCTL (PA_BCR+0x0006) /* Device Reset control */ #define PA_PCIBD (PA_BCR+0x0008) /* PCI Board detect control */ -#define PA_PCICD (PA_BCR+0x000a) /* PCI Conector detect control */ +#define PA_PCICD (PA_BCR+0x000a) /* PCI Connector detect control */ #define PA_ZIGIO1 (PA_BCR+0x000c) /* Zigbee IO control 1 */ #define PA_ZIGIO2 (PA_BCR+0x000e) /* Zigbee IO control 2 */ #define PA_ZIGIO3 (PA_BCR+0x0010) /* Zigbee IO control 3 */ diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 5f51456f4fc7..13ee4d20e622 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -302,25 +302,25 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, * Pagefault was interrupted by SIGKILL. We have no reason to * continue pagefault. */ - if (fatal_signal_pending(current)) { - if (!(fault & VM_FAULT_RETRY)) - up_read(¤t->mm->mmap_sem); + if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) no_context(regs, error_code, address); return 1; } + /* Release mmap_sem first if necessary */ + if (!(fault & VM_FAULT_RETRY)) + up_read(¤t->mm->mmap_sem); + if (!(fault & VM_FAULT_ERROR)) return 0; if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { - up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address); return 1; } - up_read(¤t->mm->mmap_sem); /* * We ran out of memory, call the OOM killer, and return the @@ -380,7 +380,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, struct mm_struct *mm; struct vm_area_struct * vma; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; @@ -481,7 +481,6 @@ good_area: regs, address); } if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c1dd6dd642f4..da515fdad83d 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 @@ -95,11 +96,6 @@ config SPARC64 select PCI_DOMAINS if PCI select ARCH_HAS_GIGANTIC_PAGE -config ARCH_DEFCONFIG - string - default "arch/sparc/configs/sparc32_defconfig" if SPARC32 - default "arch/sparc/configs/sparc64_defconfig" if SPARC64 - config ARCH_PROC_KCORE_TEXT def_bool y diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index 6c325d53a20a..bde4d21a8ac8 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -73,7 +73,6 @@ CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 62de2eb2773d..5269a704801f 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -4,21 +4,7 @@ generated-y += syscall_table_32.h generated-y += syscall_table_64.h generated-y += syscall_table_c32.h -generic-y += div64.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += export.h -generic-y += irq_regs.h -generic-y += irq_work.h generic-y += kvm_para.h -generic-y += linkage.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += module.h -generic-y += preempt.h -generic-y += serial.h -generic-y += trace_clock.h -generic-y += word-at-a-time.h 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/include/asm/string.h b/arch/sparc/include/asm/string.h index 3d9cd082716b..001a17baf2d5 100644 --- a/arch/sparc/include/asm/string.h +++ b/arch/sparc/include/asm/string.h @@ -37,6 +37,10 @@ void *memmove(void *, const void *, __kernel_size_t); #define __HAVE_ARCH_MEMCMP int memcmp(const void *,const void *,__kernel_size_t); +/* Now the str*() stuff... */ +#define __HAVE_ARCH_STRLEN +__kernel_size_t strlen(const char *); + #define __HAVE_ARCH_STRNCMP int strncmp(const char *, const char *, __kernel_size_t); diff --git a/arch/sparc/include/asm/string_64.h b/arch/sparc/include/asm/string_64.h index ee9ba67321bd..d5c563058a5b 100644 --- a/arch/sparc/include/asm/string_64.h +++ b/arch/sparc/include/asm/string_64.h @@ -12,8 +12,4 @@ #include <asm/asi.h> -/* Now the str*() stuff... */ -#define __HAVE_ARCH_STRLEN -__kernel_size_t strlen(const char *); - #endif /* !(__SPARC64_STRING_H__) */ 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/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 89976c9b936c..f6e0e601f857 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -168,7 +168,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, int from_user = !(regs->psr & PSR_PS); int code; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; if (text_fault) address = regs->pc; @@ -237,7 +237,7 @@ good_area: */ fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -261,7 +261,6 @@ good_area: 1, regs, address); } if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 8b7ddbd14b65..c0c0dd471b6b 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -271,7 +271,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) int si_code, fault_code; vm_fault_t fault; unsigned long address, mm_rss; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; fault_code = get_thread_fault_code(); @@ -425,7 +425,7 @@ good_area: fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) goto exit_exception; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -449,7 +449,6 @@ good_area: 1, regs, address); } if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index b80a1d616e4e..30575bd92975 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -36,6 +36,8 @@ #include "mconsole_kern.h" #include <os.h> +static struct vfsmount *proc_mnt = NULL; + static int do_unlink_socket(struct notifier_block *notifier, unsigned long what, void *data) { @@ -123,7 +125,7 @@ void mconsole_log(struct mc_request *req) void mconsole_proc(struct mc_request *req) { - struct vfsmount *mnt = task_active_pid_ns(current)->proc_mnt; + struct vfsmount *mnt = proc_mnt; char *buf; int len; struct file *file; @@ -134,6 +136,10 @@ void mconsole_proc(struct mc_request *req) ptr += strlen("proc"); ptr = skip_spaces(ptr); + if (!mnt) { + mconsole_reply(req, "Proc not available", 1, 0); + goto out; + } file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); @@ -683,6 +689,24 @@ void mconsole_stack(struct mc_request *req) with_console(req, stack_proc, to); } +static int __init mount_proc(void) +{ + struct file_system_type *proc_fs_type; + struct vfsmount *mnt; + + proc_fs_type = get_fs_type("proc"); + if (!proc_fs_type) + return -ENODEV; + + mnt = kern_mount(proc_fs_type); + put_filesystem(proc_fs_type); + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + + proc_mnt = mnt; + return 0; +} + /* * Changed by mconsole_setup, which is __setup, and called before SMP is * active. @@ -696,6 +720,8 @@ static int __init mconsole_init(void) int err; char file[UNIX_PATH_MAX]; + mount_proc(); + if (umid_file_name("mconsole", file, sizeof(file))) return -1; snprintf(mconsole_socket_name, sizeof(file), "%s", file); diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 0ff86391f77d..e98304d0219e 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1508,6 +1508,7 @@ static int vector_set_coalesce(struct net_device *netdev, } static const struct ethtool_ops vector_net_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_TX_USECS, .get_drvinfo = vector_net_get_drvinfo, .get_link = ethtool_op_get_link, .get_ts_info = ethtool_op_get_ts_info, diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 818553064f04..8f18cf56b3dd 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -33,7 +33,7 @@ int handle_page_fault(unsigned long address, unsigned long ip, pmd_t *pmd; pte_t *pte; int err = -EFAULT; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; *code_out = SEGV_MAPERR; @@ -97,7 +97,6 @@ good_area: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 98aa125a8f06..55026e8240d8 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -1,41 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += atomic.h -generic-y += bugs.h -generic-y += compat.h -generic-y += current.h -generic-y += device.h -generic-y += div64.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += fb.h -generic-y += ftrace.h -generic-y += futex.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += local.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h -generic-y += module.h generic-y += parport.h -generic-y += percpu.h -generic-y += preempt.h -generic-y += sections.h -generic-y += serial.h -generic-y += shmparam.h generic-y += syscalls.h -generic-y += topology.h -generic-y += trace_clock.h -generic-y += unaligned.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h 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/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c index 76342de9cf8c..a9bd08fbe588 100644 --- a/arch/unicore32/mm/fault.c +++ b/arch/unicore32/mm/fault.c @@ -202,7 +202,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs) struct mm_struct *mm; int sig, code; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; @@ -250,7 +250,7 @@ retry: * signal first. We do not need to release the mmap_sem because * it would already be released in __lock_page_or_retry in * mm/filemap.c. */ - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return 0; if (!(fault & VM_FAULT_ERROR) && (flags & FAULT_FLAG_ALLOW_RETRY)) { @@ -259,9 +259,7 @@ retry: else tsk->min_flt++; if (fault & VM_FAULT_RETRY) { - /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk - * of starvation. */ - flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; goto retry; } } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index beea77046f9b..1edf788d301c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -30,7 +30,6 @@ config X86_64 select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE select SWIOTLB - select ARCH_HAS_SYSCALL_WRAPPER config FORCE_DYNAMIC_FTRACE def_bool y @@ -57,7 +56,6 @@ config X86 select ACPI_LEGACY_TABLES_LOOKUP if ACPI select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_32BIT_OFF_T if X86_32 - select ARCH_CLOCKSOURCE_DATA select ARCH_CLOCKSOURCE_INIT select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_DEBUG_VIRTUAL @@ -80,6 +78,7 @@ config X86 select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE + select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI @@ -128,6 +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 @@ -230,6 +230,7 @@ config X86 select VIRT_TO_BUS select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS + imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI config INSTRUCTION_DECODER def_bool y @@ -240,11 +241,6 @@ config OUTPUT_FORMAT default "elf32-i386" if X86_32 default "elf64-x86-64" if X86_64 -config ARCH_DEFCONFIG - string - default "arch/x86/configs/i386_defconfig" if X86_32 - default "arch/x86/configs/x86_64_defconfig" if X86_64 - config LOCKDEP_SUPPORT def_bool y @@ -1875,7 +1871,6 @@ 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 @@ -2418,7 +2413,7 @@ config CMDLINE config CMDLINE_OVERRIDE bool "Built-in command line overrides boot loader arguments" - depends on CMDLINE_BOOL + depends on CMDLINE_BOOL && CMDLINE != "" ---help--- Set this option to 'Y' to have the kernel ignore the boot loader command line, and use ONLY the built-in command line. 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..e17be90ab312 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -68,6 +68,7 @@ clean-files += cpustr.h KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables GCOV_PROFILE := n UBSAN_SANITIZE := n @@ -88,7 +89,7 @@ $(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/apm.c b/arch/x86/boot/apm.c index b72fc10fc1be..bda15f9673d5 100644 --- a/arch/x86/boot/apm.c +++ b/arch/x86/boot/apm.c @@ -60,7 +60,7 @@ int query_apm_bios(void) intcall(0x15, &ireg, &oreg); if ((oreg.eflags & X86_EFLAGS_CF) || oreg.bx != 0x504d) { - /* Failure with 32-bit connect, try to disconect and ignore */ + /* Failure with 32-bit connect, try to disconnect and ignore */ ireg.al = 0x04; intcall(0x15, &ireg, NULL); return -1; diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 26050ae0b27e..5f7c262bcc99 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -39,6 +39,7 @@ KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_CFLAGS += -Wno-pointer-sign KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n @@ -87,10 +88,7 @@ endif vmlinux-objs-$(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..4f7e6b84be07 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) @@ -484,7 +529,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movq $z_output_len, %r9 /* decompressed length, end of relocs */ + movl $z_output_len, %r9d /* decompressed length, end of relocs */ call extract_kernel /* returns kernel location in %rax */ popq %rsi @@ -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 /* @@ -647,7 +780,7 @@ SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) /* * Space for page tables (not in .bss so not zeroed) */ - .section ".pgtable","a",@nobits + .section ".pgtable","aw",@nobits .balign 4096 SYM_DATA_LOCAL(pgtable, .fill BOOT_PGT_SIZE, 1, 0) 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/compressed/misc.h b/arch/x86/boot/compressed/misc.h index c8181392f70d..726e264410ff 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -59,7 +59,7 @@ void __puthex(unsigned long value); static inline void debug_putstr(const char *s) { } -static inline void debug_puthex(const char *s) +static inline void debug_puthex(unsigned long value) { } #define debug_putaddr(x) /* */ 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/setup.ld b/arch/x86/boot/setup.ld index 3da1c37c6dd5..24c95522f231 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -52,7 +52,6 @@ SECTIONS _end = .; /DISCARD/ : { - *(.eh_frame) *(.note*) } 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/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 59ce9ed58430..ab8b30cb978e 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -125,7 +125,6 @@ CONFIG_IP6_NF_MANGLE=y CONFIG_NET_SCHED=y CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y -CONFIG_HAMRADIO=y CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_MAC80211_LEDS=y @@ -137,7 +136,6 @@ CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y @@ -171,7 +169,6 @@ CONFIG_FORCEDETH=y CONFIG_8139TOO=y # CONFIG_8139TOO_PIO is not set CONFIG_R8169=y -CONFIG_FDDI=y CONFIG_INPUT_POLLDEV=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 0b9654c7a05c..2d196cb49084 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -123,7 +123,6 @@ CONFIG_IP6_NF_MANGLE=y CONFIG_NET_SCHED=y CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y -CONFIG_HAMRADIO=y CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_MAC80211_LEDS=y @@ -135,7 +134,6 @@ CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y @@ -164,7 +162,6 @@ CONFIG_SKY2=y CONFIG_FORCEDETH=y CONFIG_8139TOO=y CONFIG_R8169=y -CONFIG_FDDI=y CONFIG_INPUT_POLLDEV=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y 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/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c index eec7d2d24239..8a17621f7d3a 100644 --- a/arch/x86/crypto/curve25519-x86_64.c +++ b/arch/x86/crypto/curve25519-x86_64.c @@ -1,8 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// SPDX-License-Identifier: GPL-2.0 OR MIT /* - * Copyright (c) 2017 Armando Faz <armfazh@ic.unicamp.br>. All Rights Reserved. - * Copyright (C) 2018-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. - * Copyright (C) 2018 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved. + * Copyright (C) 2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + * Copyright (c) 2016-2020 INRIA, CMU and Microsoft Corporation */ #include <crypto/curve25519.h> @@ -16,2337 +15,1378 @@ #include <asm/cpufeature.h> #include <asm/processor.h> -static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2); -static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_adx); - -enum { NUM_WORDS_ELTFP25519 = 4 }; -typedef __aligned(32) u64 eltfp25519_1w[NUM_WORDS_ELTFP25519]; -typedef __aligned(32) u64 eltfp25519_1w_buffer[2 * NUM_WORDS_ELTFP25519]; - -#define mul_eltfp25519_1w_adx(c, a, b) do { \ - mul_256x256_integer_adx(m.buffer, a, b); \ - red_eltfp25519_1w_adx(c, m.buffer); \ -} while (0) - -#define mul_eltfp25519_1w_bmi2(c, a, b) do { \ - mul_256x256_integer_bmi2(m.buffer, a, b); \ - red_eltfp25519_1w_bmi2(c, m.buffer); \ -} while (0) - -#define sqr_eltfp25519_1w_adx(a) do { \ - sqr_256x256_integer_adx(m.buffer, a); \ - red_eltfp25519_1w_adx(a, m.buffer); \ -} while (0) - -#define sqr_eltfp25519_1w_bmi2(a) do { \ - sqr_256x256_integer_bmi2(m.buffer, a); \ - red_eltfp25519_1w_bmi2(a, m.buffer); \ -} while (0) - -#define mul_eltfp25519_2w_adx(c, a, b) do { \ - mul2_256x256_integer_adx(m.buffer, a, b); \ - red_eltfp25519_2w_adx(c, m.buffer); \ -} while (0) - -#define mul_eltfp25519_2w_bmi2(c, a, b) do { \ - mul2_256x256_integer_bmi2(m.buffer, a, b); \ - red_eltfp25519_2w_bmi2(c, m.buffer); \ -} while (0) - -#define sqr_eltfp25519_2w_adx(a) do { \ - sqr2_256x256_integer_adx(m.buffer, a); \ - red_eltfp25519_2w_adx(a, m.buffer); \ -} while (0) - -#define sqr_eltfp25519_2w_bmi2(a) do { \ - sqr2_256x256_integer_bmi2(m.buffer, a); \ - red_eltfp25519_2w_bmi2(a, m.buffer); \ -} while (0) - -#define sqrn_eltfp25519_1w_adx(a, times) do { \ - int ____counter = (times); \ - while (____counter-- > 0) \ - sqr_eltfp25519_1w_adx(a); \ -} while (0) - -#define sqrn_eltfp25519_1w_bmi2(a, times) do { \ - int ____counter = (times); \ - while (____counter-- > 0) \ - sqr_eltfp25519_1w_bmi2(a); \ -} while (0) - -#define copy_eltfp25519_1w(C, A) do { \ - (C)[0] = (A)[0]; \ - (C)[1] = (A)[1]; \ - (C)[2] = (A)[2]; \ - (C)[3] = (A)[3]; \ -} while (0) - -#define setzero_eltfp25519_1w(C) do { \ - (C)[0] = 0; \ - (C)[1] = 0; \ - (C)[2] = 0; \ - (C)[3] = 0; \ -} while (0) - -__aligned(32) static const u64 table_ladder_8k[252 * NUM_WORDS_ELTFP25519] = { - /* 1 */ 0xfffffffffffffff3UL, 0xffffffffffffffffUL, - 0xffffffffffffffffUL, 0x5fffffffffffffffUL, - /* 2 */ 0x6b8220f416aafe96UL, 0x82ebeb2b4f566a34UL, - 0xd5a9a5b075a5950fUL, 0x5142b2cf4b2488f4UL, - /* 3 */ 0x6aaebc750069680cUL, 0x89cf7820a0f99c41UL, - 0x2a58d9183b56d0f4UL, 0x4b5aca80e36011a4UL, - /* 4 */ 0x329132348c29745dUL, 0xf4a2e616e1642fd7UL, - 0x1e45bb03ff67bc34UL, 0x306912d0f42a9b4aUL, - /* 5 */ 0xff886507e6af7154UL, 0x04f50e13dfeec82fUL, - 0xaa512fe82abab5ceUL, 0x174e251a68d5f222UL, - /* 6 */ 0xcf96700d82028898UL, 0x1743e3370a2c02c5UL, - 0x379eec98b4e86eaaUL, 0x0c59888a51e0482eUL, - /* 7 */ 0xfbcbf1d699b5d189UL, 0xacaef0d58e9fdc84UL, - 0xc1c20d06231f7614UL, 0x2938218da274f972UL, - /* 8 */ 0xf6af49beff1d7f18UL, 0xcc541c22387ac9c2UL, - 0x96fcc9ef4015c56bUL, 0x69c1627c690913a9UL, - /* 9 */ 0x7a86fd2f4733db0eUL, 0xfdb8c4f29e087de9UL, - 0x095e4b1a8ea2a229UL, 0x1ad7a7c829b37a79UL, - /* 10 */ 0x342d89cad17ea0c0UL, 0x67bedda6cced2051UL, - 0x19ca31bf2bb42f74UL, 0x3df7b4c84980acbbUL, - /* 11 */ 0xa8c6444dc80ad883UL, 0xb91e440366e3ab85UL, - 0xc215cda00164f6d8UL, 0x3d867c6ef247e668UL, - /* 12 */ 0xc7dd582bcc3e658cUL, 0xfd2c4748ee0e5528UL, - 0xa0fd9b95cc9f4f71UL, 0x7529d871b0675ddfUL, - /* 13 */ 0xb8f568b42d3cbd78UL, 0x1233011b91f3da82UL, - 0x2dce6ccd4a7c3b62UL, 0x75e7fc8e9e498603UL, - /* 14 */ 0x2f4f13f1fcd0b6ecUL, 0xf1a8ca1f29ff7a45UL, - 0xc249c1a72981e29bUL, 0x6ebe0dbb8c83b56aUL, - /* 15 */ 0x7114fa8d170bb222UL, 0x65a2dcd5bf93935fUL, - 0xbdc41f68b59c979aUL, 0x2f0eef79a2ce9289UL, - /* 16 */ 0x42ecbf0c083c37ceUL, 0x2930bc09ec496322UL, - 0xf294b0c19cfeac0dUL, 0x3780aa4bedfabb80UL, - /* 17 */ 0x56c17d3e7cead929UL, 0xe7cb4beb2e5722c5UL, - 0x0ce931732dbfe15aUL, 0x41b883c7621052f8UL, - /* 18 */ 0xdbf75ca0c3d25350UL, 0x2936be086eb1e351UL, - 0xc936e03cb4a9b212UL, 0x1d45bf82322225aaUL, - /* 19 */ 0xe81ab1036a024cc5UL, 0xe212201c304c9a72UL, - 0xc5d73fba6832b1fcUL, 0x20ffdb5a4d839581UL, - /* 20 */ 0xa283d367be5d0fadUL, 0x6c2b25ca8b164475UL, - 0x9d4935467caaf22eUL, 0x5166408eee85ff49UL, - /* 21 */ 0x3c67baa2fab4e361UL, 0xb3e433c67ef35cefUL, - 0x5259729241159b1cUL, 0x6a621892d5b0ab33UL, - /* 22 */ 0x20b74a387555cdcbUL, 0x532aa10e1208923fUL, - 0xeaa17b7762281dd1UL, 0x61ab3443f05c44bfUL, - /* 23 */ 0x257a6c422324def8UL, 0x131c6c1017e3cf7fUL, - 0x23758739f630a257UL, 0x295a407a01a78580UL, - /* 24 */ 0xf8c443246d5da8d9UL, 0x19d775450c52fa5dUL, - 0x2afcfc92731bf83dUL, 0x7d10c8e81b2b4700UL, - /* 25 */ 0xc8e0271f70baa20bUL, 0x993748867ca63957UL, - 0x5412efb3cb7ed4bbUL, 0x3196d36173e62975UL, - /* 26 */ 0xde5bcad141c7dffcUL, 0x47cc8cd2b395c848UL, - 0xa34cd942e11af3cbUL, 0x0256dbf2d04ecec2UL, - /* 27 */ 0x875ab7e94b0e667fUL, 0xcad4dd83c0850d10UL, - 0x47f12e8f4e72c79fUL, 0x5f1a87bb8c85b19bUL, - /* 28 */ 0x7ae9d0b6437f51b8UL, 0x12c7ce5518879065UL, - 0x2ade09fe5cf77aeeUL, 0x23a05a2f7d2c5627UL, - /* 29 */ 0x5908e128f17c169aUL, 0xf77498dd8ad0852dUL, - 0x74b4c4ceab102f64UL, 0x183abadd10139845UL, - /* 30 */ 0xb165ba8daa92aaacUL, 0xd5c5ef9599386705UL, - 0xbe2f8f0cf8fc40d1UL, 0x2701e635ee204514UL, - /* 31 */ 0x629fa80020156514UL, 0xf223868764a8c1ceUL, - 0x5b894fff0b3f060eUL, 0x60d9944cf708a3faUL, - /* 32 */ 0xaeea001a1c7a201fUL, 0xebf16a633ee2ce63UL, - 0x6f7709594c7a07e1UL, 0x79b958150d0208cbUL, - /* 33 */ 0x24b55e5301d410e7UL, 0xe3a34edff3fdc84dUL, - 0xd88768e4904032d8UL, 0x131384427b3aaeecUL, - /* 34 */ 0x8405e51286234f14UL, 0x14dc4739adb4c529UL, - 0xb8a2b5b250634ffdUL, 0x2fe2a94ad8a7ff93UL, - /* 35 */ 0xec5c57efe843faddUL, 0x2843ce40f0bb9918UL, - 0xa4b561d6cf3d6305UL, 0x743629bde8fb777eUL, - /* 36 */ 0x343edd46bbaf738fUL, 0xed981828b101a651UL, - 0xa401760b882c797aUL, 0x1fc223e28dc88730UL, - /* 37 */ 0x48604e91fc0fba0eUL, 0xb637f78f052c6fa4UL, - 0x91ccac3d09e9239cUL, 0x23f7eed4437a687cUL, - /* 38 */ 0x5173b1118d9bd800UL, 0x29d641b63189d4a7UL, - 0xfdbf177988bbc586UL, 0x2959894fcad81df5UL, - /* 39 */ 0xaebc8ef3b4bbc899UL, 0x4148995ab26992b9UL, - 0x24e20b0134f92cfbUL, 0x40d158894a05dee8UL, - /* 40 */ 0x46b00b1185af76f6UL, 0x26bac77873187a79UL, - 0x3dc0bf95ab8fff5fUL, 0x2a608bd8945524d7UL, - /* 41 */ 0x26449588bd446302UL, 0x7c4bc21c0388439cUL, - 0x8e98a4f383bd11b2UL, 0x26218d7bc9d876b9UL, - /* 42 */ 0xe3081542997c178aUL, 0x3c2d29a86fb6606fUL, - 0x5c217736fa279374UL, 0x7dde05734afeb1faUL, - /* 43 */ 0x3bf10e3906d42babUL, 0xe4f7803e1980649cUL, - 0xe6053bf89595bf7aUL, 0x394faf38da245530UL, - /* 44 */ 0x7a8efb58896928f4UL, 0xfbc778e9cc6a113cUL, - 0x72670ce330af596fUL, 0x48f222a81d3d6cf7UL, - /* 45 */ 0xf01fce410d72caa7UL, 0x5a20ecc7213b5595UL, - 0x7bc21165c1fa1483UL, 0x07f89ae31da8a741UL, - /* 46 */ 0x05d2c2b4c6830ff9UL, 0xd43e330fc6316293UL, - 0xa5a5590a96d3a904UL, 0x705edb91a65333b6UL, - /* 47 */ 0x048ee15e0bb9a5f7UL, 0x3240cfca9e0aaf5dUL, - 0x8f4b71ceedc4a40bUL, 0x621c0da3de544a6dUL, - /* 48 */ 0x92872836a08c4091UL, 0xce8375b010c91445UL, - 0x8a72eb524f276394UL, 0x2667fcfa7ec83635UL, - /* 49 */ 0x7f4c173345e8752aUL, 0x061b47feee7079a5UL, - 0x25dd9afa9f86ff34UL, 0x3780cef5425dc89cUL, - /* 50 */ 0x1a46035a513bb4e9UL, 0x3e1ef379ac575adaUL, - 0xc78c5f1c5fa24b50UL, 0x321a967634fd9f22UL, - /* 51 */ 0x946707b8826e27faUL, 0x3dca84d64c506fd0UL, - 0xc189218075e91436UL, 0x6d9284169b3b8484UL, - /* 52 */ 0x3a67e840383f2ddfUL, 0x33eec9a30c4f9b75UL, - 0x3ec7c86fa783ef47UL, 0x26ec449fbac9fbc4UL, - /* 53 */ 0x5c0f38cba09b9e7dUL, 0x81168cc762a3478cUL, - 0x3e23b0d306fc121cUL, 0x5a238aa0a5efdcddUL, - /* 54 */ 0x1ba26121c4ea43ffUL, 0x36f8c77f7c8832b5UL, - 0x88fbea0b0adcf99aUL, 0x5ca9938ec25bebf9UL, - /* 55 */ 0xd5436a5e51fccda0UL, 0x1dbc4797c2cd893bUL, - 0x19346a65d3224a08UL, 0x0f5034e49b9af466UL, - /* 56 */ 0xf23c3967a1e0b96eUL, 0xe58b08fa867a4d88UL, - 0xfb2fabc6a7341679UL, 0x2a75381eb6026946UL, - /* 57 */ 0xc80a3be4c19420acUL, 0x66b1f6c681f2b6dcUL, - 0x7cf7036761e93388UL, 0x25abbbd8a660a4c4UL, - /* 58 */ 0x91ea12ba14fd5198UL, 0x684950fc4a3cffa9UL, - 0xf826842130f5ad28UL, 0x3ea988f75301a441UL, - /* 59 */ 0xc978109a695f8c6fUL, 0x1746eb4a0530c3f3UL, - 0x444d6d77b4459995UL, 0x75952b8c054e5cc7UL, - /* 60 */ 0xa3703f7915f4d6aaUL, 0x66c346202f2647d8UL, - 0xd01469df811d644bUL, 0x77fea47d81a5d71fUL, - /* 61 */ 0xc5e9529ef57ca381UL, 0x6eeeb4b9ce2f881aUL, - 0xb6e91a28e8009bd6UL, 0x4b80be3e9afc3fecUL, - /* 62 */ 0x7e3773c526aed2c5UL, 0x1b4afcb453c9a49dUL, - 0xa920bdd7baffb24dUL, 0x7c54699f122d400eUL, - /* 63 */ 0xef46c8e14fa94bc8UL, 0xe0b074ce2952ed5eUL, - 0xbea450e1dbd885d5UL, 0x61b68649320f712cUL, - /* 64 */ 0x8a485f7309ccbdd1UL, 0xbd06320d7d4d1a2dUL, - 0x25232973322dbef4UL, 0x445dc4758c17f770UL, - /* 65 */ 0xdb0434177cc8933cUL, 0xed6fe82175ea059fUL, - 0x1efebefdc053db34UL, 0x4adbe867c65daf99UL, - /* 66 */ 0x3acd71a2a90609dfUL, 0xe5e991856dd04050UL, - 0x1ec69b688157c23cUL, 0x697427f6885cfe4dUL, - /* 67 */ 0xd7be7b9b65e1a851UL, 0xa03d28d522c536ddUL, - 0x28399d658fd2b645UL, 0x49e5b7e17c2641e1UL, - /* 68 */ 0x6f8c3a98700457a4UL, 0x5078f0a25ebb6778UL, - 0xd13c3ccbc382960fUL, 0x2e003258a7df84b1UL, - /* 69 */ 0x8ad1f39be6296a1cUL, 0xc1eeaa652a5fbfb2UL, - 0x33ee0673fd26f3cbUL, 0x59256173a69d2cccUL, - /* 70 */ 0x41ea07aa4e18fc41UL, 0xd9fc19527c87a51eUL, - 0xbdaacb805831ca6fUL, 0x445b652dc916694fUL, - /* 71 */ 0xce92a3a7f2172315UL, 0x1edc282de11b9964UL, - 0xa1823aafe04c314aUL, 0x790a2d94437cf586UL, - /* 72 */ 0x71c447fb93f6e009UL, 0x8922a56722845276UL, - 0xbf70903b204f5169UL, 0x2f7a89891ba319feUL, - /* 73 */ 0x02a08eb577e2140cUL, 0xed9a4ed4427bdcf4UL, - 0x5253ec44e4323cd1UL, 0x3e88363c14e9355bUL, - /* 74 */ 0xaa66c14277110b8cUL, 0x1ae0391610a23390UL, - 0x2030bd12c93fc2a2UL, 0x3ee141579555c7abUL, - /* 75 */ 0x9214de3a6d6e7d41UL, 0x3ccdd88607f17efeUL, - 0x674f1288f8e11217UL, 0x5682250f329f93d0UL, - /* 76 */ 0x6cf00b136d2e396eUL, 0x6e4cf86f1014debfUL, - 0x5930b1b5bfcc4e83UL, 0x047069b48aba16b6UL, - /* 77 */ 0x0d4ce4ab69b20793UL, 0xb24db91a97d0fb9eUL, - 0xcdfa50f54e00d01dUL, 0x221b1085368bddb5UL, - /* 78 */ 0xe7e59468b1e3d8d2UL, 0x53c56563bd122f93UL, - 0xeee8a903e0663f09UL, 0x61efa662cbbe3d42UL, - /* 79 */ 0x2cf8ddddde6eab2aUL, 0x9bf80ad51435f231UL, - 0x5deadacec9f04973UL, 0x29275b5d41d29b27UL, - /* 80 */ 0xcfde0f0895ebf14fUL, 0xb9aab96b054905a7UL, - 0xcae80dd9a1c420fdUL, 0x0a63bf2f1673bbc7UL, - /* 81 */ 0x092f6e11958fbc8cUL, 0x672a81e804822fadUL, - 0xcac8351560d52517UL, 0x6f3f7722c8f192f8UL, - /* 82 */ 0xf8ba90ccc2e894b7UL, 0x2c7557a438ff9f0dUL, - 0x894d1d855ae52359UL, 0x68e122157b743d69UL, - /* 83 */ 0xd87e5570cfb919f3UL, 0x3f2cdecd95798db9UL, - 0x2121154710c0a2ceUL, 0x3c66a115246dc5b2UL, - /* 84 */ 0xcbedc562294ecb72UL, 0xba7143c36a280b16UL, - 0x9610c2efd4078b67UL, 0x6144735d946a4b1eUL, - /* 85 */ 0x536f111ed75b3350UL, 0x0211db8c2041d81bUL, - 0xf93cb1000e10413cUL, 0x149dfd3c039e8876UL, - /* 86 */ 0xd479dde46b63155bUL, 0xb66e15e93c837976UL, - 0xdafde43b1f13e038UL, 0x5fafda1a2e4b0b35UL, - /* 87 */ 0x3600bbdf17197581UL, 0x3972050bbe3cd2c2UL, - 0x5938906dbdd5be86UL, 0x34fce5e43f9b860fUL, - /* 88 */ 0x75a8a4cd42d14d02UL, 0x828dabc53441df65UL, - 0x33dcabedd2e131d3UL, 0x3ebad76fb814d25fUL, - /* 89 */ 0xd4906f566f70e10fUL, 0x5d12f7aa51690f5aUL, - 0x45adb16e76cefcf2UL, 0x01f768aead232999UL, - /* 90 */ 0x2b6cc77b6248febdUL, 0x3cd30628ec3aaffdUL, - 0xce1c0b80d4ef486aUL, 0x4c3bff2ea6f66c23UL, - /* 91 */ 0x3f2ec4094aeaeb5fUL, 0x61b19b286e372ca7UL, - 0x5eefa966de2a701dUL, 0x23b20565de55e3efUL, - /* 92 */ 0xe301ca5279d58557UL, 0x07b2d4ce27c2874fUL, - 0xa532cd8a9dcf1d67UL, 0x2a52fee23f2bff56UL, - /* 93 */ 0x8624efb37cd8663dUL, 0xbbc7ac20ffbd7594UL, - 0x57b85e9c82d37445UL, 0x7b3052cb86a6ec66UL, - /* 94 */ 0x3482f0ad2525e91eUL, 0x2cb68043d28edca0UL, - 0xaf4f6d052e1b003aUL, 0x185f8c2529781b0aUL, - /* 95 */ 0xaa41de5bd80ce0d6UL, 0x9407b2416853e9d6UL, - 0x563ec36e357f4c3aUL, 0x4cc4b8dd0e297bceUL, - /* 96 */ 0xa2fc1a52ffb8730eUL, 0x1811f16e67058e37UL, - 0x10f9a366cddf4ee1UL, 0x72f4a0c4a0b9f099UL, - /* 97 */ 0x8c16c06f663f4ea7UL, 0x693b3af74e970fbaUL, - 0x2102e7f1d69ec345UL, 0x0ba53cbc968a8089UL, - /* 98 */ 0xca3d9dc7fea15537UL, 0x4c6824bb51536493UL, - 0xb9886314844006b1UL, 0x40d2a72ab454cc60UL, - /* 99 */ 0x5936a1b712570975UL, 0x91b9d648debda657UL, - 0x3344094bb64330eaUL, 0x006ba10d12ee51d0UL, - /* 100 */ 0x19228468f5de5d58UL, 0x0eb12f4c38cc05b0UL, - 0xa1039f9dd5601990UL, 0x4502d4ce4fff0e0bUL, - /* 101 */ 0xeb2054106837c189UL, 0xd0f6544c6dd3b93cUL, - 0x40727064c416d74fUL, 0x6e15c6114b502ef0UL, - /* 102 */ 0x4df2a398cfb1a76bUL, 0x11256c7419f2f6b1UL, - 0x4a497962066e6043UL, 0x705b3aab41355b44UL, - /* 103 */ 0x365ef536d797b1d8UL, 0x00076bd622ddf0dbUL, - 0x3bbf33b0e0575a88UL, 0x3777aa05c8e4ca4dUL, - /* 104 */ 0x392745c85578db5fUL, 0x6fda4149dbae5ae2UL, - 0xb1f0b00b8adc9867UL, 0x09963437d36f1da3UL, - /* 105 */ 0x7e824e90a5dc3853UL, 0xccb5f6641f135cbdUL, - 0x6736d86c87ce8fccUL, 0x625f3ce26604249fUL, - /* 106 */ 0xaf8ac8059502f63fUL, 0x0c05e70a2e351469UL, - 0x35292e9c764b6305UL, 0x1a394360c7e23ac3UL, - /* 107 */ 0xd5c6d53251183264UL, 0x62065abd43c2b74fUL, - 0xb5fbf5d03b973f9bUL, 0x13a3da3661206e5eUL, - /* 108 */ 0xc6bd5837725d94e5UL, 0x18e30912205016c5UL, - 0x2088ce1570033c68UL, 0x7fba1f495c837987UL, - /* 109 */ 0x5a8c7423f2f9079dUL, 0x1735157b34023fc5UL, - 0xe4f9b49ad2fab351UL, 0x6691ff72c878e33cUL, - /* 110 */ 0x122c2adedc5eff3eUL, 0xf8dd4bf1d8956cf4UL, - 0xeb86205d9e9e5bdaUL, 0x049b92b9d975c743UL, - /* 111 */ 0xa5379730b0f6c05aUL, 0x72a0ffacc6f3a553UL, - 0xb0032c34b20dcd6dUL, 0x470e9dbc88d5164aUL, - /* 112 */ 0xb19cf10ca237c047UL, 0xb65466711f6c81a2UL, - 0xb3321bd16dd80b43UL, 0x48c14f600c5fbe8eUL, - /* 113 */ 0x66451c264aa6c803UL, 0xb66e3904a4fa7da6UL, - 0xd45f19b0b3128395UL, 0x31602627c3c9bc10UL, - /* 114 */ 0x3120dc4832e4e10dUL, 0xeb20c46756c717f7UL, - 0x00f52e3f67280294UL, 0x566d4fc14730c509UL, - /* 115 */ 0x7e3a5d40fd837206UL, 0xc1e926dc7159547aUL, - 0x216730fba68d6095UL, 0x22e8c3843f69cea7UL, - /* 116 */ 0x33d074e8930e4b2bUL, 0xb6e4350e84d15816UL, - 0x5534c26ad6ba2365UL, 0x7773c12f89f1f3f3UL, - /* 117 */ 0x8cba404da57962aaUL, 0x5b9897a81999ce56UL, - 0x508e862f121692fcUL, 0x3a81907fa093c291UL, - /* 118 */ 0x0dded0ff4725a510UL, 0x10d8cc10673fc503UL, - 0x5b9d151c9f1f4e89UL, 0x32a5c1d5cb09a44cUL, - /* 119 */ 0x1e0aa442b90541fbUL, 0x5f85eb7cc1b485dbUL, - 0xbee595ce8a9df2e5UL, 0x25e496c722422236UL, - /* 120 */ 0x5edf3c46cd0fe5b9UL, 0x34e75a7ed2a43388UL, - 0xe488de11d761e352UL, 0x0e878a01a085545cUL, - /* 121 */ 0xba493c77e021bb04UL, 0x2b4d1843c7df899aUL, - 0x9ea37a487ae80d67UL, 0x67a9958011e41794UL, - /* 122 */ 0x4b58051a6697b065UL, 0x47e33f7d8d6ba6d4UL, - 0xbb4da8d483ca46c1UL, 0x68becaa181c2db0dUL, - /* 123 */ 0x8d8980e90b989aa5UL, 0xf95eb14a2c93c99bUL, - 0x51c6c7c4796e73a2UL, 0x6e228363b5efb569UL, - /* 124 */ 0xc6bbc0b02dd624c8UL, 0x777eb47dec8170eeUL, - 0x3cde15a004cfafa9UL, 0x1dc6bc087160bf9bUL, - /* 125 */ 0x2e07e043eec34002UL, 0x18e9fc677a68dc7fUL, - 0xd8da03188bd15b9aUL, 0x48fbc3bb00568253UL, - /* 126 */ 0x57547d4cfb654ce1UL, 0xd3565b82a058e2adUL, - 0xf63eaf0bbf154478UL, 0x47531ef114dfbb18UL, - /* 127 */ 0xe1ec630a4278c587UL, 0x5507d546ca8e83f3UL, - 0x85e135c63adc0c2bUL, 0x0aa7efa85682844eUL, - /* 128 */ 0x72691ba8b3e1f615UL, 0x32b4e9701fbe3ffaUL, - 0x97b6d92e39bb7868UL, 0x2cfe53dea02e39e8UL, - /* 129 */ 0x687392cd85cd52b0UL, 0x27ff66c910e29831UL, - 0x97134556a9832d06UL, 0x269bb0360a84f8a0UL, - /* 130 */ 0x706e55457643f85cUL, 0x3734a48c9b597d1bUL, - 0x7aee91e8c6efa472UL, 0x5cd6abc198a9d9e0UL, - /* 131 */ 0x0e04de06cb3ce41aUL, 0xd8c6eb893402e138UL, - 0x904659bb686e3772UL, 0x7215c371746ba8c8UL, - /* 132 */ 0xfd12a97eeae4a2d9UL, 0x9514b7516394f2c5UL, - 0x266fd5809208f294UL, 0x5c847085619a26b9UL, - /* 133 */ 0x52985410fed694eaUL, 0x3c905b934a2ed254UL, - 0x10bb47692d3be467UL, 0x063b3d2d69e5e9e1UL, - /* 134 */ 0x472726eedda57debUL, 0xefb6c4ae10f41891UL, - 0x2b1641917b307614UL, 0x117c554fc4f45b7cUL, - /* 135 */ 0xc07cf3118f9d8812UL, 0x01dbd82050017939UL, - 0xd7e803f4171b2827UL, 0x1015e87487d225eaUL, - /* 136 */ 0xc58de3fed23acc4dUL, 0x50db91c294a7be2dUL, - 0x0b94d43d1c9cf457UL, 0x6b1640fa6e37524aUL, - /* 137 */ 0x692f346c5fda0d09UL, 0x200b1c59fa4d3151UL, - 0xb8c46f760777a296UL, 0x4b38395f3ffdfbcfUL, - /* 138 */ 0x18d25e00be54d671UL, 0x60d50582bec8aba6UL, - 0x87ad8f263b78b982UL, 0x50fdf64e9cda0432UL, - /* 139 */ 0x90f567aac578dcf0UL, 0xef1e9b0ef2a3133bUL, - 0x0eebba9242d9de71UL, 0x15473c9bf03101c7UL, - /* 140 */ 0x7c77e8ae56b78095UL, 0xb678e7666e6f078eUL, - 0x2da0b9615348ba1fUL, 0x7cf931c1ff733f0bUL, - /* 141 */ 0x26b357f50a0a366cUL, 0xe9708cf42b87d732UL, - 0xc13aeea5f91cb2c0UL, 0x35d90c991143bb4cUL, - /* 142 */ 0x47c1c404a9a0d9dcUL, 0x659e58451972d251UL, - 0x3875a8c473b38c31UL, 0x1fbd9ed379561f24UL, - /* 143 */ 0x11fabc6fd41ec28dUL, 0x7ef8dfe3cd2a2dcaUL, - 0x72e73b5d8c404595UL, 0x6135fa4954b72f27UL, - /* 144 */ 0xccfc32a2de24b69cUL, 0x3f55698c1f095d88UL, - 0xbe3350ed5ac3f929UL, 0x5e9bf806ca477eebUL, - /* 145 */ 0xe9ce8fb63c309f68UL, 0x5376f63565e1f9f4UL, - 0xd1afcfb35a6393f1UL, 0x6632a1ede5623506UL, - /* 146 */ 0x0b7d6c390c2ded4cUL, 0x56cb3281df04cb1fUL, - 0x66305a1249ecc3c7UL, 0x5d588b60a38ca72aUL, - /* 147 */ 0xa6ecbf78e8e5f42dUL, 0x86eeb44b3c8a3eecUL, - 0xec219c48fbd21604UL, 0x1aaf1af517c36731UL, - /* 148 */ 0xc306a2836769bde7UL, 0x208280622b1e2adbUL, - 0x8027f51ffbff94a6UL, 0x76cfa1ce1124f26bUL, - /* 149 */ 0x18eb00562422abb6UL, 0xf377c4d58f8c29c3UL, - 0x4dbbc207f531561aUL, 0x0253b7f082128a27UL, - /* 150 */ 0x3d1f091cb62c17e0UL, 0x4860e1abd64628a9UL, - 0x52d17436309d4253UL, 0x356f97e13efae576UL, - /* 151 */ 0xd351e11aa150535bUL, 0x3e6b45bb1dd878ccUL, - 0x0c776128bed92c98UL, 0x1d34ae93032885b8UL, - /* 152 */ 0x4ba0488ca85ba4c3UL, 0x985348c33c9ce6ceUL, - 0x66124c6f97bda770UL, 0x0f81a0290654124aUL, - /* 153 */ 0x9ed09ca6569b86fdUL, 0x811009fd18af9a2dUL, - 0xff08d03f93d8c20aUL, 0x52a148199faef26bUL, - /* 154 */ 0x3e03f9dc2d8d1b73UL, 0x4205801873961a70UL, - 0xc0d987f041a35970UL, 0x07aa1f15a1c0d549UL, - /* 155 */ 0xdfd46ce08cd27224UL, 0x6d0a024f934e4239UL, - 0x808a7a6399897b59UL, 0x0a4556e9e13d95a2UL, - /* 156 */ 0xd21a991fe9c13045UL, 0x9b0e8548fe7751b8UL, - 0x5da643cb4bf30035UL, 0x77db28d63940f721UL, - /* 157 */ 0xfc5eeb614adc9011UL, 0x5229419ae8c411ebUL, - 0x9ec3e7787d1dcf74UL, 0x340d053e216e4cb5UL, - /* 158 */ 0xcac7af39b48df2b4UL, 0xc0faec2871a10a94UL, - 0x140a69245ca575edUL, 0x0cf1c37134273a4cUL, - /* 159 */ 0xc8ee306ac224b8a5UL, 0x57eaee7ccb4930b0UL, - 0xa1e806bdaacbe74fUL, 0x7d9a62742eeb657dUL, - /* 160 */ 0x9eb6b6ef546c4830UL, 0x885cca1fddb36e2eUL, - 0xe6b9f383ef0d7105UL, 0x58654fef9d2e0412UL, - /* 161 */ 0xa905c4ffbe0e8e26UL, 0x942de5df9b31816eUL, - 0x497d723f802e88e1UL, 0x30684dea602f408dUL, - /* 162 */ 0x21e5a278a3e6cb34UL, 0xaefb6e6f5b151dc4UL, - 0xb30b8e049d77ca15UL, 0x28c3c9cf53b98981UL, - /* 163 */ 0x287fb721556cdd2aUL, 0x0d317ca897022274UL, - 0x7468c7423a543258UL, 0x4a7f11464eb5642fUL, - /* 164 */ 0xa237a4774d193aa6UL, 0xd865986ea92129a1UL, - 0x24c515ecf87c1a88UL, 0x604003575f39f5ebUL, - /* 165 */ 0x47b9f189570a9b27UL, 0x2b98cede465e4b78UL, - 0x026df551dbb85c20UL, 0x74fcd91047e21901UL, - /* 166 */ 0x13e2a90a23c1bfa3UL, 0x0cb0074e478519f6UL, - 0x5ff1cbbe3af6cf44UL, 0x67fe5438be812dbeUL, - /* 167 */ 0xd13cf64fa40f05b0UL, 0x054dfb2f32283787UL, - 0x4173915b7f0d2aeaUL, 0x482f144f1f610d4eUL, - /* 168 */ 0xf6210201b47f8234UL, 0x5d0ae1929e70b990UL, - 0xdcd7f455b049567cUL, 0x7e93d0f1f0916f01UL, - /* 169 */ 0xdd79cbf18a7db4faUL, 0xbe8391bf6f74c62fUL, - 0x027145d14b8291bdUL, 0x585a73ea2cbf1705UL, - /* 170 */ 0x485ca03e928a0db2UL, 0x10fc01a5742857e7UL, - 0x2f482edbd6d551a7UL, 0x0f0433b5048fdb8aUL, - /* 171 */ 0x60da2e8dd7dc6247UL, 0x88b4c9d38cd4819aUL, - 0x13033ac001f66697UL, 0x273b24fe3b367d75UL, - /* 172 */ 0xc6e8f66a31b3b9d4UL, 0x281514a494df49d5UL, - 0xd1726fdfc8b23da7UL, 0x4b3ae7d103dee548UL, - /* 173 */ 0xc6256e19ce4b9d7eUL, 0xff5c5cf186e3c61cUL, - 0xacc63ca34b8ec145UL, 0x74621888fee66574UL, - /* 174 */ 0x956f409645290a1eUL, 0xef0bf8e3263a962eUL, - 0xed6a50eb5ec2647bUL, 0x0694283a9dca7502UL, - /* 175 */ 0x769b963643a2dcd1UL, 0x42b7c8ea09fc5353UL, - 0x4f002aee13397eabUL, 0x63005e2c19b7d63aUL, - /* 176 */ 0xca6736da63023beaUL, 0x966c7f6db12a99b7UL, - 0xace09390c537c5e1UL, 0x0b696063a1aa89eeUL, - /* 177 */ 0xebb03e97288c56e5UL, 0x432a9f9f938c8be8UL, - 0xa6a5a93d5b717f71UL, 0x1a5fb4c3e18f9d97UL, - /* 178 */ 0x1c94e7ad1c60cdceUL, 0xee202a43fc02c4a0UL, - 0x8dafe4d867c46a20UL, 0x0a10263c8ac27b58UL, - /* 179 */ 0xd0dea9dfe4432a4aUL, 0x856af87bbe9277c5UL, - 0xce8472acc212c71aUL, 0x6f151b6d9bbb1e91UL, - /* 180 */ 0x26776c527ceed56aUL, 0x7d211cb7fbf8faecUL, - 0x37ae66a6fd4609ccUL, 0x1f81b702d2770c42UL, - /* 181 */ 0x2fb0b057eac58392UL, 0xe1dd89fe29744e9dUL, - 0xc964f8eb17beb4f8UL, 0x29571073c9a2d41eUL, - /* 182 */ 0xa948a18981c0e254UL, 0x2df6369b65b22830UL, - 0xa33eb2d75fcfd3c6UL, 0x078cd6ec4199a01fUL, - /* 183 */ 0x4a584a41ad900d2fUL, 0x32142b78e2c74c52UL, - 0x68c4e8338431c978UL, 0x7f69ea9008689fc2UL, - /* 184 */ 0x52f2c81e46a38265UL, 0xfd78072d04a832fdUL, - 0x8cd7d5fa25359e94UL, 0x4de71b7454cc29d2UL, - /* 185 */ 0x42eb60ad1eda6ac9UL, 0x0aad37dfdbc09c3aUL, - 0x81004b71e33cc191UL, 0x44e6be345122803cUL, - /* 186 */ 0x03fe8388ba1920dbUL, 0xf5d57c32150db008UL, - 0x49c8c4281af60c29UL, 0x21edb518de701aeeUL, - /* 187 */ 0x7fb63e418f06dc99UL, 0xa4460d99c166d7b8UL, - 0x24dd5248ce520a83UL, 0x5ec3ad712b928358UL, - /* 188 */ 0x15022a5fbd17930fUL, 0xa4f64a77d82570e3UL, - 0x12bc8d6915783712UL, 0x498194c0fc620abbUL, - /* 189 */ 0x38a2d9d255686c82UL, 0x785c6bd9193e21f0UL, - 0xe4d5c81ab24a5484UL, 0x56307860b2e20989UL, - /* 190 */ 0x429d55f78b4d74c4UL, 0x22f1834643350131UL, - 0x1e60c24598c71fffUL, 0x59f2f014979983efUL, - /* 191 */ 0x46a47d56eb494a44UL, 0x3e22a854d636a18eUL, - 0xb346e15274491c3bUL, 0x2ceafd4e5390cde7UL, - /* 192 */ 0xba8a8538be0d6675UL, 0x4b9074bb50818e23UL, - 0xcbdab89085d304c3UL, 0x61a24fe0e56192c4UL, - /* 193 */ 0xcb7615e6db525bcbUL, 0xdd7d8c35a567e4caUL, - 0xe6b4153acafcdd69UL, 0x2d668e097f3c9766UL, - /* 194 */ 0xa57e7e265ce55ef0UL, 0x5d9f4e527cd4b967UL, - 0xfbc83606492fd1e5UL, 0x090d52beb7c3f7aeUL, - /* 195 */ 0x09b9515a1e7b4d7cUL, 0x1f266a2599da44c0UL, - 0xa1c49548e2c55504UL, 0x7ef04287126f15ccUL, - /* 196 */ 0xfed1659dbd30ef15UL, 0x8b4ab9eec4e0277bUL, - 0x884d6236a5df3291UL, 0x1fd96ea6bf5cf788UL, - /* 197 */ 0x42a161981f190d9aUL, 0x61d849507e6052c1UL, - 0x9fe113bf285a2cd5UL, 0x7c22d676dbad85d8UL, - /* 198 */ 0x82e770ed2bfbd27dUL, 0x4c05b2ece996f5a5UL, - 0xcd40a9c2b0900150UL, 0x5895319213d9bf64UL, - /* 199 */ 0xe7cc5d703fea2e08UL, 0xb50c491258e2188cUL, - 0xcce30baa48205bf0UL, 0x537c659ccfa32d62UL, - /* 200 */ 0x37b6623a98cfc088UL, 0xfe9bed1fa4d6aca4UL, - 0x04d29b8e56a8d1b0UL, 0x725f71c40b519575UL, - /* 201 */ 0x28c7f89cd0339ce6UL, 0x8367b14469ddc18bUL, - 0x883ada83a6a1652cUL, 0x585f1974034d6c17UL, - /* 202 */ 0x89cfb266f1b19188UL, 0xe63b4863e7c35217UL, - 0xd88c9da6b4c0526aUL, 0x3e035c9df0954635UL, - /* 203 */ 0xdd9d5412fb45de9dUL, 0xdd684532e4cff40dUL, - 0x4b5c999b151d671cUL, 0x2d8c2cc811e7f690UL, - /* 204 */ 0x7f54be1d90055d40UL, 0xa464c5df464aaf40UL, - 0x33979624f0e917beUL, 0x2c018dc527356b30UL, - /* 205 */ 0xa5415024e330b3d4UL, 0x73ff3d96691652d3UL, - 0x94ec42c4ef9b59f1UL, 0x0747201618d08e5aUL, - /* 206 */ 0x4d6ca48aca411c53UL, 0x66415f2fcfa66119UL, - 0x9c4dd40051e227ffUL, 0x59810bc09a02f7ebUL, - /* 207 */ 0x2a7eb171b3dc101dUL, 0x441c5ab99ffef68eUL, - 0x32025c9b93b359eaUL, 0x5e8ce0a71e9d112fUL, - /* 208 */ 0xbfcccb92429503fdUL, 0xd271ba752f095d55UL, - 0x345ead5e972d091eUL, 0x18c8df11a83103baUL, - /* 209 */ 0x90cd949a9aed0f4cUL, 0xc5d1f4cb6660e37eUL, - 0xb8cac52d56c52e0bUL, 0x6e42e400c5808e0dUL, - /* 210 */ 0xa3b46966eeaefd23UL, 0x0c4f1f0be39ecdcaUL, - 0x189dc8c9d683a51dUL, 0x51f27f054c09351bUL, - /* 211 */ 0x4c487ccd2a320682UL, 0x587ea95bb3df1c96UL, - 0xc8ccf79e555cb8e8UL, 0x547dc829a206d73dUL, - /* 212 */ 0xb822a6cd80c39b06UL, 0xe96d54732000d4c6UL, - 0x28535b6f91463b4dUL, 0x228f4660e2486e1dUL, - /* 213 */ 0x98799538de8d3abfUL, 0x8cd8330045ebca6eUL, - 0x79952a008221e738UL, 0x4322e1a7535cd2bbUL, - /* 214 */ 0xb114c11819d1801cUL, 0x2016e4d84f3f5ec7UL, - 0xdd0e2df409260f4cUL, 0x5ec362c0ae5f7266UL, - /* 215 */ 0xc0462b18b8b2b4eeUL, 0x7cc8d950274d1afbUL, - 0xf25f7105436b02d2UL, 0x43bbf8dcbff9ccd3UL, - /* 216 */ 0xb6ad1767a039e9dfUL, 0xb0714da8f69d3583UL, - 0x5e55fa18b42931f5UL, 0x4ed5558f33c60961UL, - /* 217 */ 0x1fe37901c647a5ddUL, 0x593ddf1f8081d357UL, - 0x0249a4fd813fd7a6UL, 0x69acca274e9caf61UL, - /* 218 */ 0x047ba3ea330721c9UL, 0x83423fc20e7e1ea0UL, - 0x1df4c0af01314a60UL, 0x09a62dab89289527UL, - /* 219 */ 0xa5b325a49cc6cb00UL, 0xe94b5dc654b56cb6UL, - 0x3be28779adc994a0UL, 0x4296e8f8ba3a4aadUL, - /* 220 */ 0x328689761e451eabUL, 0x2e4d598bff59594aUL, - 0x49b96853d7a7084aUL, 0x4980a319601420a8UL, - /* 221 */ 0x9565b9e12f552c42UL, 0x8a5318db7100fe96UL, - 0x05c90b4d43add0d7UL, 0x538b4cd66a5d4edaUL, - /* 222 */ 0xf4e94fc3e89f039fUL, 0x592c9af26f618045UL, - 0x08a36eb5fd4b9550UL, 0x25fffaf6c2ed1419UL, - /* 223 */ 0x34434459cc79d354UL, 0xeeecbfb4b1d5476bUL, - 0xddeb34a061615d99UL, 0x5129cecceb64b773UL, - /* 224 */ 0xee43215894993520UL, 0x772f9c7cf14c0b3bUL, - 0xd2e2fce306bedad5UL, 0x715f42b546f06a97UL, - /* 225 */ 0x434ecdceda5b5f1aUL, 0x0da17115a49741a9UL, - 0x680bd77c73edad2eUL, 0x487c02354edd9041UL, - /* 226 */ 0xb8efeff3a70ed9c4UL, 0x56a32aa3e857e302UL, - 0xdf3a68bd48a2a5a0UL, 0x07f650b73176c444UL, - /* 227 */ 0xe38b9b1626e0ccb1UL, 0x79e053c18b09fb36UL, - 0x56d90319c9f94964UL, 0x1ca941e7ac9ff5c4UL, - /* 228 */ 0x49c4df29162fa0bbUL, 0x8488cf3282b33305UL, - 0x95dfda14cabb437dUL, 0x3391f78264d5ad86UL, - /* 229 */ 0x729ae06ae2b5095dUL, 0xd58a58d73259a946UL, - 0xe9834262d13921edUL, 0x27fedafaa54bb592UL, - /* 230 */ 0xa99dc5b829ad48bbUL, 0x5f025742499ee260UL, - 0x802c8ecd5d7513fdUL, 0x78ceb3ef3f6dd938UL, - /* 231 */ 0xc342f44f8a135d94UL, 0x7b9edb44828cdda3UL, - 0x9436d11a0537cfe7UL, 0x5064b164ec1ab4c8UL, - /* 232 */ 0x7020eccfd37eb2fcUL, 0x1f31ea3ed90d25fcUL, - 0x1b930d7bdfa1bb34UL, 0x5344467a48113044UL, - /* 233 */ 0x70073170f25e6dfbUL, 0xe385dc1a50114cc8UL, - 0x2348698ac8fc4f00UL, 0x2a77a55284dd40d8UL, - /* 234 */ 0xfe06afe0c98c6ce4UL, 0xc235df96dddfd6e4UL, - 0x1428d01e33bf1ed3UL, 0x785768ec9300bdafUL, - /* 235 */ 0x9702e57a91deb63bUL, 0x61bdb8bfe5ce8b80UL, - 0x645b426f3d1d58acUL, 0x4804a82227a557bcUL, - /* 236 */ 0x8e57048ab44d2601UL, 0x68d6501a4b3a6935UL, - 0xc39c9ec3f9e1c293UL, 0x4172f257d4de63e2UL, - /* 237 */ 0xd368b450330c6401UL, 0x040d3017418f2391UL, - 0x2c34bb6090b7d90dUL, 0x16f649228fdfd51fUL, - /* 238 */ 0xbea6818e2b928ef5UL, 0xe28ccf91cdc11e72UL, - 0x594aaa68e77a36cdUL, 0x313034806c7ffd0fUL, - /* 239 */ 0x8a9d27ac2249bd65UL, 0x19a3b464018e9512UL, - 0xc26ccff352b37ec7UL, 0x056f68341d797b21UL, - /* 240 */ 0x5e79d6757efd2327UL, 0xfabdbcb6553afe15UL, - 0xd3e7222c6eaf5a60UL, 0x7046c76d4dae743bUL, - /* 241 */ 0x660be872b18d4a55UL, 0x19992518574e1496UL, - 0xc103053a302bdcbbUL, 0x3ed8e9800b218e8eUL, - /* 242 */ 0x7b0b9239fa75e03eUL, 0xefe9fb684633c083UL, - 0x98a35fbe391a7793UL, 0x6065510fe2d0fe34UL, - /* 243 */ 0x55cb668548abad0cUL, 0xb4584548da87e527UL, - 0x2c43ecea0107c1ddUL, 0x526028809372de35UL, - /* 244 */ 0x3415c56af9213b1fUL, 0x5bee1a4d017e98dbUL, - 0x13f6b105b5cf709bUL, 0x5ff20e3482b29ab6UL, - /* 245 */ 0x0aa29c75cc2e6c90UL, 0xfc7d73ca3a70e206UL, - 0x899fc38fc4b5c515UL, 0x250386b124ffc207UL, - /* 246 */ 0x54ea28d5ae3d2b56UL, 0x9913149dd6de60ceUL, - 0x16694fc58f06d6c1UL, 0x46b23975eb018fc7UL, - /* 247 */ 0x470a6a0fb4b7b4e2UL, 0x5d92475a8f7253deUL, - 0xabeee5b52fbd3adbUL, 0x7fa20801a0806968UL, - /* 248 */ 0x76f3faf19f7714d2UL, 0xb3e840c12f4660c3UL, - 0x0fb4cd8df212744eUL, 0x4b065a251d3a2dd2UL, - /* 249 */ 0x5cebde383d77cd4aUL, 0x6adf39df882c9cb1UL, - 0xa2dd242eb09af759UL, 0x3147c0e50e5f6422UL, - /* 250 */ 0x164ca5101d1350dbUL, 0xf8d13479c33fc962UL, - 0xe640ce4d13e5da08UL, 0x4bdee0c45061f8baUL, - /* 251 */ 0xd7c46dc1a4edb1c9UL, 0x5514d7b6437fd98aUL, - 0x58942f6bb2a1c00bUL, 0x2dffb2ab1d70710eUL, - /* 252 */ 0xccdfcf2fc18b6d68UL, 0xa8ebcba8b7806167UL, - 0x980697f95e2937e3UL, 0x02fbba1cd0126e8cUL -}; - -/* c is two 512-bit products: c0[0:7]=a0[0:3]*b0[0:3] and c1[8:15]=a1[4:7]*b1[4:7] - * a is two 256-bit integers: a0[0:3] and a1[4:7] - * b is two 256-bit integers: b0[0:3] and b1[4:7] - */ -static void mul2_256x256_integer_adx(u64 *const c, const u64 *const a, - const u64 *const b) -{ - asm volatile( - "xorl %%r14d, %%r14d ;" - "movq (%1), %%rdx; " /* A[0] */ - "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ - "xorl %%r10d, %%r10d ;" - "movq %%r8, (%0) ;" - "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ - "adox %%r10, %%r15 ;" - "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ - "adox %%r8, %%rax ;" - "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ - "adox %%r10, %%rbx ;" - /******************************************/ - "adox %%r14, %%rcx ;" - - "movq 8(%1), %%rdx; " /* A[1] */ - "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ - "adox %%r15, %%r8 ;" - "movq %%r8, 8(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ - "adox %%r10, %%r9 ;" - "adcx %%r9, %%rax ;" - "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ - "adox %%r8, %%r11 ;" - "adcx %%r11, %%rbx ;" - "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ - "adox %%r10, %%r13 ;" - "adcx %%r13, %%rcx ;" - /******************************************/ - "adox %%r14, %%r15 ;" - "adcx %%r14, %%r15 ;" - - "movq 16(%1), %%rdx; " /* A[2] */ - "xorl %%r10d, %%r10d ;" - "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ - "adox %%rax, %%r8 ;" - "movq %%r8, 16(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ - "adox %%r10, %%r9 ;" - "adcx %%r9, %%rbx ;" - "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ - "adox %%r8, %%r11 ;" - "adcx %%r11, %%rcx ;" - "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ - "adox %%r10, %%r13 ;" - "adcx %%r13, %%r15 ;" - /******************************************/ - "adox %%r14, %%rax ;" - "adcx %%r14, %%rax ;" - - "movq 24(%1), %%rdx; " /* A[3] */ - "xorl %%r10d, %%r10d ;" - "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ - "adox %%rbx, %%r8 ;" - "movq %%r8, 24(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ - "adox %%r10, %%r9 ;" - "adcx %%r9, %%rcx ;" - "movq %%rcx, 32(%0) ;" - "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ - "adox %%r8, %%r11 ;" - "adcx %%r11, %%r15 ;" - "movq %%r15, 40(%0) ;" - "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ - "adox %%r10, %%r13 ;" - "adcx %%r13, %%rax ;" - "movq %%rax, 48(%0) ;" - /******************************************/ - "adox %%r14, %%rbx ;" - "adcx %%r14, %%rbx ;" - "movq %%rbx, 56(%0) ;" - - "movq 32(%1), %%rdx; " /* C[0] */ - "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ - "xorl %%r10d, %%r10d ;" - "movq %%r8, 64(%0);" - "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ - "adox %%r10, %%r15 ;" - "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ - "adox %%r8, %%rax ;" - "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ - "adox %%r10, %%rbx ;" - /******************************************/ - "adox %%r14, %%rcx ;" - - "movq 40(%1), %%rdx; " /* C[1] */ - "xorl %%r10d, %%r10d ;" - "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ - "adox %%r15, %%r8 ;" - "movq %%r8, 72(%0);" - "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ - "adox %%r10, %%r9 ;" - "adcx %%r9, %%rax ;" - "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ - "adox %%r8, %%r11 ;" - "adcx %%r11, %%rbx ;" - "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ - "adox %%r10, %%r13 ;" - "adcx %%r13, %%rcx ;" - /******************************************/ - "adox %%r14, %%r15 ;" - "adcx %%r14, %%r15 ;" - - "movq 48(%1), %%rdx; " /* C[2] */ - "xorl %%r10d, %%r10d ;" - "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ - "adox %%rax, %%r8 ;" - "movq %%r8, 80(%0);" - "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ - "adox %%r10, %%r9 ;" - "adcx %%r9, %%rbx ;" - "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ - "adox %%r8, %%r11 ;" - "adcx %%r11, %%rcx ;" - "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ - "adox %%r10, %%r13 ;" - "adcx %%r13, %%r15 ;" - /******************************************/ - "adox %%r14, %%rax ;" - "adcx %%r14, %%rax ;" - - "movq 56(%1), %%rdx; " /* C[3] */ - "xorl %%r10d, %%r10d ;" - "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ - "adox %%rbx, %%r8 ;" - "movq %%r8, 88(%0);" - "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ - "adox %%r10, %%r9 ;" - "adcx %%r9, %%rcx ;" - "movq %%rcx, 96(%0) ;" - "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ - "adox %%r8, %%r11 ;" - "adcx %%r11, %%r15 ;" - "movq %%r15, 104(%0) ;" - "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ - "adox %%r10, %%r13 ;" - "adcx %%r13, %%rax ;" - "movq %%rax, 112(%0) ;" - /******************************************/ - "adox %%r14, %%rbx ;" - "adcx %%r14, %%rbx ;" - "movq %%rbx, 120(%0) ;" - : - : "r"(c), "r"(a), "r"(b) - : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", - "%r10", "%r11", "%r13", "%r14", "%r15"); -} - -static void mul2_256x256_integer_bmi2(u64 *const c, const u64 *const a, - const u64 *const b) +static __always_inline u64 eq_mask(u64 a, u64 b) { - asm volatile( - "movq (%1), %%rdx; " /* A[0] */ - "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ - "movq %%r8, (%0) ;" - "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ - "addq %%r10, %%r15 ;" - "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ - "adcq %%r8, %%rax ;" - "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ - "adcq %%r10, %%rbx ;" - /******************************************/ - "adcq $0, %%rcx ;" - - "movq 8(%1), %%rdx; " /* A[1] */ - "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ - "addq %%r15, %%r8 ;" - "movq %%r8, 8(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ - "adcq %%r10, %%r9 ;" - "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ - "adcq %%r8, %%r11 ;" - "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%r15 ;" - - "addq %%r9, %%rax ;" - "adcq %%r11, %%rbx ;" - "adcq %%r13, %%rcx ;" - "adcq $0, %%r15 ;" - - "movq 16(%1), %%rdx; " /* A[2] */ - "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ - "addq %%rax, %%r8 ;" - "movq %%r8, 16(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ - "adcq %%r10, %%r9 ;" - "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ - "adcq %%r8, %%r11 ;" - "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%rax ;" - - "addq %%r9, %%rbx ;" - "adcq %%r11, %%rcx ;" - "adcq %%r13, %%r15 ;" - "adcq $0, %%rax ;" - - "movq 24(%1), %%rdx; " /* A[3] */ - "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ - "addq %%rbx, %%r8 ;" - "movq %%r8, 24(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ - "adcq %%r10, %%r9 ;" - "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ - "adcq %%r8, %%r11 ;" - "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%rbx ;" - - "addq %%r9, %%rcx ;" - "movq %%rcx, 32(%0) ;" - "adcq %%r11, %%r15 ;" - "movq %%r15, 40(%0) ;" - "adcq %%r13, %%rax ;" - "movq %%rax, 48(%0) ;" - "adcq $0, %%rbx ;" - "movq %%rbx, 56(%0) ;" - - "movq 32(%1), %%rdx; " /* C[0] */ - "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ - "movq %%r8, 64(%0) ;" - "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ - "addq %%r10, %%r15 ;" - "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ - "adcq %%r8, %%rax ;" - "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ - "adcq %%r10, %%rbx ;" - /******************************************/ - "adcq $0, %%rcx ;" - - "movq 40(%1), %%rdx; " /* C[1] */ - "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ - "addq %%r15, %%r8 ;" - "movq %%r8, 72(%0) ;" - "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ - "adcq %%r10, %%r9 ;" - "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ - "adcq %%r8, %%r11 ;" - "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%r15 ;" - - "addq %%r9, %%rax ;" - "adcq %%r11, %%rbx ;" - "adcq %%r13, %%rcx ;" - "adcq $0, %%r15 ;" - - "movq 48(%1), %%rdx; " /* C[2] */ - "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ - "addq %%rax, %%r8 ;" - "movq %%r8, 80(%0) ;" - "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ - "adcq %%r10, %%r9 ;" - "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ - "adcq %%r8, %%r11 ;" - "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%rax ;" - - "addq %%r9, %%rbx ;" - "adcq %%r11, %%rcx ;" - "adcq %%r13, %%r15 ;" - "adcq $0, %%rax ;" - - "movq 56(%1), %%rdx; " /* C[3] */ - "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ - "addq %%rbx, %%r8 ;" - "movq %%r8, 88(%0) ;" - "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ - "adcq %%r10, %%r9 ;" - "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ - "adcq %%r8, %%r11 ;" - "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%rbx ;" - - "addq %%r9, %%rcx ;" - "movq %%rcx, 96(%0) ;" - "adcq %%r11, %%r15 ;" - "movq %%r15, 104(%0) ;" - "adcq %%r13, %%rax ;" - "movq %%rax, 112(%0) ;" - "adcq $0, %%rbx ;" - "movq %%rbx, 120(%0) ;" - : - : "r"(c), "r"(a), "r"(b) - : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", - "%r10", "%r11", "%r13", "%r15"); + u64 x = a ^ b; + u64 minus_x = ~x + (u64)1U; + u64 x_or_minus_x = x | minus_x; + u64 xnx = x_or_minus_x >> (u32)63U; + return xnx - (u64)1U; } -static void sqr2_256x256_integer_adx(u64 *const c, const u64 *const a) +static __always_inline u64 gte_mask(u64 a, u64 b) { - asm volatile( - "movq (%1), %%rdx ;" /* A[0] */ - "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ - "xorl %%r15d, %%r15d;" - "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ - "adcx %%r14, %%r9 ;" - "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ - "adcx %%rax, %%r10 ;" - "movq 24(%1), %%rdx ;" /* A[3] */ - "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ - "adcx %%rcx, %%r11 ;" - "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ - "adcx %%rax, %%rbx ;" - "movq 8(%1), %%rdx ;" /* A[1] */ - "adcx %%r15, %%r13 ;" - "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ - "movq $0, %%r14 ;" - /******************************************/ - "adcx %%r15, %%r14 ;" - - "xorl %%r15d, %%r15d;" - "adox %%rax, %%r10 ;" - "adcx %%r8, %%r8 ;" - "adox %%rcx, %%r11 ;" - "adcx %%r9, %%r9 ;" - "adox %%r15, %%rbx ;" - "adcx %%r10, %%r10 ;" - "adox %%r15, %%r13 ;" - "adcx %%r11, %%r11 ;" - "adox %%r15, %%r14 ;" - "adcx %%rbx, %%rbx ;" - "adcx %%r13, %%r13 ;" - "adcx %%r14, %%r14 ;" - - "movq (%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ - /*******************/ - "movq %%rax, 0(%0) ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 8(%0) ;" - "movq 8(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ - "adcq %%rax, %%r9 ;" - "movq %%r9, 16(%0) ;" - "adcq %%rcx, %%r10 ;" - "movq %%r10, 24(%0) ;" - "movq 16(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ - "adcq %%rax, %%r11 ;" - "movq %%r11, 32(%0) ;" - "adcq %%rcx, %%rbx ;" - "movq %%rbx, 40(%0) ;" - "movq 24(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ - "adcq %%rax, %%r13 ;" - "movq %%r13, 48(%0) ;" - "adcq %%rcx, %%r14 ;" - "movq %%r14, 56(%0) ;" - - - "movq 32(%1), %%rdx ;" /* B[0] */ - "mulx 40(%1), %%r8, %%r14 ;" /* B[1]*B[0] */ - "xorl %%r15d, %%r15d;" - "mulx 48(%1), %%r9, %%r10 ;" /* B[2]*B[0] */ - "adcx %%r14, %%r9 ;" - "mulx 56(%1), %%rax, %%rcx ;" /* B[3]*B[0] */ - "adcx %%rax, %%r10 ;" - "movq 56(%1), %%rdx ;" /* B[3] */ - "mulx 40(%1), %%r11, %%rbx ;" /* B[1]*B[3] */ - "adcx %%rcx, %%r11 ;" - "mulx 48(%1), %%rax, %%r13 ;" /* B[2]*B[3] */ - "adcx %%rax, %%rbx ;" - "movq 40(%1), %%rdx ;" /* B[1] */ - "adcx %%r15, %%r13 ;" - "mulx 48(%1), %%rax, %%rcx ;" /* B[2]*B[1] */ - "movq $0, %%r14 ;" - /******************************************/ - "adcx %%r15, %%r14 ;" - - "xorl %%r15d, %%r15d;" - "adox %%rax, %%r10 ;" - "adcx %%r8, %%r8 ;" - "adox %%rcx, %%r11 ;" - "adcx %%r9, %%r9 ;" - "adox %%r15, %%rbx ;" - "adcx %%r10, %%r10 ;" - "adox %%r15, %%r13 ;" - "adcx %%r11, %%r11 ;" - "adox %%r15, %%r14 ;" - "adcx %%rbx, %%rbx ;" - "adcx %%r13, %%r13 ;" - "adcx %%r14, %%r14 ;" - - "movq 32(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* B[0]^2 */ - /*******************/ - "movq %%rax, 64(%0) ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 72(%0) ;" - "movq 40(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* B[1]^2 */ - "adcq %%rax, %%r9 ;" - "movq %%r9, 80(%0) ;" - "adcq %%rcx, %%r10 ;" - "movq %%r10, 88(%0) ;" - "movq 48(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* B[2]^2 */ - "adcq %%rax, %%r11 ;" - "movq %%r11, 96(%0) ;" - "adcq %%rcx, %%rbx ;" - "movq %%rbx, 104(%0) ;" - "movq 56(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* B[3]^2 */ - "adcq %%rax, %%r13 ;" - "movq %%r13, 112(%0) ;" - "adcq %%rcx, %%r14 ;" - "movq %%r14, 120(%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", - "%r10", "%r11", "%r13", "%r14", "%r15"); + u64 x = a; + u64 y = b; + u64 x_xor_y = x ^ y; + u64 x_sub_y = x - y; + u64 x_sub_y_xor_y = x_sub_y ^ y; + u64 q = x_xor_y | x_sub_y_xor_y; + u64 x_xor_q = x ^ q; + u64 x_xor_q_ = x_xor_q >> (u32)63U; + return x_xor_q_ - (u64)1U; } -static void sqr2_256x256_integer_bmi2(u64 *const c, const u64 *const a) +/* Computes the addition of four-element f1 with value in f2 + * and returns the carry (if any) */ +static inline u64 add_scalar(u64 *out, const u64 *f1, u64 f2) { - asm volatile( - "movq 8(%1), %%rdx ;" /* A[1] */ - "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ - "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ - "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ - - "movq 16(%1), %%rdx ;" /* A[2] */ - "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ - "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ - - "addq %%rax, %%r9 ;" - "adcq %%rdx, %%r10 ;" - "adcq %%rcx, %%r11 ;" - "adcq %%r14, %%r15 ;" - "adcq $0, %%r13 ;" - "movq $0, %%r14 ;" - "adcq $0, %%r14 ;" - - "movq (%1), %%rdx ;" /* A[0] */ - "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ - - "addq %%rax, %%r10 ;" - "adcq %%rcx, %%r11 ;" - "adcq $0, %%r15 ;" - "adcq $0, %%r13 ;" - "adcq $0, %%r14 ;" - - "shldq $1, %%r13, %%r14 ;" - "shldq $1, %%r15, %%r13 ;" - "shldq $1, %%r11, %%r15 ;" - "shldq $1, %%r10, %%r11 ;" - "shldq $1, %%r9, %%r10 ;" - "shldq $1, %%r8, %%r9 ;" - "shlq $1, %%r8 ;" - - /*******************/ - "mulx %%rdx, %%rax, %%rcx ; " /* A[0]^2 */ - /*******************/ - "movq %%rax, 0(%0) ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 8(%0) ;" - "movq 8(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ; " /* A[1]^2 */ - "adcq %%rax, %%r9 ;" - "movq %%r9, 16(%0) ;" - "adcq %%rcx, %%r10 ;" - "movq %%r10, 24(%0) ;" - "movq 16(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ; " /* A[2]^2 */ - "adcq %%rax, %%r11 ;" - "movq %%r11, 32(%0) ;" - "adcq %%rcx, %%r15 ;" - "movq %%r15, 40(%0) ;" - "movq 24(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ; " /* A[3]^2 */ - "adcq %%rax, %%r13 ;" - "movq %%r13, 48(%0) ;" - "adcq %%rcx, %%r14 ;" - "movq %%r14, 56(%0) ;" - - "movq 40(%1), %%rdx ;" /* B[1] */ - "mulx 32(%1), %%r8, %%r9 ;" /* B[0]*B[1] */ - "mulx 48(%1), %%r10, %%r11 ;" /* B[2]*B[1] */ - "mulx 56(%1), %%rcx, %%r14 ;" /* B[3]*B[1] */ - - "movq 48(%1), %%rdx ;" /* B[2] */ - "mulx 56(%1), %%r15, %%r13 ;" /* B[3]*B[2] */ - "mulx 32(%1), %%rax, %%rdx ;" /* B[0]*B[2] */ - - "addq %%rax, %%r9 ;" - "adcq %%rdx, %%r10 ;" - "adcq %%rcx, %%r11 ;" - "adcq %%r14, %%r15 ;" - "adcq $0, %%r13 ;" - "movq $0, %%r14 ;" - "adcq $0, %%r14 ;" - - "movq 32(%1), %%rdx ;" /* B[0] */ - "mulx 56(%1), %%rax, %%rcx ;" /* B[0]*B[3] */ - - "addq %%rax, %%r10 ;" - "adcq %%rcx, %%r11 ;" - "adcq $0, %%r15 ;" - "adcq $0, %%r13 ;" - "adcq $0, %%r14 ;" - - "shldq $1, %%r13, %%r14 ;" - "shldq $1, %%r15, %%r13 ;" - "shldq $1, %%r11, %%r15 ;" - "shldq $1, %%r10, %%r11 ;" - "shldq $1, %%r9, %%r10 ;" - "shldq $1, %%r8, %%r9 ;" - "shlq $1, %%r8 ;" - - /*******************/ - "mulx %%rdx, %%rax, %%rcx ; " /* B[0]^2 */ - /*******************/ - "movq %%rax, 64(%0) ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 72(%0) ;" - "movq 40(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ; " /* B[1]^2 */ - "adcq %%rax, %%r9 ;" - "movq %%r9, 80(%0) ;" - "adcq %%rcx, %%r10 ;" - "movq %%r10, 88(%0) ;" - "movq 48(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ; " /* B[2]^2 */ - "adcq %%rax, %%r11 ;" - "movq %%r11, 96(%0) ;" - "adcq %%rcx, %%r15 ;" - "movq %%r15, 104(%0) ;" - "movq 56(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ; " /* B[3]^2 */ - "adcq %%rax, %%r13 ;" - "movq %%r13, 112(%0) ;" - "adcq %%rcx, %%r14 ;" - "movq %%r14, 120(%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", - "%r11", "%r13", "%r14", "%r15"); -} + u64 carry_r; -static void red_eltfp25519_2w_adx(u64 *const c, const u64 *const a) -{ asm volatile( - "movl $38, %%edx; " /* 2*c = 38 = 2^256 */ - "mulx 32(%1), %%r8, %%r10; " /* c*C[4] */ - "xorl %%ebx, %%ebx ;" - "adox (%1), %%r8 ;" - "mulx 40(%1), %%r9, %%r11; " /* c*C[5] */ - "adcx %%r10, %%r9 ;" - "adox 8(%1), %%r9 ;" - "mulx 48(%1), %%r10, %%rax; " /* c*C[6] */ - "adcx %%r11, %%r10 ;" - "adox 16(%1), %%r10 ;" - "mulx 56(%1), %%r11, %%rcx; " /* c*C[7] */ - "adcx %%rax, %%r11 ;" - "adox 24(%1), %%r11 ;" - /***************************************/ - "adcx %%rbx, %%rcx ;" - "adox %%rbx, %%rcx ;" - "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ - "adcx %%rcx, %%r8 ;" - "adcx %%rbx, %%r9 ;" - "movq %%r9, 8(%0) ;" - "adcx %%rbx, %%r10 ;" - "movq %%r10, 16(%0) ;" - "adcx %%rbx, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%edx, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, (%0) ;" - - "mulx 96(%1), %%r8, %%r10; " /* c*C[4] */ - "xorl %%ebx, %%ebx ;" - "adox 64(%1), %%r8 ;" - "mulx 104(%1), %%r9, %%r11; " /* c*C[5] */ - "adcx %%r10, %%r9 ;" - "adox 72(%1), %%r9 ;" - "mulx 112(%1), %%r10, %%rax; " /* c*C[6] */ - "adcx %%r11, %%r10 ;" - "adox 80(%1), %%r10 ;" - "mulx 120(%1), %%r11, %%rcx; " /* c*C[7] */ - "adcx %%rax, %%r11 ;" - "adox 88(%1), %%r11 ;" - /****************************************/ - "adcx %%rbx, %%rcx ;" - "adox %%rbx, %%rcx ;" - "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ - "adcx %%rcx, %%r8 ;" - "adcx %%rbx, %%r9 ;" - "movq %%r9, 40(%0) ;" - "adcx %%rbx, %%r10 ;" - "movq %%r10, 48(%0) ;" - "adcx %%rbx, %%r11 ;" - "movq %%r11, 56(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%edx, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 32(%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", - "%r10", "%r11"); -} + /* Clear registers to propagate the carry bit */ + " xor %%r8, %%r8;" + " xor %%r9, %%r9;" + " xor %%r10, %%r10;" + " xor %%r11, %%r11;" + " xor %1, %1;" + + /* Begin addition chain */ + " addq 0(%3), %0;" + " movq %0, 0(%2);" + " adcxq 8(%3), %%r8;" + " movq %%r8, 8(%2);" + " adcxq 16(%3), %%r9;" + " movq %%r9, 16(%2);" + " adcxq 24(%3), %%r10;" + " movq %%r10, 24(%2);" + + /* Return the carry bit in a register */ + " adcx %%r11, %1;" + : "+&r" (f2), "=&r" (carry_r) + : "r" (out), "r" (f1) + : "%r8", "%r9", "%r10", "%r11", "memory", "cc" + ); -static void red_eltfp25519_2w_bmi2(u64 *const c, const u64 *const a) -{ - asm volatile( - "movl $38, %%edx ; " /* 2*c = 38 = 2^256 */ - "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ - "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ - "addq %%r10, %%r9 ;" - "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ - "adcq %%r11, %%r10 ;" - "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ - "adcq %%rax, %%r11 ;" - /***************************************/ - "adcq $0, %%rcx ;" - "addq (%1), %%r8 ;" - "adcq 8(%1), %%r9 ;" - "adcq 16(%1), %%r10 ;" - "adcq 24(%1), %%r11 ;" - "adcq $0, %%rcx ;" - "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ - "addq %%rcx, %%r8 ;" - "adcq $0, %%r9 ;" - "movq %%r9, 8(%0) ;" - "adcq $0, %%r10 ;" - "movq %%r10, 16(%0) ;" - "adcq $0, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%edx, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, (%0) ;" - - "mulx 96(%1), %%r8, %%r10 ;" /* c*C[4] */ - "mulx 104(%1), %%r9, %%r11 ;" /* c*C[5] */ - "addq %%r10, %%r9 ;" - "mulx 112(%1), %%r10, %%rax ;" /* c*C[6] */ - "adcq %%r11, %%r10 ;" - "mulx 120(%1), %%r11, %%rcx ;" /* c*C[7] */ - "adcq %%rax, %%r11 ;" - /****************************************/ - "adcq $0, %%rcx ;" - "addq 64(%1), %%r8 ;" - "adcq 72(%1), %%r9 ;" - "adcq 80(%1), %%r10 ;" - "adcq 88(%1), %%r11 ;" - "adcq $0, %%rcx ;" - "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ - "addq %%rcx, %%r8 ;" - "adcq $0, %%r9 ;" - "movq %%r9, 40(%0) ;" - "adcq $0, %%r10 ;" - "movq %%r10, 48(%0) ;" - "adcq $0, %%r11 ;" - "movq %%r11, 56(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%edx, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 32(%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", - "%r11"); + return carry_r; } -static void mul_256x256_integer_adx(u64 *const c, const u64 *const a, - const u64 *const b) +/* Computes the field addition of two field elements */ +static inline void fadd(u64 *out, const u64 *f1, const u64 *f2) { asm volatile( - "movq (%1), %%rdx; " /* A[0] */ - "mulx (%2), %%r8, %%r9; " /* A[0]*B[0] */ - "xorl %%r10d, %%r10d ;" - "movq %%r8, (%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[0]*B[1] */ - "adox %%r9, %%r10 ;" - "movq %%r10, 8(%0) ;" - "mulx 16(%2), %%r15, %%r13; " /* A[0]*B[2] */ - "adox %%r11, %%r15 ;" - "mulx 24(%2), %%r14, %%rdx; " /* A[0]*B[3] */ - "adox %%r13, %%r14 ;" - "movq $0, %%rax ;" - /******************************************/ - "adox %%rdx, %%rax ;" - - "movq 8(%1), %%rdx; " /* A[1] */ - "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ - "xorl %%r10d, %%r10d ;" - "adcx 8(%0), %%r8 ;" - "movq %%r8, 8(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ - "adox %%r9, %%r10 ;" - "adcx %%r15, %%r10 ;" - "movq %%r10, 16(%0) ;" - "mulx 16(%2), %%r15, %%r13; " /* A[1]*B[2] */ - "adox %%r11, %%r15 ;" - "adcx %%r14, %%r15 ;" - "movq $0, %%r8 ;" - "mulx 24(%2), %%r14, %%rdx; " /* A[1]*B[3] */ - "adox %%r13, %%r14 ;" - "adcx %%rax, %%r14 ;" - "movq $0, %%rax ;" - /******************************************/ - "adox %%rdx, %%rax ;" - "adcx %%r8, %%rax ;" - - "movq 16(%1), %%rdx; " /* A[2] */ - "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ - "xorl %%r10d, %%r10d ;" - "adcx 16(%0), %%r8 ;" - "movq %%r8, 16(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ - "adox %%r9, %%r10 ;" - "adcx %%r15, %%r10 ;" - "movq %%r10, 24(%0) ;" - "mulx 16(%2), %%r15, %%r13; " /* A[2]*B[2] */ - "adox %%r11, %%r15 ;" - "adcx %%r14, %%r15 ;" - "movq $0, %%r8 ;" - "mulx 24(%2), %%r14, %%rdx; " /* A[2]*B[3] */ - "adox %%r13, %%r14 ;" - "adcx %%rax, %%r14 ;" - "movq $0, %%rax ;" - /******************************************/ - "adox %%rdx, %%rax ;" - "adcx %%r8, %%rax ;" - - "movq 24(%1), %%rdx; " /* A[3] */ - "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ - "xorl %%r10d, %%r10d ;" - "adcx 24(%0), %%r8 ;" - "movq %%r8, 24(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ - "adox %%r9, %%r10 ;" - "adcx %%r15, %%r10 ;" - "movq %%r10, 32(%0) ;" - "mulx 16(%2), %%r15, %%r13; " /* A[3]*B[2] */ - "adox %%r11, %%r15 ;" - "adcx %%r14, %%r15 ;" - "movq %%r15, 40(%0) ;" - "movq $0, %%r8 ;" - "mulx 24(%2), %%r14, %%rdx; " /* A[3]*B[3] */ - "adox %%r13, %%r14 ;" - "adcx %%rax, %%r14 ;" - "movq %%r14, 48(%0) ;" - "movq $0, %%rax ;" - /******************************************/ - "adox %%rdx, %%rax ;" - "adcx %%r8, %%rax ;" - "movq %%rax, 56(%0) ;" - : - : "r"(c), "r"(a), "r"(b) - : "memory", "cc", "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", - "%r13", "%r14", "%r15"); + /* Compute the raw addition of f1 + f2 */ + " movq 0(%0), %%r8;" + " addq 0(%2), %%r8;" + " movq 8(%0), %%r9;" + " adcxq 8(%2), %%r9;" + " movq 16(%0), %%r10;" + " adcxq 16(%2), %%r10;" + " movq 24(%0), %%r11;" + " adcxq 24(%2), %%r11;" + + /* Wrap the result back into the field */ + + /* Step 1: Compute carry*38 */ + " mov $0, %%rax;" + " mov $38, %0;" + " cmovc %0, %%rax;" + + /* Step 2: Add carry*38 to the original sum */ + " xor %%rcx, %%rcx;" + " add %%rax, %%r8;" + " adcx %%rcx, %%r9;" + " movq %%r9, 8(%1);" + " adcx %%rcx, %%r10;" + " movq %%r10, 16(%1);" + " adcx %%rcx, %%r11;" + " movq %%r11, 24(%1);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %0, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 0(%1);" + : "+&r" (f2) + : "r" (out), "r" (f1) + : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc" + ); } -static void mul_256x256_integer_bmi2(u64 *const c, const u64 *const a, - const u64 *const b) +/* Computes the field substraction of two field elements */ +static inline void fsub(u64 *out, const u64 *f1, const u64 *f2) { asm volatile( - "movq (%1), %%rdx; " /* A[0] */ - "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ - "movq %%r8, (%0) ;" - "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ - "addq %%r10, %%r15 ;" - "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ - "adcq %%r8, %%rax ;" - "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ - "adcq %%r10, %%rbx ;" - /******************************************/ - "adcq $0, %%rcx ;" - - "movq 8(%1), %%rdx; " /* A[1] */ - "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ - "addq %%r15, %%r8 ;" - "movq %%r8, 8(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ - "adcq %%r10, %%r9 ;" - "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ - "adcq %%r8, %%r11 ;" - "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%r15 ;" - - "addq %%r9, %%rax ;" - "adcq %%r11, %%rbx ;" - "adcq %%r13, %%rcx ;" - "adcq $0, %%r15 ;" - - "movq 16(%1), %%rdx; " /* A[2] */ - "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ - "addq %%rax, %%r8 ;" - "movq %%r8, 16(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ - "adcq %%r10, %%r9 ;" - "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ - "adcq %%r8, %%r11 ;" - "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%rax ;" - - "addq %%r9, %%rbx ;" - "adcq %%r11, %%rcx ;" - "adcq %%r13, %%r15 ;" - "adcq $0, %%rax ;" - - "movq 24(%1), %%rdx; " /* A[3] */ - "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ - "addq %%rbx, %%r8 ;" - "movq %%r8, 24(%0) ;" - "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ - "adcq %%r10, %%r9 ;" - "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ - "adcq %%r8, %%r11 ;" - "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ - "adcq %%r10, %%r13 ;" - /******************************************/ - "adcq $0, %%rbx ;" - - "addq %%r9, %%rcx ;" - "movq %%rcx, 32(%0) ;" - "adcq %%r11, %%r15 ;" - "movq %%r15, 40(%0) ;" - "adcq %%r13, %%rax ;" - "movq %%rax, 48(%0) ;" - "adcq $0, %%rbx ;" - "movq %%rbx, 56(%0) ;" - : - : "r"(c), "r"(a), "r"(b) - : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", - "%r10", "%r11", "%r13", "%r15"); + /* Compute the raw substraction of f1-f2 */ + " movq 0(%1), %%r8;" + " subq 0(%2), %%r8;" + " movq 8(%1), %%r9;" + " sbbq 8(%2), %%r9;" + " movq 16(%1), %%r10;" + " sbbq 16(%2), %%r10;" + " movq 24(%1), %%r11;" + " sbbq 24(%2), %%r11;" + + /* Wrap the result back into the field */ + + /* Step 1: Compute carry*38 */ + " mov $0, %%rax;" + " mov $38, %%rcx;" + " cmovc %%rcx, %%rax;" + + /* Step 2: Substract carry*38 from the original difference */ + " sub %%rax, %%r8;" + " sbb $0, %%r9;" + " sbb $0, %%r10;" + " sbb $0, %%r11;" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rcx, %%rax;" + " sub %%rax, %%r8;" + + /* Store the result */ + " movq %%r8, 0(%0);" + " movq %%r9, 8(%0);" + " movq %%r10, 16(%0);" + " movq %%r11, 24(%0);" + : + : "r" (out), "r" (f1), "r" (f2) + : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc" + ); } -static void sqr_256x256_integer_adx(u64 *const c, const u64 *const a) +/* Computes a field multiplication: out <- f1 * f2 + * Uses the 8-element buffer tmp for intermediate results */ +static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) { asm volatile( - "movq (%1), %%rdx ;" /* A[0] */ - "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ - "xorl %%r15d, %%r15d;" - "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ - "adcx %%r14, %%r9 ;" - "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ - "adcx %%rax, %%r10 ;" - "movq 24(%1), %%rdx ;" /* A[3] */ - "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ - "adcx %%rcx, %%r11 ;" - "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ - "adcx %%rax, %%rbx ;" - "movq 8(%1), %%rdx ;" /* A[1] */ - "adcx %%r15, %%r13 ;" - "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ - "movq $0, %%r14 ;" - /******************************************/ - "adcx %%r15, %%r14 ;" - - "xorl %%r15d, %%r15d;" - "adox %%rax, %%r10 ;" - "adcx %%r8, %%r8 ;" - "adox %%rcx, %%r11 ;" - "adcx %%r9, %%r9 ;" - "adox %%r15, %%rbx ;" - "adcx %%r10, %%r10 ;" - "adox %%r15, %%r13 ;" - "adcx %%r11, %%r11 ;" - "adox %%r15, %%r14 ;" - "adcx %%rbx, %%rbx ;" - "adcx %%r13, %%r13 ;" - "adcx %%r14, %%r14 ;" - - "movq (%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ - /*******************/ - "movq %%rax, 0(%0) ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 8(%0) ;" - "movq 8(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ - "adcq %%rax, %%r9 ;" - "movq %%r9, 16(%0) ;" - "adcq %%rcx, %%r10 ;" - "movq %%r10, 24(%0) ;" - "movq 16(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ - "adcq %%rax, %%r11 ;" - "movq %%r11, 32(%0) ;" - "adcq %%rcx, %%rbx ;" - "movq %%rbx, 40(%0) ;" - "movq 24(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ - "adcq %%rax, %%r13 ;" - "movq %%r13, 48(%0) ;" - "adcq %%rcx, %%r14 ;" - "movq %%r14, 56(%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", - "%r10", "%r11", "%r13", "%r14", "%r15"); + /* Compute the raw multiplication: tmp <- src1 * src2 */ + + /* Compute src1[0] * src2 */ + " movq 0(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 8(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 16(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 24(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%0);" + /* Line up pointers */ + " mov %0, %1;" + " mov %2, %0;" + + /* Wrap the result back into the field */ + + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" + " xor %3, %3;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" + " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" + " adoxq 24(%1), %%r11;" + " adcx %3, %%rax;" + " adox %3, %%rax;" + " imul %%rdx, %%rax;" + + /* Step 2: Fold the carry back into dst */ + " add %%rax, %%r8;" + " adcx %3, %%r9;" + " movq %%r9, 8(%0);" + " adcx %3, %%r10;" + " movq %%r10, 16(%0);" + " adcx %3, %%r11;" + " movq %%r11, 24(%0);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rdx, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 0(%0);" + : "+&r" (tmp), "+&r" (f1), "+&r" (out), "+&r" (f2) + : + : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "memory", "cc" + ); } -static void sqr_256x256_integer_bmi2(u64 *const c, const u64 *const a) +/* Computes two field multiplications: + * out[0] <- f1[0] * f2[0] + * out[1] <- f1[1] * f2[1] + * Uses the 16-element buffer tmp for intermediate results. */ +static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) { asm volatile( - "movq 8(%1), %%rdx ;" /* A[1] */ - "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ - "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ - "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ - - "movq 16(%1), %%rdx ;" /* A[2] */ - "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ - "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ - - "addq %%rax, %%r9 ;" - "adcq %%rdx, %%r10 ;" - "adcq %%rcx, %%r11 ;" - "adcq %%r14, %%r15 ;" - "adcq $0, %%r13 ;" - "movq $0, %%r14 ;" - "adcq $0, %%r14 ;" - - "movq (%1), %%rdx ;" /* A[0] */ - "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ - - "addq %%rax, %%r10 ;" - "adcq %%rcx, %%r11 ;" - "adcq $0, %%r15 ;" - "adcq $0, %%r13 ;" - "adcq $0, %%r14 ;" - - "shldq $1, %%r13, %%r14 ;" - "shldq $1, %%r15, %%r13 ;" - "shldq $1, %%r11, %%r15 ;" - "shldq $1, %%r10, %%r11 ;" - "shldq $1, %%r9, %%r10 ;" - "shldq $1, %%r8, %%r9 ;" - "shlq $1, %%r8 ;" - - /*******************/ - "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ - /*******************/ - "movq %%rax, 0(%0) ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, 8(%0) ;" - "movq 8(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ - "adcq %%rax, %%r9 ;" - "movq %%r9, 16(%0) ;" - "adcq %%rcx, %%r10 ;" - "movq %%r10, 24(%0) ;" - "movq 16(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ - "adcq %%rax, %%r11 ;" - "movq %%r11, 32(%0) ;" - "adcq %%rcx, %%r15 ;" - "movq %%r15, 40(%0) ;" - "movq 24(%1), %%rdx ;" - "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ - "adcq %%rax, %%r13 ;" - "movq %%r13, 48(%0) ;" - "adcq %%rcx, %%r14 ;" - "movq %%r14, 56(%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", - "%r11", "%r13", "%r14", "%r15"); + /* Compute the raw multiplication tmp[0] <- f1[0] * f2[0] */ + + /* Compute src1[0] * src2 */ + " movq 0(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 8(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 16(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 24(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%0);" + + /* Compute the raw multiplication tmp[1] <- f1[1] * f2[1] */ + + /* Compute src1[0] * src2 */ + " movq 32(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 64(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 40(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 72(%0), %%r8;" " movq %%r8, 72(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 48(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 80(%0), %%r8;" " movq %%r8, 80(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 56(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 88(%0), %%r8;" " movq %%r8, 88(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 104(%0);" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 112(%0);" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 120(%0);" + /* Line up pointers */ + " mov %0, %1;" + " mov %2, %0;" + + /* Wrap the results back into the field */ + + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" + " xor %3, %3;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" + " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" + " adoxq 24(%1), %%r11;" + " adcx %3, %%rax;" + " adox %3, %%rax;" + " imul %%rdx, %%rax;" + + /* Step 2: Fold the carry back into dst */ + " add %%rax, %%r8;" + " adcx %3, %%r9;" + " movq %%r9, 8(%0);" + " adcx %3, %%r10;" + " movq %%r10, 16(%0);" + " adcx %3, %%r11;" + " movq %%r11, 24(%0);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rdx, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 0(%0);" + + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 96(%1), %%r8, %%r13;" + " xor %3, %3;" + " adoxq 64(%1), %%r8;" + " mulxq 104(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 72(%1), %%r9;" + " mulxq 112(%1), %%r10, %%r13;" + " adcx %%rbx, %%r10;" + " adoxq 80(%1), %%r10;" + " mulxq 120(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" + " adoxq 88(%1), %%r11;" + " adcx %3, %%rax;" + " adox %3, %%rax;" + " imul %%rdx, %%rax;" + + /* Step 2: Fold the carry back into dst */ + " add %%rax, %%r8;" + " adcx %3, %%r9;" + " movq %%r9, 40(%0);" + " adcx %3, %%r10;" + " movq %%r10, 48(%0);" + " adcx %3, %%r11;" + " movq %%r11, 56(%0);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rdx, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 32(%0);" + : "+&r" (tmp), "+&r" (f1), "+&r" (out), "+&r" (f2) + : + : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "memory", "cc" + ); } -static void red_eltfp25519_1w_adx(u64 *const c, const u64 *const a) +/* Computes the field multiplication of four-element f1 with value in f2 */ +static inline void fmul_scalar(u64 *out, const u64 *f1, u64 f2) { - asm volatile( - "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ - "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ - "xorl %%ebx, %%ebx ;" - "adox (%1), %%r8 ;" - "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ - "adcx %%r10, %%r9 ;" - "adox 8(%1), %%r9 ;" - "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ - "adcx %%r11, %%r10 ;" - "adox 16(%1), %%r10 ;" - "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ - "adcx %%rax, %%r11 ;" - "adox 24(%1), %%r11 ;" - /***************************************/ - "adcx %%rbx, %%rcx ;" - "adox %%rbx, %%rcx ;" - "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ - "adcx %%rcx, %%r8 ;" - "adcx %%rbx, %%r9 ;" - "movq %%r9, 8(%0) ;" - "adcx %%rbx, %%r10 ;" - "movq %%r10, 16(%0) ;" - "adcx %%rbx, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%edx, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, (%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", - "%r10", "%r11"); -} + register u64 f2_r asm("rdx") = f2; -static void red_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) -{ asm volatile( - "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ - "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ - "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ - "addq %%r10, %%r9 ;" - "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ - "adcq %%r11, %%r10 ;" - "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ - "adcq %%rax, %%r11 ;" - /***************************************/ - "adcq $0, %%rcx ;" - "addq (%1), %%r8 ;" - "adcq 8(%1), %%r9 ;" - "adcq 16(%1), %%r10 ;" - "adcq 24(%1), %%r11 ;" - "adcq $0, %%rcx ;" - "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ - "addq %%rcx, %%r8 ;" - "adcq $0, %%r9 ;" - "movq %%r9, 8(%0) ;" - "adcq $0, %%r10 ;" - "movq %%r10, 16(%0) ;" - "adcq $0, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%edx, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, (%0) ;" - : - : "r"(c), "r"(a) - : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", - "%r11"); + /* Compute the raw multiplication of f1*f2 */ + " mulxq 0(%2), %%r8, %%rcx;" /* f1[0]*f2 */ + " mulxq 8(%2), %%r9, %%rbx;" /* f1[1]*f2 */ + " add %%rcx, %%r9;" + " mov $0, %%rcx;" + " mulxq 16(%2), %%r10, %%r13;" /* f1[2]*f2 */ + " adcx %%rbx, %%r10;" + " mulxq 24(%2), %%r11, %%rax;" /* f1[3]*f2 */ + " adcx %%r13, %%r11;" + " adcx %%rcx, %%rax;" + + /* Wrap the result back into the field */ + + /* Step 1: Compute carry*38 */ + " mov $38, %%rdx;" + " imul %%rdx, %%rax;" + + /* Step 2: Fold the carry back into dst */ + " add %%rax, %%r8;" + " adcx %%rcx, %%r9;" + " movq %%r9, 8(%1);" + " adcx %%rcx, %%r10;" + " movq %%r10, 16(%1);" + " adcx %%rcx, %%r11;" + " movq %%r11, 24(%1);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rdx, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 0(%1);" + : "+&r" (f2_r) + : "r" (out), "r" (f1) + : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "memory", "cc" + ); } -static __always_inline void -add_eltfp25519_1w_adx(u64 *const c, const u64 *const a, const u64 *const b) +/* Computes p1 <- bit ? p2 : p1 in constant time */ +static inline void cswap2(u64 bit, const u64 *p1, const u64 *p2) { asm volatile( - "mov $38, %%eax ;" - "xorl %%ecx, %%ecx ;" - "movq (%2), %%r8 ;" - "adcx (%1), %%r8 ;" - "movq 8(%2), %%r9 ;" - "adcx 8(%1), %%r9 ;" - "movq 16(%2), %%r10 ;" - "adcx 16(%1), %%r10 ;" - "movq 24(%2), %%r11 ;" - "adcx 24(%1), %%r11 ;" - "cmovc %%eax, %%ecx ;" - "xorl %%eax, %%eax ;" - "adcx %%rcx, %%r8 ;" - "adcx %%rax, %%r9 ;" - "movq %%r9, 8(%0) ;" - "adcx %%rax, %%r10 ;" - "movq %%r10, 16(%0) ;" - "adcx %%rax, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $38, %%ecx ;" - "cmovc %%ecx, %%eax ;" - "addq %%rax, %%r8 ;" - "movq %%r8, (%0) ;" - : - : "r"(c), "r"(a), "r"(b) - : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); + /* Invert the polarity of bit to match cmov expectations */ + " add $18446744073709551615, %0;" + + /* cswap p1[0], p2[0] */ + " movq 0(%1), %%r8;" + " movq 0(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 0(%1);" + " movq %%r9, 0(%2);" + + /* cswap p1[1], p2[1] */ + " movq 8(%1), %%r8;" + " movq 8(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 8(%1);" + " movq %%r9, 8(%2);" + + /* cswap p1[2], p2[2] */ + " movq 16(%1), %%r8;" + " movq 16(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 16(%1);" + " movq %%r9, 16(%2);" + + /* cswap p1[3], p2[3] */ + " movq 24(%1), %%r8;" + " movq 24(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 24(%1);" + " movq %%r9, 24(%2);" + + /* cswap p1[4], p2[4] */ + " movq 32(%1), %%r8;" + " movq 32(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 32(%1);" + " movq %%r9, 32(%2);" + + /* cswap p1[5], p2[5] */ + " movq 40(%1), %%r8;" + " movq 40(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 40(%1);" + " movq %%r9, 40(%2);" + + /* cswap p1[6], p2[6] */ + " movq 48(%1), %%r8;" + " movq 48(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 48(%1);" + " movq %%r9, 48(%2);" + + /* cswap p1[7], p2[7] */ + " movq 56(%1), %%r8;" + " movq 56(%2), %%r9;" + " mov %%r8, %%r10;" + " cmovc %%r9, %%r8;" + " cmovc %%r10, %%r9;" + " movq %%r8, 56(%1);" + " movq %%r9, 56(%2);" + : "+&r" (bit) + : "r" (p1), "r" (p2) + : "%r8", "%r9", "%r10", "memory", "cc" + ); } -static __always_inline void -add_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a, const u64 *const b) +/* Computes the square of a field element: out <- f * f + * Uses the 8-element buffer tmp for intermediate results */ +static inline void fsqr(u64 *out, const u64 *f, u64 *tmp) { asm volatile( - "mov $38, %%eax ;" - "movq (%2), %%r8 ;" - "addq (%1), %%r8 ;" - "movq 8(%2), %%r9 ;" - "adcq 8(%1), %%r9 ;" - "movq 16(%2), %%r10 ;" - "adcq 16(%1), %%r10 ;" - "movq 24(%2), %%r11 ;" - "adcq 24(%1), %%r11 ;" - "mov $0, %%ecx ;" - "cmovc %%eax, %%ecx ;" - "addq %%rcx, %%r8 ;" - "adcq $0, %%r9 ;" - "movq %%r9, 8(%0) ;" - "adcq $0, %%r10 ;" - "movq %%r10, 16(%0) ;" - "adcq $0, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%eax, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, (%0) ;" - : - : "r"(c), "r"(a), "r"(b) - : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); + /* Compute the raw multiplication: tmp <- f * f */ + + /* Step 1: Compute all partial products */ + " movq 0(%1), %%rdx;" /* f[0] */ + " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ + " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 24(%1), %%rdx;" /* f[3] */ + " mulxq 8(%1), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ + " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ + " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ + " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + + /* Step 2: Compute two parallel carry chains */ + " xor %%r15, %%r15;" + " adox %%rax, %%r10;" + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" + " adcx %%r9, %%r9;" + " adox %%r15, %%rbx;" + " adcx %%r10, %%r10;" + " adox %%r15, %%r13;" + " adcx %%r11, %%r11;" + " adox %%r15, %%r14;" + " adcx %%rbx, %%rbx;" + " adcx %%r13, %%r13;" + " adcx %%r14, %%r14;" + + /* Step 3: Compute intermediate squares */ + " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ + " movq %%rax, 0(%0);" + " add %%rcx, %%r8;" " movq %%r8, 8(%0);" + " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ + " adcx %%rax, %%r9;" " movq %%r9, 16(%0);" + " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);" + " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ + " adcx %%rax, %%r11;" " movq %%r11, 32(%0);" + " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%0);" + " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ + " adcx %%rax, %%r13;" " movq %%r13, 48(%0);" + " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);" + + /* Line up pointers */ + " mov %0, %1;" + " mov %2, %0;" + + /* Wrap the result back into the field */ + + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" + " xor %%rcx, %%rcx;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" + " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" + " adoxq 24(%1), %%r11;" + " adcx %%rcx, %%rax;" + " adox %%rcx, %%rax;" + " imul %%rdx, %%rax;" + + /* Step 2: Fold the carry back into dst */ + " add %%rax, %%r8;" + " adcx %%rcx, %%r9;" + " movq %%r9, 8(%0);" + " adcx %%rcx, %%r10;" + " movq %%r10, 16(%0);" + " adcx %%rcx, %%r11;" + " movq %%r11, 24(%0);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rdx, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 0(%0);" + : "+&r" (tmp), "+&r" (f), "+&r" (out) + : + : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "%r15", "memory", "cc" + ); } -static __always_inline void -sub_eltfp25519_1w(u64 *const c, const u64 *const a, const u64 *const b) +/* Computes two field squarings: + * out[0] <- f[0] * f[0] + * out[1] <- f[1] * f[1] + * Uses the 16-element buffer tmp for intermediate results */ +static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) { asm volatile( - "mov $38, %%eax ;" - "movq (%1), %%r8 ;" - "subq (%2), %%r8 ;" - "movq 8(%1), %%r9 ;" - "sbbq 8(%2), %%r9 ;" - "movq 16(%1), %%r10 ;" - "sbbq 16(%2), %%r10 ;" - "movq 24(%1), %%r11 ;" - "sbbq 24(%2), %%r11 ;" - "mov $0, %%ecx ;" - "cmovc %%eax, %%ecx ;" - "subq %%rcx, %%r8 ;" - "sbbq $0, %%r9 ;" - "movq %%r9, 8(%0) ;" - "sbbq $0, %%r10 ;" - "movq %%r10, 16(%0) ;" - "sbbq $0, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%eax, %%ecx ;" - "subq %%rcx, %%r8 ;" - "movq %%r8, (%0) ;" - : - : "r"(c), "r"(a), "r"(b) - : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); + /* Step 1: Compute all partial products */ + " movq 0(%1), %%rdx;" /* f[0] */ + " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ + " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 24(%1), %%rdx;" /* f[3] */ + " mulxq 8(%1), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ + " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ + " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ + " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + + /* Step 2: Compute two parallel carry chains */ + " xor %%r15, %%r15;" + " adox %%rax, %%r10;" + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" + " adcx %%r9, %%r9;" + " adox %%r15, %%rbx;" + " adcx %%r10, %%r10;" + " adox %%r15, %%r13;" + " adcx %%r11, %%r11;" + " adox %%r15, %%r14;" + " adcx %%rbx, %%rbx;" + " adcx %%r13, %%r13;" + " adcx %%r14, %%r14;" + + /* Step 3: Compute intermediate squares */ + " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ + " movq %%rax, 0(%0);" + " add %%rcx, %%r8;" " movq %%r8, 8(%0);" + " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ + " adcx %%rax, %%r9;" " movq %%r9, 16(%0);" + " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);" + " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ + " adcx %%rax, %%r11;" " movq %%r11, 32(%0);" + " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%0);" + " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ + " adcx %%rax, %%r13;" " movq %%r13, 48(%0);" + " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);" + + /* Step 1: Compute all partial products */ + " movq 32(%1), %%rdx;" /* f[0] */ + " mulxq 40(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ + " mulxq 48(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 56(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 56(%1), %%rdx;" /* f[3] */ + " mulxq 40(%1), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ + " mulxq 48(%1), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ + " movq 40(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ + " mulxq 48(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + + /* Step 2: Compute two parallel carry chains */ + " xor %%r15, %%r15;" + " adox %%rax, %%r10;" + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" + " adcx %%r9, %%r9;" + " adox %%r15, %%rbx;" + " adcx %%r10, %%r10;" + " adox %%r15, %%r13;" + " adcx %%r11, %%r11;" + " adox %%r15, %%r14;" + " adcx %%rbx, %%rbx;" + " adcx %%r13, %%r13;" + " adcx %%r14, %%r14;" + + /* Step 3: Compute intermediate squares */ + " movq 32(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ + " movq %%rax, 64(%0);" + " add %%rcx, %%r8;" " movq %%r8, 72(%0);" + " movq 40(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ + " adcx %%rax, %%r9;" " movq %%r9, 80(%0);" + " adcx %%rcx, %%r10;" " movq %%r10, 88(%0);" + " movq 48(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ + " adcx %%rax, %%r11;" " movq %%r11, 96(%0);" + " adcx %%rcx, %%rbx;" " movq %%rbx, 104(%0);" + " movq 56(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ + " adcx %%rax, %%r13;" " movq %%r13, 112(%0);" + " adcx %%rcx, %%r14;" " movq %%r14, 120(%0);" + + /* Line up pointers */ + " mov %0, %1;" + " mov %2, %0;" + + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" + " xor %%rcx, %%rcx;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" + " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" + " adoxq 24(%1), %%r11;" + " adcx %%rcx, %%rax;" + " adox %%rcx, %%rax;" + " imul %%rdx, %%rax;" + + /* Step 2: Fold the carry back into dst */ + " add %%rax, %%r8;" + " adcx %%rcx, %%r9;" + " movq %%r9, 8(%0);" + " adcx %%rcx, %%r10;" + " movq %%r10, 16(%0);" + " adcx %%rcx, %%r11;" + " movq %%r11, 24(%0);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rdx, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 0(%0);" + + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 96(%1), %%r8, %%r13;" + " xor %%rcx, %%rcx;" + " adoxq 64(%1), %%r8;" + " mulxq 104(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 72(%1), %%r9;" + " mulxq 112(%1), %%r10, %%r13;" + " adcx %%rbx, %%r10;" + " adoxq 80(%1), %%r10;" + " mulxq 120(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" + " adoxq 88(%1), %%r11;" + " adcx %%rcx, %%rax;" + " adox %%rcx, %%rax;" + " imul %%rdx, %%rax;" + + /* Step 2: Fold the carry back into dst */ + " add %%rax, %%r8;" + " adcx %%rcx, %%r9;" + " movq %%r9, 40(%0);" + " adcx %%rcx, %%r10;" + " movq %%r10, 48(%0);" + " adcx %%rcx, %%r11;" + " movq %%r11, 56(%0);" + + /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ + " mov $0, %%rax;" + " cmovc %%rdx, %%rax;" + " add %%rax, %%r8;" + " movq %%r8, 32(%0);" + : "+&r" (tmp), "+&r" (f), "+&r" (out) + : + : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "%r15", "memory", "cc" + ); } -/* Multiplication by a24 = (A+2)/4 = (486662+2)/4 = 121666 */ -static __always_inline void -mul_a24_eltfp25519_1w(u64 *const c, const u64 *const a) +static void point_add_and_double(u64 *q, u64 *p01_tmp1, u64 *tmp2) { - const u64 a24 = 121666; - asm volatile( - "movq %2, %%rdx ;" - "mulx (%1), %%r8, %%r10 ;" - "mulx 8(%1), %%r9, %%r11 ;" - "addq %%r10, %%r9 ;" - "mulx 16(%1), %%r10, %%rax ;" - "adcq %%r11, %%r10 ;" - "mulx 24(%1), %%r11, %%rcx ;" - "adcq %%rax, %%r11 ;" - /**************************/ - "adcq $0, %%rcx ;" - "movl $38, %%edx ;" /* 2*c = 38 = 2^256 mod 2^255-19*/ - "imul %%rdx, %%rcx ;" - "addq %%rcx, %%r8 ;" - "adcq $0, %%r9 ;" - "movq %%r9, 8(%0) ;" - "adcq $0, %%r10 ;" - "movq %%r10, 16(%0) ;" - "adcq $0, %%r11 ;" - "movq %%r11, 24(%0) ;" - "mov $0, %%ecx ;" - "cmovc %%edx, %%ecx ;" - "addq %%rcx, %%r8 ;" - "movq %%r8, (%0) ;" - : - : "r"(c), "r"(a), "r"(a24) - : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", - "%r11"); + u64 *nq = p01_tmp1; + u64 *nq_p1 = p01_tmp1 + (u32)8U; + u64 *tmp1 = p01_tmp1 + (u32)16U; + u64 *x1 = q; + u64 *x2 = nq; + u64 *z2 = nq + (u32)4U; + u64 *z3 = nq_p1 + (u32)4U; + u64 *a = tmp1; + u64 *b = tmp1 + (u32)4U; + u64 *ab = tmp1; + u64 *dc = tmp1 + (u32)8U; + u64 *x3; + u64 *z31; + u64 *d0; + u64 *c0; + u64 *a1; + u64 *b1; + u64 *d; + u64 *c; + u64 *ab1; + u64 *dc1; + fadd(a, x2, z2); + fsub(b, x2, z2); + x3 = nq_p1; + z31 = nq_p1 + (u32)4U; + d0 = dc; + c0 = dc + (u32)4U; + fadd(c0, x3, z31); + fsub(d0, x3, z31); + fmul2(dc, dc, ab, tmp2); + fadd(x3, d0, c0); + fsub(z31, d0, c0); + a1 = tmp1; + b1 = tmp1 + (u32)4U; + d = tmp1 + (u32)8U; + c = tmp1 + (u32)12U; + ab1 = tmp1; + dc1 = tmp1 + (u32)8U; + fsqr2(dc1, ab1, tmp2); + fsqr2(nq_p1, nq_p1, tmp2); + a1[0U] = c[0U]; + a1[1U] = c[1U]; + a1[2U] = c[2U]; + a1[3U] = c[3U]; + fsub(c, d, c); + fmul_scalar(b1, c, (u64)121665U); + fadd(b1, b1, d); + fmul2(nq, dc1, ab1, tmp2); + fmul(z3, z3, x1, tmp2); } -static void inv_eltfp25519_1w_adx(u64 *const c, const u64 *const a) +static void point_double(u64 *nq, u64 *tmp1, u64 *tmp2) { - struct { - eltfp25519_1w_buffer buffer; - eltfp25519_1w x0, x1, x2; - } __aligned(32) m; - u64 *T[4]; - - T[0] = m.x0; - T[1] = c; /* x^(-1) */ - T[2] = m.x1; - T[3] = m.x2; - - copy_eltfp25519_1w(T[1], a); - sqrn_eltfp25519_1w_adx(T[1], 1); - copy_eltfp25519_1w(T[2], T[1]); - sqrn_eltfp25519_1w_adx(T[2], 2); - mul_eltfp25519_1w_adx(T[0], a, T[2]); - mul_eltfp25519_1w_adx(T[1], T[1], T[0]); - copy_eltfp25519_1w(T[2], T[1]); - sqrn_eltfp25519_1w_adx(T[2], 1); - mul_eltfp25519_1w_adx(T[0], T[0], T[2]); - copy_eltfp25519_1w(T[2], T[0]); - sqrn_eltfp25519_1w_adx(T[2], 5); - mul_eltfp25519_1w_adx(T[0], T[0], T[2]); - copy_eltfp25519_1w(T[2], T[0]); - sqrn_eltfp25519_1w_adx(T[2], 10); - mul_eltfp25519_1w_adx(T[2], T[2], T[0]); - copy_eltfp25519_1w(T[3], T[2]); - sqrn_eltfp25519_1w_adx(T[3], 20); - mul_eltfp25519_1w_adx(T[3], T[3], T[2]); - sqrn_eltfp25519_1w_adx(T[3], 10); - mul_eltfp25519_1w_adx(T[3], T[3], T[0]); - copy_eltfp25519_1w(T[0], T[3]); - sqrn_eltfp25519_1w_adx(T[0], 50); - mul_eltfp25519_1w_adx(T[0], T[0], T[3]); - copy_eltfp25519_1w(T[2], T[0]); - sqrn_eltfp25519_1w_adx(T[2], 100); - mul_eltfp25519_1w_adx(T[2], T[2], T[0]); - sqrn_eltfp25519_1w_adx(T[2], 50); - mul_eltfp25519_1w_adx(T[2], T[2], T[3]); - sqrn_eltfp25519_1w_adx(T[2], 5); - mul_eltfp25519_1w_adx(T[1], T[1], T[2]); - - memzero_explicit(&m, sizeof(m)); + u64 *x2 = nq; + u64 *z2 = nq + (u32)4U; + u64 *a = tmp1; + u64 *b = tmp1 + (u32)4U; + u64 *d = tmp1 + (u32)8U; + u64 *c = tmp1 + (u32)12U; + u64 *ab = tmp1; + u64 *dc = tmp1 + (u32)8U; + fadd(a, x2, z2); + fsub(b, x2, z2); + fsqr2(dc, ab, tmp2); + a[0U] = c[0U]; + a[1U] = c[1U]; + a[2U] = c[2U]; + a[3U] = c[3U]; + fsub(c, d, c); + fmul_scalar(b, c, (u64)121665U); + fadd(b, b, d); + fmul2(nq, dc, ab, tmp2); } -static void inv_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) +static void montgomery_ladder(u64 *out, const u8 *key, u64 *init1) { - struct { - eltfp25519_1w_buffer buffer; - eltfp25519_1w x0, x1, x2; - } __aligned(32) m; - u64 *T[5]; - - T[0] = m.x0; - T[1] = c; /* x^(-1) */ - T[2] = m.x1; - T[3] = m.x2; - - copy_eltfp25519_1w(T[1], a); - sqrn_eltfp25519_1w_bmi2(T[1], 1); - copy_eltfp25519_1w(T[2], T[1]); - sqrn_eltfp25519_1w_bmi2(T[2], 2); - mul_eltfp25519_1w_bmi2(T[0], a, T[2]); - mul_eltfp25519_1w_bmi2(T[1], T[1], T[0]); - copy_eltfp25519_1w(T[2], T[1]); - sqrn_eltfp25519_1w_bmi2(T[2], 1); - mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); - copy_eltfp25519_1w(T[2], T[0]); - sqrn_eltfp25519_1w_bmi2(T[2], 5); - mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); - copy_eltfp25519_1w(T[2], T[0]); - sqrn_eltfp25519_1w_bmi2(T[2], 10); - mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); - copy_eltfp25519_1w(T[3], T[2]); - sqrn_eltfp25519_1w_bmi2(T[3], 20); - mul_eltfp25519_1w_bmi2(T[3], T[3], T[2]); - sqrn_eltfp25519_1w_bmi2(T[3], 10); - mul_eltfp25519_1w_bmi2(T[3], T[3], T[0]); - copy_eltfp25519_1w(T[0], T[3]); - sqrn_eltfp25519_1w_bmi2(T[0], 50); - mul_eltfp25519_1w_bmi2(T[0], T[0], T[3]); - copy_eltfp25519_1w(T[2], T[0]); - sqrn_eltfp25519_1w_bmi2(T[2], 100); - mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); - sqrn_eltfp25519_1w_bmi2(T[2], 50); - mul_eltfp25519_1w_bmi2(T[2], T[2], T[3]); - sqrn_eltfp25519_1w_bmi2(T[2], 5); - mul_eltfp25519_1w_bmi2(T[1], T[1], T[2]); - - memzero_explicit(&m, sizeof(m)); + u64 tmp2[16U] = { 0U }; + u64 p01_tmp1_swap[33U] = { 0U }; + u64 *p0 = p01_tmp1_swap; + u64 *p01 = p01_tmp1_swap; + u64 *p03 = p01; + u64 *p11 = p01 + (u32)8U; + u64 *x0; + u64 *z0; + u64 *p01_tmp1; + u64 *p01_tmp11; + u64 *nq10; + u64 *nq_p11; + u64 *swap1; + u64 sw0; + u64 *nq1; + u64 *tmp1; + memcpy(p11, init1, (u32)8U * sizeof(init1[0U])); + x0 = p03; + z0 = p03 + (u32)4U; + x0[0U] = (u64)1U; + x0[1U] = (u64)0U; + x0[2U] = (u64)0U; + x0[3U] = (u64)0U; + z0[0U] = (u64)0U; + z0[1U] = (u64)0U; + z0[2U] = (u64)0U; + z0[3U] = (u64)0U; + p01_tmp1 = p01_tmp1_swap; + p01_tmp11 = p01_tmp1_swap; + nq10 = p01_tmp1_swap; + nq_p11 = p01_tmp1_swap + (u32)8U; + swap1 = p01_tmp1_swap + (u32)32U; + cswap2((u64)1U, nq10, nq_p11); + point_add_and_double(init1, p01_tmp11, tmp2); + swap1[0U] = (u64)1U; + { + u32 i; + for (i = (u32)0U; i < (u32)251U; i = i + (u32)1U) { + u64 *p01_tmp12 = p01_tmp1_swap; + u64 *swap2 = p01_tmp1_swap + (u32)32U; + u64 *nq2 = p01_tmp12; + u64 *nq_p12 = p01_tmp12 + (u32)8U; + u64 bit = (u64)(key[((u32)253U - i) / (u32)8U] >> ((u32)253U - i) % (u32)8U & (u8)1U); + u64 sw = swap2[0U] ^ bit; + cswap2(sw, nq2, nq_p12); + point_add_and_double(init1, p01_tmp12, tmp2); + swap2[0U] = bit; + } + } + sw0 = swap1[0U]; + cswap2(sw0, nq10, nq_p11); + nq1 = p01_tmp1; + tmp1 = p01_tmp1 + (u32)16U; + point_double(nq1, tmp1, tmp2); + point_double(nq1, tmp1, tmp2); + point_double(nq1, tmp1, tmp2); + memcpy(out, p0, (u32)8U * sizeof(p0[0U])); + + memzero_explicit(tmp2, sizeof(tmp2)); + memzero_explicit(p01_tmp1_swap, sizeof(p01_tmp1_swap)); } -/* Given c, a 256-bit number, fred_eltfp25519_1w updates c - * with a number such that 0 <= C < 2**255-19. - */ -static __always_inline void fred_eltfp25519_1w(u64 *const c) +static void fsquare_times(u64 *o, const u64 *inp, u64 *tmp, u32 n1) { - u64 tmp0 = 38, tmp1 = 19; - asm volatile( - "btrq $63, %3 ;" /* Put bit 255 in carry flag and clear */ - "cmovncl %k5, %k4 ;" /* c[255] ? 38 : 19 */ - - /* Add either 19 or 38 to c */ - "addq %4, %0 ;" - "adcq $0, %1 ;" - "adcq $0, %2 ;" - "adcq $0, %3 ;" - - /* Test for bit 255 again; only triggered on overflow modulo 2^255-19 */ - "movl $0, %k4 ;" - "cmovnsl %k5, %k4 ;" /* c[255] ? 0 : 19 */ - "btrq $63, %3 ;" /* Clear bit 255 */ - - /* Subtract 19 if necessary */ - "subq %4, %0 ;" - "sbbq $0, %1 ;" - "sbbq $0, %2 ;" - "sbbq $0, %3 ;" - - : "+r"(c[0]), "+r"(c[1]), "+r"(c[2]), "+r"(c[3]), "+r"(tmp0), - "+r"(tmp1) - : - : "memory", "cc"); + u32 i; + fsqr(o, inp, tmp); + for (i = (u32)0U; i < n1 - (u32)1U; i = i + (u32)1U) + fsqr(o, o, tmp); } -static __always_inline void cswap(u8 bit, u64 *const px, u64 *const py) +static void finv(u64 *o, const u64 *i, u64 *tmp) { - u64 temp; - asm volatile( - "test %9, %9 ;" - "movq %0, %8 ;" - "cmovnzq %4, %0 ;" - "cmovnzq %8, %4 ;" - "movq %1, %8 ;" - "cmovnzq %5, %1 ;" - "cmovnzq %8, %5 ;" - "movq %2, %8 ;" - "cmovnzq %6, %2 ;" - "cmovnzq %8, %6 ;" - "movq %3, %8 ;" - "cmovnzq %7, %3 ;" - "cmovnzq %8, %7 ;" - : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]), - "+r"(py[0]), "+r"(py[1]), "+r"(py[2]), "+r"(py[3]), - "=r"(temp) - : "r"(bit) - : "cc" - ); + u64 t1[16U] = { 0U }; + u64 *a0 = t1; + u64 *b = t1 + (u32)4U; + u64 *c = t1 + (u32)8U; + u64 *t00 = t1 + (u32)12U; + u64 *tmp1 = tmp; + u64 *a; + u64 *t0; + fsquare_times(a0, i, tmp1, (u32)1U); + fsquare_times(t00, a0, tmp1, (u32)2U); + fmul(b, t00, i, tmp); + fmul(a0, b, a0, tmp); + fsquare_times(t00, a0, tmp1, (u32)1U); + fmul(b, t00, b, tmp); + fsquare_times(t00, b, tmp1, (u32)5U); + fmul(b, t00, b, tmp); + fsquare_times(t00, b, tmp1, (u32)10U); + fmul(c, t00, b, tmp); + fsquare_times(t00, c, tmp1, (u32)20U); + fmul(t00, t00, c, tmp); + fsquare_times(t00, t00, tmp1, (u32)10U); + fmul(b, t00, b, tmp); + fsquare_times(t00, b, tmp1, (u32)50U); + fmul(c, t00, b, tmp); + fsquare_times(t00, c, tmp1, (u32)100U); + fmul(t00, t00, c, tmp); + fsquare_times(t00, t00, tmp1, (u32)50U); + fmul(t00, t00, b, tmp); + fsquare_times(t00, t00, tmp1, (u32)5U); + a = t1; + t0 = t1 + (u32)12U; + fmul(o, t0, a, tmp); } -static __always_inline void cselect(u8 bit, u64 *const px, const u64 *const py) +static void store_felem(u64 *b, u64 *f) { - asm volatile( - "test %4, %4 ;" - "cmovnzq %5, %0 ;" - "cmovnzq %6, %1 ;" - "cmovnzq %7, %2 ;" - "cmovnzq %8, %3 ;" - : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]) - : "r"(bit), "rm"(py[0]), "rm"(py[1]), "rm"(py[2]), "rm"(py[3]) - : "cc" - ); + u64 f30 = f[3U]; + u64 top_bit0 = f30 >> (u32)63U; + u64 carry0; + u64 f31; + u64 top_bit; + u64 carry; + u64 f0; + u64 f1; + u64 f2; + u64 f3; + u64 m0; + u64 m1; + u64 m2; + u64 m3; + u64 mask; + u64 f0_; + u64 f1_; + u64 f2_; + u64 f3_; + u64 o0; + u64 o1; + u64 o2; + u64 o3; + f[3U] = f30 & (u64)0x7fffffffffffffffU; + carry0 = add_scalar(f, f, (u64)19U * top_bit0); + f31 = f[3U]; + top_bit = f31 >> (u32)63U; + f[3U] = f31 & (u64)0x7fffffffffffffffU; + carry = add_scalar(f, f, (u64)19U * top_bit); + f0 = f[0U]; + f1 = f[1U]; + f2 = f[2U]; + f3 = f[3U]; + m0 = gte_mask(f0, (u64)0xffffffffffffffedU); + m1 = eq_mask(f1, (u64)0xffffffffffffffffU); + m2 = eq_mask(f2, (u64)0xffffffffffffffffU); + m3 = eq_mask(f3, (u64)0x7fffffffffffffffU); + mask = ((m0 & m1) & m2) & m3; + f0_ = f0 - (mask & (u64)0xffffffffffffffedU); + f1_ = f1 - (mask & (u64)0xffffffffffffffffU); + f2_ = f2 - (mask & (u64)0xffffffffffffffffU); + f3_ = f3 - (mask & (u64)0x7fffffffffffffffU); + o0 = f0_; + o1 = f1_; + o2 = f2_; + o3 = f3_; + b[0U] = o0; + b[1U] = o1; + b[2U] = o2; + b[3U] = o3; } -static void curve25519_adx(u8 shared[CURVE25519_KEY_SIZE], - const u8 private_key[CURVE25519_KEY_SIZE], - const u8 session_key[CURVE25519_KEY_SIZE]) +static void encode_point(u8 *o, const u64 *i) { - struct { - u64 buffer[4 * NUM_WORDS_ELTFP25519]; - u64 coordinates[4 * NUM_WORDS_ELTFP25519]; - u64 workspace[6 * NUM_WORDS_ELTFP25519]; - u8 session[CURVE25519_KEY_SIZE]; - u8 private[CURVE25519_KEY_SIZE]; - } __aligned(32) m; - - int i = 0, j = 0; - u64 prev = 0; - u64 *const X1 = (u64 *)m.session; - u64 *const key = (u64 *)m.private; - u64 *const Px = m.coordinates + 0; - u64 *const Pz = m.coordinates + 4; - u64 *const Qx = m.coordinates + 8; - u64 *const Qz = m.coordinates + 12; - u64 *const X2 = Qx; - u64 *const Z2 = Qz; - u64 *const X3 = Px; - u64 *const Z3 = Pz; - u64 *const X2Z2 = Qx; - u64 *const X3Z3 = Px; - - u64 *const A = m.workspace + 0; - u64 *const B = m.workspace + 4; - u64 *const D = m.workspace + 8; - u64 *const C = m.workspace + 12; - u64 *const DA = m.workspace + 16; - u64 *const CB = m.workspace + 20; - u64 *const AB = A; - u64 *const DC = D; - u64 *const DACB = DA; - - memcpy(m.private, private_key, sizeof(m.private)); - memcpy(m.session, session_key, sizeof(m.session)); - - curve25519_clamp_secret(m.private); - - /* As in the draft: - * When receiving such an array, implementations of curve25519 - * MUST mask the most-significant bit in the final byte. This - * is done to preserve compatibility with point formats which - * reserve the sign bit for use in other protocols and to - * increase resistance to implementation fingerprinting - */ - m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; - - copy_eltfp25519_1w(Px, X1); - setzero_eltfp25519_1w(Pz); - setzero_eltfp25519_1w(Qx); - setzero_eltfp25519_1w(Qz); - - Pz[0] = 1; - Qx[0] = 1; - - /* main-loop */ - prev = 0; - j = 62; - for (i = 3; i >= 0; --i) { - while (j >= 0) { - u64 bit = (key[i] >> j) & 0x1; - u64 swap = bit ^ prev; - prev = bit; - - add_eltfp25519_1w_adx(A, X2, Z2); /* A = (X2+Z2) */ - sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ - add_eltfp25519_1w_adx(C, X3, Z3); /* C = (X3+Z3) */ - sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ - mul_eltfp25519_2w_adx(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ - - cselect(swap, A, C); - cselect(swap, B, D); - - sqr_eltfp25519_2w_adx(AB); /* [AA|BB] = [A^2|B^2] */ - add_eltfp25519_1w_adx(X3, DA, CB); /* X3 = (DA+CB) */ - sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ - sqr_eltfp25519_2w_adx(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ - - copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ - sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ - - mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ - add_eltfp25519_1w_adx(B, B, X2); /* B = a24*E+B */ - mul_eltfp25519_2w_adx(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ - mul_eltfp25519_1w_adx(Z3, Z3, X1); /* Z3 = Z3*X1 */ - --j; - } - j = 63; - } - - inv_eltfp25519_1w_adx(A, Qz); - mul_eltfp25519_1w_adx((u64 *)shared, Qx, A); - fred_eltfp25519_1w((u64 *)shared); - - memzero_explicit(&m, sizeof(m)); + const u64 *x = i; + const u64 *z = i + (u32)4U; + u64 tmp[4U] = { 0U }; + u64 tmp_w[16U] = { 0U }; + finv(tmp, z, tmp_w); + fmul(tmp, tmp, x, tmp_w); + store_felem((u64 *)o, tmp); } -static void curve25519_adx_base(u8 session_key[CURVE25519_KEY_SIZE], - const u8 private_key[CURVE25519_KEY_SIZE]) +static void curve25519_ever64(u8 *out, const u8 *priv, const u8 *pub) { - struct { - u64 buffer[4 * NUM_WORDS_ELTFP25519]; - u64 coordinates[4 * NUM_WORDS_ELTFP25519]; - u64 workspace[4 * NUM_WORDS_ELTFP25519]; - u8 private[CURVE25519_KEY_SIZE]; - } __aligned(32) m; - - const int ite[4] = { 64, 64, 64, 63 }; - const int q = 3; - u64 swap = 1; - - int i = 0, j = 0, k = 0; - u64 *const key = (u64 *)m.private; - u64 *const Ur1 = m.coordinates + 0; - u64 *const Zr1 = m.coordinates + 4; - u64 *const Ur2 = m.coordinates + 8; - u64 *const Zr2 = m.coordinates + 12; - - u64 *const UZr1 = m.coordinates + 0; - u64 *const ZUr2 = m.coordinates + 8; - - u64 *const A = m.workspace + 0; - u64 *const B = m.workspace + 4; - u64 *const C = m.workspace + 8; - u64 *const D = m.workspace + 12; - - u64 *const AB = m.workspace + 0; - u64 *const CD = m.workspace + 8; - - const u64 *const P = table_ladder_8k; - - memcpy(m.private, private_key, sizeof(m.private)); - - curve25519_clamp_secret(m.private); - - setzero_eltfp25519_1w(Ur1); - setzero_eltfp25519_1w(Zr1); - setzero_eltfp25519_1w(Zr2); - Ur1[0] = 1; - Zr1[0] = 1; - Zr2[0] = 1; - - /* G-S */ - Ur2[3] = 0x1eaecdeee27cab34UL; - Ur2[2] = 0xadc7a0b9235d48e2UL; - Ur2[1] = 0xbbf095ae14b2edf8UL; - Ur2[0] = 0x7e94e1fec82faabdUL; - - /* main-loop */ - j = q; - for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { - while (j < ite[i]) { - u64 bit = (key[i] >> j) & 0x1; - k = (64 * i + j - q); - swap = swap ^ bit; - cswap(swap, Ur1, Ur2); - cswap(swap, Zr1, Zr2); - swap = bit; - /* Addition */ - sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ - add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ - mul_eltfp25519_1w_adx(C, &P[4 * k], B); /* C = M0-B */ - sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ - add_eltfp25519_1w_adx(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ - sqr_eltfp25519_2w_adx(AB); /* A = A^2 | B = B^2 */ - mul_eltfp25519_2w_adx(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ - ++j; + u64 init1[8U] = { 0U }; + u64 tmp[4U] = { 0U }; + u64 tmp3; + u64 *x; + u64 *z; + { + u32 i; + for (i = (u32)0U; i < (u32)4U; i = i + (u32)1U) { + u64 *os = tmp; + const u8 *bj = pub + i * (u32)8U; + u64 u = *(u64 *)bj; + u64 r = u; + u64 x0 = r; + os[i] = x0; } - j = 0; } - - /* Doubling */ - for (i = 0; i < q; ++i) { - add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ - sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ - sqr_eltfp25519_2w_adx(AB); /* A = A**2 B = B**2 */ - copy_eltfp25519_1w(C, B); /* C = B */ - sub_eltfp25519_1w(B, A, B); /* B = A-B */ - mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ - add_eltfp25519_1w_adx(D, D, C); /* D = D+C */ - mul_eltfp25519_2w_adx(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ - } - - /* Convert to affine coordinates */ - inv_eltfp25519_1w_adx(A, Zr1); - mul_eltfp25519_1w_adx((u64 *)session_key, Ur1, A); - fred_eltfp25519_1w((u64 *)session_key); - - memzero_explicit(&m, sizeof(m)); + tmp3 = tmp[3U]; + tmp[3U] = tmp3 & (u64)0x7fffffffffffffffU; + x = init1; + z = init1 + (u32)4U; + z[0U] = (u64)1U; + z[1U] = (u64)0U; + z[2U] = (u64)0U; + z[3U] = (u64)0U; + x[0U] = tmp[0U]; + x[1U] = tmp[1U]; + x[2U] = tmp[2U]; + x[3U] = tmp[3U]; + montgomery_ladder(init1, priv, init1); + encode_point(out, init1); } -static void curve25519_bmi2(u8 shared[CURVE25519_KEY_SIZE], - const u8 private_key[CURVE25519_KEY_SIZE], - const u8 session_key[CURVE25519_KEY_SIZE]) -{ - struct { - u64 buffer[4 * NUM_WORDS_ELTFP25519]; - u64 coordinates[4 * NUM_WORDS_ELTFP25519]; - u64 workspace[6 * NUM_WORDS_ELTFP25519]; - u8 session[CURVE25519_KEY_SIZE]; - u8 private[CURVE25519_KEY_SIZE]; - } __aligned(32) m; - - int i = 0, j = 0; - u64 prev = 0; - u64 *const X1 = (u64 *)m.session; - u64 *const key = (u64 *)m.private; - u64 *const Px = m.coordinates + 0; - u64 *const Pz = m.coordinates + 4; - u64 *const Qx = m.coordinates + 8; - u64 *const Qz = m.coordinates + 12; - u64 *const X2 = Qx; - u64 *const Z2 = Qz; - u64 *const X3 = Px; - u64 *const Z3 = Pz; - u64 *const X2Z2 = Qx; - u64 *const X3Z3 = Px; - - u64 *const A = m.workspace + 0; - u64 *const B = m.workspace + 4; - u64 *const D = m.workspace + 8; - u64 *const C = m.workspace + 12; - u64 *const DA = m.workspace + 16; - u64 *const CB = m.workspace + 20; - u64 *const AB = A; - u64 *const DC = D; - u64 *const DACB = DA; - - memcpy(m.private, private_key, sizeof(m.private)); - memcpy(m.session, session_key, sizeof(m.session)); - - curve25519_clamp_secret(m.private); - - /* As in the draft: - * When receiving such an array, implementations of curve25519 - * MUST mask the most-significant bit in the final byte. This - * is done to preserve compatibility with point formats which - * reserve the sign bit for use in other protocols and to - * increase resistance to implementation fingerprinting - */ - m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; - - copy_eltfp25519_1w(Px, X1); - setzero_eltfp25519_1w(Pz); - setzero_eltfp25519_1w(Qx); - setzero_eltfp25519_1w(Qz); - - Pz[0] = 1; - Qx[0] = 1; - - /* main-loop */ - prev = 0; - j = 62; - for (i = 3; i >= 0; --i) { - while (j >= 0) { - u64 bit = (key[i] >> j) & 0x1; - u64 swap = bit ^ prev; - prev = bit; - - add_eltfp25519_1w_bmi2(A, X2, Z2); /* A = (X2+Z2) */ - sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ - add_eltfp25519_1w_bmi2(C, X3, Z3); /* C = (X3+Z3) */ - sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ - mul_eltfp25519_2w_bmi2(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ - - cselect(swap, A, C); - cselect(swap, B, D); - - sqr_eltfp25519_2w_bmi2(AB); /* [AA|BB] = [A^2|B^2] */ - add_eltfp25519_1w_bmi2(X3, DA, CB); /* X3 = (DA+CB) */ - sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ - sqr_eltfp25519_2w_bmi2(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ - - copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ - sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ - - mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ - add_eltfp25519_1w_bmi2(B, B, X2); /* B = a24*E+B */ - mul_eltfp25519_2w_bmi2(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ - mul_eltfp25519_1w_bmi2(Z3, Z3, X1); /* Z3 = Z3*X1 */ - --j; - } - j = 63; - } - - inv_eltfp25519_1w_bmi2(A, Qz); - mul_eltfp25519_1w_bmi2((u64 *)shared, Qx, A); - fred_eltfp25519_1w((u64 *)shared); +/* The below constants were generated using this sage script: + * + * #!/usr/bin/env sage + * import sys + * from sage.all import * + * def limbs(n): + * n = int(n) + * l = ((n >> 0) % 2^64, (n >> 64) % 2^64, (n >> 128) % 2^64, (n >> 192) % 2^64) + * return "0x%016xULL, 0x%016xULL, 0x%016xULL, 0x%016xULL" % l + * ec = EllipticCurve(GF(2^255 - 19), [0, 486662, 0, 1, 0]) + * p_minus_s = (ec.lift_x(9) - ec.lift_x(1))[0] + * print("static const u64 p_minus_s[] = { %s };\n" % limbs(p_minus_s)) + * print("static const u64 table_ladder[] = {") + * p = ec.lift_x(9) + * for i in range(252): + * l = (p[0] + p[2]) / (p[0] - p[2]) + * print(("\t%s" + ("," if i != 251 else "")) % limbs(l)) + * p = p * 2 + * print("};") + * + */ - memzero_explicit(&m, sizeof(m)); -} +static const u64 p_minus_s[] = { 0x816b1e0137d48290ULL, 0x440f6a51eb4d1207ULL, 0x52385f46dca2b71dULL, 0x215132111d8354cbULL }; + +static const u64 table_ladder[] = { + 0xfffffffffffffff3ULL, 0xffffffffffffffffULL, 0xffffffffffffffffULL, 0x5fffffffffffffffULL, + 0x6b8220f416aafe96ULL, 0x82ebeb2b4f566a34ULL, 0xd5a9a5b075a5950fULL, 0x5142b2cf4b2488f4ULL, + 0x6aaebc750069680cULL, 0x89cf7820a0f99c41ULL, 0x2a58d9183b56d0f4ULL, 0x4b5aca80e36011a4ULL, + 0x329132348c29745dULL, 0xf4a2e616e1642fd7ULL, 0x1e45bb03ff67bc34ULL, 0x306912d0f42a9b4aULL, + 0xff886507e6af7154ULL, 0x04f50e13dfeec82fULL, 0xaa512fe82abab5ceULL, 0x174e251a68d5f222ULL, + 0xcf96700d82028898ULL, 0x1743e3370a2c02c5ULL, 0x379eec98b4e86eaaULL, 0x0c59888a51e0482eULL, + 0xfbcbf1d699b5d189ULL, 0xacaef0d58e9fdc84ULL, 0xc1c20d06231f7614ULL, 0x2938218da274f972ULL, + 0xf6af49beff1d7f18ULL, 0xcc541c22387ac9c2ULL, 0x96fcc9ef4015c56bULL, 0x69c1627c690913a9ULL, + 0x7a86fd2f4733db0eULL, 0xfdb8c4f29e087de9ULL, 0x095e4b1a8ea2a229ULL, 0x1ad7a7c829b37a79ULL, + 0x342d89cad17ea0c0ULL, 0x67bedda6cced2051ULL, 0x19ca31bf2bb42f74ULL, 0x3df7b4c84980acbbULL, + 0xa8c6444dc80ad883ULL, 0xb91e440366e3ab85ULL, 0xc215cda00164f6d8ULL, 0x3d867c6ef247e668ULL, + 0xc7dd582bcc3e658cULL, 0xfd2c4748ee0e5528ULL, 0xa0fd9b95cc9f4f71ULL, 0x7529d871b0675ddfULL, + 0xb8f568b42d3cbd78ULL, 0x1233011b91f3da82ULL, 0x2dce6ccd4a7c3b62ULL, 0x75e7fc8e9e498603ULL, + 0x2f4f13f1fcd0b6ecULL, 0xf1a8ca1f29ff7a45ULL, 0xc249c1a72981e29bULL, 0x6ebe0dbb8c83b56aULL, + 0x7114fa8d170bb222ULL, 0x65a2dcd5bf93935fULL, 0xbdc41f68b59c979aULL, 0x2f0eef79a2ce9289ULL, + 0x42ecbf0c083c37ceULL, 0x2930bc09ec496322ULL, 0xf294b0c19cfeac0dULL, 0x3780aa4bedfabb80ULL, + 0x56c17d3e7cead929ULL, 0xe7cb4beb2e5722c5ULL, 0x0ce931732dbfe15aULL, 0x41b883c7621052f8ULL, + 0xdbf75ca0c3d25350ULL, 0x2936be086eb1e351ULL, 0xc936e03cb4a9b212ULL, 0x1d45bf82322225aaULL, + 0xe81ab1036a024cc5ULL, 0xe212201c304c9a72ULL, 0xc5d73fba6832b1fcULL, 0x20ffdb5a4d839581ULL, + 0xa283d367be5d0fadULL, 0x6c2b25ca8b164475ULL, 0x9d4935467caaf22eULL, 0x5166408eee85ff49ULL, + 0x3c67baa2fab4e361ULL, 0xb3e433c67ef35cefULL, 0x5259729241159b1cULL, 0x6a621892d5b0ab33ULL, + 0x20b74a387555cdcbULL, 0x532aa10e1208923fULL, 0xeaa17b7762281dd1ULL, 0x61ab3443f05c44bfULL, + 0x257a6c422324def8ULL, 0x131c6c1017e3cf7fULL, 0x23758739f630a257ULL, 0x295a407a01a78580ULL, + 0xf8c443246d5da8d9ULL, 0x19d775450c52fa5dULL, 0x2afcfc92731bf83dULL, 0x7d10c8e81b2b4700ULL, + 0xc8e0271f70baa20bULL, 0x993748867ca63957ULL, 0x5412efb3cb7ed4bbULL, 0x3196d36173e62975ULL, + 0xde5bcad141c7dffcULL, 0x47cc8cd2b395c848ULL, 0xa34cd942e11af3cbULL, 0x0256dbf2d04ecec2ULL, + 0x875ab7e94b0e667fULL, 0xcad4dd83c0850d10ULL, 0x47f12e8f4e72c79fULL, 0x5f1a87bb8c85b19bULL, + 0x7ae9d0b6437f51b8ULL, 0x12c7ce5518879065ULL, 0x2ade09fe5cf77aeeULL, 0x23a05a2f7d2c5627ULL, + 0x5908e128f17c169aULL, 0xf77498dd8ad0852dULL, 0x74b4c4ceab102f64ULL, 0x183abadd10139845ULL, + 0xb165ba8daa92aaacULL, 0xd5c5ef9599386705ULL, 0xbe2f8f0cf8fc40d1ULL, 0x2701e635ee204514ULL, + 0x629fa80020156514ULL, 0xf223868764a8c1ceULL, 0x5b894fff0b3f060eULL, 0x60d9944cf708a3faULL, + 0xaeea001a1c7a201fULL, 0xebf16a633ee2ce63ULL, 0x6f7709594c7a07e1ULL, 0x79b958150d0208cbULL, + 0x24b55e5301d410e7ULL, 0xe3a34edff3fdc84dULL, 0xd88768e4904032d8ULL, 0x131384427b3aaeecULL, + 0x8405e51286234f14ULL, 0x14dc4739adb4c529ULL, 0xb8a2b5b250634ffdULL, 0x2fe2a94ad8a7ff93ULL, + 0xec5c57efe843faddULL, 0x2843ce40f0bb9918ULL, 0xa4b561d6cf3d6305ULL, 0x743629bde8fb777eULL, + 0x343edd46bbaf738fULL, 0xed981828b101a651ULL, 0xa401760b882c797aULL, 0x1fc223e28dc88730ULL, + 0x48604e91fc0fba0eULL, 0xb637f78f052c6fa4ULL, 0x91ccac3d09e9239cULL, 0x23f7eed4437a687cULL, + 0x5173b1118d9bd800ULL, 0x29d641b63189d4a7ULL, 0xfdbf177988bbc586ULL, 0x2959894fcad81df5ULL, + 0xaebc8ef3b4bbc899ULL, 0x4148995ab26992b9ULL, 0x24e20b0134f92cfbULL, 0x40d158894a05dee8ULL, + 0x46b00b1185af76f6ULL, 0x26bac77873187a79ULL, 0x3dc0bf95ab8fff5fULL, 0x2a608bd8945524d7ULL, + 0x26449588bd446302ULL, 0x7c4bc21c0388439cULL, 0x8e98a4f383bd11b2ULL, 0x26218d7bc9d876b9ULL, + 0xe3081542997c178aULL, 0x3c2d29a86fb6606fULL, 0x5c217736fa279374ULL, 0x7dde05734afeb1faULL, + 0x3bf10e3906d42babULL, 0xe4f7803e1980649cULL, 0xe6053bf89595bf7aULL, 0x394faf38da245530ULL, + 0x7a8efb58896928f4ULL, 0xfbc778e9cc6a113cULL, 0x72670ce330af596fULL, 0x48f222a81d3d6cf7ULL, + 0xf01fce410d72caa7ULL, 0x5a20ecc7213b5595ULL, 0x7bc21165c1fa1483ULL, 0x07f89ae31da8a741ULL, + 0x05d2c2b4c6830ff9ULL, 0xd43e330fc6316293ULL, 0xa5a5590a96d3a904ULL, 0x705edb91a65333b6ULL, + 0x048ee15e0bb9a5f7ULL, 0x3240cfca9e0aaf5dULL, 0x8f4b71ceedc4a40bULL, 0x621c0da3de544a6dULL, + 0x92872836a08c4091ULL, 0xce8375b010c91445ULL, 0x8a72eb524f276394ULL, 0x2667fcfa7ec83635ULL, + 0x7f4c173345e8752aULL, 0x061b47feee7079a5ULL, 0x25dd9afa9f86ff34ULL, 0x3780cef5425dc89cULL, + 0x1a46035a513bb4e9ULL, 0x3e1ef379ac575adaULL, 0xc78c5f1c5fa24b50ULL, 0x321a967634fd9f22ULL, + 0x946707b8826e27faULL, 0x3dca84d64c506fd0ULL, 0xc189218075e91436ULL, 0x6d9284169b3b8484ULL, + 0x3a67e840383f2ddfULL, 0x33eec9a30c4f9b75ULL, 0x3ec7c86fa783ef47ULL, 0x26ec449fbac9fbc4ULL, + 0x5c0f38cba09b9e7dULL, 0x81168cc762a3478cULL, 0x3e23b0d306fc121cULL, 0x5a238aa0a5efdcddULL, + 0x1ba26121c4ea43ffULL, 0x36f8c77f7c8832b5ULL, 0x88fbea0b0adcf99aULL, 0x5ca9938ec25bebf9ULL, + 0xd5436a5e51fccda0ULL, 0x1dbc4797c2cd893bULL, 0x19346a65d3224a08ULL, 0x0f5034e49b9af466ULL, + 0xf23c3967a1e0b96eULL, 0xe58b08fa867a4d88ULL, 0xfb2fabc6a7341679ULL, 0x2a75381eb6026946ULL, + 0xc80a3be4c19420acULL, 0x66b1f6c681f2b6dcULL, 0x7cf7036761e93388ULL, 0x25abbbd8a660a4c4ULL, + 0x91ea12ba14fd5198ULL, 0x684950fc4a3cffa9ULL, 0xf826842130f5ad28ULL, 0x3ea988f75301a441ULL, + 0xc978109a695f8c6fULL, 0x1746eb4a0530c3f3ULL, 0x444d6d77b4459995ULL, 0x75952b8c054e5cc7ULL, + 0xa3703f7915f4d6aaULL, 0x66c346202f2647d8ULL, 0xd01469df811d644bULL, 0x77fea47d81a5d71fULL, + 0xc5e9529ef57ca381ULL, 0x6eeeb4b9ce2f881aULL, 0xb6e91a28e8009bd6ULL, 0x4b80be3e9afc3fecULL, + 0x7e3773c526aed2c5ULL, 0x1b4afcb453c9a49dULL, 0xa920bdd7baffb24dULL, 0x7c54699f122d400eULL, + 0xef46c8e14fa94bc8ULL, 0xe0b074ce2952ed5eULL, 0xbea450e1dbd885d5ULL, 0x61b68649320f712cULL, + 0x8a485f7309ccbdd1ULL, 0xbd06320d7d4d1a2dULL, 0x25232973322dbef4ULL, 0x445dc4758c17f770ULL, + 0xdb0434177cc8933cULL, 0xed6fe82175ea059fULL, 0x1efebefdc053db34ULL, 0x4adbe867c65daf99ULL, + 0x3acd71a2a90609dfULL, 0xe5e991856dd04050ULL, 0x1ec69b688157c23cULL, 0x697427f6885cfe4dULL, + 0xd7be7b9b65e1a851ULL, 0xa03d28d522c536ddULL, 0x28399d658fd2b645ULL, 0x49e5b7e17c2641e1ULL, + 0x6f8c3a98700457a4ULL, 0x5078f0a25ebb6778ULL, 0xd13c3ccbc382960fULL, 0x2e003258a7df84b1ULL, + 0x8ad1f39be6296a1cULL, 0xc1eeaa652a5fbfb2ULL, 0x33ee0673fd26f3cbULL, 0x59256173a69d2cccULL, + 0x41ea07aa4e18fc41ULL, 0xd9fc19527c87a51eULL, 0xbdaacb805831ca6fULL, 0x445b652dc916694fULL, + 0xce92a3a7f2172315ULL, 0x1edc282de11b9964ULL, 0xa1823aafe04c314aULL, 0x790a2d94437cf586ULL, + 0x71c447fb93f6e009ULL, 0x8922a56722845276ULL, 0xbf70903b204f5169ULL, 0x2f7a89891ba319feULL, + 0x02a08eb577e2140cULL, 0xed9a4ed4427bdcf4ULL, 0x5253ec44e4323cd1ULL, 0x3e88363c14e9355bULL, + 0xaa66c14277110b8cULL, 0x1ae0391610a23390ULL, 0x2030bd12c93fc2a2ULL, 0x3ee141579555c7abULL, + 0x9214de3a6d6e7d41ULL, 0x3ccdd88607f17efeULL, 0x674f1288f8e11217ULL, 0x5682250f329f93d0ULL, + 0x6cf00b136d2e396eULL, 0x6e4cf86f1014debfULL, 0x5930b1b5bfcc4e83ULL, 0x047069b48aba16b6ULL, + 0x0d4ce4ab69b20793ULL, 0xb24db91a97d0fb9eULL, 0xcdfa50f54e00d01dULL, 0x221b1085368bddb5ULL, + 0xe7e59468b1e3d8d2ULL, 0x53c56563bd122f93ULL, 0xeee8a903e0663f09ULL, 0x61efa662cbbe3d42ULL, + 0x2cf8ddddde6eab2aULL, 0x9bf80ad51435f231ULL, 0x5deadacec9f04973ULL, 0x29275b5d41d29b27ULL, + 0xcfde0f0895ebf14fULL, 0xb9aab96b054905a7ULL, 0xcae80dd9a1c420fdULL, 0x0a63bf2f1673bbc7ULL, + 0x092f6e11958fbc8cULL, 0x672a81e804822fadULL, 0xcac8351560d52517ULL, 0x6f3f7722c8f192f8ULL, + 0xf8ba90ccc2e894b7ULL, 0x2c7557a438ff9f0dULL, 0x894d1d855ae52359ULL, 0x68e122157b743d69ULL, + 0xd87e5570cfb919f3ULL, 0x3f2cdecd95798db9ULL, 0x2121154710c0a2ceULL, 0x3c66a115246dc5b2ULL, + 0xcbedc562294ecb72ULL, 0xba7143c36a280b16ULL, 0x9610c2efd4078b67ULL, 0x6144735d946a4b1eULL, + 0x536f111ed75b3350ULL, 0x0211db8c2041d81bULL, 0xf93cb1000e10413cULL, 0x149dfd3c039e8876ULL, + 0xd479dde46b63155bULL, 0xb66e15e93c837976ULL, 0xdafde43b1f13e038ULL, 0x5fafda1a2e4b0b35ULL, + 0x3600bbdf17197581ULL, 0x3972050bbe3cd2c2ULL, 0x5938906dbdd5be86ULL, 0x34fce5e43f9b860fULL, + 0x75a8a4cd42d14d02ULL, 0x828dabc53441df65ULL, 0x33dcabedd2e131d3ULL, 0x3ebad76fb814d25fULL, + 0xd4906f566f70e10fULL, 0x5d12f7aa51690f5aULL, 0x45adb16e76cefcf2ULL, 0x01f768aead232999ULL, + 0x2b6cc77b6248febdULL, 0x3cd30628ec3aaffdULL, 0xce1c0b80d4ef486aULL, 0x4c3bff2ea6f66c23ULL, + 0x3f2ec4094aeaeb5fULL, 0x61b19b286e372ca7ULL, 0x5eefa966de2a701dULL, 0x23b20565de55e3efULL, + 0xe301ca5279d58557ULL, 0x07b2d4ce27c2874fULL, 0xa532cd8a9dcf1d67ULL, 0x2a52fee23f2bff56ULL, + 0x8624efb37cd8663dULL, 0xbbc7ac20ffbd7594ULL, 0x57b85e9c82d37445ULL, 0x7b3052cb86a6ec66ULL, + 0x3482f0ad2525e91eULL, 0x2cb68043d28edca0ULL, 0xaf4f6d052e1b003aULL, 0x185f8c2529781b0aULL, + 0xaa41de5bd80ce0d6ULL, 0x9407b2416853e9d6ULL, 0x563ec36e357f4c3aULL, 0x4cc4b8dd0e297bceULL, + 0xa2fc1a52ffb8730eULL, 0x1811f16e67058e37ULL, 0x10f9a366cddf4ee1ULL, 0x72f4a0c4a0b9f099ULL, + 0x8c16c06f663f4ea7ULL, 0x693b3af74e970fbaULL, 0x2102e7f1d69ec345ULL, 0x0ba53cbc968a8089ULL, + 0xca3d9dc7fea15537ULL, 0x4c6824bb51536493ULL, 0xb9886314844006b1ULL, 0x40d2a72ab454cc60ULL, + 0x5936a1b712570975ULL, 0x91b9d648debda657ULL, 0x3344094bb64330eaULL, 0x006ba10d12ee51d0ULL, + 0x19228468f5de5d58ULL, 0x0eb12f4c38cc05b0ULL, 0xa1039f9dd5601990ULL, 0x4502d4ce4fff0e0bULL, + 0xeb2054106837c189ULL, 0xd0f6544c6dd3b93cULL, 0x40727064c416d74fULL, 0x6e15c6114b502ef0ULL, + 0x4df2a398cfb1a76bULL, 0x11256c7419f2f6b1ULL, 0x4a497962066e6043ULL, 0x705b3aab41355b44ULL, + 0x365ef536d797b1d8ULL, 0x00076bd622ddf0dbULL, 0x3bbf33b0e0575a88ULL, 0x3777aa05c8e4ca4dULL, + 0x392745c85578db5fULL, 0x6fda4149dbae5ae2ULL, 0xb1f0b00b8adc9867ULL, 0x09963437d36f1da3ULL, + 0x7e824e90a5dc3853ULL, 0xccb5f6641f135cbdULL, 0x6736d86c87ce8fccULL, 0x625f3ce26604249fULL, + 0xaf8ac8059502f63fULL, 0x0c05e70a2e351469ULL, 0x35292e9c764b6305ULL, 0x1a394360c7e23ac3ULL, + 0xd5c6d53251183264ULL, 0x62065abd43c2b74fULL, 0xb5fbf5d03b973f9bULL, 0x13a3da3661206e5eULL, + 0xc6bd5837725d94e5ULL, 0x18e30912205016c5ULL, 0x2088ce1570033c68ULL, 0x7fba1f495c837987ULL, + 0x5a8c7423f2f9079dULL, 0x1735157b34023fc5ULL, 0xe4f9b49ad2fab351ULL, 0x6691ff72c878e33cULL, + 0x122c2adedc5eff3eULL, 0xf8dd4bf1d8956cf4ULL, 0xeb86205d9e9e5bdaULL, 0x049b92b9d975c743ULL, + 0xa5379730b0f6c05aULL, 0x72a0ffacc6f3a553ULL, 0xb0032c34b20dcd6dULL, 0x470e9dbc88d5164aULL, + 0xb19cf10ca237c047ULL, 0xb65466711f6c81a2ULL, 0xb3321bd16dd80b43ULL, 0x48c14f600c5fbe8eULL, + 0x66451c264aa6c803ULL, 0xb66e3904a4fa7da6ULL, 0xd45f19b0b3128395ULL, 0x31602627c3c9bc10ULL, + 0x3120dc4832e4e10dULL, 0xeb20c46756c717f7ULL, 0x00f52e3f67280294ULL, 0x566d4fc14730c509ULL, + 0x7e3a5d40fd837206ULL, 0xc1e926dc7159547aULL, 0x216730fba68d6095ULL, 0x22e8c3843f69cea7ULL, + 0x33d074e8930e4b2bULL, 0xb6e4350e84d15816ULL, 0x5534c26ad6ba2365ULL, 0x7773c12f89f1f3f3ULL, + 0x8cba404da57962aaULL, 0x5b9897a81999ce56ULL, 0x508e862f121692fcULL, 0x3a81907fa093c291ULL, + 0x0dded0ff4725a510ULL, 0x10d8cc10673fc503ULL, 0x5b9d151c9f1f4e89ULL, 0x32a5c1d5cb09a44cULL, + 0x1e0aa442b90541fbULL, 0x5f85eb7cc1b485dbULL, 0xbee595ce8a9df2e5ULL, 0x25e496c722422236ULL, + 0x5edf3c46cd0fe5b9ULL, 0x34e75a7ed2a43388ULL, 0xe488de11d761e352ULL, 0x0e878a01a085545cULL, + 0xba493c77e021bb04ULL, 0x2b4d1843c7df899aULL, 0x9ea37a487ae80d67ULL, 0x67a9958011e41794ULL, + 0x4b58051a6697b065ULL, 0x47e33f7d8d6ba6d4ULL, 0xbb4da8d483ca46c1ULL, 0x68becaa181c2db0dULL, + 0x8d8980e90b989aa5ULL, 0xf95eb14a2c93c99bULL, 0x51c6c7c4796e73a2ULL, 0x6e228363b5efb569ULL, + 0xc6bbc0b02dd624c8ULL, 0x777eb47dec8170eeULL, 0x3cde15a004cfafa9ULL, 0x1dc6bc087160bf9bULL, + 0x2e07e043eec34002ULL, 0x18e9fc677a68dc7fULL, 0xd8da03188bd15b9aULL, 0x48fbc3bb00568253ULL, + 0x57547d4cfb654ce1ULL, 0xd3565b82a058e2adULL, 0xf63eaf0bbf154478ULL, 0x47531ef114dfbb18ULL, + 0xe1ec630a4278c587ULL, 0x5507d546ca8e83f3ULL, 0x85e135c63adc0c2bULL, 0x0aa7efa85682844eULL, + 0x72691ba8b3e1f615ULL, 0x32b4e9701fbe3ffaULL, 0x97b6d92e39bb7868ULL, 0x2cfe53dea02e39e8ULL, + 0x687392cd85cd52b0ULL, 0x27ff66c910e29831ULL, 0x97134556a9832d06ULL, 0x269bb0360a84f8a0ULL, + 0x706e55457643f85cULL, 0x3734a48c9b597d1bULL, 0x7aee91e8c6efa472ULL, 0x5cd6abc198a9d9e0ULL, + 0x0e04de06cb3ce41aULL, 0xd8c6eb893402e138ULL, 0x904659bb686e3772ULL, 0x7215c371746ba8c8ULL, + 0xfd12a97eeae4a2d9ULL, 0x9514b7516394f2c5ULL, 0x266fd5809208f294ULL, 0x5c847085619a26b9ULL, + 0x52985410fed694eaULL, 0x3c905b934a2ed254ULL, 0x10bb47692d3be467ULL, 0x063b3d2d69e5e9e1ULL, + 0x472726eedda57debULL, 0xefb6c4ae10f41891ULL, 0x2b1641917b307614ULL, 0x117c554fc4f45b7cULL, + 0xc07cf3118f9d8812ULL, 0x01dbd82050017939ULL, 0xd7e803f4171b2827ULL, 0x1015e87487d225eaULL, + 0xc58de3fed23acc4dULL, 0x50db91c294a7be2dULL, 0x0b94d43d1c9cf457ULL, 0x6b1640fa6e37524aULL, + 0x692f346c5fda0d09ULL, 0x200b1c59fa4d3151ULL, 0xb8c46f760777a296ULL, 0x4b38395f3ffdfbcfULL, + 0x18d25e00be54d671ULL, 0x60d50582bec8aba6ULL, 0x87ad8f263b78b982ULL, 0x50fdf64e9cda0432ULL, + 0x90f567aac578dcf0ULL, 0xef1e9b0ef2a3133bULL, 0x0eebba9242d9de71ULL, 0x15473c9bf03101c7ULL, + 0x7c77e8ae56b78095ULL, 0xb678e7666e6f078eULL, 0x2da0b9615348ba1fULL, 0x7cf931c1ff733f0bULL, + 0x26b357f50a0a366cULL, 0xe9708cf42b87d732ULL, 0xc13aeea5f91cb2c0ULL, 0x35d90c991143bb4cULL, + 0x47c1c404a9a0d9dcULL, 0x659e58451972d251ULL, 0x3875a8c473b38c31ULL, 0x1fbd9ed379561f24ULL, + 0x11fabc6fd41ec28dULL, 0x7ef8dfe3cd2a2dcaULL, 0x72e73b5d8c404595ULL, 0x6135fa4954b72f27ULL, + 0xccfc32a2de24b69cULL, 0x3f55698c1f095d88ULL, 0xbe3350ed5ac3f929ULL, 0x5e9bf806ca477eebULL, + 0xe9ce8fb63c309f68ULL, 0x5376f63565e1f9f4ULL, 0xd1afcfb35a6393f1ULL, 0x6632a1ede5623506ULL, + 0x0b7d6c390c2ded4cULL, 0x56cb3281df04cb1fULL, 0x66305a1249ecc3c7ULL, 0x5d588b60a38ca72aULL, + 0xa6ecbf78e8e5f42dULL, 0x86eeb44b3c8a3eecULL, 0xec219c48fbd21604ULL, 0x1aaf1af517c36731ULL, + 0xc306a2836769bde7ULL, 0x208280622b1e2adbULL, 0x8027f51ffbff94a6ULL, 0x76cfa1ce1124f26bULL, + 0x18eb00562422abb6ULL, 0xf377c4d58f8c29c3ULL, 0x4dbbc207f531561aULL, 0x0253b7f082128a27ULL, + 0x3d1f091cb62c17e0ULL, 0x4860e1abd64628a9ULL, 0x52d17436309d4253ULL, 0x356f97e13efae576ULL, + 0xd351e11aa150535bULL, 0x3e6b45bb1dd878ccULL, 0x0c776128bed92c98ULL, 0x1d34ae93032885b8ULL, + 0x4ba0488ca85ba4c3ULL, 0x985348c33c9ce6ceULL, 0x66124c6f97bda770ULL, 0x0f81a0290654124aULL, + 0x9ed09ca6569b86fdULL, 0x811009fd18af9a2dULL, 0xff08d03f93d8c20aULL, 0x52a148199faef26bULL, + 0x3e03f9dc2d8d1b73ULL, 0x4205801873961a70ULL, 0xc0d987f041a35970ULL, 0x07aa1f15a1c0d549ULL, + 0xdfd46ce08cd27224ULL, 0x6d0a024f934e4239ULL, 0x808a7a6399897b59ULL, 0x0a4556e9e13d95a2ULL, + 0xd21a991fe9c13045ULL, 0x9b0e8548fe7751b8ULL, 0x5da643cb4bf30035ULL, 0x77db28d63940f721ULL, + 0xfc5eeb614adc9011ULL, 0x5229419ae8c411ebULL, 0x9ec3e7787d1dcf74ULL, 0x340d053e216e4cb5ULL, + 0xcac7af39b48df2b4ULL, 0xc0faec2871a10a94ULL, 0x140a69245ca575edULL, 0x0cf1c37134273a4cULL, + 0xc8ee306ac224b8a5ULL, 0x57eaee7ccb4930b0ULL, 0xa1e806bdaacbe74fULL, 0x7d9a62742eeb657dULL, + 0x9eb6b6ef546c4830ULL, 0x885cca1fddb36e2eULL, 0xe6b9f383ef0d7105ULL, 0x58654fef9d2e0412ULL, + 0xa905c4ffbe0e8e26ULL, 0x942de5df9b31816eULL, 0x497d723f802e88e1ULL, 0x30684dea602f408dULL, + 0x21e5a278a3e6cb34ULL, 0xaefb6e6f5b151dc4ULL, 0xb30b8e049d77ca15ULL, 0x28c3c9cf53b98981ULL, + 0x287fb721556cdd2aULL, 0x0d317ca897022274ULL, 0x7468c7423a543258ULL, 0x4a7f11464eb5642fULL, + 0xa237a4774d193aa6ULL, 0xd865986ea92129a1ULL, 0x24c515ecf87c1a88ULL, 0x604003575f39f5ebULL, + 0x47b9f189570a9b27ULL, 0x2b98cede465e4b78ULL, 0x026df551dbb85c20ULL, 0x74fcd91047e21901ULL, + 0x13e2a90a23c1bfa3ULL, 0x0cb0074e478519f6ULL, 0x5ff1cbbe3af6cf44ULL, 0x67fe5438be812dbeULL, + 0xd13cf64fa40f05b0ULL, 0x054dfb2f32283787ULL, 0x4173915b7f0d2aeaULL, 0x482f144f1f610d4eULL, + 0xf6210201b47f8234ULL, 0x5d0ae1929e70b990ULL, 0xdcd7f455b049567cULL, 0x7e93d0f1f0916f01ULL, + 0xdd79cbf18a7db4faULL, 0xbe8391bf6f74c62fULL, 0x027145d14b8291bdULL, 0x585a73ea2cbf1705ULL, + 0x485ca03e928a0db2ULL, 0x10fc01a5742857e7ULL, 0x2f482edbd6d551a7ULL, 0x0f0433b5048fdb8aULL, + 0x60da2e8dd7dc6247ULL, 0x88b4c9d38cd4819aULL, 0x13033ac001f66697ULL, 0x273b24fe3b367d75ULL, + 0xc6e8f66a31b3b9d4ULL, 0x281514a494df49d5ULL, 0xd1726fdfc8b23da7ULL, 0x4b3ae7d103dee548ULL, + 0xc6256e19ce4b9d7eULL, 0xff5c5cf186e3c61cULL, 0xacc63ca34b8ec145ULL, 0x74621888fee66574ULL, + 0x956f409645290a1eULL, 0xef0bf8e3263a962eULL, 0xed6a50eb5ec2647bULL, 0x0694283a9dca7502ULL, + 0x769b963643a2dcd1ULL, 0x42b7c8ea09fc5353ULL, 0x4f002aee13397eabULL, 0x63005e2c19b7d63aULL, + 0xca6736da63023beaULL, 0x966c7f6db12a99b7ULL, 0xace09390c537c5e1ULL, 0x0b696063a1aa89eeULL, + 0xebb03e97288c56e5ULL, 0x432a9f9f938c8be8ULL, 0xa6a5a93d5b717f71ULL, 0x1a5fb4c3e18f9d97ULL, + 0x1c94e7ad1c60cdceULL, 0xee202a43fc02c4a0ULL, 0x8dafe4d867c46a20ULL, 0x0a10263c8ac27b58ULL, + 0xd0dea9dfe4432a4aULL, 0x856af87bbe9277c5ULL, 0xce8472acc212c71aULL, 0x6f151b6d9bbb1e91ULL, + 0x26776c527ceed56aULL, 0x7d211cb7fbf8faecULL, 0x37ae66a6fd4609ccULL, 0x1f81b702d2770c42ULL, + 0x2fb0b057eac58392ULL, 0xe1dd89fe29744e9dULL, 0xc964f8eb17beb4f8ULL, 0x29571073c9a2d41eULL, + 0xa948a18981c0e254ULL, 0x2df6369b65b22830ULL, 0xa33eb2d75fcfd3c6ULL, 0x078cd6ec4199a01fULL, + 0x4a584a41ad900d2fULL, 0x32142b78e2c74c52ULL, 0x68c4e8338431c978ULL, 0x7f69ea9008689fc2ULL, + 0x52f2c81e46a38265ULL, 0xfd78072d04a832fdULL, 0x8cd7d5fa25359e94ULL, 0x4de71b7454cc29d2ULL, + 0x42eb60ad1eda6ac9ULL, 0x0aad37dfdbc09c3aULL, 0x81004b71e33cc191ULL, 0x44e6be345122803cULL, + 0x03fe8388ba1920dbULL, 0xf5d57c32150db008ULL, 0x49c8c4281af60c29ULL, 0x21edb518de701aeeULL, + 0x7fb63e418f06dc99ULL, 0xa4460d99c166d7b8ULL, 0x24dd5248ce520a83ULL, 0x5ec3ad712b928358ULL, + 0x15022a5fbd17930fULL, 0xa4f64a77d82570e3ULL, 0x12bc8d6915783712ULL, 0x498194c0fc620abbULL, + 0x38a2d9d255686c82ULL, 0x785c6bd9193e21f0ULL, 0xe4d5c81ab24a5484ULL, 0x56307860b2e20989ULL, + 0x429d55f78b4d74c4ULL, 0x22f1834643350131ULL, 0x1e60c24598c71fffULL, 0x59f2f014979983efULL, + 0x46a47d56eb494a44ULL, 0x3e22a854d636a18eULL, 0xb346e15274491c3bULL, 0x2ceafd4e5390cde7ULL, + 0xba8a8538be0d6675ULL, 0x4b9074bb50818e23ULL, 0xcbdab89085d304c3ULL, 0x61a24fe0e56192c4ULL, + 0xcb7615e6db525bcbULL, 0xdd7d8c35a567e4caULL, 0xe6b4153acafcdd69ULL, 0x2d668e097f3c9766ULL, + 0xa57e7e265ce55ef0ULL, 0x5d9f4e527cd4b967ULL, 0xfbc83606492fd1e5ULL, 0x090d52beb7c3f7aeULL, + 0x09b9515a1e7b4d7cULL, 0x1f266a2599da44c0ULL, 0xa1c49548e2c55504ULL, 0x7ef04287126f15ccULL, + 0xfed1659dbd30ef15ULL, 0x8b4ab9eec4e0277bULL, 0x884d6236a5df3291ULL, 0x1fd96ea6bf5cf788ULL, + 0x42a161981f190d9aULL, 0x61d849507e6052c1ULL, 0x9fe113bf285a2cd5ULL, 0x7c22d676dbad85d8ULL, + 0x82e770ed2bfbd27dULL, 0x4c05b2ece996f5a5ULL, 0xcd40a9c2b0900150ULL, 0x5895319213d9bf64ULL, + 0xe7cc5d703fea2e08ULL, 0xb50c491258e2188cULL, 0xcce30baa48205bf0ULL, 0x537c659ccfa32d62ULL, + 0x37b6623a98cfc088ULL, 0xfe9bed1fa4d6aca4ULL, 0x04d29b8e56a8d1b0ULL, 0x725f71c40b519575ULL, + 0x28c7f89cd0339ce6ULL, 0x8367b14469ddc18bULL, 0x883ada83a6a1652cULL, 0x585f1974034d6c17ULL, + 0x89cfb266f1b19188ULL, 0xe63b4863e7c35217ULL, 0xd88c9da6b4c0526aULL, 0x3e035c9df0954635ULL, + 0xdd9d5412fb45de9dULL, 0xdd684532e4cff40dULL, 0x4b5c999b151d671cULL, 0x2d8c2cc811e7f690ULL, + 0x7f54be1d90055d40ULL, 0xa464c5df464aaf40ULL, 0x33979624f0e917beULL, 0x2c018dc527356b30ULL, + 0xa5415024e330b3d4ULL, 0x73ff3d96691652d3ULL, 0x94ec42c4ef9b59f1ULL, 0x0747201618d08e5aULL, + 0x4d6ca48aca411c53ULL, 0x66415f2fcfa66119ULL, 0x9c4dd40051e227ffULL, 0x59810bc09a02f7ebULL, + 0x2a7eb171b3dc101dULL, 0x441c5ab99ffef68eULL, 0x32025c9b93b359eaULL, 0x5e8ce0a71e9d112fULL, + 0xbfcccb92429503fdULL, 0xd271ba752f095d55ULL, 0x345ead5e972d091eULL, 0x18c8df11a83103baULL, + 0x90cd949a9aed0f4cULL, 0xc5d1f4cb6660e37eULL, 0xb8cac52d56c52e0bULL, 0x6e42e400c5808e0dULL, + 0xa3b46966eeaefd23ULL, 0x0c4f1f0be39ecdcaULL, 0x189dc8c9d683a51dULL, 0x51f27f054c09351bULL, + 0x4c487ccd2a320682ULL, 0x587ea95bb3df1c96ULL, 0xc8ccf79e555cb8e8ULL, 0x547dc829a206d73dULL, + 0xb822a6cd80c39b06ULL, 0xe96d54732000d4c6ULL, 0x28535b6f91463b4dULL, 0x228f4660e2486e1dULL, + 0x98799538de8d3abfULL, 0x8cd8330045ebca6eULL, 0x79952a008221e738ULL, 0x4322e1a7535cd2bbULL, + 0xb114c11819d1801cULL, 0x2016e4d84f3f5ec7ULL, 0xdd0e2df409260f4cULL, 0x5ec362c0ae5f7266ULL, + 0xc0462b18b8b2b4eeULL, 0x7cc8d950274d1afbULL, 0xf25f7105436b02d2ULL, 0x43bbf8dcbff9ccd3ULL, + 0xb6ad1767a039e9dfULL, 0xb0714da8f69d3583ULL, 0x5e55fa18b42931f5ULL, 0x4ed5558f33c60961ULL, + 0x1fe37901c647a5ddULL, 0x593ddf1f8081d357ULL, 0x0249a4fd813fd7a6ULL, 0x69acca274e9caf61ULL, + 0x047ba3ea330721c9ULL, 0x83423fc20e7e1ea0ULL, 0x1df4c0af01314a60ULL, 0x09a62dab89289527ULL, + 0xa5b325a49cc6cb00ULL, 0xe94b5dc654b56cb6ULL, 0x3be28779adc994a0ULL, 0x4296e8f8ba3a4aadULL, + 0x328689761e451eabULL, 0x2e4d598bff59594aULL, 0x49b96853d7a7084aULL, 0x4980a319601420a8ULL, + 0x9565b9e12f552c42ULL, 0x8a5318db7100fe96ULL, 0x05c90b4d43add0d7ULL, 0x538b4cd66a5d4edaULL, + 0xf4e94fc3e89f039fULL, 0x592c9af26f618045ULL, 0x08a36eb5fd4b9550ULL, 0x25fffaf6c2ed1419ULL, + 0x34434459cc79d354ULL, 0xeeecbfb4b1d5476bULL, 0xddeb34a061615d99ULL, 0x5129cecceb64b773ULL, + 0xee43215894993520ULL, 0x772f9c7cf14c0b3bULL, 0xd2e2fce306bedad5ULL, 0x715f42b546f06a97ULL, + 0x434ecdceda5b5f1aULL, 0x0da17115a49741a9ULL, 0x680bd77c73edad2eULL, 0x487c02354edd9041ULL, + 0xb8efeff3a70ed9c4ULL, 0x56a32aa3e857e302ULL, 0xdf3a68bd48a2a5a0ULL, 0x07f650b73176c444ULL, + 0xe38b9b1626e0ccb1ULL, 0x79e053c18b09fb36ULL, 0x56d90319c9f94964ULL, 0x1ca941e7ac9ff5c4ULL, + 0x49c4df29162fa0bbULL, 0x8488cf3282b33305ULL, 0x95dfda14cabb437dULL, 0x3391f78264d5ad86ULL, + 0x729ae06ae2b5095dULL, 0xd58a58d73259a946ULL, 0xe9834262d13921edULL, 0x27fedafaa54bb592ULL, + 0xa99dc5b829ad48bbULL, 0x5f025742499ee260ULL, 0x802c8ecd5d7513fdULL, 0x78ceb3ef3f6dd938ULL, + 0xc342f44f8a135d94ULL, 0x7b9edb44828cdda3ULL, 0x9436d11a0537cfe7ULL, 0x5064b164ec1ab4c8ULL, + 0x7020eccfd37eb2fcULL, 0x1f31ea3ed90d25fcULL, 0x1b930d7bdfa1bb34ULL, 0x5344467a48113044ULL, + 0x70073170f25e6dfbULL, 0xe385dc1a50114cc8ULL, 0x2348698ac8fc4f00ULL, 0x2a77a55284dd40d8ULL, + 0xfe06afe0c98c6ce4ULL, 0xc235df96dddfd6e4ULL, 0x1428d01e33bf1ed3ULL, 0x785768ec9300bdafULL, + 0x9702e57a91deb63bULL, 0x61bdb8bfe5ce8b80ULL, 0x645b426f3d1d58acULL, 0x4804a82227a557bcULL, + 0x8e57048ab44d2601ULL, 0x68d6501a4b3a6935ULL, 0xc39c9ec3f9e1c293ULL, 0x4172f257d4de63e2ULL, + 0xd368b450330c6401ULL, 0x040d3017418f2391ULL, 0x2c34bb6090b7d90dULL, 0x16f649228fdfd51fULL, + 0xbea6818e2b928ef5ULL, 0xe28ccf91cdc11e72ULL, 0x594aaa68e77a36cdULL, 0x313034806c7ffd0fULL, + 0x8a9d27ac2249bd65ULL, 0x19a3b464018e9512ULL, 0xc26ccff352b37ec7ULL, 0x056f68341d797b21ULL, + 0x5e79d6757efd2327ULL, 0xfabdbcb6553afe15ULL, 0xd3e7222c6eaf5a60ULL, 0x7046c76d4dae743bULL, + 0x660be872b18d4a55ULL, 0x19992518574e1496ULL, 0xc103053a302bdcbbULL, 0x3ed8e9800b218e8eULL, + 0x7b0b9239fa75e03eULL, 0xefe9fb684633c083ULL, 0x98a35fbe391a7793ULL, 0x6065510fe2d0fe34ULL, + 0x55cb668548abad0cULL, 0xb4584548da87e527ULL, 0x2c43ecea0107c1ddULL, 0x526028809372de35ULL, + 0x3415c56af9213b1fULL, 0x5bee1a4d017e98dbULL, 0x13f6b105b5cf709bULL, 0x5ff20e3482b29ab6ULL, + 0x0aa29c75cc2e6c90ULL, 0xfc7d73ca3a70e206ULL, 0x899fc38fc4b5c515ULL, 0x250386b124ffc207ULL, + 0x54ea28d5ae3d2b56ULL, 0x9913149dd6de60ceULL, 0x16694fc58f06d6c1ULL, 0x46b23975eb018fc7ULL, + 0x470a6a0fb4b7b4e2ULL, 0x5d92475a8f7253deULL, 0xabeee5b52fbd3adbULL, 0x7fa20801a0806968ULL, + 0x76f3faf19f7714d2ULL, 0xb3e840c12f4660c3ULL, 0x0fb4cd8df212744eULL, 0x4b065a251d3a2dd2ULL, + 0x5cebde383d77cd4aULL, 0x6adf39df882c9cb1ULL, 0xa2dd242eb09af759ULL, 0x3147c0e50e5f6422ULL, + 0x164ca5101d1350dbULL, 0xf8d13479c33fc962ULL, 0xe640ce4d13e5da08ULL, 0x4bdee0c45061f8baULL, + 0xd7c46dc1a4edb1c9ULL, 0x5514d7b6437fd98aULL, 0x58942f6bb2a1c00bULL, 0x2dffb2ab1d70710eULL, + 0xccdfcf2fc18b6d68ULL, 0xa8ebcba8b7806167ULL, 0x980697f95e2937e3ULL, 0x02fbba1cd0126e8cULL +}; -static void curve25519_bmi2_base(u8 session_key[CURVE25519_KEY_SIZE], - const u8 private_key[CURVE25519_KEY_SIZE]) +static void curve25519_ever64_base(u8 *out, const u8 *priv) { - struct { - u64 buffer[4 * NUM_WORDS_ELTFP25519]; - u64 coordinates[4 * NUM_WORDS_ELTFP25519]; - u64 workspace[4 * NUM_WORDS_ELTFP25519]; - u8 private[CURVE25519_KEY_SIZE]; - } __aligned(32) m; - - const int ite[4] = { 64, 64, 64, 63 }; - const int q = 3; u64 swap = 1; - - int i = 0, j = 0, k = 0; - u64 *const key = (u64 *)m.private; - u64 *const Ur1 = m.coordinates + 0; - u64 *const Zr1 = m.coordinates + 4; - u64 *const Ur2 = m.coordinates + 8; - u64 *const Zr2 = m.coordinates + 12; - - u64 *const UZr1 = m.coordinates + 0; - u64 *const ZUr2 = m.coordinates + 8; - - u64 *const A = m.workspace + 0; - u64 *const B = m.workspace + 4; - u64 *const C = m.workspace + 8; - u64 *const D = m.workspace + 12; - - u64 *const AB = m.workspace + 0; - u64 *const CD = m.workspace + 8; - - const u64 *const P = table_ladder_8k; - - memcpy(m.private, private_key, sizeof(m.private)); - - curve25519_clamp_secret(m.private); - - setzero_eltfp25519_1w(Ur1); - setzero_eltfp25519_1w(Zr1); - setzero_eltfp25519_1w(Zr2); - Ur1[0] = 1; - Zr1[0] = 1; - Zr2[0] = 1; - - /* G-S */ - Ur2[3] = 0x1eaecdeee27cab34UL; - Ur2[2] = 0xadc7a0b9235d48e2UL; - Ur2[1] = 0xbbf095ae14b2edf8UL; - Ur2[0] = 0x7e94e1fec82faabdUL; - - /* main-loop */ - j = q; - for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { - while (j < ite[i]) { - u64 bit = (key[i] >> j) & 0x1; - k = (64 * i + j - q); + int i, j, k; + u64 tmp[16 + 32 + 4]; + u64 *x1 = &tmp[0]; + u64 *z1 = &tmp[4]; + u64 *x2 = &tmp[8]; + u64 *z2 = &tmp[12]; + u64 *xz1 = &tmp[0]; + u64 *xz2 = &tmp[8]; + u64 *a = &tmp[0 + 16]; + u64 *b = &tmp[4 + 16]; + u64 *c = &tmp[8 + 16]; + u64 *ab = &tmp[0 + 16]; + u64 *abcd = &tmp[0 + 16]; + u64 *ef = &tmp[16 + 16]; + u64 *efgh = &tmp[16 + 16]; + u64 *key = &tmp[0 + 16 + 32]; + + memcpy(key, priv, 32); + ((u8 *)key)[0] &= 248; + ((u8 *)key)[31] = (((u8 *)key)[31] & 127) | 64; + + x1[0] = 1, x1[1] = x1[2] = x1[3] = 0; + z1[0] = 1, z1[1] = z1[2] = z1[3] = 0; + z2[0] = 1, z2[1] = z2[2] = z2[3] = 0; + memcpy(x2, p_minus_s, sizeof(p_minus_s)); + + j = 3; + for (i = 0; i < 4; ++i) { + while (j < (const int[]){ 64, 64, 64, 63 }[i]) { + u64 bit = (key[i] >> j) & 1; + k = (64 * i + j - 3); swap = swap ^ bit; - cswap(swap, Ur1, Ur2); - cswap(swap, Zr1, Zr2); + cswap2(swap, xz1, xz2); swap = bit; - /* Addition */ - sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ - add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ - mul_eltfp25519_1w_bmi2(C, &P[4 * k], B);/* C = M0-B */ - sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ - add_eltfp25519_1w_bmi2(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ - sqr_eltfp25519_2w_bmi2(AB); /* A = A^2 | B = B^2 */ - mul_eltfp25519_2w_bmi2(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ + fsub(b, x1, z1); + fadd(a, x1, z1); + fmul(c, &table_ladder[4 * k], b, ef); + fsub(b, a, c); + fadd(a, a, c); + fsqr2(ab, ab, efgh); + fmul2(xz1, xz2, ab, efgh); ++j; } j = 0; } - /* Doubling */ - for (i = 0; i < q; ++i) { - add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ - sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ - sqr_eltfp25519_2w_bmi2(AB); /* A = A**2 B = B**2 */ - copy_eltfp25519_1w(C, B); /* C = B */ - sub_eltfp25519_1w(B, A, B); /* B = A-B */ - mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ - add_eltfp25519_1w_bmi2(D, D, C); /* D = D+C */ - mul_eltfp25519_2w_bmi2(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ - } + point_double(xz1, abcd, efgh); + point_double(xz1, abcd, efgh); + point_double(xz1, abcd, efgh); + encode_point(out, xz1); - /* Convert to affine coordinates */ - inv_eltfp25519_1w_bmi2(A, Zr1); - mul_eltfp25519_1w_bmi2((u64 *)session_key, Ur1, A); - fred_eltfp25519_1w((u64 *)session_key); - - memzero_explicit(&m, sizeof(m)); + memzero_explicit(tmp, sizeof(tmp)); } +static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2_adx); + void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE], const u8 basepoint[CURVE25519_KEY_SIZE]) { - if (static_branch_likely(&curve25519_use_adx)) - curve25519_adx(mypublic, secret, basepoint); - else if (static_branch_likely(&curve25519_use_bmi2)) - curve25519_bmi2(mypublic, secret, basepoint); + if (static_branch_likely(&curve25519_use_bmi2_adx)) + curve25519_ever64(mypublic, secret, basepoint); else curve25519_generic(mypublic, secret, basepoint); } @@ -2355,10 +1395,8 @@ EXPORT_SYMBOL(curve25519_arch); void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE]) { - if (static_branch_likely(&curve25519_use_adx)) - curve25519_adx_base(pub, secret); - else if (static_branch_likely(&curve25519_use_bmi2)) - curve25519_bmi2_base(pub, secret); + if (static_branch_likely(&curve25519_use_bmi2_adx)) + curve25519_ever64_base(pub, secret); else curve25519_generic(pub, secret, curve25519_base_point); } @@ -2449,12 +1487,11 @@ static struct kpp_alg curve25519_alg = { .max_size = curve25519_max_size, }; + static int __init curve25519_mod_init(void) { - if (boot_cpu_has(X86_FEATURE_BMI2)) - static_branch_enable(&curve25519_use_bmi2); - else if (boot_cpu_has(X86_FEATURE_ADX)) - static_branch_enable(&curve25519_use_adx); + if (boot_cpu_has(X86_FEATURE_BMI2) && boot_cpu_has(X86_FEATURE_ADX)) + static_branch_enable(&curve25519_use_bmi2_adx); else return 0; return IS_REACHABLE(CONFIG_CRYPTO_KPP) ? @@ -2474,3 +1511,4 @@ module_exit(curve25519_mod_exit); MODULE_ALIAS_CRYPTO("curve25519"); MODULE_ALIAS_CRYPTO("curve25519-x86"); MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); 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/entry/Makefile b/arch/x86/entry/Makefile index 06fc70cf5433..85eb381259c2 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -14,4 +14,5 @@ obj-y += vdso/ obj-y += vsyscall/ obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o +obj-$(CONFIG_X86_X32_ABI) += syscall_x32.o diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 9747876980b5..76735ec813e6 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -34,6 +34,7 @@ #include <asm/fpu/api.h> #include <asm/nospec-branch.h> #include <asm/io_bitmap.h> +#include <asm/syscall.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -333,20 +334,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) if (likely(nr < IA32_NR_syscalls)) { nr = array_index_nospec(nr, IA32_NR_syscalls); -#ifdef CONFIG_IA32_EMULATION regs->ax = ia32_sys_call_table[nr](regs); -#else - /* - * It's possible that a 32-bit syscall implementation - * takes a 64-bit parameter but nonetheless assumes that - * the high bits are zero. Make sure we zero-extend all - * of the args. - */ - regs->ax = ia32_sys_call_table[nr]( - (unsigned int)regs->bx, (unsigned int)regs->cx, - (unsigned int)regs->dx, (unsigned int)regs->si, - (unsigned int)regs->di, (unsigned int)regs->bp); -#endif /* CONFIG_IA32_EMULATION */ } syscall_return_slowpath(regs); @@ -438,3 +426,8 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) #endif } #endif + +SYSCALL_DEFINE0(ni_syscall) +{ + return -ENOSYS; +} diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 7e0560442538..b67bae7091d7 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1088,10 +1088,10 @@ SYM_FUNC_START(entry_INT80_32) STACKLEAK_ERASE restore_all: - TRACE_IRQS_IRET + TRACE_IRQS_ON SWITCH_TO_ENTRY_STACK CHECK_AND_APPLY_ESPFIX -.Lrestore_nocheck: + /* Switch back to user CR3 */ SWITCH_TO_USER_CR3 scratch_reg=%eax @@ -1290,7 +1290,7 @@ SYM_CODE_END(simd_coprocessor_error) SYM_CODE_START(device_not_available) ASM_CLAC - pushl $-1 # mark this as an int + pushl $0 pushl $do_device_not_available jmp common_exception SYM_CODE_END(device_not_available) @@ -1365,7 +1365,7 @@ SYM_CODE_END(divide_error) SYM_CODE_START(machine_check) ASM_CLAC pushl $0 - pushl machine_check_vector + pushl $do_mce jmp common_exception SYM_CODE_END(machine_check) #endif @@ -1531,7 +1531,7 @@ SYM_CODE_START(debug) * Entry from sysenter is now handled in common_exception */ ASM_CLAC - pushl $-1 # mark this as an int + pushl $0 pushl $do_debug jmp common_exception SYM_CODE_END(debug) @@ -1682,18 +1682,13 @@ SYM_CODE_END(nmi) SYM_CODE_START(int3) ASM_CLAC - pushl $-1 # mark this as an int - - SAVE_ALL switch_stacks=1 - ENCODE_FRAME_POINTER - TRACE_IRQS_OFF - xorl %edx, %edx # zero error code - movl %esp, %eax # pt_regs pointer - call do_int3 - jmp ret_from_exception + pushl $0 + pushl $do_int3 + jmp common_exception SYM_CODE_END(int3) SYM_CODE_START(general_protection) + ASM_CLAC pushl $do_general_protection jmp common_exception SYM_CODE_END(general_protection) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f2bb91e87877..0e9504fabe52 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -174,7 +174,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) movq %rsp, %rsi call do_syscall_64 /* returns with IRQs disabled */ - TRACE_IRQS_IRETQ /* we're about to change IF */ + TRACE_IRQS_ON /* return enables interrupts */ /* * Try to use SYSRET instead of IRET if we're returning to @@ -619,7 +619,7 @@ ret_from_intr: .Lretint_user: mov %rsp,%rdi call prepare_exit_to_usermode - TRACE_IRQS_IRETQ + TRACE_IRQS_ON SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) #ifdef CONFIG_DEBUG_ENTRY diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 7d17b3addbbb..86eb0d89d46f 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -4,29 +4,22 @@ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> -#include <asm/asm-offsets.h> +#include <linux/syscalls.h> +#include <asm/unistd.h> #include <asm/syscall.h> -#ifdef CONFIG_IA32_EMULATION -/* On X86_64, we use struct pt_regs * to pass parameters to syscalls */ -#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); -#define __sys_ni_syscall __ia32_sys_ni_syscall -#else /* CONFIG_IA32_EMULATION */ -#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -#define __sys_ni_syscall sys_ni_syscall -#endif /* CONFIG_IA32_EMULATION */ +#define __SYSCALL_I386(nr, sym) extern long __ia32_##sym(const struct pt_regs *); #include <asm/syscalls_32.h> #undef __SYSCALL_I386 -#define __SYSCALL_I386(nr, sym, qual) [nr] = sym, +#define __SYSCALL_I386(nr, sym) [nr] = __ia32_##sym, -__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = { +__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_compat_max] = &__sys_ni_syscall, + [0 ... __NR_ia32_syscall_max] = &__ia32_sys_ni_syscall, #include <asm/syscalls_32.h> }; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index adf619a856e8..1594ec72bcbb 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -5,24 +5,17 @@ #include <linux/sys.h> #include <linux/cache.h> #include <linux/syscalls.h> -#include <asm/asm-offsets.h> +#include <asm/unistd.h> #include <asm/syscall.h> -extern asmlinkage long sys_ni_syscall(void); +#define __SYSCALL_X32(nr, sym) +#define __SYSCALL_COMMON(nr, sym) __SYSCALL_64(nr, sym) -SYSCALL_DEFINE0(ni_syscall) -{ - return sys_ni_syscall(); -} - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); -#define __SYSCALL_X32(nr, sym, qual) __SYSCALL_64(nr, sym, qual) +#define __SYSCALL_64(nr, sym) extern long __x64_##sym(const struct pt_regs *); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#undef __SYSCALL_X32 -#define __SYSCALL_64(nr, sym, qual) [nr] = sym, -#define __SYSCALL_X32(nr, sym, qual) +#define __SYSCALL_64(nr, sym) [nr] = __x64_##sym, asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* @@ -32,25 +25,3 @@ asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { [0 ... __NR_syscall_max] = &__x64_sys_ni_syscall, #include <asm/syscalls_64.h> }; - -#undef __SYSCALL_64 -#undef __SYSCALL_X32 - -#ifdef CONFIG_X86_X32_ABI - -#define __SYSCALL_64(nr, sym, qual) -#define __SYSCALL_X32(nr, sym, qual) [nr] = sym, - -asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_syscall_x32_max+1] = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_syscall_x32_max] = &__x64_sys_ni_syscall, -#include <asm/syscalls_64.h> -}; - -#undef __SYSCALL_64 -#undef __SYSCALL_X32 - -#endif diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c new file mode 100644 index 000000000000..3d8d70d3896c --- /dev/null +++ b/arch/x86/entry/syscall_x32.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* System call table for x32 ABI. */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <linux/syscalls.h> +#include <asm/unistd.h> +#include <asm/syscall.h> + +#define __SYSCALL_64(nr, sym) + +#define __SYSCALL_X32(nr, sym) extern long __x32_##sym(const struct pt_regs *); +#define __SYSCALL_COMMON(nr, sym) extern long __x64_##sym(const struct pt_regs *); +#include <asm/syscalls_64.h> +#undef __SYSCALL_X32 +#undef __SYSCALL_COMMON + +#define __SYSCALL_X32(nr, sym) [nr] = __x32_##sym, +#define __SYSCALL_COMMON(nr, sym) [nr] = __x64_##sym, + +asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_x32_syscall_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_x32_syscall_max] = &__x64_sys_ni_syscall, +#include <asm/syscalls_64.h> +}; diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index c17cb77eb150..54581ac671b4 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -11,434 +11,434 @@ # # The abi is always "i386" for this file. # -0 i386 restart_syscall sys_restart_syscall __ia32_sys_restart_syscall -1 i386 exit sys_exit __ia32_sys_exit -2 i386 fork sys_fork __ia32_sys_fork -3 i386 read sys_read __ia32_sys_read -4 i386 write sys_write __ia32_sys_write -5 i386 open sys_open __ia32_compat_sys_open -6 i386 close sys_close __ia32_sys_close -7 i386 waitpid sys_waitpid __ia32_sys_waitpid -8 i386 creat sys_creat __ia32_sys_creat -9 i386 link sys_link __ia32_sys_link -10 i386 unlink sys_unlink __ia32_sys_unlink -11 i386 execve sys_execve __ia32_compat_sys_execve -12 i386 chdir sys_chdir __ia32_sys_chdir -13 i386 time sys_time32 __ia32_sys_time32 -14 i386 mknod sys_mknod __ia32_sys_mknod -15 i386 chmod sys_chmod __ia32_sys_chmod -16 i386 lchown sys_lchown16 __ia32_sys_lchown16 +0 i386 restart_syscall sys_restart_syscall +1 i386 exit sys_exit +2 i386 fork sys_fork +3 i386 read sys_read +4 i386 write sys_write +5 i386 open sys_open compat_sys_open +6 i386 close sys_close +7 i386 waitpid sys_waitpid +8 i386 creat sys_creat +9 i386 link sys_link +10 i386 unlink sys_unlink +11 i386 execve sys_execve compat_sys_execve +12 i386 chdir sys_chdir +13 i386 time sys_time32 +14 i386 mknod sys_mknod +15 i386 chmod sys_chmod +16 i386 lchown sys_lchown16 17 i386 break -18 i386 oldstat sys_stat __ia32_sys_stat -19 i386 lseek sys_lseek __ia32_compat_sys_lseek -20 i386 getpid sys_getpid __ia32_sys_getpid -21 i386 mount sys_mount __ia32_compat_sys_mount -22 i386 umount sys_oldumount __ia32_sys_oldumount -23 i386 setuid sys_setuid16 __ia32_sys_setuid16 -24 i386 getuid sys_getuid16 __ia32_sys_getuid16 -25 i386 stime sys_stime32 __ia32_sys_stime32 -26 i386 ptrace sys_ptrace __ia32_compat_sys_ptrace -27 i386 alarm sys_alarm __ia32_sys_alarm -28 i386 oldfstat sys_fstat __ia32_sys_fstat -29 i386 pause sys_pause __ia32_sys_pause -30 i386 utime sys_utime32 __ia32_sys_utime32 +18 i386 oldstat sys_stat +19 i386 lseek sys_lseek compat_sys_lseek +20 i386 getpid sys_getpid +21 i386 mount sys_mount compat_sys_mount +22 i386 umount sys_oldumount +23 i386 setuid sys_setuid16 +24 i386 getuid sys_getuid16 +25 i386 stime sys_stime32 +26 i386 ptrace sys_ptrace compat_sys_ptrace +27 i386 alarm sys_alarm +28 i386 oldfstat sys_fstat +29 i386 pause sys_pause +30 i386 utime sys_utime32 31 i386 stty 32 i386 gtty -33 i386 access sys_access __ia32_sys_access -34 i386 nice sys_nice __ia32_sys_nice +33 i386 access sys_access +34 i386 nice sys_nice 35 i386 ftime -36 i386 sync sys_sync __ia32_sys_sync -37 i386 kill sys_kill __ia32_sys_kill -38 i386 rename sys_rename __ia32_sys_rename -39 i386 mkdir sys_mkdir __ia32_sys_mkdir -40 i386 rmdir sys_rmdir __ia32_sys_rmdir -41 i386 dup sys_dup __ia32_sys_dup -42 i386 pipe sys_pipe __ia32_sys_pipe -43 i386 times sys_times __ia32_compat_sys_times +36 i386 sync sys_sync +37 i386 kill sys_kill +38 i386 rename sys_rename +39 i386 mkdir sys_mkdir +40 i386 rmdir sys_rmdir +41 i386 dup sys_dup +42 i386 pipe sys_pipe +43 i386 times sys_times compat_sys_times 44 i386 prof -45 i386 brk sys_brk __ia32_sys_brk -46 i386 setgid sys_setgid16 __ia32_sys_setgid16 -47 i386 getgid sys_getgid16 __ia32_sys_getgid16 -48 i386 signal sys_signal __ia32_sys_signal -49 i386 geteuid sys_geteuid16 __ia32_sys_geteuid16 -50 i386 getegid sys_getegid16 __ia32_sys_getegid16 -51 i386 acct sys_acct __ia32_sys_acct -52 i386 umount2 sys_umount __ia32_sys_umount +45 i386 brk sys_brk +46 i386 setgid sys_setgid16 +47 i386 getgid sys_getgid16 +48 i386 signal sys_signal +49 i386 geteuid sys_geteuid16 +50 i386 getegid sys_getegid16 +51 i386 acct sys_acct +52 i386 umount2 sys_umount 53 i386 lock -54 i386 ioctl sys_ioctl __ia32_compat_sys_ioctl -55 i386 fcntl sys_fcntl __ia32_compat_sys_fcntl64 +54 i386 ioctl sys_ioctl compat_sys_ioctl +55 i386 fcntl sys_fcntl compat_sys_fcntl64 56 i386 mpx -57 i386 setpgid sys_setpgid __ia32_sys_setpgid +57 i386 setpgid sys_setpgid 58 i386 ulimit -59 i386 oldolduname sys_olduname __ia32_sys_olduname -60 i386 umask sys_umask __ia32_sys_umask -61 i386 chroot sys_chroot __ia32_sys_chroot -62 i386 ustat sys_ustat __ia32_compat_sys_ustat -63 i386 dup2 sys_dup2 __ia32_sys_dup2 -64 i386 getppid sys_getppid __ia32_sys_getppid -65 i386 getpgrp sys_getpgrp __ia32_sys_getpgrp -66 i386 setsid sys_setsid __ia32_sys_setsid -67 i386 sigaction sys_sigaction __ia32_compat_sys_sigaction -68 i386 sgetmask sys_sgetmask __ia32_sys_sgetmask -69 i386 ssetmask sys_ssetmask __ia32_sys_ssetmask -70 i386 setreuid sys_setreuid16 __ia32_sys_setreuid16 -71 i386 setregid sys_setregid16 __ia32_sys_setregid16 -72 i386 sigsuspend sys_sigsuspend __ia32_sys_sigsuspend -73 i386 sigpending sys_sigpending __ia32_compat_sys_sigpending -74 i386 sethostname sys_sethostname __ia32_sys_sethostname -75 i386 setrlimit sys_setrlimit __ia32_compat_sys_setrlimit -76 i386 getrlimit sys_old_getrlimit __ia32_compat_sys_old_getrlimit -77 i386 getrusage sys_getrusage __ia32_compat_sys_getrusage -78 i386 gettimeofday sys_gettimeofday __ia32_compat_sys_gettimeofday -79 i386 settimeofday sys_settimeofday __ia32_compat_sys_settimeofday -80 i386 getgroups sys_getgroups16 __ia32_sys_getgroups16 -81 i386 setgroups sys_setgroups16 __ia32_sys_setgroups16 -82 i386 select sys_old_select __ia32_compat_sys_old_select -83 i386 symlink sys_symlink __ia32_sys_symlink -84 i386 oldlstat sys_lstat __ia32_sys_lstat -85 i386 readlink sys_readlink __ia32_sys_readlink -86 i386 uselib sys_uselib __ia32_sys_uselib -87 i386 swapon sys_swapon __ia32_sys_swapon -88 i386 reboot sys_reboot __ia32_sys_reboot -89 i386 readdir sys_old_readdir __ia32_compat_sys_old_readdir -90 i386 mmap sys_old_mmap __ia32_compat_sys_x86_mmap -91 i386 munmap sys_munmap __ia32_sys_munmap -92 i386 truncate sys_truncate __ia32_compat_sys_truncate -93 i386 ftruncate sys_ftruncate __ia32_compat_sys_ftruncate -94 i386 fchmod sys_fchmod __ia32_sys_fchmod -95 i386 fchown sys_fchown16 __ia32_sys_fchown16 -96 i386 getpriority sys_getpriority __ia32_sys_getpriority -97 i386 setpriority sys_setpriority __ia32_sys_setpriority +59 i386 oldolduname sys_olduname +60 i386 umask sys_umask +61 i386 chroot sys_chroot +62 i386 ustat sys_ustat compat_sys_ustat +63 i386 dup2 sys_dup2 +64 i386 getppid sys_getppid +65 i386 getpgrp sys_getpgrp +66 i386 setsid sys_setsid +67 i386 sigaction sys_sigaction compat_sys_sigaction +68 i386 sgetmask sys_sgetmask +69 i386 ssetmask sys_ssetmask +70 i386 setreuid sys_setreuid16 +71 i386 setregid sys_setregid16 +72 i386 sigsuspend sys_sigsuspend +73 i386 sigpending sys_sigpending compat_sys_sigpending +74 i386 sethostname sys_sethostname +75 i386 setrlimit sys_setrlimit compat_sys_setrlimit +76 i386 getrlimit sys_old_getrlimit compat_sys_old_getrlimit +77 i386 getrusage sys_getrusage compat_sys_getrusage +78 i386 gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 i386 settimeofday sys_settimeofday compat_sys_settimeofday +80 i386 getgroups sys_getgroups16 +81 i386 setgroups sys_setgroups16 +82 i386 select sys_old_select compat_sys_old_select +83 i386 symlink sys_symlink +84 i386 oldlstat sys_lstat +85 i386 readlink sys_readlink +86 i386 uselib sys_uselib +87 i386 swapon sys_swapon +88 i386 reboot sys_reboot +89 i386 readdir sys_old_readdir compat_sys_old_readdir +90 i386 mmap sys_old_mmap compat_sys_ia32_mmap +91 i386 munmap sys_munmap +92 i386 truncate sys_truncate compat_sys_truncate +93 i386 ftruncate sys_ftruncate compat_sys_ftruncate +94 i386 fchmod sys_fchmod +95 i386 fchown sys_fchown16 +96 i386 getpriority sys_getpriority +97 i386 setpriority sys_setpriority 98 i386 profil -99 i386 statfs sys_statfs __ia32_compat_sys_statfs -100 i386 fstatfs sys_fstatfs __ia32_compat_sys_fstatfs -101 i386 ioperm sys_ioperm __ia32_sys_ioperm -102 i386 socketcall sys_socketcall __ia32_compat_sys_socketcall -103 i386 syslog sys_syslog __ia32_sys_syslog -104 i386 setitimer sys_setitimer __ia32_compat_sys_setitimer -105 i386 getitimer sys_getitimer __ia32_compat_sys_getitimer -106 i386 stat sys_newstat __ia32_compat_sys_newstat -107 i386 lstat sys_newlstat __ia32_compat_sys_newlstat -108 i386 fstat sys_newfstat __ia32_compat_sys_newfstat -109 i386 olduname sys_uname __ia32_sys_uname -110 i386 iopl sys_iopl __ia32_sys_iopl -111 i386 vhangup sys_vhangup __ia32_sys_vhangup +99 i386 statfs sys_statfs compat_sys_statfs +100 i386 fstatfs sys_fstatfs compat_sys_fstatfs +101 i386 ioperm sys_ioperm +102 i386 socketcall sys_socketcall compat_sys_socketcall +103 i386 syslog sys_syslog +104 i386 setitimer sys_setitimer compat_sys_setitimer +105 i386 getitimer sys_getitimer compat_sys_getitimer +106 i386 stat sys_newstat compat_sys_newstat +107 i386 lstat sys_newlstat compat_sys_newlstat +108 i386 fstat sys_newfstat compat_sys_newfstat +109 i386 olduname sys_uname +110 i386 iopl sys_iopl +111 i386 vhangup sys_vhangup 112 i386 idle -113 i386 vm86old sys_vm86old __ia32_sys_ni_syscall -114 i386 wait4 sys_wait4 __ia32_compat_sys_wait4 -115 i386 swapoff sys_swapoff __ia32_sys_swapoff -116 i386 sysinfo sys_sysinfo __ia32_compat_sys_sysinfo -117 i386 ipc sys_ipc __ia32_compat_sys_ipc -118 i386 fsync sys_fsync __ia32_sys_fsync -119 i386 sigreturn sys_sigreturn __ia32_compat_sys_sigreturn -120 i386 clone sys_clone __ia32_compat_sys_x86_clone -121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname -122 i386 uname sys_newuname __ia32_sys_newuname -123 i386 modify_ldt sys_modify_ldt __ia32_sys_modify_ldt -124 i386 adjtimex sys_adjtimex_time32 __ia32_sys_adjtimex_time32 -125 i386 mprotect sys_mprotect __ia32_sys_mprotect -126 i386 sigprocmask sys_sigprocmask __ia32_compat_sys_sigprocmask +113 i386 vm86old sys_vm86old sys_ni_syscall +114 i386 wait4 sys_wait4 compat_sys_wait4 +115 i386 swapoff sys_swapoff +116 i386 sysinfo sys_sysinfo compat_sys_sysinfo +117 i386 ipc sys_ipc compat_sys_ipc +118 i386 fsync sys_fsync +119 i386 sigreturn sys_sigreturn compat_sys_sigreturn +120 i386 clone sys_clone compat_sys_ia32_clone +121 i386 setdomainname sys_setdomainname +122 i386 uname sys_newuname +123 i386 modify_ldt sys_modify_ldt +124 i386 adjtimex sys_adjtimex_time32 +125 i386 mprotect sys_mprotect +126 i386 sigprocmask sys_sigprocmask compat_sys_sigprocmask 127 i386 create_module -128 i386 init_module sys_init_module __ia32_sys_init_module -129 i386 delete_module sys_delete_module __ia32_sys_delete_module +128 i386 init_module sys_init_module +129 i386 delete_module sys_delete_module 130 i386 get_kernel_syms -131 i386 quotactl sys_quotactl __ia32_compat_sys_quotactl32 -132 i386 getpgid sys_getpgid __ia32_sys_getpgid -133 i386 fchdir sys_fchdir __ia32_sys_fchdir -134 i386 bdflush sys_bdflush __ia32_sys_bdflush -135 i386 sysfs sys_sysfs __ia32_sys_sysfs -136 i386 personality sys_personality __ia32_sys_personality +131 i386 quotactl sys_quotactl compat_sys_quotactl32 +132 i386 getpgid sys_getpgid +133 i386 fchdir sys_fchdir +134 i386 bdflush sys_bdflush +135 i386 sysfs sys_sysfs +136 i386 personality sys_personality 137 i386 afs_syscall -138 i386 setfsuid sys_setfsuid16 __ia32_sys_setfsuid16 -139 i386 setfsgid sys_setfsgid16 __ia32_sys_setfsgid16 -140 i386 _llseek sys_llseek __ia32_sys_llseek -141 i386 getdents sys_getdents __ia32_compat_sys_getdents -142 i386 _newselect sys_select __ia32_compat_sys_select -143 i386 flock sys_flock __ia32_sys_flock -144 i386 msync sys_msync __ia32_sys_msync -145 i386 readv sys_readv __ia32_compat_sys_readv -146 i386 writev sys_writev __ia32_compat_sys_writev -147 i386 getsid sys_getsid __ia32_sys_getsid -148 i386 fdatasync sys_fdatasync __ia32_sys_fdatasync -149 i386 _sysctl sys_sysctl __ia32_compat_sys_sysctl -150 i386 mlock sys_mlock __ia32_sys_mlock -151 i386 munlock sys_munlock __ia32_sys_munlock -152 i386 mlockall sys_mlockall __ia32_sys_mlockall -153 i386 munlockall sys_munlockall __ia32_sys_munlockall -154 i386 sched_setparam sys_sched_setparam __ia32_sys_sched_setparam -155 i386 sched_getparam sys_sched_getparam __ia32_sys_sched_getparam -156 i386 sched_setscheduler sys_sched_setscheduler __ia32_sys_sched_setscheduler -157 i386 sched_getscheduler sys_sched_getscheduler __ia32_sys_sched_getscheduler -158 i386 sched_yield sys_sched_yield __ia32_sys_sched_yield -159 i386 sched_get_priority_max sys_sched_get_priority_max __ia32_sys_sched_get_priority_max -160 i386 sched_get_priority_min sys_sched_get_priority_min __ia32_sys_sched_get_priority_min -161 i386 sched_rr_get_interval sys_sched_rr_get_interval_time32 __ia32_sys_sched_rr_get_interval_time32 -162 i386 nanosleep sys_nanosleep_time32 __ia32_sys_nanosleep_time32 -163 i386 mremap sys_mremap __ia32_sys_mremap -164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16 -165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16 -166 i386 vm86 sys_vm86 __ia32_sys_ni_syscall +138 i386 setfsuid sys_setfsuid16 +139 i386 setfsgid sys_setfsgid16 +140 i386 _llseek sys_llseek +141 i386 getdents sys_getdents compat_sys_getdents +142 i386 _newselect sys_select compat_sys_select +143 i386 flock sys_flock +144 i386 msync sys_msync +145 i386 readv sys_readv compat_sys_readv +146 i386 writev sys_writev compat_sys_writev +147 i386 getsid sys_getsid +148 i386 fdatasync sys_fdatasync +149 i386 _sysctl sys_sysctl compat_sys_sysctl +150 i386 mlock sys_mlock +151 i386 munlock sys_munlock +152 i386 mlockall sys_mlockall +153 i386 munlockall sys_munlockall +154 i386 sched_setparam sys_sched_setparam +155 i386 sched_getparam sys_sched_getparam +156 i386 sched_setscheduler sys_sched_setscheduler +157 i386 sched_getscheduler sys_sched_getscheduler +158 i386 sched_yield sys_sched_yield +159 i386 sched_get_priority_max sys_sched_get_priority_max +160 i386 sched_get_priority_min sys_sched_get_priority_min +161 i386 sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 i386 nanosleep sys_nanosleep_time32 +163 i386 mremap sys_mremap +164 i386 setresuid sys_setresuid16 +165 i386 getresuid sys_getresuid16 +166 i386 vm86 sys_vm86 sys_ni_syscall 167 i386 query_module -168 i386 poll sys_poll __ia32_sys_poll +168 i386 poll sys_poll 169 i386 nfsservctl -170 i386 setresgid sys_setresgid16 __ia32_sys_setresgid16 -171 i386 getresgid sys_getresgid16 __ia32_sys_getresgid16 -172 i386 prctl sys_prctl __ia32_sys_prctl -173 i386 rt_sigreturn sys_rt_sigreturn __ia32_compat_sys_rt_sigreturn -174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction -175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_compat_sys_rt_sigprocmask -176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending -177 i386 rt_sigtimedwait sys_rt_sigtimedwait_time32 __ia32_compat_sys_rt_sigtimedwait_time32 -178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __ia32_compat_sys_rt_sigqueueinfo -179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_compat_sys_rt_sigsuspend -180 i386 pread64 sys_pread64 __ia32_compat_sys_x86_pread -181 i386 pwrite64 sys_pwrite64 __ia32_compat_sys_x86_pwrite -182 i386 chown sys_chown16 __ia32_sys_chown16 -183 i386 getcwd sys_getcwd __ia32_sys_getcwd -184 i386 capget sys_capget __ia32_sys_capget -185 i386 capset sys_capset __ia32_sys_capset -186 i386 sigaltstack sys_sigaltstack __ia32_compat_sys_sigaltstack -187 i386 sendfile sys_sendfile __ia32_compat_sys_sendfile +170 i386 setresgid sys_setresgid16 +171 i386 getresgid sys_getresgid16 +172 i386 prctl sys_prctl +173 i386 rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn +174 i386 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 i386 rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 i386 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 i386 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 i386 rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 i386 pread64 sys_ia32_pread64 +181 i386 pwrite64 sys_ia32_pwrite64 +182 i386 chown sys_chown16 +183 i386 getcwd sys_getcwd +184 i386 capget sys_capget +185 i386 capset sys_capset +186 i386 sigaltstack sys_sigaltstack compat_sys_sigaltstack +187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork __ia32_sys_vfork -191 i386 ugetrlimit sys_getrlimit __ia32_compat_sys_getrlimit -192 i386 mmap2 sys_mmap_pgoff __ia32_sys_mmap_pgoff -193 i386 truncate64 sys_truncate64 __ia32_compat_sys_x86_truncate64 -194 i386 ftruncate64 sys_ftruncate64 __ia32_compat_sys_x86_ftruncate64 -195 i386 stat64 sys_stat64 __ia32_compat_sys_x86_stat64 -196 i386 lstat64 sys_lstat64 __ia32_compat_sys_x86_lstat64 -197 i386 fstat64 sys_fstat64 __ia32_compat_sys_x86_fstat64 -198 i386 lchown32 sys_lchown __ia32_sys_lchown -199 i386 getuid32 sys_getuid __ia32_sys_getuid -200 i386 getgid32 sys_getgid __ia32_sys_getgid -201 i386 geteuid32 sys_geteuid __ia32_sys_geteuid -202 i386 getegid32 sys_getegid __ia32_sys_getegid -203 i386 setreuid32 sys_setreuid __ia32_sys_setreuid -204 i386 setregid32 sys_setregid __ia32_sys_setregid -205 i386 getgroups32 sys_getgroups __ia32_sys_getgroups -206 i386 setgroups32 sys_setgroups __ia32_sys_setgroups -207 i386 fchown32 sys_fchown __ia32_sys_fchown -208 i386 setresuid32 sys_setresuid __ia32_sys_setresuid -209 i386 getresuid32 sys_getresuid __ia32_sys_getresuid -210 i386 setresgid32 sys_setresgid __ia32_sys_setresgid -211 i386 getresgid32 sys_getresgid __ia32_sys_getresgid -212 i386 chown32 sys_chown __ia32_sys_chown -213 i386 setuid32 sys_setuid __ia32_sys_setuid -214 i386 setgid32 sys_setgid __ia32_sys_setgid -215 i386 setfsuid32 sys_setfsuid __ia32_sys_setfsuid -216 i386 setfsgid32 sys_setfsgid __ia32_sys_setfsgid -217 i386 pivot_root sys_pivot_root __ia32_sys_pivot_root -218 i386 mincore sys_mincore __ia32_sys_mincore -219 i386 madvise sys_madvise __ia32_sys_madvise -220 i386 getdents64 sys_getdents64 __ia32_sys_getdents64 -221 i386 fcntl64 sys_fcntl64 __ia32_compat_sys_fcntl64 +190 i386 vfork sys_vfork +191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit +192 i386 mmap2 sys_mmap_pgoff +193 i386 truncate64 sys_ia32_truncate64 +194 i386 ftruncate64 sys_ia32_ftruncate64 +195 i386 stat64 sys_stat64 compat_sys_ia32_stat64 +196 i386 lstat64 sys_lstat64 compat_sys_ia32_lstat64 +197 i386 fstat64 sys_fstat64 compat_sys_ia32_fstat64 +198 i386 lchown32 sys_lchown +199 i386 getuid32 sys_getuid +200 i386 getgid32 sys_getgid +201 i386 geteuid32 sys_geteuid +202 i386 getegid32 sys_getegid +203 i386 setreuid32 sys_setreuid +204 i386 setregid32 sys_setregid +205 i386 getgroups32 sys_getgroups +206 i386 setgroups32 sys_setgroups +207 i386 fchown32 sys_fchown +208 i386 setresuid32 sys_setresuid +209 i386 getresuid32 sys_getresuid +210 i386 setresgid32 sys_setresgid +211 i386 getresgid32 sys_getresgid +212 i386 chown32 sys_chown +213 i386 setuid32 sys_setuid +214 i386 setgid32 sys_setgid +215 i386 setfsuid32 sys_setfsuid +216 i386 setfsgid32 sys_setfsgid +217 i386 pivot_root sys_pivot_root +218 i386 mincore sys_mincore +219 i386 madvise sys_madvise +220 i386 getdents64 sys_getdents64 +221 i386 fcntl64 sys_fcntl64 compat_sys_fcntl64 # 222 is unused # 223 is unused -224 i386 gettid sys_gettid __ia32_sys_gettid -225 i386 readahead sys_readahead __ia32_compat_sys_x86_readahead -226 i386 setxattr sys_setxattr __ia32_sys_setxattr -227 i386 lsetxattr sys_lsetxattr __ia32_sys_lsetxattr -228 i386 fsetxattr sys_fsetxattr __ia32_sys_fsetxattr -229 i386 getxattr sys_getxattr __ia32_sys_getxattr -230 i386 lgetxattr sys_lgetxattr __ia32_sys_lgetxattr -231 i386 fgetxattr sys_fgetxattr __ia32_sys_fgetxattr -232 i386 listxattr sys_listxattr __ia32_sys_listxattr -233 i386 llistxattr sys_llistxattr __ia32_sys_llistxattr -234 i386 flistxattr sys_flistxattr __ia32_sys_flistxattr -235 i386 removexattr sys_removexattr __ia32_sys_removexattr -236 i386 lremovexattr sys_lremovexattr __ia32_sys_lremovexattr -237 i386 fremovexattr sys_fremovexattr __ia32_sys_fremovexattr -238 i386 tkill sys_tkill __ia32_sys_tkill -239 i386 sendfile64 sys_sendfile64 __ia32_sys_sendfile64 -240 i386 futex sys_futex_time32 __ia32_sys_futex_time32 -241 i386 sched_setaffinity sys_sched_setaffinity __ia32_compat_sys_sched_setaffinity -242 i386 sched_getaffinity sys_sched_getaffinity __ia32_compat_sys_sched_getaffinity -243 i386 set_thread_area sys_set_thread_area __ia32_sys_set_thread_area -244 i386 get_thread_area sys_get_thread_area __ia32_sys_get_thread_area -245 i386 io_setup sys_io_setup __ia32_compat_sys_io_setup -246 i386 io_destroy sys_io_destroy __ia32_sys_io_destroy -247 i386 io_getevents sys_io_getevents_time32 __ia32_sys_io_getevents_time32 -248 i386 io_submit sys_io_submit __ia32_compat_sys_io_submit -249 i386 io_cancel sys_io_cancel __ia32_sys_io_cancel -250 i386 fadvise64 sys_fadvise64 __ia32_compat_sys_x86_fadvise64 +224 i386 gettid sys_gettid +225 i386 readahead sys_ia32_readahead +226 i386 setxattr sys_setxattr +227 i386 lsetxattr sys_lsetxattr +228 i386 fsetxattr sys_fsetxattr +229 i386 getxattr sys_getxattr +230 i386 lgetxattr sys_lgetxattr +231 i386 fgetxattr sys_fgetxattr +232 i386 listxattr sys_listxattr +233 i386 llistxattr sys_llistxattr +234 i386 flistxattr sys_flistxattr +235 i386 removexattr sys_removexattr +236 i386 lremovexattr sys_lremovexattr +237 i386 fremovexattr sys_fremovexattr +238 i386 tkill sys_tkill +239 i386 sendfile64 sys_sendfile64 +240 i386 futex sys_futex_time32 +241 i386 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +242 i386 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +243 i386 set_thread_area sys_set_thread_area +244 i386 get_thread_area sys_get_thread_area +245 i386 io_setup sys_io_setup compat_sys_io_setup +246 i386 io_destroy sys_io_destroy +247 i386 io_getevents sys_io_getevents_time32 +248 i386 io_submit sys_io_submit compat_sys_io_submit +249 i386 io_cancel sys_io_cancel +250 i386 fadvise64 sys_ia32_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) -252 i386 exit_group sys_exit_group __ia32_sys_exit_group -253 i386 lookup_dcookie sys_lookup_dcookie __ia32_compat_sys_lookup_dcookie -254 i386 epoll_create sys_epoll_create __ia32_sys_epoll_create -255 i386 epoll_ctl sys_epoll_ctl __ia32_sys_epoll_ctl -256 i386 epoll_wait sys_epoll_wait __ia32_sys_epoll_wait -257 i386 remap_file_pages sys_remap_file_pages __ia32_sys_remap_file_pages -258 i386 set_tid_address sys_set_tid_address __ia32_sys_set_tid_address -259 i386 timer_create sys_timer_create __ia32_compat_sys_timer_create -260 i386 timer_settime sys_timer_settime32 __ia32_sys_timer_settime32 -261 i386 timer_gettime sys_timer_gettime32 __ia32_sys_timer_gettime32 -262 i386 timer_getoverrun sys_timer_getoverrun __ia32_sys_timer_getoverrun -263 i386 timer_delete sys_timer_delete __ia32_sys_timer_delete -264 i386 clock_settime sys_clock_settime32 __ia32_sys_clock_settime32 -265 i386 clock_gettime sys_clock_gettime32 __ia32_sys_clock_gettime32 -266 i386 clock_getres sys_clock_getres_time32 __ia32_sys_clock_getres_time32 -267 i386 clock_nanosleep sys_clock_nanosleep_time32 __ia32_sys_clock_nanosleep_time32 -268 i386 statfs64 sys_statfs64 __ia32_compat_sys_statfs64 -269 i386 fstatfs64 sys_fstatfs64 __ia32_compat_sys_fstatfs64 -270 i386 tgkill sys_tgkill __ia32_sys_tgkill -271 i386 utimes sys_utimes_time32 __ia32_sys_utimes_time32 -272 i386 fadvise64_64 sys_fadvise64_64 __ia32_compat_sys_x86_fadvise64_64 +252 i386 exit_group sys_exit_group +253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +254 i386 epoll_create sys_epoll_create +255 i386 epoll_ctl sys_epoll_ctl +256 i386 epoll_wait sys_epoll_wait +257 i386 remap_file_pages sys_remap_file_pages +258 i386 set_tid_address sys_set_tid_address +259 i386 timer_create sys_timer_create compat_sys_timer_create +260 i386 timer_settime sys_timer_settime32 +261 i386 timer_gettime sys_timer_gettime32 +262 i386 timer_getoverrun sys_timer_getoverrun +263 i386 timer_delete sys_timer_delete +264 i386 clock_settime sys_clock_settime32 +265 i386 clock_gettime sys_clock_gettime32 +266 i386 clock_getres sys_clock_getres_time32 +267 i386 clock_nanosleep sys_clock_nanosleep_time32 +268 i386 statfs64 sys_statfs64 compat_sys_statfs64 +269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +270 i386 tgkill sys_tgkill +271 i386 utimes sys_utimes_time32 +272 i386 fadvise64_64 sys_ia32_fadvise64_64 273 i386 vserver -274 i386 mbind sys_mbind __ia32_sys_mbind -275 i386 get_mempolicy sys_get_mempolicy __ia32_compat_sys_get_mempolicy -276 i386 set_mempolicy sys_set_mempolicy __ia32_sys_set_mempolicy -277 i386 mq_open sys_mq_open __ia32_compat_sys_mq_open -278 i386 mq_unlink sys_mq_unlink __ia32_sys_mq_unlink -279 i386 mq_timedsend sys_mq_timedsend_time32 __ia32_sys_mq_timedsend_time32 -280 i386 mq_timedreceive sys_mq_timedreceive_time32 __ia32_sys_mq_timedreceive_time32 -281 i386 mq_notify sys_mq_notify __ia32_compat_sys_mq_notify -282 i386 mq_getsetattr sys_mq_getsetattr __ia32_compat_sys_mq_getsetattr -283 i386 kexec_load sys_kexec_load __ia32_compat_sys_kexec_load -284 i386 waitid sys_waitid __ia32_compat_sys_waitid +274 i386 mbind sys_mbind +275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +276 i386 set_mempolicy sys_set_mempolicy +277 i386 mq_open sys_mq_open compat_sys_mq_open +278 i386 mq_unlink sys_mq_unlink +279 i386 mq_timedsend sys_mq_timedsend_time32 +280 i386 mq_timedreceive sys_mq_timedreceive_time32 +281 i386 mq_notify sys_mq_notify compat_sys_mq_notify +282 i386 mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +283 i386 kexec_load sys_kexec_load compat_sys_kexec_load +284 i386 waitid sys_waitid compat_sys_waitid # 285 sys_setaltroot -286 i386 add_key sys_add_key __ia32_sys_add_key -287 i386 request_key sys_request_key __ia32_sys_request_key -288 i386 keyctl sys_keyctl __ia32_compat_sys_keyctl -289 i386 ioprio_set sys_ioprio_set __ia32_sys_ioprio_set -290 i386 ioprio_get sys_ioprio_get __ia32_sys_ioprio_get -291 i386 inotify_init sys_inotify_init __ia32_sys_inotify_init -292 i386 inotify_add_watch sys_inotify_add_watch __ia32_sys_inotify_add_watch -293 i386 inotify_rm_watch sys_inotify_rm_watch __ia32_sys_inotify_rm_watch -294 i386 migrate_pages sys_migrate_pages __ia32_sys_migrate_pages -295 i386 openat sys_openat __ia32_compat_sys_openat -296 i386 mkdirat sys_mkdirat __ia32_sys_mkdirat -297 i386 mknodat sys_mknodat __ia32_sys_mknodat -298 i386 fchownat sys_fchownat __ia32_sys_fchownat -299 i386 futimesat sys_futimesat_time32 __ia32_sys_futimesat_time32 -300 i386 fstatat64 sys_fstatat64 __ia32_compat_sys_x86_fstatat -301 i386 unlinkat sys_unlinkat __ia32_sys_unlinkat -302 i386 renameat sys_renameat __ia32_sys_renameat -303 i386 linkat sys_linkat __ia32_sys_linkat -304 i386 symlinkat sys_symlinkat __ia32_sys_symlinkat -305 i386 readlinkat sys_readlinkat __ia32_sys_readlinkat -306 i386 fchmodat sys_fchmodat __ia32_sys_fchmodat -307 i386 faccessat sys_faccessat __ia32_sys_faccessat -308 i386 pselect6 sys_pselect6_time32 __ia32_compat_sys_pselect6_time32 -309 i386 ppoll sys_ppoll_time32 __ia32_compat_sys_ppoll_time32 -310 i386 unshare sys_unshare __ia32_sys_unshare -311 i386 set_robust_list sys_set_robust_list __ia32_compat_sys_set_robust_list -312 i386 get_robust_list sys_get_robust_list __ia32_compat_sys_get_robust_list -313 i386 splice sys_splice __ia32_sys_splice -314 i386 sync_file_range sys_sync_file_range __ia32_compat_sys_x86_sync_file_range -315 i386 tee sys_tee __ia32_sys_tee -316 i386 vmsplice sys_vmsplice __ia32_compat_sys_vmsplice -317 i386 move_pages sys_move_pages __ia32_compat_sys_move_pages -318 i386 getcpu sys_getcpu __ia32_sys_getcpu -319 i386 epoll_pwait sys_epoll_pwait __ia32_sys_epoll_pwait -320 i386 utimensat sys_utimensat_time32 __ia32_sys_utimensat_time32 -321 i386 signalfd sys_signalfd __ia32_compat_sys_signalfd -322 i386 timerfd_create sys_timerfd_create __ia32_sys_timerfd_create -323 i386 eventfd sys_eventfd __ia32_sys_eventfd -324 i386 fallocate sys_fallocate __ia32_compat_sys_x86_fallocate -325 i386 timerfd_settime sys_timerfd_settime32 __ia32_sys_timerfd_settime32 -326 i386 timerfd_gettime sys_timerfd_gettime32 __ia32_sys_timerfd_gettime32 -327 i386 signalfd4 sys_signalfd4 __ia32_compat_sys_signalfd4 -328 i386 eventfd2 sys_eventfd2 __ia32_sys_eventfd2 -329 i386 epoll_create1 sys_epoll_create1 __ia32_sys_epoll_create1 -330 i386 dup3 sys_dup3 __ia32_sys_dup3 -331 i386 pipe2 sys_pipe2 __ia32_sys_pipe2 -332 i386 inotify_init1 sys_inotify_init1 __ia32_sys_inotify_init1 -333 i386 preadv sys_preadv __ia32_compat_sys_preadv -334 i386 pwritev sys_pwritev __ia32_compat_sys_pwritev -335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo __ia32_compat_sys_rt_tgsigqueueinfo -336 i386 perf_event_open sys_perf_event_open __ia32_sys_perf_event_open -337 i386 recvmmsg sys_recvmmsg_time32 __ia32_compat_sys_recvmmsg_time32 -338 i386 fanotify_init sys_fanotify_init __ia32_sys_fanotify_init -339 i386 fanotify_mark sys_fanotify_mark __ia32_compat_sys_fanotify_mark -340 i386 prlimit64 sys_prlimit64 __ia32_sys_prlimit64 -341 i386 name_to_handle_at sys_name_to_handle_at __ia32_sys_name_to_handle_at -342 i386 open_by_handle_at sys_open_by_handle_at __ia32_compat_sys_open_by_handle_at -343 i386 clock_adjtime sys_clock_adjtime32 __ia32_sys_clock_adjtime32 -344 i386 syncfs sys_syncfs __ia32_sys_syncfs -345 i386 sendmmsg sys_sendmmsg __ia32_compat_sys_sendmmsg -346 i386 setns sys_setns __ia32_sys_setns -347 i386 process_vm_readv sys_process_vm_readv __ia32_compat_sys_process_vm_readv -348 i386 process_vm_writev sys_process_vm_writev __ia32_compat_sys_process_vm_writev -349 i386 kcmp sys_kcmp __ia32_sys_kcmp -350 i386 finit_module sys_finit_module __ia32_sys_finit_module -351 i386 sched_setattr sys_sched_setattr __ia32_sys_sched_setattr -352 i386 sched_getattr sys_sched_getattr __ia32_sys_sched_getattr -353 i386 renameat2 sys_renameat2 __ia32_sys_renameat2 -354 i386 seccomp sys_seccomp __ia32_sys_seccomp -355 i386 getrandom sys_getrandom __ia32_sys_getrandom -356 i386 memfd_create sys_memfd_create __ia32_sys_memfd_create -357 i386 bpf sys_bpf __ia32_sys_bpf -358 i386 execveat sys_execveat __ia32_compat_sys_execveat -359 i386 socket sys_socket __ia32_sys_socket -360 i386 socketpair sys_socketpair __ia32_sys_socketpair -361 i386 bind sys_bind __ia32_sys_bind -362 i386 connect sys_connect __ia32_sys_connect -363 i386 listen sys_listen __ia32_sys_listen -364 i386 accept4 sys_accept4 __ia32_sys_accept4 -365 i386 getsockopt sys_getsockopt __ia32_compat_sys_getsockopt -366 i386 setsockopt sys_setsockopt __ia32_compat_sys_setsockopt -367 i386 getsockname sys_getsockname __ia32_sys_getsockname -368 i386 getpeername sys_getpeername __ia32_sys_getpeername -369 i386 sendto sys_sendto __ia32_sys_sendto -370 i386 sendmsg sys_sendmsg __ia32_compat_sys_sendmsg -371 i386 recvfrom sys_recvfrom __ia32_compat_sys_recvfrom -372 i386 recvmsg sys_recvmsg __ia32_compat_sys_recvmsg -373 i386 shutdown sys_shutdown __ia32_sys_shutdown -374 i386 userfaultfd sys_userfaultfd __ia32_sys_userfaultfd -375 i386 membarrier sys_membarrier __ia32_sys_membarrier -376 i386 mlock2 sys_mlock2 __ia32_sys_mlock2 -377 i386 copy_file_range sys_copy_file_range __ia32_sys_copy_file_range -378 i386 preadv2 sys_preadv2 __ia32_compat_sys_preadv2 -379 i386 pwritev2 sys_pwritev2 __ia32_compat_sys_pwritev2 -380 i386 pkey_mprotect sys_pkey_mprotect __ia32_sys_pkey_mprotect -381 i386 pkey_alloc sys_pkey_alloc __ia32_sys_pkey_alloc -382 i386 pkey_free sys_pkey_free __ia32_sys_pkey_free -383 i386 statx sys_statx __ia32_sys_statx -384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl -385 i386 io_pgetevents sys_io_pgetevents_time32 __ia32_compat_sys_io_pgetevents -386 i386 rseq sys_rseq __ia32_sys_rseq -393 i386 semget sys_semget __ia32_sys_semget -394 i386 semctl sys_semctl __ia32_compat_sys_semctl -395 i386 shmget sys_shmget __ia32_sys_shmget -396 i386 shmctl sys_shmctl __ia32_compat_sys_shmctl -397 i386 shmat sys_shmat __ia32_compat_sys_shmat -398 i386 shmdt sys_shmdt __ia32_sys_shmdt -399 i386 msgget sys_msgget __ia32_sys_msgget -400 i386 msgsnd sys_msgsnd __ia32_compat_sys_msgsnd -401 i386 msgrcv sys_msgrcv __ia32_compat_sys_msgrcv -402 i386 msgctl sys_msgctl __ia32_compat_sys_msgctl -403 i386 clock_gettime64 sys_clock_gettime __ia32_sys_clock_gettime -404 i386 clock_settime64 sys_clock_settime __ia32_sys_clock_settime -405 i386 clock_adjtime64 sys_clock_adjtime __ia32_sys_clock_adjtime -406 i386 clock_getres_time64 sys_clock_getres __ia32_sys_clock_getres -407 i386 clock_nanosleep_time64 sys_clock_nanosleep __ia32_sys_clock_nanosleep -408 i386 timer_gettime64 sys_timer_gettime __ia32_sys_timer_gettime -409 i386 timer_settime64 sys_timer_settime __ia32_sys_timer_settime -410 i386 timerfd_gettime64 sys_timerfd_gettime __ia32_sys_timerfd_gettime -411 i386 timerfd_settime64 sys_timerfd_settime __ia32_sys_timerfd_settime -412 i386 utimensat_time64 sys_utimensat __ia32_sys_utimensat -413 i386 pselect6_time64 sys_pselect6 __ia32_compat_sys_pselect6_time64 -414 i386 ppoll_time64 sys_ppoll __ia32_compat_sys_ppoll_time64 -416 i386 io_pgetevents_time64 sys_io_pgetevents __ia32_sys_io_pgetevents -417 i386 recvmmsg_time64 sys_recvmmsg __ia32_compat_sys_recvmmsg_time64 -418 i386 mq_timedsend_time64 sys_mq_timedsend __ia32_sys_mq_timedsend -419 i386 mq_timedreceive_time64 sys_mq_timedreceive __ia32_sys_mq_timedreceive -420 i386 semtimedop_time64 sys_semtimedop __ia32_sys_semtimedop -421 i386 rt_sigtimedwait_time64 sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait_time64 -422 i386 futex_time64 sys_futex __ia32_sys_futex -423 i386 sched_rr_get_interval_time64 sys_sched_rr_get_interval __ia32_sys_sched_rr_get_interval -424 i386 pidfd_send_signal sys_pidfd_send_signal __ia32_sys_pidfd_send_signal -425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup -426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter -427 i386 io_uring_register sys_io_uring_register __ia32_sys_io_uring_register -428 i386 open_tree sys_open_tree __ia32_sys_open_tree -429 i386 move_mount sys_move_mount __ia32_sys_move_mount -430 i386 fsopen sys_fsopen __ia32_sys_fsopen -431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig -432 i386 fsmount sys_fsmount __ia32_sys_fsmount -433 i386 fspick sys_fspick __ia32_sys_fspick -434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open -435 i386 clone3 sys_clone3 __ia32_sys_clone3 -437 i386 openat2 sys_openat2 __ia32_sys_openat2 -438 i386 pidfd_getfd sys_pidfd_getfd __ia32_sys_pidfd_getfd +286 i386 add_key sys_add_key +287 i386 request_key sys_request_key +288 i386 keyctl sys_keyctl compat_sys_keyctl +289 i386 ioprio_set sys_ioprio_set +290 i386 ioprio_get sys_ioprio_get +291 i386 inotify_init sys_inotify_init +292 i386 inotify_add_watch sys_inotify_add_watch +293 i386 inotify_rm_watch sys_inotify_rm_watch +294 i386 migrate_pages sys_migrate_pages +295 i386 openat sys_openat compat_sys_openat +296 i386 mkdirat sys_mkdirat +297 i386 mknodat sys_mknodat +298 i386 fchownat sys_fchownat +299 i386 futimesat sys_futimesat_time32 +300 i386 fstatat64 sys_fstatat64 compat_sys_ia32_fstatat64 +301 i386 unlinkat sys_unlinkat +302 i386 renameat sys_renameat +303 i386 linkat sys_linkat +304 i386 symlinkat sys_symlinkat +305 i386 readlinkat sys_readlinkat +306 i386 fchmodat sys_fchmodat +307 i386 faccessat sys_faccessat +308 i386 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +309 i386 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +310 i386 unshare sys_unshare +311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list +312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list +313 i386 splice sys_splice +314 i386 sync_file_range sys_ia32_sync_file_range +315 i386 tee sys_tee +316 i386 vmsplice sys_vmsplice compat_sys_vmsplice +317 i386 move_pages sys_move_pages compat_sys_move_pages +318 i386 getcpu sys_getcpu +319 i386 epoll_pwait sys_epoll_pwait +320 i386 utimensat sys_utimensat_time32 +321 i386 signalfd sys_signalfd compat_sys_signalfd +322 i386 timerfd_create sys_timerfd_create +323 i386 eventfd sys_eventfd +324 i386 fallocate sys_ia32_fallocate +325 i386 timerfd_settime sys_timerfd_settime32 +326 i386 timerfd_gettime sys_timerfd_gettime32 +327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 +328 i386 eventfd2 sys_eventfd2 +329 i386 epoll_create1 sys_epoll_create1 +330 i386 dup3 sys_dup3 +331 i386 pipe2 sys_pipe2 +332 i386 inotify_init1 sys_inotify_init1 +333 i386 preadv sys_preadv compat_sys_preadv +334 i386 pwritev sys_pwritev compat_sys_pwritev +335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +336 i386 perf_event_open sys_perf_event_open +337 i386 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +338 i386 fanotify_init sys_fanotify_init +339 i386 fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +340 i386 prlimit64 sys_prlimit64 +341 i386 name_to_handle_at sys_name_to_handle_at +342 i386 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +343 i386 clock_adjtime sys_clock_adjtime32 +344 i386 syncfs sys_syncfs +345 i386 sendmmsg sys_sendmmsg compat_sys_sendmmsg +346 i386 setns sys_setns +347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv +348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +349 i386 kcmp sys_kcmp +350 i386 finit_module sys_finit_module +351 i386 sched_setattr sys_sched_setattr +352 i386 sched_getattr sys_sched_getattr +353 i386 renameat2 sys_renameat2 +354 i386 seccomp sys_seccomp +355 i386 getrandom sys_getrandom +356 i386 memfd_create sys_memfd_create +357 i386 bpf sys_bpf +358 i386 execveat sys_execveat compat_sys_execveat +359 i386 socket sys_socket +360 i386 socketpair sys_socketpair +361 i386 bind sys_bind +362 i386 connect sys_connect +363 i386 listen sys_listen +364 i386 accept4 sys_accept4 +365 i386 getsockopt sys_getsockopt compat_sys_getsockopt +366 i386 setsockopt sys_setsockopt compat_sys_setsockopt +367 i386 getsockname sys_getsockname +368 i386 getpeername sys_getpeername +369 i386 sendto sys_sendto +370 i386 sendmsg sys_sendmsg compat_sys_sendmsg +371 i386 recvfrom sys_recvfrom compat_sys_recvfrom +372 i386 recvmsg sys_recvmsg compat_sys_recvmsg +373 i386 shutdown sys_shutdown +374 i386 userfaultfd sys_userfaultfd +375 i386 membarrier sys_membarrier +376 i386 mlock2 sys_mlock2 +377 i386 copy_file_range sys_copy_file_range +378 i386 preadv2 sys_preadv2 compat_sys_preadv2 +379 i386 pwritev2 sys_pwritev2 compat_sys_pwritev2 +380 i386 pkey_mprotect sys_pkey_mprotect +381 i386 pkey_alloc sys_pkey_alloc +382 i386 pkey_free sys_pkey_free +383 i386 statx sys_statx +384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl +385 i386 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +386 i386 rseq sys_rseq +393 i386 semget sys_semget +394 i386 semctl sys_semctl compat_sys_semctl +395 i386 shmget sys_shmget +396 i386 shmctl sys_shmctl compat_sys_shmctl +397 i386 shmat sys_shmat compat_sys_shmat +398 i386 shmdt sys_shmdt +399 i386 msgget sys_msgget +400 i386 msgsnd sys_msgsnd compat_sys_msgsnd +401 i386 msgrcv sys_msgrcv compat_sys_msgrcv +402 i386 msgctl sys_msgctl compat_sys_msgctl +403 i386 clock_gettime64 sys_clock_gettime +404 i386 clock_settime64 sys_clock_settime +405 i386 clock_adjtime64 sys_clock_adjtime +406 i386 clock_getres_time64 sys_clock_getres +407 i386 clock_nanosleep_time64 sys_clock_nanosleep +408 i386 timer_gettime64 sys_timer_gettime +409 i386 timer_settime64 sys_timer_settime +410 i386 timerfd_gettime64 sys_timerfd_gettime +411 i386 timerfd_settime64 sys_timerfd_settime +412 i386 utimensat_time64 sys_utimensat +413 i386 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 i386 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 i386 io_pgetevents_time64 sys_io_pgetevents +417 i386 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 i386 mq_timedsend_time64 sys_mq_timedsend +419 i386 mq_timedreceive_time64 sys_mq_timedreceive +420 i386 semtimedop_time64 sys_semtimedop +421 i386 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 i386 futex_time64 sys_futex +423 i386 sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 i386 pidfd_send_signal sys_pidfd_send_signal +425 i386 io_uring_setup sys_io_uring_setup +426 i386 io_uring_enter sys_io_uring_enter +427 i386 io_uring_register sys_io_uring_register +428 i386 open_tree sys_open_tree +429 i386 move_mount sys_move_mount +430 i386 fsopen sys_fsopen +431 i386 fsconfig sys_fsconfig +432 i386 fsmount sys_fsmount +433 i386 fspick sys_fspick +434 i386 pidfd_open sys_pidfd_open +435 i386 clone3 sys_clone3 +437 i386 openat2 sys_openat2 +438 i386 pidfd_getfd sys_pidfd_getfd diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 44d510bc9b78..37b844f839bc 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -8,357 +8,357 @@ # # The abi is "common", "64" or "x32" for this file. # -0 common read __x64_sys_read -1 common write __x64_sys_write -2 common open __x64_sys_open -3 common close __x64_sys_close -4 common stat __x64_sys_newstat -5 common fstat __x64_sys_newfstat -6 common lstat __x64_sys_newlstat -7 common poll __x64_sys_poll -8 common lseek __x64_sys_lseek -9 common mmap __x64_sys_mmap -10 common mprotect __x64_sys_mprotect -11 common munmap __x64_sys_munmap -12 common brk __x64_sys_brk -13 64 rt_sigaction __x64_sys_rt_sigaction -14 common rt_sigprocmask __x64_sys_rt_sigprocmask -15 64 rt_sigreturn __x64_sys_rt_sigreturn/ptregs -16 64 ioctl __x64_sys_ioctl -17 common pread64 __x64_sys_pread64 -18 common pwrite64 __x64_sys_pwrite64 -19 64 readv __x64_sys_readv -20 64 writev __x64_sys_writev -21 common access __x64_sys_access -22 common pipe __x64_sys_pipe -23 common select __x64_sys_select -24 common sched_yield __x64_sys_sched_yield -25 common mremap __x64_sys_mremap -26 common msync __x64_sys_msync -27 common mincore __x64_sys_mincore -28 common madvise __x64_sys_madvise -29 common shmget __x64_sys_shmget -30 common shmat __x64_sys_shmat -31 common shmctl __x64_sys_shmctl -32 common dup __x64_sys_dup -33 common dup2 __x64_sys_dup2 -34 common pause __x64_sys_pause -35 common nanosleep __x64_sys_nanosleep -36 common getitimer __x64_sys_getitimer -37 common alarm __x64_sys_alarm -38 common setitimer __x64_sys_setitimer -39 common getpid __x64_sys_getpid -40 common sendfile __x64_sys_sendfile64 -41 common socket __x64_sys_socket -42 common connect __x64_sys_connect -43 common accept __x64_sys_accept -44 common sendto __x64_sys_sendto -45 64 recvfrom __x64_sys_recvfrom -46 64 sendmsg __x64_sys_sendmsg -47 64 recvmsg __x64_sys_recvmsg -48 common shutdown __x64_sys_shutdown -49 common bind __x64_sys_bind -50 common listen __x64_sys_listen -51 common getsockname __x64_sys_getsockname -52 common getpeername __x64_sys_getpeername -53 common socketpair __x64_sys_socketpair -54 64 setsockopt __x64_sys_setsockopt -55 64 getsockopt __x64_sys_getsockopt -56 common clone __x64_sys_clone/ptregs -57 common fork __x64_sys_fork/ptregs -58 common vfork __x64_sys_vfork/ptregs -59 64 execve __x64_sys_execve/ptregs -60 common exit __x64_sys_exit -61 common wait4 __x64_sys_wait4 -62 common kill __x64_sys_kill -63 common uname __x64_sys_newuname -64 common semget __x64_sys_semget -65 common semop __x64_sys_semop -66 common semctl __x64_sys_semctl -67 common shmdt __x64_sys_shmdt -68 common msgget __x64_sys_msgget -69 common msgsnd __x64_sys_msgsnd -70 common msgrcv __x64_sys_msgrcv -71 common msgctl __x64_sys_msgctl -72 common fcntl __x64_sys_fcntl -73 common flock __x64_sys_flock -74 common fsync __x64_sys_fsync -75 common fdatasync __x64_sys_fdatasync -76 common truncate __x64_sys_truncate -77 common ftruncate __x64_sys_ftruncate -78 common getdents __x64_sys_getdents -79 common getcwd __x64_sys_getcwd -80 common chdir __x64_sys_chdir -81 common fchdir __x64_sys_fchdir -82 common rename __x64_sys_rename -83 common mkdir __x64_sys_mkdir -84 common rmdir __x64_sys_rmdir -85 common creat __x64_sys_creat -86 common link __x64_sys_link -87 common unlink __x64_sys_unlink -88 common symlink __x64_sys_symlink -89 common readlink __x64_sys_readlink -90 common chmod __x64_sys_chmod -91 common fchmod __x64_sys_fchmod -92 common chown __x64_sys_chown -93 common fchown __x64_sys_fchown -94 common lchown __x64_sys_lchown -95 common umask __x64_sys_umask -96 common gettimeofday __x64_sys_gettimeofday -97 common getrlimit __x64_sys_getrlimit -98 common getrusage __x64_sys_getrusage -99 common sysinfo __x64_sys_sysinfo -100 common times __x64_sys_times -101 64 ptrace __x64_sys_ptrace -102 common getuid __x64_sys_getuid -103 common syslog __x64_sys_syslog -104 common getgid __x64_sys_getgid -105 common setuid __x64_sys_setuid -106 common setgid __x64_sys_setgid -107 common geteuid __x64_sys_geteuid -108 common getegid __x64_sys_getegid -109 common setpgid __x64_sys_setpgid -110 common getppid __x64_sys_getppid -111 common getpgrp __x64_sys_getpgrp -112 common setsid __x64_sys_setsid -113 common setreuid __x64_sys_setreuid -114 common setregid __x64_sys_setregid -115 common getgroups __x64_sys_getgroups -116 common setgroups __x64_sys_setgroups -117 common setresuid __x64_sys_setresuid -118 common getresuid __x64_sys_getresuid -119 common setresgid __x64_sys_setresgid -120 common getresgid __x64_sys_getresgid -121 common getpgid __x64_sys_getpgid -122 common setfsuid __x64_sys_setfsuid -123 common setfsgid __x64_sys_setfsgid -124 common getsid __x64_sys_getsid -125 common capget __x64_sys_capget -126 common capset __x64_sys_capset -127 64 rt_sigpending __x64_sys_rt_sigpending -128 64 rt_sigtimedwait __x64_sys_rt_sigtimedwait -129 64 rt_sigqueueinfo __x64_sys_rt_sigqueueinfo -130 common rt_sigsuspend __x64_sys_rt_sigsuspend -131 64 sigaltstack __x64_sys_sigaltstack -132 common utime __x64_sys_utime -133 common mknod __x64_sys_mknod +0 common read sys_read +1 common write sys_write +2 common open sys_open +3 common close sys_close +4 common stat sys_newstat +5 common fstat sys_newfstat +6 common lstat sys_newlstat +7 common poll sys_poll +8 common lseek sys_lseek +9 common mmap sys_mmap +10 common mprotect sys_mprotect +11 common munmap sys_munmap +12 common brk sys_brk +13 64 rt_sigaction sys_rt_sigaction +14 common rt_sigprocmask sys_rt_sigprocmask +15 64 rt_sigreturn sys_rt_sigreturn +16 64 ioctl sys_ioctl +17 common pread64 sys_pread64 +18 common pwrite64 sys_pwrite64 +19 64 readv sys_readv +20 64 writev sys_writev +21 common access sys_access +22 common pipe sys_pipe +23 common select sys_select +24 common sched_yield sys_sched_yield +25 common mremap sys_mremap +26 common msync sys_msync +27 common mincore sys_mincore +28 common madvise sys_madvise +29 common shmget sys_shmget +30 common shmat sys_shmat +31 common shmctl sys_shmctl +32 common dup sys_dup +33 common dup2 sys_dup2 +34 common pause sys_pause +35 common nanosleep sys_nanosleep +36 common getitimer sys_getitimer +37 common alarm sys_alarm +38 common setitimer sys_setitimer +39 common getpid sys_getpid +40 common sendfile sys_sendfile64 +41 common socket sys_socket +42 common connect sys_connect +43 common accept sys_accept +44 common sendto sys_sendto +45 64 recvfrom sys_recvfrom +46 64 sendmsg sys_sendmsg +47 64 recvmsg sys_recvmsg +48 common shutdown sys_shutdown +49 common bind sys_bind +50 common listen sys_listen +51 common getsockname sys_getsockname +52 common getpeername sys_getpeername +53 common socketpair sys_socketpair +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt +56 common clone sys_clone +57 common fork sys_fork +58 common vfork sys_vfork +59 64 execve sys_execve +60 common exit sys_exit +61 common wait4 sys_wait4 +62 common kill sys_kill +63 common uname sys_newuname +64 common semget sys_semget +65 common semop sys_semop +66 common semctl sys_semctl +67 common shmdt sys_shmdt +68 common msgget sys_msgget +69 common msgsnd sys_msgsnd +70 common msgrcv sys_msgrcv +71 common msgctl sys_msgctl +72 common fcntl sys_fcntl +73 common flock sys_flock +74 common fsync sys_fsync +75 common fdatasync sys_fdatasync +76 common truncate sys_truncate +77 common ftruncate sys_ftruncate +78 common getdents sys_getdents +79 common getcwd sys_getcwd +80 common chdir sys_chdir +81 common fchdir sys_fchdir +82 common rename sys_rename +83 common mkdir sys_mkdir +84 common rmdir sys_rmdir +85 common creat sys_creat +86 common link sys_link +87 common unlink sys_unlink +88 common symlink sys_symlink +89 common readlink sys_readlink +90 common chmod sys_chmod +91 common fchmod sys_fchmod +92 common chown sys_chown +93 common fchown sys_fchown +94 common lchown sys_lchown +95 common umask sys_umask +96 common gettimeofday sys_gettimeofday +97 common getrlimit sys_getrlimit +98 common getrusage sys_getrusage +99 common sysinfo sys_sysinfo +100 common times sys_times +101 64 ptrace sys_ptrace +102 common getuid sys_getuid +103 common syslog sys_syslog +104 common getgid sys_getgid +105 common setuid sys_setuid +106 common setgid sys_setgid +107 common geteuid sys_geteuid +108 common getegid sys_getegid +109 common setpgid sys_setpgid +110 common getppid sys_getppid +111 common getpgrp sys_getpgrp +112 common setsid sys_setsid +113 common setreuid sys_setreuid +114 common setregid sys_setregid +115 common getgroups sys_getgroups +116 common setgroups sys_setgroups +117 common setresuid sys_setresuid +118 common getresuid sys_getresuid +119 common setresgid sys_setresgid +120 common getresgid sys_getresgid +121 common getpgid sys_getpgid +122 common setfsuid sys_setfsuid +123 common setfsgid sys_setfsgid +124 common getsid sys_getsid +125 common capget sys_capget +126 common capset sys_capset +127 64 rt_sigpending sys_rt_sigpending +128 64 rt_sigtimedwait sys_rt_sigtimedwait +129 64 rt_sigqueueinfo sys_rt_sigqueueinfo +130 common rt_sigsuspend sys_rt_sigsuspend +131 64 sigaltstack sys_sigaltstack +132 common utime sys_utime +133 common mknod sys_mknod 134 64 uselib -135 common personality __x64_sys_personality -136 common ustat __x64_sys_ustat -137 common statfs __x64_sys_statfs -138 common fstatfs __x64_sys_fstatfs -139 common sysfs __x64_sys_sysfs -140 common getpriority __x64_sys_getpriority -141 common setpriority __x64_sys_setpriority -142 common sched_setparam __x64_sys_sched_setparam -143 common sched_getparam __x64_sys_sched_getparam -144 common sched_setscheduler __x64_sys_sched_setscheduler -145 common sched_getscheduler __x64_sys_sched_getscheduler -146 common sched_get_priority_max __x64_sys_sched_get_priority_max -147 common sched_get_priority_min __x64_sys_sched_get_priority_min -148 common sched_rr_get_interval __x64_sys_sched_rr_get_interval -149 common mlock __x64_sys_mlock -150 common munlock __x64_sys_munlock -151 common mlockall __x64_sys_mlockall -152 common munlockall __x64_sys_munlockall -153 common vhangup __x64_sys_vhangup -154 common modify_ldt __x64_sys_modify_ldt -155 common pivot_root __x64_sys_pivot_root -156 64 _sysctl __x64_sys_sysctl -157 common prctl __x64_sys_prctl -158 common arch_prctl __x64_sys_arch_prctl -159 common adjtimex __x64_sys_adjtimex -160 common setrlimit __x64_sys_setrlimit -161 common chroot __x64_sys_chroot -162 common sync __x64_sys_sync -163 common acct __x64_sys_acct -164 common settimeofday __x64_sys_settimeofday -165 common mount __x64_sys_mount -166 common umount2 __x64_sys_umount -167 common swapon __x64_sys_swapon -168 common swapoff __x64_sys_swapoff -169 common reboot __x64_sys_reboot -170 common sethostname __x64_sys_sethostname -171 common setdomainname __x64_sys_setdomainname -172 common iopl __x64_sys_iopl/ptregs -173 common ioperm __x64_sys_ioperm +135 common personality sys_personality +136 common ustat sys_ustat +137 common statfs sys_statfs +138 common fstatfs sys_fstatfs +139 common sysfs sys_sysfs +140 common getpriority sys_getpriority +141 common setpriority sys_setpriority +142 common sched_setparam sys_sched_setparam +143 common sched_getparam sys_sched_getparam +144 common sched_setscheduler sys_sched_setscheduler +145 common sched_getscheduler sys_sched_getscheduler +146 common sched_get_priority_max sys_sched_get_priority_max +147 common sched_get_priority_min sys_sched_get_priority_min +148 common sched_rr_get_interval sys_sched_rr_get_interval +149 common mlock sys_mlock +150 common munlock sys_munlock +151 common mlockall sys_mlockall +152 common munlockall sys_munlockall +153 common vhangup sys_vhangup +154 common modify_ldt sys_modify_ldt +155 common pivot_root sys_pivot_root +156 64 _sysctl sys_sysctl +157 common prctl sys_prctl +158 common arch_prctl sys_arch_prctl +159 common adjtimex sys_adjtimex +160 common setrlimit sys_setrlimit +161 common chroot sys_chroot +162 common sync sys_sync +163 common acct sys_acct +164 common settimeofday sys_settimeofday +165 common mount sys_mount +166 common umount2 sys_umount +167 common swapon sys_swapon +168 common swapoff sys_swapoff +169 common reboot sys_reboot +170 common sethostname sys_sethostname +171 common setdomainname sys_setdomainname +172 common iopl sys_iopl +173 common ioperm sys_ioperm 174 64 create_module -175 common init_module __x64_sys_init_module -176 common delete_module __x64_sys_delete_module +175 common init_module sys_init_module +176 common delete_module sys_delete_module 177 64 get_kernel_syms 178 64 query_module -179 common quotactl __x64_sys_quotactl +179 common quotactl sys_quotactl 180 64 nfsservctl 181 common getpmsg 182 common putpmsg 183 common afs_syscall 184 common tuxcall 185 common security -186 common gettid __x64_sys_gettid -187 common readahead __x64_sys_readahead -188 common setxattr __x64_sys_setxattr -189 common lsetxattr __x64_sys_lsetxattr -190 common fsetxattr __x64_sys_fsetxattr -191 common getxattr __x64_sys_getxattr -192 common lgetxattr __x64_sys_lgetxattr -193 common fgetxattr __x64_sys_fgetxattr -194 common listxattr __x64_sys_listxattr -195 common llistxattr __x64_sys_llistxattr -196 common flistxattr __x64_sys_flistxattr -197 common removexattr __x64_sys_removexattr -198 common lremovexattr __x64_sys_lremovexattr -199 common fremovexattr __x64_sys_fremovexattr -200 common tkill __x64_sys_tkill -201 common time __x64_sys_time -202 common futex __x64_sys_futex -203 common sched_setaffinity __x64_sys_sched_setaffinity -204 common sched_getaffinity __x64_sys_sched_getaffinity +186 common gettid sys_gettid +187 common readahead sys_readahead +188 common setxattr sys_setxattr +189 common lsetxattr sys_lsetxattr +190 common fsetxattr sys_fsetxattr +191 common getxattr sys_getxattr +192 common lgetxattr sys_lgetxattr +193 common fgetxattr sys_fgetxattr +194 common listxattr sys_listxattr +195 common llistxattr sys_llistxattr +196 common flistxattr sys_flistxattr +197 common removexattr sys_removexattr +198 common lremovexattr sys_lremovexattr +199 common fremovexattr sys_fremovexattr +200 common tkill sys_tkill +201 common time sys_time +202 common futex sys_futex +203 common sched_setaffinity sys_sched_setaffinity +204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 64 io_setup __x64_sys_io_setup -207 common io_destroy __x64_sys_io_destroy -208 common io_getevents __x64_sys_io_getevents -209 64 io_submit __x64_sys_io_submit -210 common io_cancel __x64_sys_io_cancel +206 64 io_setup sys_io_setup +207 common io_destroy sys_io_destroy +208 common io_getevents sys_io_getevents +209 64 io_submit sys_io_submit +210 common io_cancel sys_io_cancel 211 64 get_thread_area -212 common lookup_dcookie __x64_sys_lookup_dcookie -213 common epoll_create __x64_sys_epoll_create +212 common lookup_dcookie sys_lookup_dcookie +213 common epoll_create sys_epoll_create 214 64 epoll_ctl_old 215 64 epoll_wait_old -216 common remap_file_pages __x64_sys_remap_file_pages -217 common getdents64 __x64_sys_getdents64 -218 common set_tid_address __x64_sys_set_tid_address -219 common restart_syscall __x64_sys_restart_syscall -220 common semtimedop __x64_sys_semtimedop -221 common fadvise64 __x64_sys_fadvise64 -222 64 timer_create __x64_sys_timer_create -223 common timer_settime __x64_sys_timer_settime -224 common timer_gettime __x64_sys_timer_gettime -225 common timer_getoverrun __x64_sys_timer_getoverrun -226 common timer_delete __x64_sys_timer_delete -227 common clock_settime __x64_sys_clock_settime -228 common clock_gettime __x64_sys_clock_gettime -229 common clock_getres __x64_sys_clock_getres -230 common clock_nanosleep __x64_sys_clock_nanosleep -231 common exit_group __x64_sys_exit_group -232 common epoll_wait __x64_sys_epoll_wait -233 common epoll_ctl __x64_sys_epoll_ctl -234 common tgkill __x64_sys_tgkill -235 common utimes __x64_sys_utimes +216 common remap_file_pages sys_remap_file_pages +217 common getdents64 sys_getdents64 +218 common set_tid_address sys_set_tid_address +219 common restart_syscall sys_restart_syscall +220 common semtimedop sys_semtimedop +221 common fadvise64 sys_fadvise64 +222 64 timer_create sys_timer_create +223 common timer_settime sys_timer_settime +224 common timer_gettime sys_timer_gettime +225 common timer_getoverrun sys_timer_getoverrun +226 common timer_delete sys_timer_delete +227 common clock_settime sys_clock_settime +228 common clock_gettime sys_clock_gettime +229 common clock_getres sys_clock_getres +230 common clock_nanosleep sys_clock_nanosleep +231 common exit_group sys_exit_group +232 common epoll_wait sys_epoll_wait +233 common epoll_ctl sys_epoll_ctl +234 common tgkill sys_tgkill +235 common utimes sys_utimes 236 64 vserver -237 common mbind __x64_sys_mbind -238 common set_mempolicy __x64_sys_set_mempolicy -239 common get_mempolicy __x64_sys_get_mempolicy -240 common mq_open __x64_sys_mq_open -241 common mq_unlink __x64_sys_mq_unlink -242 common mq_timedsend __x64_sys_mq_timedsend -243 common mq_timedreceive __x64_sys_mq_timedreceive -244 64 mq_notify __x64_sys_mq_notify -245 common mq_getsetattr __x64_sys_mq_getsetattr -246 64 kexec_load __x64_sys_kexec_load -247 64 waitid __x64_sys_waitid -248 common add_key __x64_sys_add_key -249 common request_key __x64_sys_request_key -250 common keyctl __x64_sys_keyctl -251 common ioprio_set __x64_sys_ioprio_set -252 common ioprio_get __x64_sys_ioprio_get -253 common inotify_init __x64_sys_inotify_init -254 common inotify_add_watch __x64_sys_inotify_add_watch -255 common inotify_rm_watch __x64_sys_inotify_rm_watch -256 common migrate_pages __x64_sys_migrate_pages -257 common openat __x64_sys_openat -258 common mkdirat __x64_sys_mkdirat -259 common mknodat __x64_sys_mknodat -260 common fchownat __x64_sys_fchownat -261 common futimesat __x64_sys_futimesat -262 common newfstatat __x64_sys_newfstatat -263 common unlinkat __x64_sys_unlinkat -264 common renameat __x64_sys_renameat -265 common linkat __x64_sys_linkat -266 common symlinkat __x64_sys_symlinkat -267 common readlinkat __x64_sys_readlinkat -268 common fchmodat __x64_sys_fchmodat -269 common faccessat __x64_sys_faccessat -270 common pselect6 __x64_sys_pselect6 -271 common ppoll __x64_sys_ppoll -272 common unshare __x64_sys_unshare -273 64 set_robust_list __x64_sys_set_robust_list -274 64 get_robust_list __x64_sys_get_robust_list -275 common splice __x64_sys_splice -276 common tee __x64_sys_tee -277 common sync_file_range __x64_sys_sync_file_range -278 64 vmsplice __x64_sys_vmsplice -279 64 move_pages __x64_sys_move_pages -280 common utimensat __x64_sys_utimensat -281 common epoll_pwait __x64_sys_epoll_pwait -282 common signalfd __x64_sys_signalfd -283 common timerfd_create __x64_sys_timerfd_create -284 common eventfd __x64_sys_eventfd -285 common fallocate __x64_sys_fallocate -286 common timerfd_settime __x64_sys_timerfd_settime -287 common timerfd_gettime __x64_sys_timerfd_gettime -288 common accept4 __x64_sys_accept4 -289 common signalfd4 __x64_sys_signalfd4 -290 common eventfd2 __x64_sys_eventfd2 -291 common epoll_create1 __x64_sys_epoll_create1 -292 common dup3 __x64_sys_dup3 -293 common pipe2 __x64_sys_pipe2 -294 common inotify_init1 __x64_sys_inotify_init1 -295 64 preadv __x64_sys_preadv -296 64 pwritev __x64_sys_pwritev -297 64 rt_tgsigqueueinfo __x64_sys_rt_tgsigqueueinfo -298 common perf_event_open __x64_sys_perf_event_open -299 64 recvmmsg __x64_sys_recvmmsg -300 common fanotify_init __x64_sys_fanotify_init -301 common fanotify_mark __x64_sys_fanotify_mark -302 common prlimit64 __x64_sys_prlimit64 -303 common name_to_handle_at __x64_sys_name_to_handle_at -304 common open_by_handle_at __x64_sys_open_by_handle_at -305 common clock_adjtime __x64_sys_clock_adjtime -306 common syncfs __x64_sys_syncfs -307 64 sendmmsg __x64_sys_sendmmsg -308 common setns __x64_sys_setns -309 common getcpu __x64_sys_getcpu -310 64 process_vm_readv __x64_sys_process_vm_readv -311 64 process_vm_writev __x64_sys_process_vm_writev -312 common kcmp __x64_sys_kcmp -313 common finit_module __x64_sys_finit_module -314 common sched_setattr __x64_sys_sched_setattr -315 common sched_getattr __x64_sys_sched_getattr -316 common renameat2 __x64_sys_renameat2 -317 common seccomp __x64_sys_seccomp -318 common getrandom __x64_sys_getrandom -319 common memfd_create __x64_sys_memfd_create -320 common kexec_file_load __x64_sys_kexec_file_load -321 common bpf __x64_sys_bpf -322 64 execveat __x64_sys_execveat/ptregs -323 common userfaultfd __x64_sys_userfaultfd -324 common membarrier __x64_sys_membarrier -325 common mlock2 __x64_sys_mlock2 -326 common copy_file_range __x64_sys_copy_file_range -327 64 preadv2 __x64_sys_preadv2 -328 64 pwritev2 __x64_sys_pwritev2 -329 common pkey_mprotect __x64_sys_pkey_mprotect -330 common pkey_alloc __x64_sys_pkey_alloc -331 common pkey_free __x64_sys_pkey_free -332 common statx __x64_sys_statx -333 common io_pgetevents __x64_sys_io_pgetevents -334 common rseq __x64_sys_rseq +237 common mbind sys_mbind +238 common set_mempolicy sys_set_mempolicy +239 common get_mempolicy sys_get_mempolicy +240 common mq_open sys_mq_open +241 common mq_unlink sys_mq_unlink +242 common mq_timedsend sys_mq_timedsend +243 common mq_timedreceive sys_mq_timedreceive +244 64 mq_notify sys_mq_notify +245 common mq_getsetattr sys_mq_getsetattr +246 64 kexec_load sys_kexec_load +247 64 waitid sys_waitid +248 common add_key sys_add_key +249 common request_key sys_request_key +250 common keyctl sys_keyctl +251 common ioprio_set sys_ioprio_set +252 common ioprio_get sys_ioprio_get +253 common inotify_init sys_inotify_init +254 common inotify_add_watch sys_inotify_add_watch +255 common inotify_rm_watch sys_inotify_rm_watch +256 common migrate_pages sys_migrate_pages +257 common openat sys_openat +258 common mkdirat sys_mkdirat +259 common mknodat sys_mknodat +260 common fchownat sys_fchownat +261 common futimesat sys_futimesat +262 common newfstatat sys_newfstatat +263 common unlinkat sys_unlinkat +264 common renameat sys_renameat +265 common linkat sys_linkat +266 common symlinkat sys_symlinkat +267 common readlinkat sys_readlinkat +268 common fchmodat sys_fchmodat +269 common faccessat sys_faccessat +270 common pselect6 sys_pselect6 +271 common ppoll sys_ppoll +272 common unshare sys_unshare +273 64 set_robust_list sys_set_robust_list +274 64 get_robust_list sys_get_robust_list +275 common splice sys_splice +276 common tee sys_tee +277 common sync_file_range sys_sync_file_range +278 64 vmsplice sys_vmsplice +279 64 move_pages sys_move_pages +280 common utimensat sys_utimensat +281 common epoll_pwait sys_epoll_pwait +282 common signalfd sys_signalfd +283 common timerfd_create sys_timerfd_create +284 common eventfd sys_eventfd +285 common fallocate sys_fallocate +286 common timerfd_settime sys_timerfd_settime +287 common timerfd_gettime sys_timerfd_gettime +288 common accept4 sys_accept4 +289 common signalfd4 sys_signalfd4 +290 common eventfd2 sys_eventfd2 +291 common epoll_create1 sys_epoll_create1 +292 common dup3 sys_dup3 +293 common pipe2 sys_pipe2 +294 common inotify_init1 sys_inotify_init1 +295 64 preadv sys_preadv +296 64 pwritev sys_pwritev +297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +298 common perf_event_open sys_perf_event_open +299 64 recvmmsg sys_recvmmsg +300 common fanotify_init sys_fanotify_init +301 common fanotify_mark sys_fanotify_mark +302 common prlimit64 sys_prlimit64 +303 common name_to_handle_at sys_name_to_handle_at +304 common open_by_handle_at sys_open_by_handle_at +305 common clock_adjtime sys_clock_adjtime +306 common syncfs sys_syncfs +307 64 sendmmsg sys_sendmmsg +308 common setns sys_setns +309 common getcpu sys_getcpu +310 64 process_vm_readv sys_process_vm_readv +311 64 process_vm_writev sys_process_vm_writev +312 common kcmp sys_kcmp +313 common finit_module sys_finit_module +314 common sched_setattr sys_sched_setattr +315 common sched_getattr sys_sched_getattr +316 common renameat2 sys_renameat2 +317 common seccomp sys_seccomp +318 common getrandom sys_getrandom +319 common memfd_create sys_memfd_create +320 common kexec_file_load sys_kexec_file_load +321 common bpf sys_bpf +322 64 execveat sys_execveat +323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range +327 64 preadv2 sys_preadv2 +328 64 pwritev2 sys_pwritev2 +329 common pkey_mprotect sys_pkey_mprotect +330 common pkey_alloc sys_pkey_alloc +331 common pkey_free sys_pkey_free +332 common statx sys_statx +333 common io_pgetevents sys_io_pgetevents +334 common rseq sys_rseq # don't use numbers 387 through 423, add new calls after the last # 'common' entry -424 common pidfd_send_signal __x64_sys_pidfd_send_signal -425 common io_uring_setup __x64_sys_io_uring_setup -426 common io_uring_enter __x64_sys_io_uring_enter -427 common io_uring_register __x64_sys_io_uring_register -428 common open_tree __x64_sys_open_tree -429 common move_mount __x64_sys_move_mount -430 common fsopen __x64_sys_fsopen -431 common fsconfig __x64_sys_fsconfig -432 common fsmount __x64_sys_fsmount -433 common fspick __x64_sys_fspick -434 common pidfd_open __x64_sys_pidfd_open -435 common clone3 __x64_sys_clone3/ptregs -437 common openat2 __x64_sys_openat2 -438 common pidfd_getfd __x64_sys_pidfd_getfd +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd # # x32-specific system call numbers start at 512 to avoid cache impact @@ -366,39 +366,39 @@ # on-the-fly for compat_sys_*() compatibility system calls if X86_X32 # is defined. # -512 x32 rt_sigaction __x32_compat_sys_rt_sigaction -513 x32 rt_sigreturn sys32_x32_rt_sigreturn -514 x32 ioctl __x32_compat_sys_ioctl -515 x32 readv __x32_compat_sys_readv -516 x32 writev __x32_compat_sys_writev -517 x32 recvfrom __x32_compat_sys_recvfrom -518 x32 sendmsg __x32_compat_sys_sendmsg -519 x32 recvmsg __x32_compat_sys_recvmsg -520 x32 execve __x32_compat_sys_execve/ptregs -521 x32 ptrace __x32_compat_sys_ptrace -522 x32 rt_sigpending __x32_compat_sys_rt_sigpending -523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait_time64 -524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo -525 x32 sigaltstack __x32_compat_sys_sigaltstack -526 x32 timer_create __x32_compat_sys_timer_create -527 x32 mq_notify __x32_compat_sys_mq_notify -528 x32 kexec_load __x32_compat_sys_kexec_load -529 x32 waitid __x32_compat_sys_waitid -530 x32 set_robust_list __x32_compat_sys_set_robust_list -531 x32 get_robust_list __x32_compat_sys_get_robust_list -532 x32 vmsplice __x32_compat_sys_vmsplice -533 x32 move_pages __x32_compat_sys_move_pages -534 x32 preadv __x32_compat_sys_preadv64 -535 x32 pwritev __x32_compat_sys_pwritev64 -536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo -537 x32 recvmmsg __x32_compat_sys_recvmmsg_time64 -538 x32 sendmmsg __x32_compat_sys_sendmmsg -539 x32 process_vm_readv __x32_compat_sys_process_vm_readv -540 x32 process_vm_writev __x32_compat_sys_process_vm_writev -541 x32 setsockopt __x32_compat_sys_setsockopt -542 x32 getsockopt __x32_compat_sys_getsockopt -543 x32 io_setup __x32_compat_sys_io_setup -544 x32 io_submit __x32_compat_sys_io_submit -545 x32 execveat __x32_compat_sys_execveat/ptregs -546 x32 preadv2 __x32_compat_sys_preadv64v2 -547 x32 pwritev2 __x32_compat_sys_pwritev64v2 +512 x32 rt_sigaction compat_sys_rt_sigaction +513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn +514 x32 ioctl compat_sys_ioctl +515 x32 readv compat_sys_readv +516 x32 writev compat_sys_writev +517 x32 recvfrom compat_sys_recvfrom +518 x32 sendmsg compat_sys_sendmsg +519 x32 recvmsg compat_sys_recvmsg +520 x32 execve compat_sys_execve +521 x32 ptrace compat_sys_ptrace +522 x32 rt_sigpending compat_sys_rt_sigpending +523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo +525 x32 sigaltstack compat_sys_sigaltstack +526 x32 timer_create compat_sys_timer_create +527 x32 mq_notify compat_sys_mq_notify +528 x32 kexec_load compat_sys_kexec_load +529 x32 waitid compat_sys_waitid +530 x32 set_robust_list compat_sys_set_robust_list +531 x32 get_robust_list compat_sys_get_robust_list +532 x32 vmsplice compat_sys_vmsplice +533 x32 move_pages compat_sys_move_pages +534 x32 preadv compat_sys_preadv64 +535 x32 pwritev compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg compat_sys_recvmmsg_time64 +538 x32 sendmmsg compat_sys_sendmmsg +539 x32 process_vm_readv compat_sys_process_vm_readv +540 x32 process_vm_writev compat_sys_process_vm_writev +541 x32 setsockopt compat_sys_setsockopt +542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit +545 x32 execveat compat_sys_execveat +546 x32 preadv2 compat_sys_preadv64v2 +547 x32 pwritev2 compat_sys_pwritev64v2 diff --git a/arch/x86/entry/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh index 12fbbcfe7ef3..cc1e63857427 100644 --- a/arch/x86/entry/syscalls/syscallhdr.sh +++ b/arch/x86/entry/syscalls/syscallhdr.sh @@ -15,14 +15,21 @@ grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | ( echo "#define ${fileguard} 1" echo "" + max=0 while read nr abi name entry ; do if [ -z "$offset" ]; then echo "#define __NR_${prefix}${name} $nr" else echo "#define __NR_${prefix}${name} ($offset + $nr)" fi + + max=$nr done echo "" + echo "#ifdef __KERNEL__" + echo "#define __NR_${prefix}syscall_max $max" + echo "#endif" + echo "" echo "#endif /* ${fileguard} */" ) > "$out" diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 1af2be39e7d9..929bde120d6b 100644 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh @@ -9,15 +9,7 @@ syscall_macro() { local nr="$2" local entry="$3" - # Entry can be either just a function name or "function/qualifier" - real_entry="${entry%%/*}" - if [ "$entry" = "$real_entry" ]; then - qualifier= - else - qualifier=${entry#*/} - fi - - echo "__SYSCALL_${abi}($nr, $real_entry, $qualifier)" + echo "__SYSCALL_${abi}($nr, $entry)" } emit() { @@ -25,27 +17,15 @@ emit() { local nr="$2" local entry="$3" local compat="$4" - local umlentry="" if [ "$abi" != "I386" -a -n "$compat" ]; then echo "a compat entry ($abi: $compat) for a 64-bit syscall makes no sense" >&2 exit 1 fi - # For CONFIG_UML, we need to strip the __x64_sys prefix - if [ "$abi" = "64" -a "${entry}" != "${entry#__x64_sys}" ]; then - umlentry="sys${entry#__x64_sys}" - fi - if [ -z "$compat" ]; then - if [ -n "$entry" -a -z "$umlentry" ]; then - syscall_macro "$abi" "$nr" "$entry" - elif [ -n "$umlentry" ]; then # implies -n "$entry" - echo "#ifdef CONFIG_X86" + if [ -n "$entry" ]; then syscall_macro "$abi" "$nr" "$entry" - echo "#else /* CONFIG_UML */" - syscall_macro "$abi" "$nr" "$umlentry" - echo "#endif" fi else echo "#ifdef CONFIG_X86_32" @@ -61,24 +41,6 @@ emit() { grep '^[0-9]' "$in" | sort -n | ( while read nr abi name entry compat; do abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` - if [ "$abi" = "COMMON" -o "$abi" = "64" ]; then - emit 64 "$nr" "$entry" "$compat" - if [ "$abi" = "COMMON" ]; then - # COMMON means that this syscall exists in the same form for - # 64-bit and X32. - echo "#ifdef CONFIG_X86_X32_ABI" - emit X32 "$nr" "$entry" "$compat" - echo "#endif" - fi - elif [ "$abi" = "X32" ]; then - echo "#ifdef CONFIG_X86_X32_ABI" - emit X32 "$nr" "$entry" "$compat" - echo "#endif" - elif [ "$abi" = "I386" ]; then - emit "$abi" "$nr" "$entry" "$compat" - else - echo "Unknown abi $abi" >&2 - exit 1 - fi + emit "$abi" "$nr" "$entry" "$compat" done ) > "$out" diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index e010d4ae11f1..3a07ce3ec70b 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -35,9 +35,9 @@ SYM_CODE_END(\name) #endif #ifdef CONFIG_PREEMPTION - THUNK ___preempt_schedule, preempt_schedule - THUNK ___preempt_schedule_notrace, preempt_schedule_notrace - EXPORT_SYMBOL(___preempt_schedule) - EXPORT_SYMBOL(___preempt_schedule_notrace) + THUNK preempt_schedule_thunk, preempt_schedule + THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace + EXPORT_SYMBOL(preempt_schedule_thunk) + EXPORT_SYMBOL(preempt_schedule_notrace_thunk) #endif diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index c5c3b6e86e62..dbe4493b534e 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -47,10 +47,10 @@ SYM_FUNC_END(\name) #endif #ifdef CONFIG_PREEMPTION - THUNK ___preempt_schedule, preempt_schedule - THUNK ___preempt_schedule_notrace, preempt_schedule_notrace - EXPORT_SYMBOL(___preempt_schedule) - EXPORT_SYMBOL(___preempt_schedule_notrace) + THUNK preempt_schedule_thunk, preempt_schedule + THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace + EXPORT_SYMBOL(preempt_schedule_thunk) + EXPORT_SYMBOL(preempt_schedule_notrace_thunk) #endif #if defined(CONFIG_TRACE_IRQFLAGS) \ diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index ea7e0155c604..4d152933547d 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -57,6 +57,13 @@ SECTIONS *(.gnu.linkonce.b.*) } :text + /* + * Discard .note.gnu.property sections which are unused and have + * different alignment requirement from vDSO note sections. + */ + /DISCARD/ : { + *(.note.gnu.property) + } .note : { *(.note.*) } :text :note .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 9242b28418d5..1e82bd43286c 100644 --- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -13,6 +13,7 @@ */ #undef CONFIG_64BIT #undef CONFIG_X86_64 +#undef CONFIG_COMPAT #undef CONFIG_PGTABLE_LEVELS #undef CONFIG_ILLEGAL_POINTER_VALUE #undef CONFIG_SPARSEMEM_VMEMMAP diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index c1b8496b5606..43428cc514c8 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -38,6 +38,8 @@ struct vdso_data *arch_get_vdso_data(void *vvar_page) } #undef EMIT_VVAR +unsigned int vclocks_used __read_mostly; + #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; #endif @@ -219,7 +221,7 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, } else if (sym_offset == image->sym_pvclock_page) { struct pvclock_vsyscall_time_info *pvti = pvclock_get_pvti_cpu0_va(); - if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) { + if (pvti && vclock_was_used(VDSO_CLOCKMODE_PVCLOCK)) { return vmf_insert_pfn_prot(vma, vmf->address, __pa(pvti) >> PAGE_SHIFT, pgprot_decrypted(vma->vm_page_prot)); @@ -227,7 +229,7 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, } else if (sym_offset == image->sym_hvclock_page) { struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page(); - if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK)) + if (tsc_pg && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK)) return vmf_insert_pfn(vma, vmf->address, virt_to_phys(tsc_pg) >> PAGE_SHIFT); } else if (sym_offset == image->sym_timens_page) { @@ -445,6 +447,8 @@ __setup("vdso=", vdso_setup); static int __init init_vdso(void) { + BUILD_BUG_ON(VDSO_CLOCKMODE_MAX >= 32); + init_vdso_image(&vdso_image_64); #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 1f22b6bbda68..39eb276d0277 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -250,6 +250,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, 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/core.c b/arch/x86/events/core.c index 3bb738f5a472..a619763e96e1 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2490,7 +2490,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent /* 32-bit process in 64-bit kernel. */ unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; - const void __user *fp; + const struct stack_frame_ia32 __user *fp; if (!test_thread_flag(TIF_IA32)) return 0; @@ -2501,18 +2501,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); while (entry->nr < entry->max_stack) { - unsigned long bytes; - frame.next_frame = 0; - frame.return_address = 0; - if (!valid_user_frame(fp, sizeof(frame))) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); - if (bytes != 0) + if (__get_user(frame.next_frame, &fp->next_frame)) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4); - if (bytes != 0) + if (__get_user(frame.return_address, &fp->return_address)) break; perf_callchain_store(entry, cs_base + frame.return_address); @@ -2533,7 +2527,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; - const unsigned long __user *fp; + const struct stack_frame __user *fp; if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ @@ -2546,7 +2540,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; - fp = (unsigned long __user *)regs->bp; + fp = (void __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -2558,19 +2552,12 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_disable(); while (entry->nr < entry->max_stack) { - unsigned long bytes; - - frame.next_frame = NULL; - frame.return_address = 0; - if (!valid_user_frame(fp, sizeof(frame))) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); - if (bytes != 0) + if (__get_user(frame.next_frame, &fp->next_frame)) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); - if (bytes != 0) + if (__get_user(frame.return_address, &fp->return_address)) break; perf_callchain_store(entry, frame.return_address); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 3be51aa06e67..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); } /* @@ -4765,6 +4784,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index e1daf4151e11..e4aa20c0426f 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,17 +40,18 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL + * Available model: SLM,AMT,GLM,CNL,TNT * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM, - * CNL,KBL,CML + * CNL,KBL,CML,TNT * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, - * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -60,17 +61,18 @@ * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,TGL + * KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, - * GLM,CNL,KBL,CML,ICL,TGL + * GLM,CNL,KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -87,7 +89,8 @@ * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL + * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * */ @@ -591,62 +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_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(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_SANDYBRIDGE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE_X, snb_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_IVYBRIDGE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_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_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(IVYBRIDGE, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_L, hswult_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_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(HASWELL_L, &hswult_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(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_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(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_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(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_CANNONLAKE_L, cnl_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_XEON_PHI_KNL, knl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &cnl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_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_PLUS, 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/ds.c b/arch/x86/events/intel/ds.c index 4b94ae4ae369..dc43cc124e09 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1714,6 +1714,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) old = ((s64)(prev_raw_count << shift) >> shift); local64_add(new - old + count * period, &event->count); + local64_set(&hwc->period_left, -new); + perf_event_update_userpage(event); return 0; 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/events/msr.c b/arch/x86/events/msr.c index 6f86650b3f77..a949f6f55991 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -75,8 +75,9 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_ATOM_GOLDMONT_D: - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index d13b352b2aa7..8e4d0391ff6c 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -3,7 +3,7 @@ # Makefile for the ia32 kernel emulation subsystem. # -obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o +obj-$(CONFIG_IA32_EMULATION) := ia32_signal.o obj-$(CONFIG_IA32_AOUT) += ia32_aout.o diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index a3aefe9b9401..f9d8804144d0 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -36,70 +36,56 @@ #include <asm/sighandling.h> #include <asm/smap.h> +static inline void reload_segments(struct sigcontext_32 *sc) +{ + unsigned int cur; + + savesegment(gs, cur); + if ((sc->gs | 0x03) != cur) + load_gs_index(sc->gs | 0x03); + savesegment(fs, cur); + if ((sc->fs | 0x03) != cur) + loadsegment(fs, sc->fs | 0x03); + savesegment(ds, cur); + if ((sc->ds | 0x03) != cur) + loadsegment(ds, sc->ds | 0x03); + savesegment(es, cur); + if ((sc->es | 0x03) != cur) + loadsegment(es, sc->es | 0x03); +} + /* * Do a signal return; undo the signal stack. */ -#define loadsegment_gs(v) load_gs_index(v) -#define loadsegment_fs(v) loadsegment(fs, v) -#define loadsegment_ds(v) loadsegment(ds, v) -#define loadsegment_es(v) loadsegment(es, v) - -#define get_user_seg(seg) ({ unsigned int v; savesegment(seg, v); v; }) -#define set_user_seg(seg, v) loadsegment_##seg(v) - -#define COPY(x) { \ - get_user_ex(regs->x, &sc->x); \ -} - -#define GET_SEG(seg) ({ \ - unsigned short tmp; \ - get_user_ex(tmp, &sc->seg); \ - tmp; \ -}) - -#define COPY_SEG_CPL3(seg) do { \ - regs->seg = GET_SEG(seg) | 3; \ -} while (0) - -#define RELOAD_SEG(seg) { \ - unsigned int pre = (seg) | 3; \ - unsigned int cur = get_user_seg(seg); \ - if (pre != cur) \ - set_user_seg(seg, pre); \ -} - static int ia32_restore_sigcontext(struct pt_regs *regs, - struct sigcontext_32 __user *sc) + struct sigcontext_32 __user *usc) { - unsigned int tmpflags, err = 0; - u16 gs, fs, es, ds; - void __user *buf; - u32 tmp; + struct sigcontext_32 sc; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; - get_user_try { - gs = GET_SEG(gs); - fs = GET_SEG(fs); - ds = GET_SEG(ds); - es = GET_SEG(es); - - COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); COPY(ax); - /* Don't touch extended registers */ - - COPY_SEG_CPL3(cs); - COPY_SEG_CPL3(ss); - - get_user_ex(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); - /* disable syscall checks */ - regs->orig_ax = -1; + if (unlikely(copy_from_user(&sc, usc, sizeof(sc)))) + return -EFAULT; - get_user_ex(tmp, &sc->fpstate); - buf = compat_ptr(tmp); - } get_user_catch(err); + /* Get only the ia32 registers. */ + regs->bx = sc.bx; + regs->cx = sc.cx; + regs->dx = sc.dx; + regs->si = sc.si; + regs->di = sc.di; + regs->bp = sc.bp; + regs->ax = sc.ax; + regs->sp = sc.sp; + regs->ip = sc.ip; + + /* Get CS/SS and force CPL3 */ + regs->cs = sc.cs | 0x03; + regs->ss = sc.ss | 0x03; + + regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); + /* disable syscall checks */ + regs->orig_ax = -1; /* * Reload fs and gs if they have changed in the signal @@ -107,14 +93,8 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, * the handler, but does not clobber them at least in the * normal case. */ - RELOAD_SEG(gs); - RELOAD_SEG(fs); - RELOAD_SEG(ds); - RELOAD_SEG(es); - - err |= fpu__restore_sig(buf, 1); - - return err; + reload_segments(&sc); + return fpu__restore_sig(compat_ptr(sc.fpstate), 1); } COMPAT_SYSCALL_DEFINE0(sigreturn) @@ -126,10 +106,7 @@ COMPAT_SYSCALL_DEFINE0(sigreturn) if (!access_ok(frame, sizeof(*frame))) goto badframe; if (__get_user(set.sig[0], &frame->sc.oldmask) - || (_COMPAT_NSIG_WORDS > 1 - && __copy_from_user((((char *) &set.sig) + 4), - &frame->extramask, - sizeof(frame->extramask)))) + || __get_user(((__u32 *)&set)[1], &frame->extramask[0])) goto badframe; set_current_blocked(&set); @@ -153,7 +130,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn) if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; set_current_blocked(&set); @@ -175,44 +152,51 @@ badframe: * Set up a signal frame. */ -static int ia32_setup_sigcontext(struct sigcontext_32 __user *sc, - void __user *fpstate, - struct pt_regs *regs, unsigned int mask) +#define get_user_seg(seg) ({ unsigned int v; savesegment(seg, v); v; }) + +static __always_inline int +__unsafe_setup_sigcontext32(struct sigcontext_32 __user *sc, + void __user *fpstate, + struct pt_regs *regs, unsigned int mask) { - int err = 0; - - put_user_try { - put_user_ex(get_user_seg(gs), (unsigned int __user *)&sc->gs); - put_user_ex(get_user_seg(fs), (unsigned int __user *)&sc->fs); - put_user_ex(get_user_seg(ds), (unsigned int __user *)&sc->ds); - put_user_ex(get_user_seg(es), (unsigned int __user *)&sc->es); - - put_user_ex(regs->di, &sc->di); - put_user_ex(regs->si, &sc->si); - put_user_ex(regs->bp, &sc->bp); - put_user_ex(regs->sp, &sc->sp); - put_user_ex(regs->bx, &sc->bx); - put_user_ex(regs->dx, &sc->dx); - put_user_ex(regs->cx, &sc->cx); - put_user_ex(regs->ax, &sc->ax); - put_user_ex(current->thread.trap_nr, &sc->trapno); - put_user_ex(current->thread.error_code, &sc->err); - put_user_ex(regs->ip, &sc->ip); - put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); - put_user_ex(regs->flags, &sc->flags); - put_user_ex(regs->sp, &sc->sp_at_signal); - put_user_ex(regs->ss, (unsigned int __user *)&sc->ss); - - put_user_ex(ptr_to_compat(fpstate), &sc->fpstate); - - /* non-iBCS2 extensions.. */ - put_user_ex(mask, &sc->oldmask); - put_user_ex(current->thread.cr2, &sc->cr2); - } put_user_catch(err); - - return err; + unsafe_put_user(get_user_seg(gs), (unsigned int __user *)&sc->gs, Efault); + unsafe_put_user(get_user_seg(fs), (unsigned int __user *)&sc->fs, Efault); + unsafe_put_user(get_user_seg(ds), (unsigned int __user *)&sc->ds, Efault); + unsafe_put_user(get_user_seg(es), (unsigned int __user *)&sc->es, Efault); + + unsafe_put_user(regs->di, &sc->di, Efault); + unsafe_put_user(regs->si, &sc->si, Efault); + unsafe_put_user(regs->bp, &sc->bp, Efault); + unsafe_put_user(regs->sp, &sc->sp, Efault); + unsafe_put_user(regs->bx, &sc->bx, Efault); + unsafe_put_user(regs->dx, &sc->dx, Efault); + unsafe_put_user(regs->cx, &sc->cx, Efault); + unsafe_put_user(regs->ax, &sc->ax, Efault); + unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); + unsafe_put_user(current->thread.error_code, &sc->err, Efault); + unsafe_put_user(regs->ip, &sc->ip, Efault); + unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault); + unsafe_put_user(regs->flags, &sc->flags, Efault); + unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault); + unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault); + + unsafe_put_user(ptr_to_compat(fpstate), &sc->fpstate, Efault); + + /* non-iBCS2 extensions.. */ + unsafe_put_user(mask, &sc->oldmask, Efault); + unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); + return 0; + +Efault: + return -EFAULT; } +#define unsafe_put_sigcontext32(sc, fp, regs, set, label) \ +do { \ + if (__unsafe_setup_sigcontext32(sc, fp, regs, set->sig[0])) \ + goto label; \ +} while(0) + /* * Determine which stack to use.. */ @@ -252,8 +236,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, { struct sigframe_ia32 __user *frame; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; + void __user *fp = NULL; /* copy_to_user optimizes that into a single 8 byte store */ static const struct { @@ -266,22 +249,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, 0x80cd, /* int $0x80 */ }; - frame = get_sigframe(ksig, regs, sizeof(*frame), &fpstate); - - if (!access_ok(frame, sizeof(*frame))) - return -EFAULT; - - if (__put_user(sig, &frame->sig)) - return -EFAULT; - - if (ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0])) - return -EFAULT; - - if (_COMPAT_NSIG_WORDS > 1) { - if (__copy_to_user(frame->extramask, &set->sig[1], - sizeof(frame->extramask))) - return -EFAULT; - } + frame = get_sigframe(ksig, regs, sizeof(*frame), &fp); if (ksig->ka.sa.sa_flags & SA_RESTORER) { restorer = ksig->ka.sa.sa_restorer; @@ -294,19 +262,20 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, restorer = &frame->retcode; } - put_user_try { - put_user_ex(ptr_to_compat(restorer), &frame->pretcode); - - /* - * These are actually not used anymore, but left because some - * gdb versions depend on them as a marker. - */ - put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); - } put_user_catch(err); - - if (err) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; + unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_sigcontext32(&frame->sc, fp, regs, set, Efault); + unsafe_put_user(set->sig[1], &frame->extramask[0], Efault); + unsafe_put_user(ptr_to_compat(restorer), &frame->pretcode, Efault); + /* + * These are actually not used anymore, but left because some + * gdb versions depend on them as a marker. + */ + unsafe_put_user(*((u64 *)&code), (u64 __user *)frame->retcode, Efault); + user_access_end(); + /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; regs->ip = (unsigned long) ksig->ka.sa.sa_handler; @@ -323,6 +292,9 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, regs->ss = __USER32_DS; return 0; +Efault: + user_access_end(); + return -EFAULT; } int ia32_setup_rt_frame(int sig, struct ksignal *ksig, @@ -330,10 +302,9 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, { struct rt_sigframe_ia32 __user *frame; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; + void __user *fp = NULL; - /* __copy_to_user optimizes that into a single 8 byte store */ + /* unsafe_put_user optimizes that into a single 8 byte store */ static const struct { u8 movl; u32 val; @@ -346,44 +317,40 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, 0, }; - frame = get_sigframe(ksig, regs, sizeof(*frame), &fpstate); + frame = get_sigframe(ksig, regs, sizeof(*frame), &fp); - if (!access_ok(frame, sizeof(*frame))) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - put_user_try { - put_user_ex(sig, &frame->sig); - put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo); - put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); + unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_user(ptr_to_compat(&frame->info), &frame->pinfo, Efault); + unsafe_put_user(ptr_to_compat(&frame->uc), &frame->puc, Efault); - /* Create the ucontext. */ - if (static_cpu_has(X86_FEATURE_XSAVE)) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); + /* Create the ucontext. */ + if (static_cpu_has(X86_FEATURE_XSAVE)) + unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault); + else + unsafe_put_user(0, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - if (ksig->ka.sa.sa_flags & SA_RESTORER) - restorer = ksig->ka.sa.sa_restorer; - else - restorer = current->mm->context.vdso + - vdso_image_32.sym___kernel_rt_sigreturn; - put_user_ex(ptr_to_compat(restorer), &frame->pretcode); - - /* - * Not actually used anymore, but left because some gdb - * versions need it. - */ - put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); - } put_user_catch(err); - - err |= __copy_siginfo_to_user32(&frame->info, &ksig->info, false); - err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (err) + if (ksig->ka.sa.sa_flags & SA_RESTORER) + restorer = ksig->ka.sa.sa_restorer; + else + restorer = current->mm->context.vdso + + vdso_image_32.sym___kernel_rt_sigreturn; + unsafe_put_user(ptr_to_compat(restorer), &frame->pretcode, Efault); + + /* + * Not actually used anymore, but left because some gdb + * versions need it. + */ + unsafe_put_user(*((u64 *)&code), (u64 __user *)frame->retcode, Efault); + unsafe_put_sigcontext32(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_user(*(__u64 *)set, (__u64 *)&frame->uc.uc_sigmask, Efault); + user_access_end(); + + if (__copy_siginfo_to_user32(&frame->info, &ksig->info, false)) return -EFAULT; /* Set up registers for signal handler */ @@ -402,4 +369,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, regs->ss = __USER32_DS; return 0; +Efault: + user_access_end(); + return -EFAULT; } diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index ea34464d6221..b19ec8282d50 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -10,5 +10,3 @@ generated-y += xen-hypercalls.h generic-y += early_ioremap.h generic-y += export.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h 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/asm.h b/arch/x86/include/asm/asm.h index cd339b88d5d4..0f63585edf5f 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -138,9 +138,6 @@ # define _ASM_EXTABLE_FAULT(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) -# define _ASM_EXTABLE_EX(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) - # define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ _ASM_ALIGN ; \ @@ -166,9 +163,6 @@ # define _ASM_EXTABLE_FAULT(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) -# define _ASM_EXTABLE_EX(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) - /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 062cdecb2f24..53f246e9df5a 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -54,7 +54,7 @@ arch_set_bit(long nr, volatile unsigned long *addr) if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "orb %1,%0" : CONST_MASK_ADDR(nr, addr) - : "iq" ((u8)CONST_MASK(nr)) + : "iq" (CONST_MASK(nr) & 0xff) : "memory"); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" @@ -74,7 +74,7 @@ arch_clear_bit(long nr, volatile unsigned long *addr) if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "andb %1,%0" : CONST_MASK_ADDR(nr, addr) - : "iq" ((u8)~CONST_MASK(nr))); + : "iq" (CONST_MASK(nr) ^ 0xff)); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index dc4cfc888d6d..dc9dc7b3911a 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -4,14 +4,18 @@ #ifndef _ASM_X86_CLOCKSOURCE_H #define _ASM_X86_CLOCKSOURCE_H -#define VCLOCK_NONE 0 /* No vDSO clock available. */ -#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ -#define VCLOCK_PVCLOCK 2 /* vDSO should use vread_pvclock. */ -#define VCLOCK_HVCLOCK 3 /* vDSO should use vread_hvclock. */ -#define VCLOCK_MAX 3 +#include <asm/vdso/clocksource.h> -struct arch_clocksource_data { - int vclock_mode; -}; +extern unsigned int vclocks_used; + +static inline bool vclock_was_used(int vclock) +{ + return READ_ONCE(vclocks_used) & (1U << vclock); +} + +static inline void vclocks_set_used(unsigned int which) +{ + WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << which)); +} #endif /* _ASM_X86_CLOCKSOURCE_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index adc6cc86b062..ff6f3ca649b3 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -40,4 +40,16 @@ int mwait_usable(const struct cpuinfo_x86 *); unsigned int x86_family(unsigned int sig); unsigned int x86_model(unsigned int sig); unsigned int x86_stepping(unsigned int sig); +#ifdef CONFIG_CPU_SUP_INTEL +extern void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c); +extern void switch_to_sld(unsigned long tifn); +extern bool handle_user_split_lock(struct pt_regs *regs, long error_code); +#else +static inline void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) {} +static inline void switch_to_sld(unsigned long tifn) {} +static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code) +{ + return false; +} +#endif #endif /* _ASM_X86_CPU_H */ 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..db189945e9b0 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 */ @@ -285,6 +285,7 @@ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -299,6 +300,7 @@ #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. */ @@ -367,6 +369,7 @@ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ /* diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index ae391f609840..f71a0cce9373 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -42,8 +42,8 @@ * Emit CFI data in .debug_frame sections, not .eh_frame sections. * The latter we currently just discard since we don't do DWARF * unwinding at runtime. So only the offline DWARF information is - * useful to anyone. Note we should not use this directive if - * vmlinux.lds.S gets changed so it doesn't discard .eh_frame. + * useful to anyone. Note we should not use this directive if we + * ever decide to enable DWARF unwinding at runtime. */ .cfi_sections .debug_frame #else 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/irq.h b/arch/x86/include/asm/irq.h index a176f6165d85..72fba0eeeb30 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -36,7 +36,7 @@ extern void native_init_IRQ(void); extern void handle_irq(struct irq_desc *desc, struct pt_regs *regs); -extern __visible unsigned int do_IRQ(struct pt_regs *regs); +extern __visible void do_IRQ(struct pt_regs *regs); extern void init_ISA_irqs(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_host.h b/arch/x86/include/asm/kvm_host.h index 4dffbc10d3f8..42a2d0d3984a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -49,13 +49,16 @@ #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS +#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ + KVM_DIRTY_LOG_INITIALLY_SET) + /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) #define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) #define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) #define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) -#define KVM_REQ_LOAD_CR3 KVM_ARCH_REQ(5) +#define KVM_REQ_LOAD_MMU_PGD KVM_ARCH_REQ(5) #define KVM_REQ_EVENT KVM_ARCH_REQ(6) #define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) @@ -182,7 +185,10 @@ enum exit_fastpath_completion { EXIT_FASTPATH_SKIP_EMUL_INS, }; -#include <asm/kvm_emulate.h> +struct x86_emulate_ctxt; +struct x86_exception; +enum x86_intercept; +enum x86_intercept_stage; #define KVM_NR_MEM_OBJS 40 @@ -297,7 +303,6 @@ union kvm_mmu_extended_role { unsigned int cr4_pke:1; unsigned int cr4_smap:1; unsigned int cr4_smep:1; - unsigned int cr4_la57:1; unsigned int maxphyaddr:6; }; }; @@ -382,8 +387,7 @@ struct kvm_mmu_root_info { * current mmu mode. */ struct kvm_mmu { - void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); - unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); + unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, bool prefault); @@ -678,7 +682,7 @@ struct kvm_vcpu_arch { /* emulate context */ - struct x86_emulate_ctxt emulate_ctxt; + struct x86_emulate_ctxt *emulate_ctxt; bool emulate_regs_need_sync_to_vcpu; bool emulate_regs_need_sync_from_vcpu; int (*complete_userspace_io)(struct kvm_vcpu *vcpu); @@ -781,9 +785,19 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; /* - * Indicate whether the access faults on its page table in guest - * which is set when fix page fault and used to detect unhandeable - * instruction. + * Indicates the guest is trying to write a gfn that contains one or + * more of the PTEs used to translate the write itself, i.e. the access + * is changing its own translation in the guest page tables. KVM exits + * to userspace if emulation of the faulting instruction fails and this + * flag is set, as KVM cannot make forward progress. + * + * If emulation fails for a write to guest page tables, KVM unprotects + * (zaps) the shadow page for the target gfn and resumes the guest to + * retry the non-emulatable instruction (on hardware). Unprotecting the + * gfn doesn't allow forward progress for a self-changing access because + * doing so also zaps the translation for the gfn, i.e. retrying the + * instruction will hit a !PRESENT fault, which results in a new shadow + * page and sends KVM back to square one. */ bool write_fault_to_shadow_pgtable; @@ -798,10 +812,6 @@ struct kvm_vcpu_arch { int pending_ioapic_eoi; int pending_external_vector; - /* GPA available */ - bool gpa_available; - gpa_t gpa_val; - /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; @@ -880,6 +890,7 @@ enum kvm_irqchip_mode { #define APICV_INHIBIT_REASON_NESTED 2 #define APICV_INHIBIT_REASON_IRQWIN 3 #define APICV_INHIBIT_REASON_PIT_REINJ 4 +#define APICV_INHIBIT_REASON_X2APIC 5 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -910,6 +921,7 @@ struct kvm_arch { atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; + bool apic_map_dirty; bool apic_access_page_done; unsigned long apicv_inhibit_reasons; @@ -1042,19 +1054,14 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) } struct kvm_x86_ops { - int (*cpu_has_kvm_support)(void); /* __init */ - int (*disabled_by_bios)(void); /* __init */ int (*hardware_enable)(void); void (*hardware_disable)(void); - int (*check_processor_compatibility)(void);/* __init */ - int (*hardware_setup)(void); /* __init */ - void (*hardware_unsetup)(void); /* __exit */ + void (*hardware_unsetup)(void); bool (*cpu_has_accelerated_tpr)(void); bool (*has_emulated_msr)(int index); void (*cpuid_update)(struct kvm_vcpu *vcpu); - struct kvm *(*vm_alloc)(void); - void (*vm_free)(struct kvm *); + unsigned int vm_size; int (*vm_init)(struct kvm *kvm); void (*vm_destroy)(struct kvm *kvm); @@ -1080,7 +1087,6 @@ struct kvm_x86_ops { void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu); void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); - void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); @@ -1112,6 +1118,7 @@ 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, @@ -1136,19 +1143,14 @@ 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); int (*get_tdp_level)(struct kvm_vcpu *vcpu); u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); - int (*get_lpage_level)(void); - bool (*rdtscp_supported)(void); - bool (*invpcid_supported)(void); - - void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); - void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry); + void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, unsigned long cr3); bool (*has_wbinvd_exit)(void); @@ -1160,16 +1162,12 @@ struct kvm_x86_ops { int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, - enum x86_intercept_stage stage); + enum x86_intercept_stage stage, + struct x86_exception *exception); void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion *exit_fastpath); - bool (*mpx_supported)(void); - bool (*xsaves_supported)(void); - bool (*umip_emulated)(void); - bool (*pt_supported)(void); - bool (*pku_supported)(void); - int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + int (*check_nested_events)(struct kvm_vcpu *vcpu); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1258,6 +1256,15 @@ struct kvm_x86_ops { int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); }; +struct kvm_x86_init_ops { + int (*cpu_has_kvm_support)(void); + int (*disabled_by_bios)(void); + int (*check_processor_compatibility)(void); + int (*hardware_setup)(void); + + struct kvm_x86_ops *runtime_ops; +}; + struct kvm_arch_async_pf { u32 token; gfn_t gfn; @@ -1265,25 +1272,24 @@ struct kvm_arch_async_pf { bool direct_map; }; -extern struct kvm_x86_ops *kvm_x86_ops; +extern u64 __read_mostly host_efer; + +extern struct kvm_x86_ops kvm_x86_ops; extern struct kmem_cache *x86_fpu_cache; #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { - return kvm_x86_ops->vm_alloc(); -} - -static inline void kvm_arch_free_vm(struct kvm *kvm) -{ - return kvm_x86_ops->vm_free(kvm); + return __vmalloc(kvm_x86_ops.vm_size, + GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL); } +void kvm_arch_free_vm(struct kvm *kvm); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) { - if (kvm_x86_ops->tlb_remote_flush && - !kvm_x86_ops->tlb_remote_flush(kvm)) + if (kvm_x86_ops.tlb_remote_flush && + !kvm_x86_ops.tlb_remote_flush(kvm)) return 0; else return -ENOTSUPP; @@ -1302,7 +1308,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot); + struct kvm_memory_slot *memslot, + int start_level); void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, @@ -1368,10 +1375,11 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to * decode the instruction length. For use *only* by - * kvm_x86_ops->skip_emulated_instruction() implementations. + * kvm_x86_ops.skip_emulated_instruction() implementations. * - * EMULTYPE_ALLOW_RETRY - Set when the emulator should resume the guest to - * retry native execution under certain conditions. + * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to + * retry native execution under certain conditions, + * Can only be set in conjunction with EMULTYPE_PF. * * EMULTYPE_TRAP_UD_FORCED - Set when emulating an intercepted #UD that was * triggered by KVM's magic "force emulation" prefix, @@ -1384,13 +1392,18 @@ extern u64 kvm_mce_cap_supported; * backdoor emulation, which is opt in via module param. * VMware backoor emulation handles select instructions * and reinjects the #GP for all other cases. + * + * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which + * case the CR2/GPA value pass on the stack is valid. */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -#define EMULTYPE_ALLOW_RETRY (1 << 3) +#define EMULTYPE_ALLOW_RETRY_PF (1 << 3) #define EMULTYPE_TRAP_UD_FORCED (1 << 4) #define EMULTYPE_VMWARE_GP (1 << 5) +#define EMULTYPE_PF (1 << 6) + int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); @@ -1403,8 +1416,6 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data); int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu); int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu); -struct x86_emulate_ctxt; - int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); @@ -1501,8 +1512,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush); -void kvm_enable_tdp(void); -void kvm_disable_tdp(void); +void kvm_configure_mmu(bool enable_tdp, int tdp_page_level); static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception) @@ -1659,14 +1669,14 @@ static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->vcpu_blocking) - kvm_x86_ops->vcpu_blocking(vcpu); + if (kvm_x86_ops.vcpu_blocking) + kvm_x86_ops.vcpu_blocking(vcpu); } static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->vcpu_unblocking) - kvm_x86_ops->vcpu_unblocking(vcpu); + if (kvm_x86_ops.vcpu_unblocking) + kvm_x86_ops.vcpu_unblocking(vcpu); } static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 172f9749dbb2..87bd6025d91d 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -49,8 +49,7 @@ struct kvm_page_track_notifier_node { void kvm_page_track_init(struct kvm *kvm); void kvm_page_track_cleanup(struct kvm *kvm); -void kvm_page_track_free_memslot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); +void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4359b955e0b7..f9cea081c05b 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 { @@ -238,9 +238,6 @@ extern void mce_disable_bank(int bank); /* * Exception handler */ - -/* Call the installed machine check handler for this CPU setup. */ -extern void (*machine_check_vector)(struct pt_regs *, long error_code); void do_machine_check(struct pt_regs *, long); /* diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index b538d9ddee9c..4e55370e48e8 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -213,21 +213,6 @@ static inline void arch_unmap(struct mm_struct *mm, unsigned long start, * So do not enforce things if the VMA is not from the current * mm, or if we are in a kernel thread. */ -static inline bool vma_is_foreign(struct vm_area_struct *vma) -{ - if (!current->mm) - return true; - /* - * Should PKRU be enforced on the access to this VMA? If - * the VMA is from another process, then PKRU has no - * relevance and should not be enforced. - */ - if (current->mm != vma->vm_mm) - return true; - - return false; -} - static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 6b79515abb82..edc2c581704a 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -46,7 +46,9 @@ typedef int (*hyperv_fill_flush_list_func)( #define hv_set_reference_tsc(val) \ wrmsrl(HV_X64_MSR_REFERENCE_TSC, val) #define hv_set_clocksource_vdso(val) \ - ((val).archdata.vclock_mode = VCLOCK_HVCLOCK) + ((val).vdso_clock_mode = VDSO_CLOCKMODE_HVCLOCK) +#define hv_enable_vdso_clocksource() \ + vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK); #define hv_get_raw_timer() rdtsc_ordered() void hyperv_callback_vector(void); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ebe1685e92dd..12c9684d59ba 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -41,6 +41,10 @@ /* Intel MSRs. Some also available on other CPUs */ +#define MSR_TEST_CTRL 0x00000033 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) + #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS BIT(0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ @@ -70,6 +74,11 @@ */ #define MSR_IA32_UMWAIT_CONTROL_TIME_MASK (~0x03U) +/* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */ +#define MSR_IA32_CORE_CAPS 0x000000cf +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT 5 +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT) + #define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) #define NHM_C1_AUTO_DEMOTE (1UL << 26) @@ -512,6 +521,8 @@ #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/mwait.h b/arch/x86/include/asm/mwait.h index 9d5252c9685c..b809f117f3f4 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -23,6 +23,8 @@ #define MWAITX_MAX_LOOPS ((u32)-1) #define MWAITX_DISABLE_CSTATES 0xf0 +u32 get_umwait_control_msr(void); + static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) { 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/pgtable.h b/arch/x86/include/asm/pgtable.h index 7e118660bbd9..afda66a6d325 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -595,12 +595,6 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } -static inline pud_t pud_mknotpresent(pud_t pud) -{ - return pfn_pud(pud_pfn(pud), - __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); -} - static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) @@ -627,12 +621,15 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return __pmd(val); } -/* mprotect needs to preserve PAT bits when updating vm_page_prot */ +/* + * mprotect needs to preserve PAT and encryption bits when updating + * vm_page_prot + */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; - pgprotval_t addbits = pgprot_val(newprot); + pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0239998d8cdc..65c2ecd730c5 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -118,7 +118,7 @@ */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) /* diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 19b137f1b3be..2ff9b98812b7 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -4,6 +4,11 @@ #define ARCH_DEFAULT_PKEY 0 +/* + * If more than 16 keys are ever supported, a thorough audit + * will be necessary to ensure that the types that store key + * numbers and masks have sufficient capacity. + */ #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 3d4cb83a8828..69485ca13665 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -103,14 +103,14 @@ static __always_inline bool should_resched(int preempt_offset) } #ifdef CONFIG_PREEMPTION - extern asmlinkage void ___preempt_schedule(void); + extern asmlinkage void preempt_schedule_thunk(void); # define __preempt_schedule() \ - asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT) + asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); - extern asmlinkage void ___preempt_schedule_notrace(void); + extern asmlinkage void preempt_schedule_notrace_thunk(void); # define __preempt_schedule_notrace() \ - asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT) + asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule_notrace(void); #endif diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 09705ccc393c..3bcf27caf6c9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -26,6 +26,7 @@ struct vm86; #include <asm/fpu/types.h> #include <asm/unwind_hints.h> #include <asm/vmxfeatures.h> +#include <asm/vdso/processor.h> #include <linux/personality.h> #include <linux/cache.h> @@ -541,7 +542,6 @@ struct thread_struct { mm_segment_t addr_limit; unsigned int sig_on_uaccess_err:1; - unsigned int uaccess_err:1; /* uaccess failed */ /* Floating point and extended processor state */ struct fpu fpu; @@ -677,17 +677,6 @@ static inline unsigned int cpuid_edx(unsigned int op) return edx; } -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static __always_inline void rep_nop(void) -{ - asm volatile("rep; nop" ::: "memory"); -} - -static __always_inline void cpu_relax(void) -{ - rep_nop(); -} - /* * This function forces the icache and prefetched instruction stream to * catch up with reality in two very specific cases: diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 036c360910c5..a6e8373a5170 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_SECTIONS_H #define _ASM_X86_SECTIONS_H +#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed + #include <asm-generic/sections.h> #include <asm/extable.h> @@ -14,4 +16,22 @@ extern char __end_rodata_hpage_align[]; extern char __end_of_kernel_reserve[]; +extern unsigned long _brk_start, _brk_end; + +static inline bool arch_is_kernel_initmem_freed(unsigned long addr) +{ + /* + * If _brk_start has not been cleared, brk allocation is incomplete, + * and we can not make assumptions about its use. + */ + if (_brk_start) + return 0; + + /* + * After brk allocation is complete, space between _brk_end and _end + * is available for allocation. + */ + return addr >= _brk_end && addr < (unsigned long)&_end; +} + #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 64c3dce374e5..950532ccbc4a 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -46,6 +46,8 @@ int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); int set_memory_np_noalias(unsigned long addr, int numpages); +int set_memory_nonglobal(unsigned long addr, int numpages); +int set_memory_global(unsigned long addr, int numpages); int set_pages_array_uc(struct page **pages, int addrinarray); int set_pages_array_wc(struct page **pages, int addrinarray); diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index f176114c04d4..84eab2724875 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -33,11 +33,7 @@ struct sigframe_ia32 { * legacy application accessing/modifying it. */ struct _fpstate_32 fpstate_unused; -#ifdef CONFIG_IA32_EMULATION - unsigned int extramask[_COMPAT_NSIG_WORDS-1]; -#else /* !CONFIG_IA32_EMULATION */ - unsigned long extramask[_NSIG_WORDS-1]; -#endif /* CONFIG_IA32_EMULATION */ + unsigned int extramask[1]; char retcode[8]; /* fp state follows here */ }; diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index 2fcbd6f33ef7..65e667279e0f 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -14,12 +14,5 @@ X86_EFLAGS_CF | X86_EFLAGS_RF) void signal_fault(struct pt_regs *regs, void __user *frame, char *where); -int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, - struct pt_regs *regs, unsigned long mask); - - -#ifdef CONFIG_X86_X32_ABI -asmlinkage long sys32_x32_rt_sigreturn(void); -#endif #endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 8db3fdb6102e..7cbf733d11af 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -13,23 +13,14 @@ #include <uapi/linux/audit.h> #include <linux/sched.h> #include <linux/err.h> -#include <asm/asm-offsets.h> /* For NR_syscalls */ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> -#ifdef CONFIG_X86_64 -typedef asmlinkage long (*sys_call_ptr_t)(const struct pt_regs *); -#else -typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, - unsigned long, unsigned long, - unsigned long, unsigned long); -#endif /* CONFIG_X86_64 */ +typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; #if defined(CONFIG_X86_32) #define ia32_sys_call_table sys_call_table -#define __NR_syscall_compat_max __NR_syscall_max -#define IA32_NR_syscalls NR_syscalls #endif #if defined(CONFIG_IA32_EMULATION) @@ -168,6 +159,11 @@ static inline int syscall_get_arch(struct task_struct *task) task->thread_info.status & TS_COMPAT) ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; } + +void do_syscall_64(unsigned long nr, struct pt_regs *regs); +void do_int80_syscall_32(struct pt_regs *regs); +long do_fast_syscall_32(struct pt_regs *regs); + #endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_SYSCALL_H */ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index e2389ce9bf58..a84333adeef2 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -8,6 +8,50 @@ struct pt_regs; +extern long __x64_sys_ni_syscall(const struct pt_regs *regs); +extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); + +/* + * Instead of the generic __SYSCALL_DEFINEx() definition, the x86 version takes + * struct pt_regs *regs as the only argument of the syscall stub(s) named as: + * __x64_sys_*() - 64-bit native syscall + * __ia32_sys_*() - 32-bit native syscall or common compat syscall + * __ia32_compat_sys_*() - 32-bit compat syscall + * __x32_compat_sys_*() - 64-bit X32 compat syscall + * + * The registers are decoded according to the ABI: + * 64-bit: RDI, RSI, RDX, R10, R8, R9 + * 32-bit: EBX, ECX, EDX, ESI, EDI, EBP + * + * The stub then passes the decoded arguments to the __se_sys_*() wrapper to + * perform sign-extension (omitted for zero-argument syscalls). Finally the + * arguments are passed to the __do_sys_*() function which is the actual + * syscall. These wrappers are marked as inline so the compiler can optimize + * the functions where appropriate. + * + * Example assembly (slightly re-ordered for better readability): + * + * <__x64_sys_recv>: <-- syscall with 4 parameters + * callq <__fentry__> + * + * mov 0x70(%rdi),%rdi <-- decode regs->di + * mov 0x68(%rdi),%rsi <-- decode regs->si + * mov 0x60(%rdi),%rdx <-- decode regs->dx + * mov 0x38(%rdi),%rcx <-- decode regs->r10 + * + * xor %r9d,%r9d <-- clear %r9 + * xor %r8d,%r8d <-- clear %r8 + * + * callq __sys_recvfrom <-- do the actual work in __sys_recvfrom() + * which takes 6 arguments + * + * cltq <-- extend return value to 64-bit + * retq <-- return + * + * This approach avoids leaking random user-provided register content down + * the call chain. + */ + /* Mapping of registers to parameters for syscalls on x86-64 and x32 */ #define SC_X86_64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ @@ -21,68 +65,96 @@ struct pt_regs; ,,(unsigned int)regs->dx,,(unsigned int)regs->si \ ,,(unsigned int)regs->di,,(unsigned int)regs->bp) -#ifdef CONFIG_IA32_EMULATION -/* - * For IA32 emulation, we need to handle "compat" syscalls *and* create - * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the - * ia32 regs in the proper order for shared or "common" syscalls. As some - * syscalls may not be implemented, we need to expand COND_SYSCALL in - * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this - * case as well. - */ -#define __IA32_COMPAT_SYS_STUB0(x, name) \ - asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO); \ - asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\ +#define __SYS_STUB0(abi, name) \ + long __##abi##_##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__##abi##_##name, ERRNO); \ + long __##abi##_##name(const struct pt_regs *regs) \ + __alias(__do_##name); + +#define __SYS_STUBx(abi, name, ...) \ + long __##abi##_##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__##abi##_##name, ERRNO); \ + long __##abi##_##name(const struct pt_regs *regs) \ { \ - return __se_compat_sys_##name(); \ + return __se_##name(__VA_ARGS__); \ } -#define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ - asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \ - asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\ +#define __COND_SYSCALL(abi, name) \ + __weak long __##abi##_##name(const struct pt_regs *__unused) \ { \ - return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ + return sys_ni_syscall(); \ } +#define __SYS_NI(abi, name) \ + SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers); + +#ifdef CONFIG_X86_64 +#define __X64_SYS_STUB0(name) \ + __SYS_STUB0(x64, sys_##name) + +#define __X64_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(x64, sys##name, \ + SC_X86_64_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __X64_COND_SYSCALL(name) \ + __COND_SYSCALL(x64, sys_##name) + +#define __X64_SYS_NI(name) \ + __SYS_NI(x64, sys_##name) +#else /* CONFIG_X86_64 */ +#define __X64_SYS_STUB0(name) +#define __X64_SYS_STUBx(x, name, ...) +#define __X64_COND_SYSCALL(name) +#define __X64_SYS_NI(name) +#endif /* CONFIG_X86_64 */ + +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +#define __IA32_SYS_STUB0(name) \ + __SYS_STUB0(ia32, sys_##name) + #define __IA32_SYS_STUBx(x, name, ...) \ - asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \ - ALLOW_ERROR_INJECTION(__ia32_sys##name, ERRNO); \ - asmlinkage long __ia32_sys##name(const struct pt_regs *regs) \ - { \ - return __se_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ - } + __SYS_STUBx(ia32, sys##name, \ + SC_IA32_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __IA32_COND_SYSCALL(name) \ + __COND_SYSCALL(ia32, sys_##name) +#define __IA32_SYS_NI(name) \ + __SYS_NI(ia32, sys_##name) +#else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ +#define __IA32_SYS_STUB0(name) +#define __IA32_SYS_STUBx(x, name, ...) +#define __IA32_COND_SYSCALL(name) +#define __IA32_SYS_NI(name) +#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ + +#ifdef CONFIG_IA32_EMULATION /* - * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias - * named __ia32_sys_*() + * For IA32 emulation, we need to handle "compat" syscalls *and* create + * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the + * ia32 regs in the proper order for shared or "common" syscalls. As some + * syscalls may not be implemented, we need to expand COND_SYSCALL in + * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this + * case as well. */ +#define __IA32_COMPAT_SYS_STUB0(name) \ + __SYS_STUB0(ia32, compat_sys_##name) -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) +#define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(ia32, compat_sys##name, \ + SC_IA32_REGS_TO_ARGS(x, __VA_ARGS__)) -#define COND_SYSCALL(name) \ - asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ - { \ - return sys_ni_syscall(); \ - } \ - asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\ - { \ - return sys_ni_syscall(); \ - } +#define __IA32_COMPAT_COND_SYSCALL(name) \ + __COND_SYSCALL(ia32, compat_sys_##name) -#define SYS_NI(name) \ - SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \ - SYSCALL_ALIAS(__ia32_sys_##name, sys_ni_posix_timers) +#define __IA32_COMPAT_SYS_NI(name) \ + __SYS_NI(ia32, compat_sys_##name) #else /* CONFIG_IA32_EMULATION */ +#define __IA32_COMPAT_SYS_STUB0(name) #define __IA32_COMPAT_SYS_STUBx(x, name, ...) -#define __IA32_SYS_STUBx(x, fullname, name, ...) +#define __IA32_COMPAT_COND_SYSCALL(name) +#define __IA32_COMPAT_SYS_NI(name) #endif /* CONFIG_IA32_EMULATION */ @@ -92,25 +164,23 @@ struct pt_regs; * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common * with x86_64 obviously do not need such care. */ -#define __X32_COMPAT_SYS_STUB0(x, name, ...) \ - asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO); \ - asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\ - { \ - return __se_compat_sys_##name();\ - } +#define __X32_COMPAT_SYS_STUB0(name) \ + __SYS_STUB0(x32, compat_sys_##name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) \ - asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \ - asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\ - { \ - return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } + __SYS_STUBx(x32, compat_sys##name, \ + SC_X86_64_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __X32_COMPAT_COND_SYSCALL(name) \ + __COND_SYSCALL(x32, compat_sys_##name) +#define __X32_COMPAT_SYS_NI(name) \ + __SYS_NI(x32, compat_sys_##name) #else /* CONFIG_X86_X32 */ -#define __X32_COMPAT_SYS_STUB0(x, name) +#define __X32_COMPAT_SYS_STUB0(name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) +#define __X32_COMPAT_COND_SYSCALL(name) +#define __X32_COMPAT_SYS_NI(name) #endif /* CONFIG_X86_X32 */ @@ -121,15 +191,12 @@ struct pt_regs; * of them. */ #define COMPAT_SYSCALL_DEFINE0(name) \ - static long __se_compat_sys_##name(void); \ - static inline long __do_compat_sys_##name(void); \ - __IA32_COMPAT_SYS_STUB0(x, name) \ - __X32_COMPAT_SYS_STUB0(x, name) \ - static long __se_compat_sys_##name(void) \ - { \ - return __do_compat_sys_##name(); \ - } \ - static inline long __do_compat_sys_##name(void) + static long \ + __do_compat_sys_##name(const struct pt_regs *__unused); \ + __IA32_COMPAT_SYS_STUB0(name) \ + __X32_COMPAT_SYS_STUB0(name) \ + static long \ + __do_compat_sys_##name(const struct pt_regs *__unused) #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ @@ -148,58 +215,19 @@ struct pt_regs; * kernel/time/posix-stubs.c to cover this case as well. */ #define COND_SYSCALL_COMPAT(name) \ - cond_syscall(__ia32_compat_sys_##name); \ - cond_syscall(__x32_compat_sys_##name) + __IA32_COMPAT_COND_SYSCALL(name) \ + __X32_COMPAT_COND_SYSCALL(name) #define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__ia32_compat_sys_##name, sys_ni_posix_timers); \ - SYSCALL_ALIAS(__x32_compat_sys_##name, sys_ni_posix_timers) + __IA32_COMPAT_SYS_NI(name) \ + __X32_COMPAT_SYS_NI(name) #endif /* CONFIG_COMPAT */ - -/* - * Instead of the generic __SYSCALL_DEFINEx() definition, this macro takes - * struct pt_regs *regs as the only argument of the syscall stub named - * __x64_sys_*(). It decodes just the registers it needs and passes them on to - * the __se_sys_*() wrapper performing sign extension and then to the - * __do_sys_*() function doing the actual job. These wrappers and functions - * are inlined (at least in very most cases), meaning that the assembly looks - * as follows (slightly re-ordered for better readability): - * - * <__x64_sys_recv>: <-- syscall with 4 parameters - * callq <__fentry__> - * - * mov 0x70(%rdi),%rdi <-- decode regs->di - * mov 0x68(%rdi),%rsi <-- decode regs->si - * mov 0x60(%rdi),%rdx <-- decode regs->dx - * mov 0x38(%rdi),%rcx <-- decode regs->r10 - * - * xor %r9d,%r9d <-- clear %r9 - * xor %r8d,%r8d <-- clear %r8 - * - * callq __sys_recvfrom <-- do the actual work in __sys_recvfrom() - * which takes 6 arguments - * - * cltq <-- extend return value to 64-bit - * retq <-- return - * - * This approach avoids leaking random user-provided register content down - * the call chain. - * - * If IA32_EMULATION is enabled, this macro generates an additional wrapper - * named __ia32_sys_*() which decodes the struct pt_regs *regs according - * to the i386 calling convention (bx, cx, dx, si, di, bp). - */ #define __SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long __x64_sys##name(const struct pt_regs *regs); \ - ALLOW_ERROR_INJECTION(__x64_sys##name, ERRNO); \ static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ - asmlinkage long __x64_sys##name(const struct pt_regs *regs) \ - { \ - return __se_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + __X64_SYS_STUBx(x, name, __VA_ARGS__) \ __IA32_SYS_STUBx(x, name, __VA_ARGS__) \ static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ @@ -217,33 +245,28 @@ struct pt_regs; * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI() * macros to work correctly. */ -#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) -#endif - -#ifndef COND_SYSCALL -#define COND_SYSCALL(name) \ - asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ - { \ - return sys_ni_syscall(); \ - } -#endif + static long __do_sys_##sname(const struct pt_regs *__unused); \ + __X64_SYS_STUB0(sname) \ + __IA32_SYS_STUB0(sname) \ + static long __do_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + __X64_COND_SYSCALL(name) \ + __IA32_COND_SYSCALL(name) -#ifndef SYS_NI -#define SYS_NI(name) SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); -#endif +#define SYS_NI(name) \ + __X64_SYS_NI(name) \ + __IA32_SYS_NI(name) /* * For VSYSCALLS, we need to declare these three syscalls with the new * pt_regs-based calling convention for in-kernel use. */ -asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs); -asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs); -asmlinkage long __x64_sys_time(const struct pt_regs *regs); +long __x64_sys_getcpu(const struct pt_regs *regs); +long __x64_sys_gettimeofday(const struct pt_regs *regs); +long __x64_sys_time(const struct pt_regs *regs); #endif /* _ASM_X86_SYSCALL_WRAPPER_H */ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 91b7b6e1a115..6714a358235d 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -8,42 +8,8 @@ #ifndef _ASM_X86_SYSCALLS_H #define _ASM_X86_SYSCALLS_H -#include <linux/compiler.h> -#include <linux/linkage.h> -#include <linux/signal.h> -#include <linux/types.h> - /* Common in X86_32 and X86_64 */ /* kernel/ioport.c */ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on); -#ifdef CONFIG_X86_32 -/* - * These definitions are only valid on pure 32-bit systems; x86-64 uses a - * different syscall calling convention - */ -asmlinkage long sys_ioperm(unsigned long, unsigned long, int); -asmlinkage long sys_iopl(unsigned int); - -/* kernel/ldt.c */ -asmlinkage long sys_modify_ldt(int, void __user *, unsigned long); - -/* kernel/signal.c */ -asmlinkage long sys_rt_sigreturn(void); - -/* kernel/tls.c */ -asmlinkage long sys_set_thread_area(struct user_desc __user *); -asmlinkage long sys_get_thread_area(struct user_desc __user *); - -/* X86_32 only */ - -/* kernel/signal.c */ -asmlinkage long sys_sigreturn(void); - -/* kernel/vm86_32.c */ -struct vm86_struct; -asmlinkage long sys_vm86old(struct vm86_struct __user *); -asmlinkage long sys_vm86(unsigned long, unsigned long); - -#endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_SYSCALLS_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index cf4327986e98..8de8ceccb8bc 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -92,7 +92,7 @@ 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_SLD 18 /* Restore split lock detection on context switch */ #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 +122,7 @@ 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_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) @@ -133,19 +133,15 @@ 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 \ (_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP | \ - _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) + _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE | _TIF_SLD) /* * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated. 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/traps.h b/arch/x86/include/asm/traps.h index ffa0dc8a535e..c26a7e1d8a2c 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -76,27 +76,24 @@ dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *regs, long err dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code); dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code); dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code); -#ifdef CONFIG_X86_64 -dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long address); -asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); -asmlinkage __visible notrace -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); -void __init trap_init(void); -#endif dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code); dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address); dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code); dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code); dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code); -#ifdef CONFIG_X86_MCE -dotraplinkage void do_machine_check(struct pt_regs *regs, long error_code); -#endif dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code); #endif dotraplinkage void do_mce(struct pt_regs *regs, long error_code); +#ifdef CONFIG_X86_64 +asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); +asmlinkage __visible notrace +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); +void __init trap_init(void); +#endif + static inline int get_si_code(unsigned long condition) { if (condition & DR_STEP) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 61d93f062a36..d8f283b9a569 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -126,11 +126,17 @@ extern int __get_user_bad(void); }) /* - * This is a type: either unsigned long, if the argument fits into - * that type, or otherwise unsigned long long. + * This is the smallest unsigned integer type that can fit a value + * (up to 'long long') */ -#define __inttype(x) \ -__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) +#define __inttype(x) __typeof__( \ + __typefits(x,char, \ + __typefits(x,short, \ + __typefits(x,int, \ + __typefits(x,long,0ULL))))) + +#define __typefits(x,type,not) \ + __builtin_choose_expr(sizeof(x)<=sizeof(type),(unsigned type)0,not) /** * get_user - Get a simple variable from user space. @@ -193,23 +199,12 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) : : "A" (x), "r" (addr) \ : : label) -#define __put_user_asm_ex_u64(x, addr) \ - asm volatile("\n" \ - "1: movl %%eax,0(%1)\n" \ - "2: movl %%edx,4(%1)\n" \ - "3:" \ - _ASM_EXTABLE_EX(1b, 2b) \ - _ASM_EXTABLE_EX(2b, 3b) \ - : : "A" (x), "r" (addr)) - #define __put_user_x8(x, ptr, __ret_pu) \ asm volatile("call __put_user_8" : "=a" (__ret_pu) \ : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") #else #define __put_user_goto_u64(x, ptr, label) \ - __put_user_goto(x, ptr, "q", "", "er", label) -#define __put_user_asm_ex_u64(x, addr) \ - __put_user_asm_ex(x, addr, "q", "", "er") + __put_user_goto(x, ptr, "q", "er", label) #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu) #endif @@ -273,13 +268,13 @@ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ - __put_user_goto(x, ptr, "b", "b", "iq", label); \ + __put_user_goto(x, ptr, "b", "iq", label); \ break; \ case 2: \ - __put_user_goto(x, ptr, "w", "w", "ir", label); \ + __put_user_goto(x, ptr, "w", "ir", label); \ break; \ case 4: \ - __put_user_goto(x, ptr, "l", "k", "ir", label); \ + __put_user_goto(x, ptr, "l", "ir", label); \ break; \ case 8: \ __put_user_goto_u64(x, ptr, label); \ @@ -289,141 +284,70 @@ do { \ } \ } while (0) -/* - * This doesn't do __uaccess_begin/end - the exception handling - * around it must do that. - */ -#define __put_user_size_ex(x, ptr, size) \ -do { \ - __chk_user_ptr(ptr); \ - switch (size) { \ - case 1: \ - __put_user_asm_ex(x, ptr, "b", "b", "iq"); \ - break; \ - case 2: \ - __put_user_asm_ex(x, ptr, "w", "w", "ir"); \ - break; \ - case 4: \ - __put_user_asm_ex(x, ptr, "l", "k", "ir"); \ - break; \ - case 8: \ - __put_user_asm_ex_u64((__typeof__(*ptr))(x), ptr); \ - break; \ - default: \ - __put_user_bad(); \ - } \ -} while (0) - #ifdef CONFIG_X86_32 -#define __get_user_asm_u64(x, ptr, retval, errret) \ +#define __get_user_asm_u64(x, ptr, retval) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ - asm volatile("\n" \ - "1: movl %2,%%eax\n" \ - "2: movl %3,%%edx\n" \ - "3:\n" \ + asm volatile("\n" \ + "1: movl %[lowbits],%%eax\n" \ + "2: movl %[highbits],%%edx\n" \ + "3:\n" \ ".section .fixup,\"ax\"\n" \ - "4: mov %4,%0\n" \ + "4: mov %[efault],%[errout]\n" \ " xorl %%eax,%%eax\n" \ " xorl %%edx,%%edx\n" \ " jmp 3b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 4b) \ _ASM_EXTABLE_UA(2b, 4b) \ - : "=r" (retval), "=&A"(x) \ - : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \ - "i" (errret), "0" (retval)); \ + : [errout] "=r" (retval), \ + [output] "=&A"(x) \ + : [lowbits] "m" (__m(__ptr)), \ + [highbits] "m" __m(((u32 __user *)(__ptr)) + 1), \ + [efault] "i" (-EFAULT), "0" (retval)); \ }) -#define __get_user_asm_ex_u64(x, ptr) (x) = __get_user_bad() #else -#define __get_user_asm_u64(x, ptr, retval, errret) \ - __get_user_asm(x, ptr, retval, "q", "", "=r", errret) -#define __get_user_asm_ex_u64(x, ptr) \ - __get_user_asm_ex(x, ptr, "q", "", "=r") +#define __get_user_asm_u64(x, ptr, retval) \ + __get_user_asm(x, ptr, retval, "q", "=r") #endif -#define __get_user_size(x, ptr, size, retval, errret) \ +#define __get_user_size(x, ptr, size, retval) \ do { \ retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ - __get_user_asm(x, ptr, retval, "b", "b", "=q", errret); \ + __get_user_asm(x, ptr, retval, "b", "=q"); \ break; \ case 2: \ - __get_user_asm(x, ptr, retval, "w", "w", "=r", errret); \ + __get_user_asm(x, ptr, retval, "w", "=r"); \ break; \ case 4: \ - __get_user_asm(x, ptr, retval, "l", "k", "=r", errret); \ + __get_user_asm(x, ptr, retval, "l", "=r"); \ break; \ case 8: \ - __get_user_asm_u64(x, ptr, retval, errret); \ + __get_user_asm_u64(x, ptr, retval); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) -#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile("\n" \ - "1: mov"itype" %2,%"rtype"1\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: mov %3,%0\n" \ - " xor"itype" %"rtype"1,%"rtype"1\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE_UA(1b, 3b) \ - : "=r" (err), ltype(x) \ - : "m" (__m(addr)), "i" (errret), "0" (err)) - -#define __get_user_asm_nozero(x, addr, err, itype, rtype, ltype, errret) \ +#define __get_user_asm(x, addr, err, itype, ltype) \ asm volatile("\n" \ - "1: mov"itype" %2,%"rtype"1\n" \ + "1: mov"itype" %[umem],%[output]\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ - "3: mov %3,%0\n" \ + "3: mov %[efault],%[errout]\n" \ + " xor"itype" %[output],%[output]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ - : "=r" (err), ltype(x) \ - : "m" (__m(addr)), "i" (errret), "0" (err)) - -/* - * This doesn't do __uaccess_begin/end - the exception handling - * around it must do that. - */ -#define __get_user_size_ex(x, ptr, size) \ -do { \ - __chk_user_ptr(ptr); \ - switch (size) { \ - case 1: \ - __get_user_asm_ex(x, ptr, "b", "b", "=q"); \ - break; \ - case 2: \ - __get_user_asm_ex(x, ptr, "w", "w", "=r"); \ - break; \ - case 4: \ - __get_user_asm_ex(x, ptr, "l", "k", "=r"); \ - break; \ - case 8: \ - __get_user_asm_ex_u64(x, ptr); \ - break; \ - default: \ - (x) = __get_user_bad(); \ - } \ -} while (0) - -#define __get_user_asm_ex(x, addr, itype, rtype, ltype) \ - asm volatile("1: mov"itype" %1,%"rtype"0\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3:xor"itype" %"rtype"0,%"rtype"0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE_EX(1b, 3b) \ - : ltype(x) : "m" (__m(addr))) + : [errout] "=r" (err), \ + [output] ltype(x) \ + : [umem] "m" (__m(addr)), \ + [efault] "i" (-EFAULT), "0" (err)) #define __put_user_nocheck(x, ptr, size) \ ({ \ @@ -447,7 +371,7 @@ __pu_label: \ __typeof__(ptr) __gu_ptr = (ptr); \ __typeof__(size) __gu_size = (size); \ __uaccess_begin_nospec(); \ - __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err, -EFAULT); \ + __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __builtin_expect(__gu_err, 0); \ @@ -462,47 +386,13 @@ struct __large_struct { unsigned long buf[100]; }; * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ -#define __put_user_goto(x, addr, itype, rtype, ltype, label) \ +#define __put_user_goto(x, addr, itype, ltype, label) \ asm_volatile_goto("\n" \ - "1: mov"itype" %"rtype"0,%1\n" \ - _ASM_EXTABLE_UA(1b, %l2) \ + "1: mov"itype" %0,%1\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ : : label) -#define __put_user_failed(x, addr, itype, rtype, ltype, errret) \ - ({ __label__ __puflab; \ - int __pufret = errret; \ - __put_user_goto(x,addr,itype,rtype,ltype,__puflab); \ - __pufret = 0; \ - __puflab: __pufret; }) - -#define __put_user_asm(x, addr, retval, itype, rtype, ltype, errret) do { \ - retval = __put_user_failed(x, addr, itype, rtype, ltype, errret); \ -} while (0) - -#define __put_user_asm_ex(x, addr, itype, rtype, ltype) \ - asm volatile("1: mov"itype" %"rtype"0,%1\n" \ - "2:\n" \ - _ASM_EXTABLE_EX(1b, 2b) \ - : : ltype(x), "m" (__m(addr))) - -/* - * uaccess_try and catch - */ -#define uaccess_try do { \ - current->thread.uaccess_err = 0; \ - __uaccess_begin(); \ - barrier(); - -#define uaccess_try_nospec do { \ - current->thread.uaccess_err = 0; \ - __uaccess_begin_nospec(); \ - -#define uaccess_catch(err) \ - __uaccess_end(); \ - (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ -} while (0) - /** * __get_user - Get a simple variable from user space, with less checking. * @x: Variable to store result. @@ -552,28 +442,6 @@ struct __large_struct { unsigned long buf[100]; }; #define __put_user(x, ptr) \ __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) -/* - * {get|put}_user_try and catch - * - * get_user_try { - * get_user_ex(...); - * } get_user_catch(err) - */ -#define get_user_try uaccess_try_nospec -#define get_user_catch(err) uaccess_catch(err) - -#define get_user_ex(x, ptr) do { \ - unsigned long __gue_val; \ - __get_user_size_ex((__gue_val), (ptr), (sizeof(*(ptr)))); \ - (x) = (__force __typeof__(*(ptr)))__gue_val; \ -} while (0) - -#define put_user_try uaccess_try -#define put_user_catch(err) uaccess_catch(err) - -#define put_user_ex(x, ptr) \ - __put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) - extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long @@ -584,99 +452,6 @@ 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 */ @@ -695,15 +470,6 @@ extern struct movsl_mask { #endif /* - * We rely on the nested NMI work to allow atomic faults from the NMI path; the - * nested NMI paths are careful to preserve CR2. - * - * Caller must use pagefault_enable/disable, or run in interrupt context, - * and also do a uaccess_ok() check - */ -#define __copy_from_user_nmi __copy_from_user_inatomic - -/* * The "unsafe" user accesses aren't really "unsafe", but the naming * is a big fat warning: you have to not only do the access_ok() * checking before using them, but you have to surround them with the @@ -729,7 +495,7 @@ static __must_check __always_inline bool user_access_begin(const void __user *pt do { \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \ + __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ } while (0) diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index ba2dc1930630..388a40660c7b 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -23,33 +23,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) static __always_inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) { - if (__builtin_constant_p(n)) { - unsigned long ret; - - switch (n) { - case 1: - ret = 0; - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u8 *)to, from, ret, - "b", "b", "=q", 1); - __uaccess_end(); - return ret; - case 2: - ret = 0; - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u16 *)to, from, ret, - "w", "w", "=r", 2); - __uaccess_end(); - return ret; - case 4: - ret = 0; - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u32 *)to, from, ret, - "l", "k", "=r", 4); - __uaccess_end(); - return ret; - } - } return __copy_user_ll(to, (__force const void *)from, n); } diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 5cd1caa8bc65..bc10e3dc64fe 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -65,117 +65,13 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len) static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { - int ret = 0; - - if (!__builtin_constant_p(size)) - return copy_user_generic(dst, (__force void *)src, size); - switch (size) { - case 1: - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src, - ret, "b", "b", "=q", 1); - __uaccess_end(); - return ret; - case 2: - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src, - ret, "w", "w", "=r", 2); - __uaccess_end(); - return ret; - case 4: - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src, - ret, "l", "k", "=r", 4); - __uaccess_end(); - return ret; - case 8: - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, - ret, "q", "", "=r", 8); - __uaccess_end(); - return ret; - case 10: - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, - ret, "q", "", "=r", 10); - if (likely(!ret)) - __get_user_asm_nozero(*(u16 *)(8 + (char *)dst), - (u16 __user *)(8 + (char __user *)src), - ret, "w", "w", "=r", 2); - __uaccess_end(); - return ret; - case 16: - __uaccess_begin_nospec(); - __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, - ret, "q", "", "=r", 16); - if (likely(!ret)) - __get_user_asm_nozero(*(u64 *)(8 + (char *)dst), - (u64 __user *)(8 + (char __user *)src), - ret, "q", "", "=r", 8); - __uaccess_end(); - return ret; - default: - return copy_user_generic(dst, (__force void *)src, size); - } + return copy_user_generic(dst, (__force void *)src, size); } static __always_inline __must_check unsigned long raw_copy_to_user(void __user *dst, const void *src, unsigned long size) { - int ret = 0; - - if (!__builtin_constant_p(size)) - return copy_user_generic((__force void *)dst, src, size); - switch (size) { - case 1: - __uaccess_begin(); - __put_user_asm(*(u8 *)src, (u8 __user *)dst, - ret, "b", "b", "iq", 1); - __uaccess_end(); - return ret; - case 2: - __uaccess_begin(); - __put_user_asm(*(u16 *)src, (u16 __user *)dst, - ret, "w", "w", "ir", 2); - __uaccess_end(); - return ret; - case 4: - __uaccess_begin(); - __put_user_asm(*(u32 *)src, (u32 __user *)dst, - ret, "l", "k", "ir", 4); - __uaccess_end(); - return ret; - case 8: - __uaccess_begin(); - __put_user_asm(*(u64 *)src, (u64 __user *)dst, - ret, "q", "", "er", 8); - __uaccess_end(); - return ret; - case 10: - __uaccess_begin(); - __put_user_asm(*(u64 *)src, (u64 __user *)dst, - ret, "q", "", "er", 10); - if (likely(!ret)) { - asm("":::"memory"); - __put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst, - ret, "w", "w", "ir", 2); - } - __uaccess_end(); - return ret; - case 16: - __uaccess_begin(); - __put_user_asm(*(u64 *)src, (u64 __user *)dst, - ret, "q", "", "er", 16); - if (likely(!ret)) { - asm("":::"memory"); - __put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst, - ret, "q", "", "er", 8); - } - __uaccess_end(); - return ret; - default: - return copy_user_generic((__force void *)dst, src, size); - } + return copy_user_generic((__force void *)dst, src, size); } static __always_inline __must_check diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index a7dd080749ce..c1c3d31b15c0 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -13,10 +13,13 @@ # define __ARCH_WANT_SYS_OLD_MMAP # define __ARCH_WANT_SYS_OLD_SELECT +# define __NR_ia32_syscall_max __NR_syscall_max + # else # include <asm/unistd_64.h> # include <asm/unistd_64_x32.h> +# include <asm/unistd_32_ia32.h> # define __ARCH_WANT_SYS_TIME # define __ARCH_WANT_SYS_UTIME # define __ARCH_WANT_COMPAT_SYS_PREADV64 @@ -26,6 +29,10 @@ # endif +# define NR_syscalls (__NR_syscall_max + 1) +# define X32_NR_syscalls (__NR_x32_syscall_max + 1) +# define IA32_NR_syscalls (__NR_ia32_syscall_max + 1) + # define __ARCH_WANT_NEW_STAT # define __ARCH_WANT_OLD_READDIR # define __ARCH_WANT_OLD_STAT diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 7803114aa140..13687bf0e0a9 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -858,4 +858,6 @@ static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) return 1; } +void uv_bau_message_interrupt(struct pt_regs *regs); + #endif /* _ASM_X86_UV_UV_BAU_H */ diff --git a/arch/x86/include/asm/vdso/clocksource.h b/arch/x86/include/asm/vdso/clocksource.h new file mode 100644 index 000000000000..119ac8612d89 --- /dev/null +++ b/arch/x86/include/asm/vdso/clocksource.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_CLOCKSOURCE_H +#define __ASM_VDSO_CLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES \ + VDSO_CLOCKMODE_TSC, \ + VDSO_CLOCKMODE_PVCLOCK, \ + VDSO_CLOCKMODE_HVCLOCK + +#endif /* __ASM_VDSO_CLOCKSOURCE_H */ diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index 6ee1f7dba34b..9a6dc9b4ec99 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -243,7 +243,7 @@ static u64 vread_hvclock(void) static inline u64 __arch_get_hw_counter(s32 clock_mode) { - if (clock_mode == VCLOCK_TSC) + if (likely(clock_mode == VDSO_CLOCKMODE_TSC)) return (u64)rdtsc_ordered(); /* * For any memory-mapped vclock type, we need to make sure that gcc @@ -252,13 +252,13 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode) * question isn't enabled, which will segfault. Hence the barriers. */ #ifdef CONFIG_PARAVIRT_CLOCK - if (clock_mode == VCLOCK_PVCLOCK) { + if (clock_mode == VDSO_CLOCKMODE_PVCLOCK) { barrier(); return vread_pvclock(); } #endif #ifdef CONFIG_HYPERV_TIMER - if (clock_mode == VCLOCK_HVCLOCK) { + if (clock_mode == VDSO_CLOCKMODE_HVCLOCK) { barrier(); return vread_hvclock(); } diff --git a/arch/x86/include/asm/vdso/processor.h b/arch/x86/include/asm/vdso/processor.h new file mode 100644 index 000000000000..57b1a7034c64 --- /dev/null +++ b/arch/x86/include/asm/vdso/processor.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_VDSO_PROCESSOR_H +#define __ASM_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLY__ + +/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ +static __always_inline void rep_nop(void) +{ + asm volatile("rep; nop" ::: "memory"); +} + +static __always_inline void cpu_relax(void) +{ + rep_nop(); +} + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h index 0026ab2123ce..be199a9b2676 100644 --- a/arch/x86/include/asm/vdso/vsyscall.h +++ b/arch/x86/include/asm/vdso/vsyscall.h @@ -10,8 +10,6 @@ #include <asm/vgtod.h> #include <asm/vvar.h> -int vclocks_used __read_mostly; - DEFINE_VVAR(struct vdso_data, _vdso_data); /* * Update the vDSO data page to keep in sync with kernel timekeeping. @@ -23,19 +21,6 @@ struct vdso_data *__x86_get_k_vdso_data(void) } #define __arch_get_k_vdso_data __x86_get_k_vdso_data -static __always_inline -int __x86_get_clock_mode(struct timekeeper *tk) -{ - int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; - - /* Mark the new vclock used. */ - BUILD_BUG_ON(VCLOCK_MAX >= 32); - WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode)); - - return vclock_mode; -} -#define __arch_get_clock_mode __x86_get_clock_mode - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index a2638c6124ed..7aa38b2ad8a9 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -2,6 +2,11 @@ #ifndef _ASM_X86_VGTOD_H #define _ASM_X86_VGTOD_H +/* + * This check is required to prevent ARCH=um to include + * unwanted headers. + */ +#ifdef CONFIG_GENERIC_GETTIMEOFDAY #include <linux/compiler.h> #include <asm/clocksource.h> #include <vdso/datapage.h> @@ -14,11 +19,6 @@ typedef u64 gtod_long_t; #else typedef unsigned long gtod_long_t; #endif - -extern int vclocks_used; -static inline bool vclock_was_used(int vclock) -{ - return READ_ONCE(vclocks_used) & (1 << vclock); -} +#endif /* CONFIG_GENERIC_GETTIMEOFDAY */ #endif /* _ASM_X86_VGTOD_H */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2a85287b3685..5e090d1f03f8 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) @@ -500,6 +500,18 @@ enum vmcs_field { VMX_EPT_EXECUTABLE_MASK) #define VMX_EPT_MT_MASK (7ull << VMX_EPT_MT_EPTE_SHIFT) +static inline u8 vmx_eptp_page_walk_level(u64 eptp) +{ + u64 encoded_level = eptp & VMX_EPTP_PWL_MASK; + + if (encoded_level == VMX_EPTP_PWL_5) + return 5; + + /* @eptp must be pre-validated by the caller. */ + WARN_ON_ONCE(encoded_level != VMX_EPTP_PWL_4); + return 4; +} + /* The mask to use to trigger an EPT Misconfiguration in order to track MMIO */ #define VMX_EPT_MISCONFIG_WX_VALUE (VMX_EPT_WRITABLE_MASK | \ VMX_EPT_EXECUTABLE_MASK) 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..ba89cabe5fcf 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_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch.o := y @@ -53,6 +52,8 @@ obj-y += setup.o x86_init.o i8259.o irqinit.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o +obj-$(CONFIG_X86_32) += sys_ia32.o +obj-$(CONFIG_IA32_EMULATION) += sys_ia32.o obj-$(CONFIG_X86_64) += sys_x86_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o @@ -154,6 +155,4 @@ ifeq ($(CONFIG_X86_64),y) obj-y += vsmp_64.o endif -ifdef CONFIG_EFI -obj-$(CONFIG_IMA) += ima_arch.o -endif +obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_arch.o 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/alternative.c b/arch/x86/kernel/alternative.c index 15ac0d5f4b40..7867dfb3963e 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1167,8 +1167,8 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries atomic_cond_read_acquire(&desc.refs, !VAL); } -void text_poke_loc_init(struct text_poke_loc *tp, void *addr, - const void *opcode, size_t len, const void *emulate) +static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, + const void *opcode, size_t len, const void *emulate) { struct insn insn; 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..6e043f295a60 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -3,12 +3,9 @@ # error "Please do not build this file directly, build asm-offsets.c instead" #endif -#include <asm/ucontext.h> +#include <linux/efi.h> -#define __SYSCALL_I386(nr, sym, qual) [nr] = 1, -static char syscalls[] = { -#include <asm/syscalls_32.h> -}; +#include <asm/ucontext.h> /* workaround for a warning with -Wmissing-prototypes */ void foo(void); @@ -62,6 +59,5 @@ void foo(void) #endif BLANK(); - DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); - DEFINE(NR_syscalls, sizeof(syscalls)); + DEFINE(EFI_svam, offsetof(efi_runtime_services_t, set_virtual_address_map)); } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 24d2fde30d00..c2a47016f243 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -5,30 +5,6 @@ #include <asm/ia32.h> -#define __SYSCALL_64(nr, sym, qual) [nr] = 1, -#define __SYSCALL_X32(nr, sym, qual) -static char syscalls_64[] = { -#include <asm/syscalls_64.h> -}; -#undef __SYSCALL_64 -#undef __SYSCALL_X32 - -#ifdef CONFIG_X86_X32_ABI -#define __SYSCALL_64(nr, sym, qual) -#define __SYSCALL_X32(nr, sym, qual) [nr] = 1, -static char syscalls_x32[] = { -#include <asm/syscalls_64.h> -}; -#undef __SYSCALL_64 -#undef __SYSCALL_X32 -#endif - -#define __SYSCALL_I386(nr, sym, qual) [nr] = 1, -static char syscalls_ia32[] = { -#include <asm/syscalls_32.h> -}; -#undef __SYSCALL_I386 - #if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) #include <asm/kvm_para.h> #endif @@ -90,17 +66,5 @@ int main(void) DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary)); BLANK(); #endif - - DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); - DEFINE(NR_syscalls, sizeof(syscalls_64)); - -#ifdef CONFIG_X86_X32_ABI - DEFINE(__NR_syscall_x32_max, sizeof(syscalls_x32) - 1); - DEFINE(X32_NR_syscalls, sizeof(syscalls_x32)); -#endif - - DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1); - DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); - return 0; } 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..bed0cb83fe24 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) @@ -1224,6 +1224,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_set_bug_bits(c); + cpu_set_core_cap_bits(c); + fpu__init_system(c); #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 0268185bef94..29a3bedabd06 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -5,6 +5,7 @@ #include <asm/msr-index.h> #include <asm/processor.h> #include <asm/vmx.h> +#include "cpu.h" #undef pr_fmt #define pr_fmt(fmt) "x86/cpu: " fmt diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index be82cd5841c3..9a26e972cdea 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -19,6 +19,8 @@ #include <asm/microcode_intel.h> #include <asm/hwcap2.h> #include <asm/elf.h> +#include <asm/cpu_device_id.h> +#include <asm/cmdline.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -31,6 +33,20 @@ #include <asm/apic.h> #endif +enum split_lock_detect_state { + sld_off = 0, + sld_warn, + sld_fatal, +}; + +/* + * Default to sld_off because most systems do not support split lock detection + * split_lock_setup() will switch this to sld_warn on systems that support + * split lock detect, unless there is a command line override. + */ +static enum split_lock_detect_state sld_state __ro_after_init = sld_off; +static u64 msr_test_ctrl_cache __ro_after_init; + /* * Processors which have self-snooping capability can handle conflicting * memory type across CPUs by snooping its own cache. However, there exists @@ -570,6 +586,8 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c) wrmsrl(MSR_MISC_FEATURES_ENABLES, msr); } +static void split_lock_init(void); + static void init_intel(struct cpuinfo_x86 *c) { early_init_intel(c); @@ -684,6 +702,8 @@ static void init_intel(struct cpuinfo_x86 *c) tsx_enable(); if (tsx_ctrl_state == TSX_CTRL_DISABLE) tsx_disable(); + + split_lock_init(); } #ifdef CONFIG_X86_32 @@ -945,3 +965,166 @@ static const struct cpu_dev intel_cpu_dev = { }; cpu_dev_register(intel_cpu_dev); + +#undef pr_fmt +#define pr_fmt(fmt) "x86/split lock detection: " fmt + +static const struct { + const char *option; + enum split_lock_detect_state state; +} sld_options[] __initconst = { + { "off", sld_off }, + { "warn", sld_warn }, + { "fatal", sld_fatal }, +}; + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static bool split_lock_verify_msr(bool on) +{ + u64 ctrl, tmp; + + if (rdmsrl_safe(MSR_TEST_CTRL, &ctrl)) + return false; + if (on) + ctrl |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT; + else + ctrl &= ~MSR_TEST_CTRL_SPLIT_LOCK_DETECT; + if (wrmsrl_safe(MSR_TEST_CTRL, ctrl)) + return false; + rdmsrl(MSR_TEST_CTRL, tmp); + return ctrl == tmp; +} + +static void __init split_lock_setup(void) +{ + enum split_lock_detect_state state = sld_warn; + char arg[20]; + int i, ret; + + if (!split_lock_verify_msr(false)) { + pr_info("MSR access failed: Disabled\n"); + return; + } + + ret = cmdline_find_option(boot_command_line, "split_lock_detect", + arg, sizeof(arg)); + if (ret >= 0) { + for (i = 0; i < ARRAY_SIZE(sld_options); i++) { + if (match_option(arg, ret, sld_options[i].option)) { + state = sld_options[i].state; + break; + } + } + } + + switch (state) { + case sld_off: + pr_info("disabled\n"); + return; + case sld_warn: + pr_info("warning about user-space split_locks\n"); + break; + case sld_fatal: + pr_info("sending SIGBUS on user-space split_locks\n"); + break; + } + + rdmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache); + + if (!split_lock_verify_msr(true)) { + pr_info("MSR access failed: Disabled\n"); + return; + } + + sld_state = state; + setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT); +} + +/* + * MSR_TEST_CTRL is per core, but we treat it like a per CPU MSR. Locking + * is not implemented as one thread could undo the setting of the other + * thread immediately after dropping the lock anyway. + */ +static void sld_update_msr(bool on) +{ + u64 test_ctrl_val = msr_test_ctrl_cache; + + if (on) + test_ctrl_val |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT; + + wrmsrl(MSR_TEST_CTRL, test_ctrl_val); +} + +static void split_lock_init(void) +{ + split_lock_verify_msr(sld_state != sld_off); +} + +bool handle_user_split_lock(struct pt_regs *regs, long error_code) +{ + if ((regs->flags & X86_EFLAGS_AC) || sld_state == sld_fatal) + return false; + + pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n", + current->comm, current->pid, regs->ip); + + /* + * Disable the split lock detection for this task so it can make + * progress and set TIF_SLD so the detection is re-enabled via + * switch_to_sld() when the task is scheduled out. + */ + sld_update_msr(false); + set_tsk_thread_flag(current, TIF_SLD); + return true; +} + +/* + * This function is called only when switching between tasks with + * different split-lock detection modes. It sets the MSR for the + * mode of the new task. This is right most of the time, but since + * the MSR is shared by hyperthreads on a physical core there can + * be glitches when the two threads need different modes. + */ +void switch_to_sld(unsigned long tifn) +{ + sld_update_msr(!(tifn & _TIF_SLD)); +} + +#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY} + +/* + * The following processors have the split lock detection feature. But + * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot + * be enumerated. Enable it by family and model matching on these + * processors. + */ +static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { + SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X), + SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L), + {} +}; + +void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) +{ + u64 ia32_core_caps = 0; + + if (c->x86_vendor != X86_VENDOR_INTEL) + return; + if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) { + /* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */ + rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps); + } else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + /* Enumerate split lock detection by family and model. */ + if (x86_match_cpu(split_lock_cpu_ids)) + ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT; + } + + if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT) + split_lock_setup(); +} 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..54165f3569e8 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; } @@ -1213,8 +1215,14 @@ static void __mc_scan_banks(struct mce *m, struct mce *final, * On Intel systems this is entered on all CPUs in parallel through * MCE broadcast. However some CPUs might be broken beyond repair, * so be always careful when synchronizing with others. + * + * Tracing and kprobes are disabled: if we interrupted a kernel context + * with IF=1, we need to minimize stack usage. There are also recursion + * issues: if the machine check was due to a failure of the memory + * backing the user stack, tracing that reads the user stack will cause + * potentially infinite recursion. */ -void do_machine_check(struct pt_regs *regs, long error_code) +void notrace do_machine_check(struct pt_regs *regs, long error_code) { DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); DECLARE_BITMAP(toclear, MAX_NR_BANKS); @@ -1360,6 +1368,7 @@ out_ist: ist_exit(regs); } EXPORT_SYMBOL_GPL(do_machine_check); +NOKPROBE_SYMBOL(do_machine_check); #ifndef CONFIG_MEMORY_FAILURE int memory_failure(unsigned long pfn, int flags) @@ -1877,6 +1886,8 @@ 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; } @@ -1892,10 +1903,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; -dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +dotraplinkage notrace void do_mce(struct pt_regs *regs, long error_code) { machine_check_vector(regs, error_code); } +NOKPROBE_SYMBOL(do_mce); /* * Called for each booted CPU to set up machine checks. 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..3b008172ad73 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -8,6 +8,9 @@ #include <linux/device.h> #include <asm/mce.h> +/* Pointer to the installed machine check handler for this CPU setup. */ +extern void (*machine_check_vector)(struct pt_regs *, long error_code); + enum severity_level { MCE_NO_SEVERITY, MCE_DEFERRED_SEVERITY, @@ -48,6 +51,7 @@ 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 +60,7 @@ 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/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index c222f283b456..300e3fd5ade3 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -4,6 +4,7 @@ #include <linux/cpu.h> #include <asm/msr.h> +#include <asm/mwait.h> #define UMWAIT_C02_ENABLE 0 diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 46d732696c1c..9b6fafa69be9 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -25,6 +25,8 @@ #include <linux/init.h> #include <linux/export.h> #include <linux/clocksource.h> +#include <linux/cpu.h> +#include <linux/reboot.h> #include <asm/div64.h> #include <asm/x86_init.h> #include <asm/hypervisor.h> @@ -47,6 +49,11 @@ #define VMWARE_CMD_GETVCPU_INFO 68 #define VMWARE_CMD_LEGACY_X2APIC 3 #define VMWARE_CMD_VCPU_RESERVED 31 +#define VMWARE_CMD_STEALCLOCK 91 + +#define STEALCLOCK_NOT_AVAILABLE (-1) +#define STEALCLOCK_DISABLED 0 +#define STEALCLOCK_ENABLED 1 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ __asm__("inl (%%dx), %%eax" : \ @@ -86,6 +93,18 @@ } \ } while (0) +struct vmware_steal_time { + union { + uint64_t clock; /* stolen time counter in units of vtsc */ + struct { + /* only for little-endian */ + uint32_t clock_low; + uint32_t clock_high; + }; + }; + uint64_t reserved[7]; +}; + static unsigned long vmware_tsc_khz __ro_after_init; static u8 vmware_hypercall_mode __ro_after_init; @@ -103,15 +122,25 @@ static unsigned long vmware_get_tsc_khz(void) #ifdef CONFIG_PARAVIRT static struct cyc2ns_data vmware_cyc2ns __ro_after_init; -static int vmw_sched_clock __initdata = 1; +static bool vmw_sched_clock __initdata = true; +static DEFINE_PER_CPU_DECRYPTED(struct vmware_steal_time, vmw_steal_time) __aligned(64); +static bool has_steal_clock; +static bool steal_acc __initdata = true; /* steal time accounting */ static __init int setup_vmw_sched_clock(char *s) { - vmw_sched_clock = 0; + vmw_sched_clock = false; return 0; } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); +static __init int parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} +early_param("no-steal-acc", parse_no_stealacc); + static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; @@ -122,7 +151,7 @@ static unsigned long long notrace vmware_sched_clock(void) return ns; } -static void __init vmware_sched_clock_setup(void) +static void __init vmware_cyc2ns_setup(void) { struct cyc2ns_data *d = &vmware_cyc2ns; unsigned long long tsc_now = rdtsc(); @@ -132,17 +161,201 @@ static void __init vmware_sched_clock_setup(void) d->cyc2ns_offset = mul_u64_u32_shr(tsc_now, d->cyc2ns_mul, d->cyc2ns_shift); - pv_ops.time.sched_clock = vmware_sched_clock; - pr_info("using sched offset of %llu ns\n", d->cyc2ns_offset); + pr_info("using clock offset of %llu ns\n", d->cyc2ns_offset); +} + +static int vmware_cmd_stealclock(uint32_t arg1, uint32_t arg2) +{ + uint32_t result, info; + + asm volatile (VMWARE_HYPERCALL : + "=a"(result), + "=c"(info) : + "a"(VMWARE_HYPERVISOR_MAGIC), + "b"(0), + "c"(VMWARE_CMD_STEALCLOCK), + "d"(0), + "S"(arg1), + "D"(arg2) : + "memory"); + return result; +} + +static bool stealclock_enable(phys_addr_t pa) +{ + return vmware_cmd_stealclock(upper_32_bits(pa), + lower_32_bits(pa)) == STEALCLOCK_ENABLED; +} + +static int __stealclock_disable(void) +{ + return vmware_cmd_stealclock(0, 1); +} + +static void stealclock_disable(void) +{ + __stealclock_disable(); +} + +static bool vmware_is_stealclock_available(void) +{ + return __stealclock_disable() != STEALCLOCK_NOT_AVAILABLE; +} + +/** + * vmware_steal_clock() - read the per-cpu steal clock + * @cpu: the cpu number whose steal clock we want to read + * + * The function reads the steal clock if we are on a 64-bit system, otherwise + * reads it in parts, checking that the high part didn't change in the + * meantime. + * + * Return: + * The steal clock reading in ns. + */ +static uint64_t vmware_steal_clock(int cpu) +{ + struct vmware_steal_time *steal = &per_cpu(vmw_steal_time, cpu); + uint64_t clock; + + if (IS_ENABLED(CONFIG_64BIT)) + clock = READ_ONCE(steal->clock); + else { + uint32_t initial_high, low, high; + + do { + initial_high = READ_ONCE(steal->clock_high); + /* Do not reorder initial_high and high readings */ + virt_rmb(); + low = READ_ONCE(steal->clock_low); + /* Keep low reading in between */ + virt_rmb(); + high = READ_ONCE(steal->clock_high); + } while (initial_high != high); + + clock = ((uint64_t)high << 32) | low; + } + + return mul_u64_u32_shr(clock, vmware_cyc2ns.cyc2ns_mul, + vmware_cyc2ns.cyc2ns_shift); +} + +static void vmware_register_steal_time(void) +{ + int cpu = smp_processor_id(); + struct vmware_steal_time *st = &per_cpu(vmw_steal_time, cpu); + + if (!has_steal_clock) + return; + + if (!stealclock_enable(slow_virt_to_phys(st))) { + has_steal_clock = false; + return; + } + + pr_info("vmware-stealtime: cpu %d, pa %llx\n", + cpu, (unsigned long long) slow_virt_to_phys(st)); } +static void vmware_disable_steal_time(void) +{ + if (!has_steal_clock) + return; + + stealclock_disable(); +} + +static void vmware_guest_cpu_init(void) +{ + if (has_steal_clock) + vmware_register_steal_time(); +} + +static void vmware_pv_guest_cpu_reboot(void *unused) +{ + vmware_disable_steal_time(); +} + +static int vmware_pv_reboot_notify(struct notifier_block *nb, + unsigned long code, void *unused) +{ + if (code == SYS_RESTART) + on_each_cpu(vmware_pv_guest_cpu_reboot, NULL, 1); + return NOTIFY_DONE; +} + +static struct notifier_block vmware_pv_reboot_nb = { + .notifier_call = vmware_pv_reboot_notify, +}; + +#ifdef CONFIG_SMP +static void __init vmware_smp_prepare_boot_cpu(void) +{ + vmware_guest_cpu_init(); + native_smp_prepare_boot_cpu(); +} + +static int vmware_cpu_online(unsigned int cpu) +{ + local_irq_disable(); + vmware_guest_cpu_init(); + local_irq_enable(); + return 0; +} + +static int vmware_cpu_down_prepare(unsigned int cpu) +{ + local_irq_disable(); + vmware_disable_steal_time(); + local_irq_enable(); + return 0; +} +#endif + +static __init int activate_jump_labels(void) +{ + if (has_steal_clock) { + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + } + + return 0; +} +arch_initcall(activate_jump_labels); + static void __init vmware_paravirt_ops_setup(void) { pv_info.name = "VMware hypervisor"; pv_ops.cpu.io_delay = paravirt_nop; - if (vmware_tsc_khz && vmw_sched_clock) - vmware_sched_clock_setup(); + if (vmware_tsc_khz == 0) + return; + + vmware_cyc2ns_setup(); + + if (vmw_sched_clock) + pv_ops.time.sched_clock = vmware_sched_clock; + + if (vmware_is_stealclock_available()) { + has_steal_clock = true; + pv_ops.time.steal_clock = vmware_steal_clock; + + /* We use reboot notifier only to disable steal clock */ + register_reboot_notifier(&vmware_pv_reboot_nb); + +#ifdef CONFIG_SMP + smp_ops.smp_prepare_boot_cpu = + vmware_smp_prepare_boot_cpu; + if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "x86/vmware:online", + vmware_cpu_online, + vmware_cpu_down_prepare) < 0) + pr_err("vmware_guest: Failed to install cpu hotplug callbacks\n"); +#else + vmware_guest_cpu_init(); +#endif + } } #else #define vmware_paravirt_ops_setup() do {} while (0) @@ -213,7 +426,7 @@ static void __init vmware_platform_setup(void) vmware_set_capabilities(); } -static u8 vmware_select_hypercall(void) +static u8 __init vmware_select_hypercall(void) { int eax, ebx, ecx, edx; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index a1806598aaa4..32b153d38748 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -120,11 +120,6 @@ static bool xfeature_is_supervisor(int xfeature_nr) return ecx & 1; } -static bool xfeature_is_user(int xfeature_nr) -{ - return !xfeature_is_supervisor(xfeature_nr); -} - /* * When executing XSAVEOPT (or other optimized XSAVE instructions), if * a processor implementation detects that an FPU state component is still @@ -265,21 +260,25 @@ static void __init setup_xstate_features(void) cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_sizes[i] = eax; + /* - * If an xfeature is supervisor state, the offset - * in EBX is invalid. We leave it to -1. + * If an xfeature is supervisor state, the offset in EBX is + * invalid, leave it to -1. */ - if (xfeature_is_user(i)) - xstate_offsets[i] = ebx; + if (xfeature_is_supervisor(i)) + continue; + + xstate_offsets[i] = ebx; - xstate_sizes[i] = eax; /* - * In our xstate size checks, we assume that the - * highest-numbered xstate feature has the - * highest offset in the buffer. Ensure it does. + * In our xstate size checks, we assume that the highest-numbered + * xstate feature has the highest offset in the buffer. Ensure + * it does. */ WARN_ONCE(last_good_offset > xstate_offsets[i], - "x86/fpu: misordered xstate at %d\n", last_good_offset); + "x86/fpu: misordered xstate at %d\n", last_good_offset); + last_good_offset = xstate_offsets[i]; } } @@ -326,6 +325,13 @@ static int xfeature_is_aligned(int xfeature_nr) u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); + + if (!xfeature_enabled(xfeature_nr)) { + WARN_ONCE(1, "Checking alignment of disabled xfeature %d\n", + xfeature_nr); + return 0; + } + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); /* * The value returned by ECX[1] indicates the alignment @@ -338,11 +344,11 @@ static int xfeature_is_aligned(int xfeature_nr) /* * This function sets up offsets and sizes of all extended states in * xsave area. This supports both standard format and compacted format - * of the xsave aread. + * of the xsave area. */ -static void __init setup_xstate_comp(void) +static void __init setup_xstate_comp_offsets(void) { - unsigned int xstate_comp_sizes[XFEATURE_MAX]; + unsigned int next_offset; int i; /* @@ -356,31 +362,23 @@ static void __init setup_xstate_comp(void) if (!boot_cpu_has(X86_FEATURE_XSAVES)) { for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (xfeature_enabled(i)) { + if (xfeature_enabled(i)) xstate_comp_offsets[i] = xstate_offsets[i]; - xstate_comp_sizes[i] = xstate_sizes[i]; - } } return; } - xstate_comp_offsets[FIRST_EXTENDED_XFEATURE] = - FXSAVE_SIZE + XSAVE_HDR_SIZE; + next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE; for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (xfeature_enabled(i)) - xstate_comp_sizes[i] = xstate_sizes[i]; - else - xstate_comp_sizes[i] = 0; + if (!xfeature_enabled(i)) + continue; - if (i > FIRST_EXTENDED_XFEATURE) { - xstate_comp_offsets[i] = xstate_comp_offsets[i-1] - + xstate_comp_sizes[i-1]; + if (xfeature_is_aligned(i)) + next_offset = ALIGN(next_offset, 64); - if (xfeature_is_aligned(i)) - xstate_comp_offsets[i] = - ALIGN(xstate_comp_offsets[i], 64); - } + xstate_comp_offsets[i] = next_offset; + next_offset += xstate_sizes[i]; } } @@ -774,7 +772,7 @@ void __init fpu__init_system_xstate(void) fpu__init_prepare_fx_sw_frame(); setup_init_fpu_buf(); - setup_xstate_comp(); + setup_xstate_comp_offsets(); print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", @@ -897,8 +895,6 @@ const void *get_xsave_field_ptr(int xfeature_nr) #ifdef CONFIG_ARCH_HAS_PKEYS -#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) -#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -917,6 +913,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * This code should only be called with valid 'pkey' + * values originating from in-kernel users. Complain + * if a bad value is observed. + */ + WARN_ON_ONCE(pkey >= arch_max_pkey()); + /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; 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/ioport.c b/arch/x86/kernel/ioport.c index 8abeee0dd7bf..a53e7b4a7419 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -13,6 +13,7 @@ #include <asm/io_bitmap.h> #include <asm/desc.h> +#include <asm/syscalls.h> #ifdef CONFIG_X86_IOPL_IOPERM diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 21efee32e2b1..c7965ff429c5 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -230,7 +230,7 @@ u64 arch_irq_stat(void) * SMP cross-CPU interrupts have their own specific * handlers). */ -__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) +__visible void __irq_entry do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); struct irq_desc * desc; @@ -263,7 +263,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) exiting_irq(); set_irq_regs(old_regs); - return 1; } #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 16919a9671fa..5aa523c2d573 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -44,15 +44,6 @@ * (these are usually mapped into the 0x30-0xff vector range) */ -/* - * IRQ2 is cascade interrupt to second interrupt controller - */ -static struct irqaction irq2 = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; @@ -84,7 +75,7 @@ void __init init_IRQ(void) * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15. * If these IRQ's are handled by legacy interrupt-controllers like PIC, * then this configuration will likely be static after the boot. If - * these IRQ's are handled by more mordern controllers like IO-APIC, + * these IRQs are handled by more modern controllers like IO-APIC, * then this vector space can be freed and re-used dynamically as the * irq's migrate etc. */ @@ -104,6 +95,9 @@ void __init native_init_IRQ(void) idt_setup_apic_and_irq_gates(); lapic_assign_system_vectors(); - if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) - setup_irq(2, &irq2); + if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) { + /* IRQ2 is cascade interrupt to second interrupt controller */ + if (request_irq(2, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("%s: request_irq() failed\n", "cascade"); + } } diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 9c4498ea0b3c..5ba8477c2cb7 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -58,7 +58,7 @@ __jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, return code; } -static void inline __jump_label_transform(struct jump_entry *entry, +static inline void __jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { 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/kvmclock.c b/arch/x86/kernel/kvmclock.c index 904494b924c1..34b18f6eeb2c 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -159,12 +159,19 @@ bool kvm_check_and_clear_guest_paused(void) return ret; } +static int kvm_cs_enable(struct clocksource *cs) +{ + vclocks_set_used(VDSO_CLOCKMODE_PVCLOCK); + return 0; +} + struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .enable = kvm_cs_enable, }; EXPORT_SYMBOL_GPL(kvm_clock); @@ -272,7 +279,7 @@ static int __init kvm_setup_vsyscall_timeinfo(void) if (!(flags & PVCLOCK_TSC_STABLE_BIT)) return 0; - kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; + kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; #endif kvmclock_init_mem(); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index c57e1ca70fd1..84c3ba32f211 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -27,7 +27,6 @@ #include <asm/tlb.h> #include <asm/desc.h> #include <asm/mmu_context.h> -#include <asm/syscalls.h> #include <asm/pgtable_areas.h> /* This is a multiple of PAGE_SIZE. */ diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 54c21d6abd5a..6407ea21fa1b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -403,9 +403,9 @@ static void default_do_nmi(struct pt_regs *regs) * a 'real' unknown NMI. For example, while processing * a perf NMI another perf NMI comes in along with a * 'real' unknown NMI. These two NMIs get combined into - * one (as descibed above). When the next NMI gets + * one (as described above). When the next NMI gets * processed, it will be flagged by perf as handled, but - * noone will know that there was a 'real' unknown NMI sent + * no one will know that there was a 'real' unknown NMI sent * also. As a result it gets swallowed. Or if the first * perf NMI returns two events handled then the second * NMI will get eaten by the logic below, again losing a 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..9da70b279dad 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -28,7 +28,6 @@ #include <linux/hw_breakpoint.h> #include <asm/cpu.h> #include <asm/apic.h> -#include <asm/syscalls.h> #include <linux/uaccess.h> #include <asm/mwait.h> #include <asm/fpu/internal.h> @@ -374,7 +373,7 @@ 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; @@ -650,6 +649,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) /* Enforce MSR update to ensure consistent state */ __speculation_ctrl_update(~tifn, tifn); } + + if ((tifp ^ tifn) & _TIF_SLD) + switch_to_sld(tifn); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 5052ced43373..954b013cc585 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -49,7 +49,6 @@ #include <asm/tlbflush.h> #include <asm/cpu.h> -#include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ffd497804dbc..5ef9d8f25b0e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -48,7 +48,6 @@ #include <asm/desc.h> #include <asm/proto.h> #include <asm/ia32.h> -#include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 10125358b9c4..11065dc03f5b 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -145,7 +145,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti) { - WARN_ON(vclock_was_used(VCLOCK_PVCLOCK)); + WARN_ON(vclock_was_used(VDSO_CLOCKMODE_PVCLOCK)); pvti_cpu0_va = pvti; } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0cc7c0b106bb..3ca43be4f9cf 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -531,7 +531,7 @@ static void emergency_vmx_disable_all(void) /* * We need to disable VMX on all CPUs before rebooting, otherwise - * we risk hanging up the machine, because the CPU ignore INIT + * we risk hanging up the machine, because the CPU ignores INIT * signals when VMX is enabled. * * We can't take any locks and we may be on an inconsistent 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/setup.c b/arch/x86/kernel/setup.c index a74262c71484..e6b545047f38 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -64,7 +64,6 @@ RESERVE_BRK(dmi_alloc, 65536); * at link time, with RESERVE_BRK*() facility reserving additional * chunks. */ -static __initdata unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 8a29573851a3..83b74fb38c8f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -42,29 +42,9 @@ #endif /* CONFIG_X86_64 */ #include <asm/syscall.h> -#include <asm/syscalls.h> - #include <asm/sigframe.h> #include <asm/signal.h> -#define COPY(x) do { \ - get_user_ex(regs->x, &sc->x); \ -} while (0) - -#define GET_SEG(seg) ({ \ - unsigned short tmp; \ - get_user_ex(tmp, &sc->seg); \ - tmp; \ -}) - -#define COPY_SEG(seg) do { \ - regs->seg = GET_SEG(seg); \ -} while (0) - -#define COPY_SEG_CPL3(seg) do { \ - regs->seg = GET_SEG(seg) | 3; \ -} while (0) - #ifdef CONFIG_X86_64 /* * If regs->ss will cause an IRET fault, change it. Otherwise leave it @@ -92,53 +72,58 @@ static void force_valid_ss(struct pt_regs *regs) ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) regs->ss = __USER_DS; } +# define CONTEXT_COPY_SIZE offsetof(struct sigcontext, reserved1) +#else +# define CONTEXT_COPY_SIZE sizeof(struct sigcontext) #endif static int restore_sigcontext(struct pt_regs *regs, - struct sigcontext __user *sc, + struct sigcontext __user *usc, unsigned long uc_flags) { - unsigned long buf_val; - void __user *buf; - unsigned int tmpflags; - unsigned int err = 0; + struct sigcontext sc; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; - get_user_try { + if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE)) + return -EFAULT; #ifdef CONFIG_X86_32 - set_user_gs(regs, GET_SEG(gs)); - COPY_SEG(fs); - COPY_SEG(es); - COPY_SEG(ds); + set_user_gs(regs, sc.gs); + regs->fs = sc.fs; + regs->es = sc.es; + regs->ds = sc.ds; #endif /* CONFIG_X86_32 */ - COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); COPY(ax); + regs->bx = sc.bx; + regs->cx = sc.cx; + regs->dx = sc.dx; + regs->si = sc.si; + regs->di = sc.di; + regs->bp = sc.bp; + regs->ax = sc.ax; + regs->sp = sc.sp; + regs->ip = sc.ip; #ifdef CONFIG_X86_64 - COPY(r8); - COPY(r9); - COPY(r10); - COPY(r11); - COPY(r12); - COPY(r13); - COPY(r14); - COPY(r15); + regs->r8 = sc.r8; + regs->r9 = sc.r9; + regs->r10 = sc.r10; + regs->r11 = sc.r11; + regs->r12 = sc.r12; + regs->r13 = sc.r13; + regs->r14 = sc.r14; + regs->r15 = sc.r15; #endif /* CONFIG_X86_64 */ - COPY_SEG_CPL3(cs); - COPY_SEG_CPL3(ss); - - get_user_ex(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); - regs->orig_ax = -1; /* disable syscall checks */ + /* Get CS/SS and force CPL3 */ + regs->cs = sc.cs | 0x03; + regs->ss = sc.ss | 0x03; - get_user_ex(buf_val, &sc->fpstate); - buf = (void __user *)buf_val; - } get_user_catch(err); + regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); + /* disable syscall checks */ + regs->orig_ax = -1; #ifdef CONFIG_X86_64 /* @@ -149,70 +134,78 @@ static int restore_sigcontext(struct pt_regs *regs, force_valid_ss(regs); #endif - err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); - - return err; + return fpu__restore_sig((void __user *)sc.fpstate, + IS_ENABLED(CONFIG_X86_32)); } -int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, +static __always_inline int +__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask) { - int err = 0; - - put_user_try { - #ifdef CONFIG_X86_32 - put_user_ex(get_user_gs(regs), (unsigned int __user *)&sc->gs); - put_user_ex(regs->fs, (unsigned int __user *)&sc->fs); - put_user_ex(regs->es, (unsigned int __user *)&sc->es); - put_user_ex(regs->ds, (unsigned int __user *)&sc->ds); + unsafe_put_user(get_user_gs(regs), + (unsigned int __user *)&sc->gs, Efault); + unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); + unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); + unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); #endif /* CONFIG_X86_32 */ - put_user_ex(regs->di, &sc->di); - put_user_ex(regs->si, &sc->si); - put_user_ex(regs->bp, &sc->bp); - put_user_ex(regs->sp, &sc->sp); - put_user_ex(regs->bx, &sc->bx); - put_user_ex(regs->dx, &sc->dx); - put_user_ex(regs->cx, &sc->cx); - put_user_ex(regs->ax, &sc->ax); + unsafe_put_user(regs->di, &sc->di, Efault); + unsafe_put_user(regs->si, &sc->si, Efault); + unsafe_put_user(regs->bp, &sc->bp, Efault); + unsafe_put_user(regs->sp, &sc->sp, Efault); + unsafe_put_user(regs->bx, &sc->bx, Efault); + unsafe_put_user(regs->dx, &sc->dx, Efault); + unsafe_put_user(regs->cx, &sc->cx, Efault); + unsafe_put_user(regs->ax, &sc->ax, Efault); #ifdef CONFIG_X86_64 - put_user_ex(regs->r8, &sc->r8); - put_user_ex(regs->r9, &sc->r9); - put_user_ex(regs->r10, &sc->r10); - put_user_ex(regs->r11, &sc->r11); - put_user_ex(regs->r12, &sc->r12); - put_user_ex(regs->r13, &sc->r13); - put_user_ex(regs->r14, &sc->r14); - put_user_ex(regs->r15, &sc->r15); + unsafe_put_user(regs->r8, &sc->r8, Efault); + unsafe_put_user(regs->r9, &sc->r9, Efault); + unsafe_put_user(regs->r10, &sc->r10, Efault); + unsafe_put_user(regs->r11, &sc->r11, Efault); + unsafe_put_user(regs->r12, &sc->r12, Efault); + unsafe_put_user(regs->r13, &sc->r13, Efault); + unsafe_put_user(regs->r14, &sc->r14, Efault); + unsafe_put_user(regs->r15, &sc->r15, Efault); #endif /* CONFIG_X86_64 */ - put_user_ex(current->thread.trap_nr, &sc->trapno); - put_user_ex(current->thread.error_code, &sc->err); - put_user_ex(regs->ip, &sc->ip); + unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); + unsafe_put_user(current->thread.error_code, &sc->err, Efault); + unsafe_put_user(regs->ip, &sc->ip, Efault); #ifdef CONFIG_X86_32 - put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); - put_user_ex(regs->flags, &sc->flags); - put_user_ex(regs->sp, &sc->sp_at_signal); - put_user_ex(regs->ss, (unsigned int __user *)&sc->ss); + unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault); + unsafe_put_user(regs->flags, &sc->flags, Efault); + unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault); + unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault); #else /* !CONFIG_X86_32 */ - put_user_ex(regs->flags, &sc->flags); - put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->gs); - put_user_ex(0, &sc->fs); - put_user_ex(regs->ss, &sc->ss); + unsafe_put_user(regs->flags, &sc->flags, Efault); + unsafe_put_user(regs->cs, &sc->cs, Efault); + unsafe_put_user(0, &sc->gs, Efault); + unsafe_put_user(0, &sc->fs, Efault); + unsafe_put_user(regs->ss, &sc->ss, Efault); #endif /* CONFIG_X86_32 */ - put_user_ex(fpstate, (unsigned long __user *)&sc->fpstate); - - /* non-iBCS2 extensions.. */ - put_user_ex(mask, &sc->oldmask); - put_user_ex(current->thread.cr2, &sc->cr2); - } put_user_catch(err); + unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault); - return err; + /* non-iBCS2 extensions.. */ + unsafe_put_user(mask, &sc->oldmask, Efault); + unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); + return 0; +Efault: + return -EFAULT; } +#define unsafe_put_sigcontext(sc, fp, regs, set, label) \ +do { \ + if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \ + goto label; \ +} while(0); + +#define unsafe_put_sigmask(set, frame, label) \ + unsafe_put_user(*(__u64 *)(set), \ + (__u64 __user *)&(frame)->uc.uc_sigmask, \ + label) + /* * Set up a signal frame. */ @@ -312,26 +305,16 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, { struct sigframe __user *frame; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); - - if (!access_ok(frame, sizeof(*frame))) - return -EFAULT; + void __user *fp = NULL; - if (__put_user(sig, &frame->sig)) - return -EFAULT; + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - if (setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0])) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - if (_NSIG_WORDS > 1) { - if (__copy_to_user(&frame->extramask, &set->sig[1], - sizeof(frame->extramask))) - return -EFAULT; - } - + unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_sigcontext(&frame->sc, fp, regs, set, Efault); + unsafe_put_user(set->sig[1], &frame->extramask[0], Efault); if (current->mm->context.vdso) restorer = current->mm->context.vdso + vdso_image_32.sym___kernel_sigreturn; @@ -341,7 +324,7 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, restorer = ksig->ka.sa.sa_restorer; /* Set up to return from userspace. */ - err |= __put_user(restorer, &frame->pretcode); + unsafe_put_user(restorer, &frame->pretcode, Efault); /* * This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80 @@ -350,10 +333,8 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, * reasons and because gdb uses it as a signature to notice * signal handler stack frames. */ - err |= __put_user(*((u64 *)&retcode), (u64 *)frame->retcode); - - if (err) - return -EFAULT; + unsafe_put_user(*((u64 *)&retcode), (u64 *)frame->retcode, Efault); + user_access_end(); /* Set up registers for signal handler */ regs->sp = (unsigned long)frame; @@ -368,6 +349,10 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, regs->cs = __USER_CS; return 0; + +Efault: + user_access_end(); + return -EFAULT; } static int __setup_rt_frame(int sig, struct ksignal *ksig, @@ -375,50 +360,45 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, { struct rt_sigframe __user *frame; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; + void __user *fp = NULL; - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - if (!access_ok(frame, sizeof(*frame))) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - put_user_try { - put_user_ex(sig, &frame->sig); - put_user_ex(&frame->info, &frame->pinfo); - put_user_ex(&frame->uc, &frame->puc); + unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_user(&frame->info, &frame->pinfo, Efault); + unsafe_put_user(&frame->uc, &frame->puc, Efault); - /* Create the ucontext. */ - if (static_cpu_has(X86_FEATURE_XSAVE)) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - save_altstack_ex(&frame->uc.uc_stack, regs->sp); + /* Create the ucontext. */ + if (static_cpu_has(X86_FEATURE_XSAVE)) + unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault); + else + unsafe_put_user(0, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - /* Set up to return from userspace. */ - restorer = current->mm->context.vdso + - vdso_image_32.sym___kernel_rt_sigreturn; - if (ksig->ka.sa.sa_flags & SA_RESTORER) - restorer = ksig->ka.sa.sa_restorer; - put_user_ex(restorer, &frame->pretcode); + /* Set up to return from userspace. */ + restorer = current->mm->context.vdso + + vdso_image_32.sym___kernel_rt_sigreturn; + if (ksig->ka.sa.sa_flags & SA_RESTORER) + restorer = ksig->ka.sa.sa_restorer; + unsafe_put_user(restorer, &frame->pretcode, Efault); - /* - * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode); - } put_user_catch(err); + /* + * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 + * + * WE DO NOT USE IT ANY MORE! It's only left here for historical + * reasons and because gdb uses it as a signature to notice + * signal handler stack frames. + */ + unsafe_put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); - err |= copy_siginfo_to_user(&frame->info, &ksig->info); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (err) + if (copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; /* Set up registers for signal handler */ @@ -434,6 +414,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->cs = __USER_CS; return 0; +Efault: + user_access_end(); + return -EFAULT; } #else /* !CONFIG_X86_32 */ static unsigned long frame_uc_flags(struct pt_regs *regs) @@ -457,43 +440,34 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, struct rt_sigframe __user *frame; void __user *fp = NULL; unsigned long uc_flags; - int err = 0; + + /* x86-64 should always use SA_RESTORER. */ + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return -EFAULT; frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); + uc_flags = frame_uc_flags(regs); - if (!access_ok(frame, sizeof(*frame))) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { if (copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; } - uc_flags = frame_uc_flags(regs); - - put_user_try { - /* Create the ucontext. */ - put_user_ex(uc_flags, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - save_altstack_ex(&frame->uc.uc_stack, regs->sp); - - /* Set up to return from userspace. If provided, use a stub - already in userspace. */ - /* x86-64 should always use SA_RESTORER. */ - if (ksig->ka.sa.sa_flags & SA_RESTORER) { - put_user_ex(ksig->ka.sa.sa_restorer, &frame->pretcode); - } else { - /* could use a vstub here */ - err |= -EFAULT; - } - } put_user_catch(err); - - err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (err) - return -EFAULT; - /* Set up registers for signal handler */ regs->di = sig; /* In case the signal handler was declared without prototypes */ @@ -530,6 +504,10 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, force_valid_ss(regs); return 0; + +Efault: + user_access_end(); + return -EFAULT; } #endif /* CONFIG_X86_32 */ @@ -541,44 +519,33 @@ static int x32_setup_rt_frame(struct ksignal *ksig, struct rt_sigframe_x32 __user *frame; unsigned long uc_flags; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); + void __user *fp = NULL; - if (!access_ok(frame, sizeof(*frame))) + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) return -EFAULT; - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true)) - return -EFAULT; - } + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); uc_flags = frame_uc_flags(regs); - put_user_try { - /* Create the ucontext. */ - put_user_ex(uc_flags, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); - put_user_ex(0, &frame->uc.uc__pad0); - - if (ksig->ka.sa.sa_flags & SA_RESTORER) { - restorer = ksig->ka.sa.sa_restorer; - } else { - /* could use a vstub here */ - restorer = NULL; - err |= -EFAULT; - } - put_user_ex(restorer, (unsigned long __user *)&frame->pretcode); - } put_user_catch(err); + if (!user_access_begin(frame, sizeof(*frame))) + return -EFAULT; - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + unsafe_put_user(0, &frame->uc.uc__pad0, Efault); + restorer = ksig->ka.sa.sa_restorer; + unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); - if (err) - return -EFAULT; + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true)) + return -EFAULT; + } /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; @@ -597,6 +564,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig, #endif /* CONFIG_X86_X32_ABI */ return 0; +#ifdef CONFIG_X86_X32_ABI +Efault: + user_access_end(); + return -EFAULT; +#endif } /* @@ -613,9 +585,8 @@ SYSCALL_DEFINE0(sigreturn) if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1 - && __copy_from_user(&set.sig[1], &frame->extramask, - sizeof(frame->extramask)))) + if (__get_user(set.sig[0], &frame->sc.oldmask) || + __get_user(set.sig[1], &frame->extramask[0])) goto badframe; set_current_blocked(&set); @@ -645,7 +616,7 @@ SYSCALL_DEFINE0(rt_sigreturn) frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; if (__get_user(uc_flags, &frame->uc.uc_flags)) goto badframe; @@ -859,7 +830,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) } #ifdef CONFIG_X86_X32_ABI -asmlinkage long sys32_x32_rt_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_x32 __user *frame; @@ -870,7 +841,7 @@ asmlinkage long sys32_x32_rt_sigreturn(void) if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; if (__get_user(uc_flags, &frame->uc.uc_flags)) goto badframe; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 69881b2d446c..fe3ab9632f3b 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) { @@ -1434,7 +1438,7 @@ early_param("possible_cpus", _setup_possible_cpus); /* * cpu_possible_mask should be static, it cannot change as cpu's * are onlined, or offlined. The reason is per-cpu data-structures - * are allocated by some modules at init time, and dont expect to + * are allocated by some modules at init time, and don't expect to * do this dynamically on cpu arrival/departure. * cpu_present_mask on the other hand can change dynamically. * In case when cpu_hotplug is not compiled, then we resort to current @@ -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/stacktrace.c b/arch/x86/kernel/stacktrace.c index 2d6898c2cb64..6ad43fc44556 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -96,7 +96,8 @@ struct stack_frame_user { }; static int -copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) +copy_stack_frame(const struct stack_frame_user __user *fp, + struct stack_frame_user *frame) { int ret; @@ -105,7 +106,8 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) ret = 1; pagefault_disable(); - if (__copy_from_user_inatomic(frame, fp, sizeof(*frame))) + if (__get_user(frame->next_fp, &fp->next_fp) || + __get_user(frame->ret_addr, &fp->ret_addr)) ret = 0; pagefault_enable(); diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/kernel/sys_ia32.c index 21790307121e..ab03fede1422 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/kernel/sys_ia32.c @@ -51,20 +51,80 @@ #define AA(__x) ((unsigned long)(__x)) - -COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, - unsigned long, offset_low, unsigned long, offset_high) +SYSCALL_DEFINE3(ia32_truncate64, const char __user *, filename, + unsigned long, offset_low, unsigned long, offset_high) { return ksys_truncate(filename, ((loff_t) offset_high << 32) | offset_low); } -COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, - unsigned long, offset_low, unsigned long, offset_high) +SYSCALL_DEFINE3(ia32_ftruncate64, unsigned int, fd, + unsigned long, offset_low, unsigned long, offset_high) { return ksys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); } +/* warning: next two assume little endian */ +SYSCALL_DEFINE5(ia32_pread64, unsigned int, fd, char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) +{ + return ksys_pread64(fd, ubuf, count, + ((loff_t)AA(poshi) << 32) | AA(poslo)); +} + +SYSCALL_DEFINE5(ia32_pwrite64, unsigned int, fd, const char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) +{ + return ksys_pwrite64(fd, ubuf, count, + ((loff_t)AA(poshi) << 32) | AA(poslo)); +} + + +/* + * Some system calls that need sign extended arguments. This could be + * done by a generic wrapper. + */ +SYSCALL_DEFINE6(ia32_fadvise64_64, int, fd, __u32, offset_low, + __u32, offset_high, __u32, len_low, __u32, len_high, + int, advice) +{ + return ksys_fadvise64_64(fd, + (((u64)offset_high)<<32) | offset_low, + (((u64)len_high)<<32) | len_low, + advice); +} + +SYSCALL_DEFINE4(ia32_readahead, int, fd, unsigned int, off_lo, + unsigned int, off_hi, size_t, count) +{ + return ksys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); +} + +SYSCALL_DEFINE6(ia32_sync_file_range, int, fd, unsigned int, off_low, + unsigned int, off_hi, unsigned int, n_low, + unsigned int, n_hi, int, flags) +{ + return ksys_sync_file_range(fd, + ((u64)off_hi << 32) | off_low, + ((u64)n_hi << 32) | n_low, flags); +} + +SYSCALL_DEFINE5(ia32_fadvise64, int, fd, unsigned int, offset_lo, + unsigned int, offset_hi, size_t, len, int, advice) +{ + return ksys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, + len, advice); +} + +SYSCALL_DEFINE6(ia32_fallocate, int, fd, int, mode, + unsigned int, offset_lo, unsigned int, offset_hi, + unsigned int, len_lo, unsigned int, len_hi) +{ + return ksys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, + ((u64)len_hi << 32) | len_lo); +} + +#ifdef CONFIG_IA32_EMULATION /* * Another set for IA32/LFS -- x86_64 struct stat is different due to * support for 64bit inode numbers. @@ -97,7 +157,7 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename, +COMPAT_SYSCALL_DEFINE2(ia32_stat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; @@ -108,7 +168,7 @@ COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename, return ret; } -COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename, +COMPAT_SYSCALL_DEFINE2(ia32_lstat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; @@ -118,7 +178,7 @@ COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename, return ret; } -COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd, +COMPAT_SYSCALL_DEFINE2(ia32_fstat64, unsigned int, fd, struct stat64 __user *, statbuf) { struct kstat stat; @@ -128,7 +188,7 @@ COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd, return ret; } -COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd, +COMPAT_SYSCALL_DEFINE4(ia32_fstatat64, unsigned int, dfd, const char __user *, filename, struct stat64 __user *, statbuf, int, flag) { @@ -156,7 +216,7 @@ struct mmap_arg_struct32 { unsigned int offset; }; -COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) +COMPAT_SYSCALL_DEFINE1(ia32_mmap, struct mmap_arg_struct32 __user *, arg) { struct mmap_arg_struct32 a; @@ -170,70 +230,10 @@ COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) a.offset>>PAGE_SHIFT); } -/* warning: next two assume little endian */ -COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf, - u32, count, u32, poslo, u32, poshi) -{ - return ksys_pread64(fd, ubuf, count, - ((loff_t)AA(poshi) << 32) | AA(poslo)); -} - -COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf, - u32, count, u32, poslo, u32, poshi) -{ - return ksys_pwrite64(fd, ubuf, count, - ((loff_t)AA(poshi) << 32) | AA(poslo)); -} - - -/* - * Some system calls that need sign extended arguments. This could be - * done by a generic wrapper. - */ -COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, - __u32, offset_high, __u32, len_low, __u32, len_high, - int, advice) -{ - return ksys_fadvise64_64(fd, - (((u64)offset_high)<<32) | offset_low, - (((u64)len_high)<<32) | len_low, - advice); -} - -COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, - unsigned int, off_hi, size_t, count) -{ - return ksys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); -} - -COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, - unsigned int, off_hi, unsigned int, n_low, - unsigned int, n_hi, int, flags) -{ - return ksys_sync_file_range(fd, - ((u64)off_hi << 32) | off_low, - ((u64)n_hi << 32) | n_low, flags); -} - -COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, - unsigned int, offset_hi, size_t, len, int, advice) -{ - return ksys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, - len, advice); -} - -COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, - unsigned int, offset_lo, unsigned int, offset_hi, - unsigned int, len_lo, unsigned int, len_hi) -{ - return ksys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, - ((u64)len_hi << 32) | len_lo); -} - /* * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS */ -COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, +COMPAT_SYSCALL_DEFINE5(ia32_clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls_val, int __user *, child_tidptr) { @@ -252,3 +252,4 @@ COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, return _do_fork(&args); } +#endif /* CONFIG_IA32_EMULATION */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index ca3c11a17b5a..504fa5425bce 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -21,7 +21,6 @@ #include <asm/elf.h> #include <asm/ia32.h> -#include <asm/syscalls.h> /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index d8673d8a779b..106e7f87f534 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -62,19 +62,16 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, - .name = "timer" -}; - static void __init setup_default_timer_irq(void) { + unsigned long flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER; + /* - * Unconditionally register the legacy timer; even without legacy - * PIC/PIT we need this for the HPET0 in legacy replacement mode. + * Unconditionally register the legacy timer interrupt; even + * without legacy PIC/PIT we need this for the HPET0 in legacy + * replacement mode. */ - if (setup_irq(0, &irq0)) + if (request_irq(0, timer_interrupt, flags, "timer", NULL)) pr_info("Failed to register legacy timer interrupt\n"); } @@ -122,18 +119,12 @@ void __init time_init(void) */ void clocksource_arch_init(struct clocksource *cs) { - if (cs->archdata.vclock_mode == VCLOCK_NONE) + if (cs->vdso_clock_mode == VDSO_CLOCKMODE_NONE) return; - if (cs->archdata.vclock_mode > VCLOCK_MAX) { - pr_warn("clocksource %s registered with invalid vclock_mode %d. Disabling vclock.\n", - cs->name, cs->archdata.vclock_mode); - cs->archdata.vclock_mode = VCLOCK_NONE; - } - if (cs->mask != CLOCKSOURCE_MASK(64)) { - pr_warn("clocksource %s registered with invalid mask %016llx. Disabling vclock.\n", + pr_warn("clocksource %s registered with invalid mask %016llx for VDSO. Disabling VDSO support.\n", cs->name, cs->mask); - cs->archdata.vclock_mode = VCLOCK_NONE; + cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE; } } 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/traps.c b/arch/x86/kernel/traps.c index 6ef00eb6fbb9..d54cffdc7cac 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -46,6 +46,7 @@ #include <asm/traps.h> #include <asm/desc.h> #include <asm/fpu/internal.h> +#include <asm/cpu.h> #include <asm/cpu_entry_area.h> #include <asm/mce.h> #include <asm/fixmap.h> @@ -242,7 +243,6 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, { struct task_struct *tsk = current; - if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code)) return; @@ -288,9 +288,29 @@ DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, 0, NULL, "coprocessor segment overru DO_ERROR(X86_TRAP_TS, SIGSEGV, 0, NULL, "invalid TSS", invalid_TSS) DO_ERROR(X86_TRAP_NP, SIGBUS, 0, NULL, "segment not present", segment_not_present) DO_ERROR(X86_TRAP_SS, SIGBUS, 0, NULL, "stack segment", stack_segment) -DO_ERROR(X86_TRAP_AC, SIGBUS, BUS_ADRALN, NULL, "alignment check", alignment_check) #undef IP +dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code) +{ + char *str = "alignment check"; + + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + + if (notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_AC, SIGBUS) == NOTIFY_STOP) + return; + + if (!user_mode(regs)) + die("Split lock detected\n", regs, error_code); + + local_irq_enable(); + + if (handle_user_split_lock(regs, error_code)) + return; + + do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs, + error_code, BUS_ADRALN, NULL); +} + #ifdef CONFIG_VMAP_STACK __visible void __noreturn handle_stack_overflow(const char *message, struct pt_regs *regs, @@ -572,14 +592,20 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) return; /* - * Use ist_enter despite the fact that we don't use an IST stack. - * We can be called from a kprobe in non-CONTEXT_KERNEL kernel - * mode or even during context tracking state changes. + * Unlike any other non-IST entry, we can be called from a kprobe in + * non-CONTEXT_KERNEL kernel mode or even during context tracking + * state changes. Make sure that we wake up RCU even if we're coming + * from kernel code. * - * This means that we can't schedule. That's okay. + * This means that we can't schedule even if we came from a + * preemptible kernel context. That's okay. */ - ist_enter(regs); + if (!user_mode(regs)) { + rcu_nmi_enter(); + preempt_disable(); + } RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -600,7 +626,10 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) cond_local_irq_disable(regs); exit: - ist_exit(regs); + if (!user_mode(regs)) { + preempt_enable_no_resched(); + rcu_nmi_exit(); + } } NOKPROBE_SYMBOL(do_int3); @@ -862,7 +891,25 @@ do_simd_coprocessor_error(struct pt_regs *regs, long error_code) dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) { - cond_local_irq_enable(regs); + /* + * This addresses a Pentium Pro Erratum: + * + * PROBLEM: If the APIC subsystem is configured in mixed mode with + * Virtual Wire mode implemented through the local APIC, an + * interrupt vector of 0Fh (Intel reserved encoding) may be + * generated by the local APIC (Int 15). This vector may be + * generated upon receipt of a spurious interrupt (an interrupt + * which is removed before the system receives the INTA sequence) + * instead of the programmed 8259 spurious interrupt vector. + * + * IMPLICATION: The spurious interrupt vector programmed in the + * 8259 is normally handled by an operating system's spurious + * interrupt handler. However, a vector of 0Fh is unknown to some + * operating systems, which would crash if this erratum occurred. + * + * In theory this could be limited to 32bit, but the handler is not + * hurting and who knows which other CPUs suffer from this. + */ } dotraplinkage void diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7e322e2daaf5..fdd4c1078632 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -477,7 +477,7 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) * transition from one expected value to another with a fairly * high accuracy, and we didn't miss any events. We can thus * use the TSC value at the transitions to calculate a pretty - * good value for the TSC frequencty. + * good value for the TSC frequency. */ static inline int pit_verify_msb(unsigned char val) { @@ -1108,17 +1108,24 @@ static void tsc_cs_tick_stable(struct clocksource *cs) sched_clock_tick_stable(); } +static int tsc_cs_enable(struct clocksource *cs) +{ + vclocks_set_used(VDSO_CLOCKMODE_TSC); + return 0; +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ static struct clocksource clocksource_tsc_early = { - .name = "tsc-early", - .rating = 299, - .read = read_tsc, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS | + .name = "tsc-early", + .rating = 299, + .read = read_tsc, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, - .archdata = { .vclock_mode = VCLOCK_TSC }, + .vdso_clock_mode = VDSO_CLOCKMODE_TSC, + .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, @@ -1131,14 +1138,15 @@ static struct clocksource clocksource_tsc_early = { * been found good. */ static struct clocksource clocksource_tsc = { - .name = "tsc", - .rating = 300, - .read = read_tsc, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS | + .name = "tsc", + .rating = 300, + .read = read_tsc, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_MUST_VERIFY, - .archdata = { .vclock_mode = VCLOCK_TSC }, + .vdso_clock_mode = VDSO_CLOCKMODE_TSC, + .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index e0cbe4f2af49..4fec6f3a1858 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -15,18 +15,46 @@ #include <asm/param.h> #include <asm/tsc.h> -#define MAX_NUM_FREQS 9 +#define MAX_NUM_FREQS 16 /* 4 bits to select the frequency */ + +/* + * The frequency numbers in the SDM are e.g. 83.3 MHz, which does not contain a + * lot of accuracy which leads to clock drift. As far as we know Bay Trail SoCs + * use a 25 MHz crystal and Cherry Trail uses a 19.2 MHz crystal, the crystal + * is the source clk for a root PLL which outputs 1600 and 100 MHz. It is + * unclear if the root PLL outputs are used directly by the CPU clock PLL or + * if there is another PLL in between. + * This does not matter though, we can model the chain of PLLs as a single PLL + * with a quotient equal to the quotients of all PLLs in the chain multiplied. + * So we can create a simplified model of the CPU clock setup using a reference + * clock of 100 MHz plus a quotient which gets us as close to the frequency + * from the SDM as possible. + * For the 83.3 MHz example from above this would give us 100 MHz * 5 / 6 = + * 83 and 1/3 MHz, which matches exactly what has been measured on actual hw. + */ +#define TSC_REFERENCE_KHZ 100000 + +struct muldiv { + u32 multiplier; + u32 divider; +}; /* * If MSR_PERF_STAT[31] is set, the maximum resolved bus ratio can be * read in MSR_PLATFORM_ID[12:8], otherwise in MSR_PERF_STAT[44:40]. * Unfortunately some Intel Atom SoCs aren't quite compliant to this, * so we need manually differentiate SoC families. This is what the - * field msr_plat does. + * field use_msr_plat does. */ struct freq_desc { - u8 msr_plat; /* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */ + bool use_msr_plat; + struct muldiv muldiv[MAX_NUM_FREQS]; + /* + * Some CPU frequencies in the SDM do not map to known PLL freqs, in + * that case the muldiv array is empty and the freqs array is used. + */ u32 freqs[MAX_NUM_FREQS]; + u32 mask; }; /* @@ -35,41 +63,91 @@ struct freq_desc { * by MSR based on SDM. */ static const struct freq_desc freq_desc_pnw = { - 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } + .use_msr_plat = false, + .freqs = { 0, 0, 0, 0, 0, 99840, 0, 83200 }, + .mask = 0x07, }; static const struct freq_desc freq_desc_clv = { - 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } + .use_msr_plat = false, + .freqs = { 0, 133200, 0, 0, 0, 99840, 0, 83200 }, + .mask = 0x07, }; +/* + * Bay Trail SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 000: 100 * 5 / 6 = 83.3333 MHz + * 001: 100 * 1 / 1 = 100.0000 MHz + * 010: 100 * 4 / 3 = 133.3333 MHz + * 011: 100 * 7 / 6 = 116.6667 MHz + * 100: 100 * 4 / 5 = 80.0000 MHz + */ static const struct freq_desc freq_desc_byt = { - 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 }, + { 4, 5 } }, + .mask = 0x07, }; +/* + * Cherry Trail SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0000: 100 * 5 / 6 = 83.3333 MHz + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + * 0011: 100 * 7 / 6 = 116.6667 MHz + * 0100: 100 * 4 / 5 = 80.0000 MHz + * 0101: 100 * 14 / 15 = 93.3333 MHz + * 0110: 100 * 9 / 10 = 90.0000 MHz + * 0111: 100 * 8 / 9 = 88.8889 MHz + * 1000: 100 * 7 / 8 = 87.5000 MHz + */ static const struct freq_desc freq_desc_cht = { - 1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 }, + { 4, 5 }, { 14, 15 }, { 9, 10 }, { 8, 9 }, + { 7, 8 } }, + .mask = 0x0f, }; +/* + * Merriefield SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + */ static const struct freq_desc freq_desc_tng = { - 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 0, 0 }, { 1, 1 }, { 4, 3 } }, + .mask = 0x07, }; +/* + * Moorefield SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0000: 100 * 5 / 6 = 83.3333 MHz + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + * 0011: 100 * 1 / 1 = 100.0000 MHz + */ static const struct freq_desc freq_desc_ann = { - 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 1, 1 } }, + .mask = 0x0f, }; +/* 24 MHz crystal? : 24 * 13 / 4 = 78 MHz */ static const struct freq_desc freq_desc_lgm = { - 1, { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 } + .use_msr_plat = true, + .freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 }, + .mask = 0x0f, }; 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), {} }; @@ -81,17 +159,19 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = { */ unsigned long cpu_khz_from_msr(void) { - u32 lo, hi, ratio, freq; + u32 lo, hi, ratio, freq, tscref; const struct freq_desc *freq_desc; const struct x86_cpu_id *id; + const struct muldiv *md; unsigned long res; + int index; id = x86_match_cpu(tsc_msr_cpu_ids); if (!id) return 0; freq_desc = (struct freq_desc *)id->driver_data; - if (freq_desc->msr_plat) { + if (freq_desc->use_msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); ratio = (lo >> 8) & 0xff; } else { @@ -101,12 +181,28 @@ unsigned long cpu_khz_from_msr(void) /* Get FSB FREQ ID */ rdmsr(MSR_FSB_FREQ, lo, hi); + index = lo & freq_desc->mask; + md = &freq_desc->muldiv[index]; - /* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */ - freq = freq_desc->freqs[lo & 0x7]; + /* + * Note this also catches cases where the index points to an unpopulated + * part of muldiv, in that case the else will set freq and res to 0. + */ + if (md->divider) { + tscref = TSC_REFERENCE_KHZ * md->multiplier; + freq = DIV_ROUND_CLOSEST(tscref, md->divider); + /* + * Multiplying by ratio before the division has better + * accuracy than just calculating freq * ratio. + */ + res = DIV_ROUND_CLOSEST(tscref * ratio, md->divider); + } else { + freq = freq_desc->freqs[index]; + res = freq * ratio; + } - /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ - res = freq * ratio; + if (freq == 0) + pr_err("Error MSR_FSB_FREQ index %d is unknown\n", index); #ifdef CONFIG_X86_LOCAL_APIC lapic_timer_period = (freq * 1000) / HZ; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 32a818764e03..3d3c761eb74a 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -295,7 +295,7 @@ static cycles_t check_tsc_warp(unsigned int timeout) * But as the TSC is per-logical CPU and can potentially be modified wrongly * by the bios, TSC sync test for smaller duration should be able * to catch such errors. Also this will catch the condition where all the - * cores in the socket doesn't get reset at the same time. + * cores in the socket don't get reset at the same time. */ static inline unsigned int loop_timeout(int cpu) { diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 91d55454e702..47a8676c7395 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -98,7 +98,6 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) struct task_struct *tsk = current; struct vm86plus_struct __user *user; struct vm86 *vm86 = current->thread.vm86; - long err = 0; /* * This gets called from entry.S with interrupts disabled, but @@ -114,37 +113,30 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); user = vm86->user_vm86; - if (!access_ok(user, vm86->vm86plus.is_vm86pus ? + if (!user_access_begin(user, vm86->vm86plus.is_vm86pus ? sizeof(struct vm86plus_struct) : - sizeof(struct vm86_struct))) { - pr_alert("could not access userspace vm86 info\n"); - do_exit(SIGSEGV); - } - - put_user_try { - put_user_ex(regs->pt.bx, &user->regs.ebx); - put_user_ex(regs->pt.cx, &user->regs.ecx); - put_user_ex(regs->pt.dx, &user->regs.edx); - put_user_ex(regs->pt.si, &user->regs.esi); - put_user_ex(regs->pt.di, &user->regs.edi); - put_user_ex(regs->pt.bp, &user->regs.ebp); - put_user_ex(regs->pt.ax, &user->regs.eax); - put_user_ex(regs->pt.ip, &user->regs.eip); - put_user_ex(regs->pt.cs, &user->regs.cs); - put_user_ex(regs->pt.flags, &user->regs.eflags); - put_user_ex(regs->pt.sp, &user->regs.esp); - put_user_ex(regs->pt.ss, &user->regs.ss); - put_user_ex(regs->es, &user->regs.es); - put_user_ex(regs->ds, &user->regs.ds); - put_user_ex(regs->fs, &user->regs.fs); - put_user_ex(regs->gs, &user->regs.gs); - - put_user_ex(vm86->screen_bitmap, &user->screen_bitmap); - } put_user_catch(err); - if (err) { - pr_alert("could not access userspace vm86 info\n"); - do_exit(SIGSEGV); - } + sizeof(struct vm86_struct))) + goto Efault; + + unsafe_put_user(regs->pt.bx, &user->regs.ebx, Efault_end); + unsafe_put_user(regs->pt.cx, &user->regs.ecx, Efault_end); + unsafe_put_user(regs->pt.dx, &user->regs.edx, Efault_end); + unsafe_put_user(regs->pt.si, &user->regs.esi, Efault_end); + unsafe_put_user(regs->pt.di, &user->regs.edi, Efault_end); + unsafe_put_user(regs->pt.bp, &user->regs.ebp, Efault_end); + unsafe_put_user(regs->pt.ax, &user->regs.eax, Efault_end); + unsafe_put_user(regs->pt.ip, &user->regs.eip, Efault_end); + unsafe_put_user(regs->pt.cs, &user->regs.cs, Efault_end); + unsafe_put_user(regs->pt.flags, &user->regs.eflags, Efault_end); + unsafe_put_user(regs->pt.sp, &user->regs.esp, Efault_end); + unsafe_put_user(regs->pt.ss, &user->regs.ss, Efault_end); + unsafe_put_user(regs->es, &user->regs.es, Efault_end); + unsafe_put_user(regs->ds, &user->regs.ds, Efault_end); + unsafe_put_user(regs->fs, &user->regs.fs, Efault_end); + unsafe_put_user(regs->gs, &user->regs.gs, Efault_end); + unsafe_put_user(vm86->screen_bitmap, &user->screen_bitmap, Efault_end); + + user_access_end(); preempt_disable(); tsk->thread.sp0 = vm86->saved_sp0; @@ -159,6 +151,13 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) lazy_load_gs(vm86->regs32.gs); regs->pt.ax = retval; + return; + +Efault_end: + user_access_end(); +Efault: + pr_alert("could not access userspace vm86 info\n"); + do_exit(SIGSEGV); } static void mark_screen_rdonly(struct mm_struct *mm) @@ -243,6 +242,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) struct kernel_vm86_regs vm86regs; struct pt_regs *regs = current_pt_regs(); unsigned long err = 0; + struct vm86_struct v; err = security_mmap_addr(0); if (err) { @@ -278,39 +278,32 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) if (vm86->saved_sp0) return -EPERM; - if (!access_ok(user_vm86, plus ? - sizeof(struct vm86_struct) : - sizeof(struct vm86plus_struct))) + if (copy_from_user(&v, user_vm86, + offsetof(struct vm86_struct, int_revectored))) return -EFAULT; memset(&vm86regs, 0, sizeof(vm86regs)); - get_user_try { - unsigned short seg; - get_user_ex(vm86regs.pt.bx, &user_vm86->regs.ebx); - get_user_ex(vm86regs.pt.cx, &user_vm86->regs.ecx); - get_user_ex(vm86regs.pt.dx, &user_vm86->regs.edx); - get_user_ex(vm86regs.pt.si, &user_vm86->regs.esi); - get_user_ex(vm86regs.pt.di, &user_vm86->regs.edi); - get_user_ex(vm86regs.pt.bp, &user_vm86->regs.ebp); - get_user_ex(vm86regs.pt.ax, &user_vm86->regs.eax); - get_user_ex(vm86regs.pt.ip, &user_vm86->regs.eip); - get_user_ex(seg, &user_vm86->regs.cs); - vm86regs.pt.cs = seg; - get_user_ex(vm86regs.pt.flags, &user_vm86->regs.eflags); - get_user_ex(vm86regs.pt.sp, &user_vm86->regs.esp); - get_user_ex(seg, &user_vm86->regs.ss); - vm86regs.pt.ss = seg; - get_user_ex(vm86regs.es, &user_vm86->regs.es); - get_user_ex(vm86regs.ds, &user_vm86->regs.ds); - get_user_ex(vm86regs.fs, &user_vm86->regs.fs); - get_user_ex(vm86regs.gs, &user_vm86->regs.gs); - - get_user_ex(vm86->flags, &user_vm86->flags); - get_user_ex(vm86->screen_bitmap, &user_vm86->screen_bitmap); - get_user_ex(vm86->cpu_type, &user_vm86->cpu_type); - } get_user_catch(err); - if (err) - return err; + + vm86regs.pt.bx = v.regs.ebx; + vm86regs.pt.cx = v.regs.ecx; + vm86regs.pt.dx = v.regs.edx; + vm86regs.pt.si = v.regs.esi; + vm86regs.pt.di = v.regs.edi; + vm86regs.pt.bp = v.regs.ebp; + vm86regs.pt.ax = v.regs.eax; + vm86regs.pt.ip = v.regs.eip; + vm86regs.pt.cs = v.regs.cs; + vm86regs.pt.flags = v.regs.eflags; + vm86regs.pt.sp = v.regs.esp; + vm86regs.pt.ss = v.regs.ss; + vm86regs.es = v.regs.es; + vm86regs.ds = v.regs.ds; + vm86regs.fs = v.regs.fs; + vm86regs.gs = v.regs.gs; + + vm86->flags = v.flags; + vm86->screen_bitmap = v.screen_bitmap; + vm86->cpu_type = v.cpu_type; if (copy_from_user(&vm86->int_revectored, &user_vm86->int_revectored, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e3296aa028fe..1bf7e312361f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -21,6 +21,7 @@ #define LOAD_OFFSET __START_KERNEL_map #endif +#define RUNTIME_DISCARD_EXIT #define EMITS_PT_NOTE #define RO_EXCEPTION_TABLE_ALIGN 16 @@ -313,8 +314,8 @@ SECTIONS . = ALIGN(8); /* - * .exit.text is discard at runtime, not link time, to deal with - * references from .altinstructions and .eh_frame + * .exit.text is discarded at runtime, not link time, to deal with + * references from .altinstructions */ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { EXIT_TEXT @@ -412,9 +413,6 @@ SECTIONS DWARF_DEBUG DISCARDS - /DISCARD/ : { - *(.eh_frame) - } } 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/cpuid.c b/arch/x86/kvm/cpuid.c index b1c469446b07..901cd1fdecd9 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -24,6 +24,13 @@ #include "trace.h" #include "pmu.h" +/* + * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be + * aligned to sizeof(unsigned long) because it's not accessed via bitops. + */ +u32 kvm_cpu_caps[NCAPINTS] __read_mostly; +EXPORT_SYMBOL_GPL(kvm_cpu_caps); + static u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; @@ -45,23 +52,6 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } -bool kvm_mpx_supported(void) -{ - return ((host_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) - && kvm_x86_ops->mpx_supported()); -} -EXPORT_SYMBOL_GPL(kvm_mpx_supported); - -u64 kvm_supported_xcr0(void) -{ - u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0; - - if (!kvm_mpx_supported()) - xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); - - return xcr0; -} - #define F feature_bit int kvm_update_cpuid(struct kvm_vcpu *vcpu) @@ -74,32 +64,24 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) return 0; /* Update OSXSAVE bit */ - if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) { - best->ecx &= ~F(OSXSAVE); - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) - best->ecx |= F(OSXSAVE); - } + if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) + cpuid_entry_change(best, X86_FEATURE_OSXSAVE, + kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)); - best->edx &= ~F(APIC); - if (vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE) - best->edx |= F(APIC); + cpuid_entry_change(best, X86_FEATURE_APIC, + vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); if (apic) { - if (best->ecx & F(TSC_DEADLINE_TIMER)) + if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER)) apic->lapic_timer.timer_mode_mask = 3 << 17; else apic->lapic_timer.timer_mode_mask = 1 << 17; } best = kvm_find_cpuid_entry(vcpu, 7, 0); - if (best) { - /* Update OSPKE bit */ - if (boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) { - best->ecx &= ~F(OSPKE); - if (kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) - best->ecx |= F(OSPKE); - } - } + if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) + cpuid_entry_change(best, X86_FEATURE_OSPKE, + kvm_read_cr4_bits(vcpu, X86_CR4_PKE)); best = kvm_find_cpuid_entry(vcpu, 0xD, 0); if (!best) { @@ -107,14 +89,14 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; } else { vcpu->arch.guest_supported_xcr0 = - (best->eax | ((u64)best->edx << 32)) & - kvm_supported_xcr0(); + (best->eax | ((u64)best->edx << 32)) & supported_xcr0; vcpu->arch.guest_xstate_size = best->ebx = xstate_required_size(vcpu->arch.xcr0, false); } best = kvm_find_cpuid_entry(vcpu, 0xD, 1); - if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) + if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || + cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); /* @@ -136,12 +118,10 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = kvm_find_cpuid_entry(vcpu, 0x1, 0); - if (best) { - if (vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT) - best->ecx |= F(MWAIT); - else - best->ecx &= ~F(MWAIT); - } + if (best) + cpuid_entry_change(best, X86_FEATURE_MWAIT, + vcpu->arch.ia32_misc_enable_msr & + MSR_IA32_MISC_ENABLE_MWAIT); } /* Update physical-address width */ @@ -154,10 +134,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) static int is_efer_nx(void) { - unsigned long long efer = 0; - - rdmsrl_safe(MSR_EFER, &efer); - return efer & EFER_NX; + return host_efer & EFER_NX; } static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) @@ -173,8 +150,8 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) break; } } - if (entry && (entry->edx & F(NX)) && !is_efer_nx()) { - entry->edx &= ~F(NX); + if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) { + cpuid_entry_clear(entry, X86_FEATURE_NX); printk(KERN_INFO "kvm: guest NX capability removed\n"); } } @@ -232,7 +209,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, vcpu->arch.cpuid_nent = cpuid->nent; cpuid_fix_nx_cap(vcpu); kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); + kvm_x86_ops.cpuid_update(vcpu); r = kvm_update_cpuid(vcpu); out: @@ -255,7 +232,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, goto out; vcpu->arch.cpuid_nent = cpuid->nent; kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); + kvm_x86_ops.cpuid_update(vcpu); r = kvm_update_cpuid(vcpu); out: return r; @@ -281,15 +258,189 @@ out: return r; } -static __always_inline void cpuid_mask(u32 *word, int wordnum) +static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { - reverse_cpuid_check(wordnum); - *word &= boot_cpu_data.x86_capability[wordnum]; + const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); + struct kvm_cpuid_entry2 entry; + + reverse_cpuid_check(leaf); + kvm_cpu_caps[leaf] &= mask; + + cpuid_count(cpuid.function, cpuid.index, + &entry.eax, &entry.ebx, &entry.ecx, &entry.edx); + + kvm_cpu_caps[leaf] &= *__cpuid_entry_get_reg(&entry, cpuid.reg); +} + +void kvm_set_cpu_caps(void) +{ + unsigned int f_nx = is_efer_nx() ? F(NX) : 0; +#ifdef CONFIG_X86_64 + unsigned int f_gbpages = F(GBPAGES); + unsigned int f_lm = F(LM); +#else + unsigned int f_gbpages = 0; + unsigned int f_lm = 0; +#endif + + BUILD_BUG_ON(sizeof(kvm_cpu_caps) > + sizeof(boot_cpu_data.x86_capability)); + + memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability, + sizeof(kvm_cpu_caps)); + + kvm_cpu_cap_mask(CPUID_1_ECX, + /* + * NOTE: MONITOR (and MWAIT) are emulated as NOP, but *not* + * advertised to guests via CPUID! + */ + F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | + 0 /* DS-CPL, VMX, SMX, EST */ | + 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | + F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | + F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | + F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | + 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | + F(F16C) | F(RDRAND) + ); + /* KVM emulates x2apic in software irrespective of host support. */ + kvm_cpu_cap_set(X86_FEATURE_X2APIC); + + kvm_cpu_cap_mask(CPUID_1_EDX, + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) | + 0 /* Reserved, DS, ACPI */ | F(MMX) | + F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | + 0 /* HTT, TM, Reserved, PBE */ + ); + + kvm_cpu_cap_mask(CPUID_7_0_EBX, + F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | + F(BMI2) | F(ERMS) | 0 /*INVPCID*/ | F(RTM) | 0 /*MPX*/ | F(RDSEED) | + F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | + F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | + F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/ + ); + + kvm_cpu_cap_mask(CPUID_7_ECX, + F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) | + F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | + F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | + F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ + ); + /* Set LA57 based on hardware capability. */ + if (cpuid_ecx(7) & F(LA57)) + kvm_cpu_cap_set(X86_FEATURE_LA57); + + kvm_cpu_cap_mask(CPUID_7_EDX, + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | + F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) + ); + + /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ + kvm_cpu_cap_set(X86_FEATURE_TSC_ADJUST); + kvm_cpu_cap_set(X86_FEATURE_ARCH_CAPABILITIES); + + if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) + kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + kvm_cpu_cap_set(X86_FEATURE_INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_AMD_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); + + kvm_cpu_cap_mask(CPUID_7_1_EAX, + F(AVX512_BF16) + ); + + kvm_cpu_cap_mask(CPUID_D_1_EAX, + F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) + ); + + kvm_cpu_cap_mask(CPUID_8000_0001_ECX, + F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | + F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | + F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | + F(TOPOEXT) | F(PERFCTR_CORE) + ); + + kvm_cpu_cap_mask(CPUID_8000_0001_EDX, + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* Reserved */ | + f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | + 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) + ); + + if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) + kvm_cpu_cap_set(X86_FEATURE_GBPAGES); + + kvm_cpu_cap_mask(CPUID_8000_0008_EBX, + F(CLZERO) | F(XSAVEERPTR) | + F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | + F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) + ); + + /* + * AMD has separate bits for each SPEC_CTRL bit. + * arch/x86/kernel/cpu/bugs.c is kind enough to + * record that in cpufeatures so use them. + */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + kvm_cpu_cap_set(X86_FEATURE_AMD_IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + kvm_cpu_cap_set(X86_FEATURE_AMD_IBRS); + if (boot_cpu_has(X86_FEATURE_STIBP)) + kvm_cpu_cap_set(X86_FEATURE_AMD_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_AMD_SSBD); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + kvm_cpu_cap_set(X86_FEATURE_AMD_SSB_NO); + /* + * The preference is to use SPEC CTRL MSR instead of the + * VIRT_SPEC MSR. + */ + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !boot_cpu_has(X86_FEATURE_AMD_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + + /* + * Hide all SVM features by default, SVM will set the cap bits for + * features it emulates and/or exposes for L1. + */ + kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0); + + kvm_cpu_cap_mask(CPUID_C000_0001_EDX, + F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | + F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | + F(PMM) | F(PMM_EN) + ); } +EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); -static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index) +struct kvm_cpuid_array { + struct kvm_cpuid_entry2 *entries; + const int maxnent; + int nent; +}; + +static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, + u32 function, u32 index) { + struct kvm_cpuid_entry2 *entry; + + if (array->nent >= array->maxnent) + return NULL; + + entry = &array->entries[array->nent++]; + entry->function = function; entry->index = index; entry->flags = 0; @@ -298,9 +449,6 @@ static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); switch (function) { - case 2: - entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - break; case 4: case 7: case 0xb: @@ -316,11 +464,18 @@ static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; break; } + + return entry; } -static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, - u32 func, int *nent, int maxnent) +static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) { + struct kvm_cpuid_entry2 *entry; + + if (array->nent >= array->maxnent) + return -E2BIG; + + entry = &array->entries[array->nent]; entry->function = func; entry->index = 0; entry->flags = 0; @@ -328,17 +483,17 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, switch (func) { case 0: entry->eax = 7; - ++*nent; + ++array->nent; break; case 1: entry->ecx = F(MOVBE); - ++*nent; + ++array->nent; break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; entry->ecx = F(RDPID); - ++*nent; + ++array->nent; default: break; } @@ -346,223 +501,60 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, return 0; } -static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) +static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) { - unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; - unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0; - unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; - unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; - unsigned f_la57; - unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0; - - /* cpuid 7.0.ebx */ - const u32 kvm_cpuid_7_0_ebx_x86_features = - F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) | - F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | - F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt; - - /* cpuid 7.0.ecx*/ - const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) | - F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | - F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/; - - /* cpuid 7.0.edx*/ - const u32 kvm_cpuid_7_0_edx_x86_features = - F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | - F(MD_CLEAR); - - /* cpuid 7.1.eax */ - const u32 kvm_cpuid_7_1_eax_x86_features = - F(AVX512_BF16); - - switch (index) { - case 0: - entry->eax = min(entry->eax, 1u); - entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_7_0_EBX); - /* TSC_ADJUST is emulated */ - entry->ebx |= F(TSC_ADJUST); - - entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; - f_la57 = entry->ecx & F(LA57); - cpuid_mask(&entry->ecx, CPUID_7_ECX); - /* Set LA57 based on hardware capability. */ - entry->ecx |= f_la57; - entry->ecx |= f_umip; - entry->ecx |= f_pku; - /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) - entry->ecx &= ~F(PKU); - - entry->edx &= kvm_cpuid_7_0_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_7_EDX); - if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) - entry->edx |= F(SPEC_CTRL); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->edx |= F(SPEC_CTRL_SSBD); - /* - * We emulate ARCH_CAPABILITIES in software even - * if the host doesn't support it. - */ - entry->edx |= F(ARCH_CAPABILITIES); - break; - case 1: - entry->eax &= kvm_cpuid_7_1_eax_x86_features; - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - break; - default: - WARN_ON_ONCE(1); - entry->eax = 0; - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - break; - } -} - -static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, - int *nent, int maxnent) -{ - int r; - unsigned f_nx = is_efer_nx() ? F(NX) : 0; -#ifdef CONFIG_X86_64 - unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL) - ? F(GBPAGES) : 0; - unsigned f_lm = F(LM); -#else - unsigned f_gbpages = 0; - unsigned f_lm = 0; -#endif - unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; - unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0; - unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; - - /* cpuid 1.edx */ - const u32 kvm_cpuid_1_edx_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) | - 0 /* Reserved, DS, ACPI */ | F(MMX) | - F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | - 0 /* HTT, TM, Reserved, PBE */; - /* cpuid 0x80000001.edx */ - const u32 kvm_cpuid_8000_0001_edx_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | - F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp | - 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); - /* cpuid 1.ecx */ - const u32 kvm_cpuid_1_ecx_x86_features = - /* NOTE: MONITOR (and MWAIT) are emulated as NOP, - * but *not* advertised to guests via CPUID ! */ - F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | - 0 /* DS-CPL, VMX, SMX, EST */ | - 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | - F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | - F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | - F(F16C) | F(RDRAND); - /* cpuid 0x80000001.ecx */ - const u32 kvm_cpuid_8000_0001_ecx_x86_features = - F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | - F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | - F(TOPOEXT) | F(PERFCTR_CORE); - - /* cpuid 0x80000008.ebx */ - const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(CLZERO) | F(XSAVEERPTR) | - F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | - F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); - - /* cpuid 0xC0000001.edx */ - const u32 kvm_cpuid_C000_0001_edx_x86_features = - F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | - F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | - F(PMM) | F(PMM_EN); - - /* cpuid 0xD.1.eax */ - const u32 kvm_cpuid_D_1_eax_x86_features = - F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves; + struct kvm_cpuid_entry2 *entry; + int r, i, max_idx; /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); r = -E2BIG; - if (WARN_ON(*nent >= maxnent)) + entry = do_host_cpuid(array, function, 0); + if (!entry) goto out; - do_host_cpuid(entry, function, 0); - ++*nent; - switch (function) { case 0: /* Limited to the highest leaf implemented in KVM. */ entry->eax = min(entry->eax, 0x1fU); break; case 1: - entry->edx &= kvm_cpuid_1_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_1_EDX); - entry->ecx &= kvm_cpuid_1_ecx_x86_features; - cpuid_mask(&entry->ecx, CPUID_1_ECX); - /* we support x2apic emulation even if host does not support - * it since we emulate x2apic in software */ - entry->ecx |= F(X2APIC); + cpuid_entry_override(entry, CPUID_1_EDX); + cpuid_entry_override(entry, CPUID_1_ECX); break; - /* function 2 entries are STATEFUL. That is, repeated cpuid commands - * may return different values. This forces us to get_cpu() before - * issuing the first command, and also to emulate this annoying behavior - * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ - case 2: { - int t, times = entry->eax & 0xff; - - entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - for (t = 1; t < times; ++t) { - if (*nent >= maxnent) - goto out; - - do_host_cpuid(&entry[t], function, 0); - ++*nent; - } + case 2: + /* + * On ancient CPUs, function 2 entries are STATEFUL. That is, + * CPUID(function=2, index=0) may return different results each + * time, with the least-significant byte in EAX enumerating the + * number of times software should do CPUID(2, 0). + * + * Modern CPUs, i.e. every CPU KVM has *ever* run on are less + * idiotic. Intel's SDM states that EAX & 0xff "will always + * return 01H. Software should ignore this value and not + * interpret it as an informational descriptor", while AMD's + * APM states that CPUID(2) is reserved. + * + * WARN if a frankenstein CPU that supports virtualization and + * a stateful CPUID.0x2 is encountered. + */ + WARN_ON_ONCE((entry->eax & 0xff) > 1); break; - } /* functions 4 and 0x8000001d have additional index. */ case 4: - case 0x8000001d: { - int i, cache_type; - - /* read more entries until cache_type is zero */ - for (i = 1; ; ++i) { - if (*nent >= maxnent) + case 0x8000001d: + /* + * Read entries until the cache type in the previous entry is + * zero, i.e. indicates an invalid entry. + */ + for (i = 1; entry->eax & 0x1f; ++i) { + entry = do_host_cpuid(array, function, i); + if (!entry) goto out; - - cache_type = entry[i - 1].eax & 0x1f; - if (!cache_type) - break; - do_host_cpuid(&entry[i], function, i); - ++*nent; } break; - } case 6: /* Thermal management */ entry->eax = 0x4; /* allow ARAT */ entry->ebx = 0; @@ -570,22 +562,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->edx = 0; break; /* function 7 has additional index. */ - case 7: { - int i; - - for (i = 0; ; ) { - do_cpuid_7_mask(&entry[i], i); - if (i == entry->eax) - break; - if (*nent >= maxnent) + case 7: + entry->eax = min(entry->eax, 1u); + cpuid_entry_override(entry, CPUID_7_0_EBX); + cpuid_entry_override(entry, CPUID_7_ECX); + cpuid_entry_override(entry, CPUID_7_EDX); + + /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ + if (entry->eax == 1) { + entry = do_host_cpuid(array, function, 1); + if (!entry) goto out; - ++i; - do_host_cpuid(&entry[i], function, i); - ++*nent; + cpuid_entry_override(entry, CPUID_7_1_EAX); + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; } break; - } case 9: break; case 0xa: { /* Architectural Performance Monitoring */ @@ -622,79 +616,81 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, * thus they can be handled by common code. */ case 0x1f: - case 0xb: { - int i; - + case 0xb: /* - * We filled in entry[0] for CPUID(EAX=<function>, - * ECX=00H) above. If its level type (ECX[15:8]) is - * zero, then the leaf is unimplemented, and we're - * done. Otherwise, continue to populate entries - * until the level type (ECX[15:8]) of the previously - * added entry is zero. + * Populate entries until the level type (ECX[15:8]) of the + * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is + * the starting entry, filled by the primary do_host_cpuid(). */ - for (i = 1; entry[i - 1].ecx & 0xff00; ++i) { - if (*nent >= maxnent) + for (i = 1; entry->ecx & 0xff00; ++i) { + entry = do_host_cpuid(array, function, i); + if (!entry) goto out; - - do_host_cpuid(&entry[i], function, i); - ++*nent; } break; - } - case 0xd: { - int idx, i; - u64 supported = kvm_supported_xcr0(); - - entry->eax &= supported; - entry->ebx = xstate_required_size(supported, false); + case 0xd: + entry->eax &= supported_xcr0; + entry->ebx = xstate_required_size(supported_xcr0, false); entry->ecx = entry->ebx; - entry->edx &= supported >> 32; - if (!supported) + entry->edx &= supported_xcr0 >> 32; + if (!supported_xcr0) break; - for (idx = 1, i = 1; idx < 64; ++idx) { - u64 mask = ((u64)1 << idx); - if (*nent >= maxnent) + entry = do_host_cpuid(array, function, 1); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_D_1_EAX); + if (entry->eax & (F(XSAVES)|F(XSAVEC))) + entry->ebx = xstate_required_size(supported_xcr0 | supported_xss, + true); + else { + WARN_ON_ONCE(supported_xss != 0); + entry->ebx = 0; + } + entry->ecx &= supported_xss; + entry->edx &= supported_xss >> 32; + + for (i = 2; i < 64; ++i) { + bool s_state; + if (supported_xcr0 & BIT_ULL(i)) + s_state = false; + else if (supported_xss & BIT_ULL(i)) + s_state = true; + else + continue; + + entry = do_host_cpuid(array, function, i); + if (!entry) goto out; - do_host_cpuid(&entry[i], function, idx); - if (idx == 1) { - entry[i].eax &= kvm_cpuid_D_1_eax_x86_features; - cpuid_mask(&entry[i].eax, CPUID_D_1_EAX); - entry[i].ebx = 0; - if (entry[i].eax & (F(XSAVES)|F(XSAVEC))) - entry[i].ebx = - xstate_required_size(supported, - true); - } else { - if (entry[i].eax == 0 || !(supported & mask)) - continue; - if (WARN_ON_ONCE(entry[i].ecx & 1)) - continue; + /* + * The supported check above should have filtered out + * invalid sub-leafs. Only valid sub-leafs should + * reach this point, and they should have a non-zero + * save state size. Furthermore, check whether the + * processor agrees with supported_xcr0/supported_xss + * on whether this is an XCR0- or IA32_XSS-managed area. + */ + if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) { + --array->nent; + continue; } - entry[i].ecx = 0; - entry[i].edx = 0; - ++*nent; - ++i; + entry->edx = 0; } break; - } /* Intel PT */ - case 0x14: { - int t, times = entry->eax; - - if (!f_intel_pt) + case 0x14: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; + } - for (t = 1; t <= times; ++t) { - if (*nent >= maxnent) + for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) { + if (!do_host_cpuid(array, function, i)) goto out; - do_host_cpuid(&entry[t], function, t); - ++*nent; } break; - } case KVM_CPUID_SIGNATURE: { static const char signature[12] = "KVMKVMKVM\0\0"; const u32 *sigptr = (const u32 *)signature; @@ -729,10 +725,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->eax = min(entry->eax, 0x8000001f); break; case 0x80000001: - entry->edx &= kvm_cpuid_8000_0001_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_8000_0001_EDX); - entry->ecx &= kvm_cpuid_8000_0001_ecx_x86_features; - cpuid_mask(&entry->ecx, CPUID_8000_0001_ECX); + cpuid_entry_override(entry, CPUID_8000_0001_EDX); + cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ @@ -750,33 +744,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; - entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); - /* - * AMD has separate bits for each SPEC_CTRL bit. - * arch/x86/kernel/cpu/bugs.c is kind enough to - * record that in cpufeatures so use them. - */ - if (boot_cpu_has(X86_FEATURE_IBPB)) - entry->ebx |= F(AMD_IBPB); - if (boot_cpu_has(X86_FEATURE_IBRS)) - entry->ebx |= F(AMD_IBRS); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->ebx |= F(AMD_STIBP); - if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->ebx |= F(AMD_SSBD); - if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) - entry->ebx |= F(AMD_SSB_NO); - /* - * The preference is to use SPEC CTRL MSR instead of the - * VIRT_SPEC MSR. - */ - if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) && - !boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->ebx |= F(VIRT_SSBD); + cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; } + case 0x8000000A: + if (!kvm_cpu_cap_has(X86_FEATURE_SVM)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + entry->eax = 1; /* SVM revision 1 */ + entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper + ASID emulation to nested SVM */ + entry->ecx = 0; /* Reserved */ + cpuid_entry_override(entry, CPUID_8000_000A_EDX); + break; case 0x80000019: entry->ecx = entry->edx = 0; break; @@ -794,8 +775,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->eax = min(entry->eax, 0xC0000004); break; case 0xC0000001: - entry->edx &= kvm_cpuid_C000_0001_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_C000_0001_EDX); + cpuid_entry_override(entry, CPUID_C000_0001_EDX); break; case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ @@ -807,8 +787,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, break; } - kvm_x86_ops->set_supported_cpuid(function, entry); - r = 0; out: @@ -817,26 +795,39 @@ out: return r; } -static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, - int *nent, int maxnent, unsigned int type) +static int do_cpuid_func(struct kvm_cpuid_array *array, u32 func, + unsigned int type) { - if (*nent >= maxnent) - return -E2BIG; - if (type == KVM_GET_EMULATED_CPUID) - return __do_cpuid_func_emulated(entry, func, nent, maxnent); + return __do_cpuid_func_emulated(array, func); - return __do_cpuid_func(entry, func, nent, maxnent); + return __do_cpuid_func(array, func); } -struct kvm_cpuid_param { - u32 func; - bool (*qualifier)(const struct kvm_cpuid_param *param); -}; +#define CENTAUR_CPUID_SIGNATURE 0xC0000000 -static bool is_centaur_cpu(const struct kvm_cpuid_param *param) +static int get_cpuid_func(struct kvm_cpuid_array *array, u32 func, + unsigned int type) { - return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; + u32 limit; + int r; + + if (func == CENTAUR_CPUID_SIGNATURE && + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR) + return 0; + + r = do_cpuid_func(array, func, type); + if (r) + return r; + + limit = array->entries[array->nent - 1].eax; + for (func = func + 1; func <= limit; ++func) { + r = do_cpuid_func(array, func, type); + if (r) + break; + } + + return r; } static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, @@ -870,157 +861,145 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries, unsigned int type) { - struct kvm_cpuid_entry2 *cpuid_entries; - int limit, nent = 0, r = -E2BIG, i; - u32 func; - static const struct kvm_cpuid_param param[] = { - { .func = 0 }, - { .func = 0x80000000 }, - { .func = 0xC0000000, .qualifier = is_centaur_cpu }, - { .func = KVM_CPUID_SIGNATURE }, + static const u32 funcs[] = { + 0, 0x80000000, CENTAUR_CPUID_SIGNATURE, KVM_CPUID_SIGNATURE, + }; + + struct kvm_cpuid_array array = { + .nent = 0, + .maxnent = cpuid->nent, }; + int r, i; if (cpuid->nent < 1) - goto out; + return -E2BIG; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; - r = -ENOMEM; - cpuid_entries = vzalloc(array_size(sizeof(struct kvm_cpuid_entry2), + array.entries = vzalloc(array_size(sizeof(struct kvm_cpuid_entry2), cpuid->nent)); - if (!cpuid_entries) - goto out; - - r = 0; - for (i = 0; i < ARRAY_SIZE(param); i++) { - const struct kvm_cpuid_param *ent = ¶m[i]; - - if (ent->qualifier && !ent->qualifier(ent)) - continue; - - r = do_cpuid_func(&cpuid_entries[nent], ent->func, - &nent, cpuid->nent, type); - - if (r) - goto out_free; - - limit = cpuid_entries[nent - 1].eax; - for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) - r = do_cpuid_func(&cpuid_entries[nent], func, - &nent, cpuid->nent, type); + if (!array.entries) + return -ENOMEM; + for (i = 0; i < ARRAY_SIZE(funcs); i++) { + r = get_cpuid_func(&array, funcs[i], type); if (r) goto out_free; } + cpuid->nent = array.nent; - r = -EFAULT; - if (copy_to_user(entries, cpuid_entries, - nent * sizeof(struct kvm_cpuid_entry2))) - goto out_free; - cpuid->nent = nent; - r = 0; + if (copy_to_user(entries, array.entries, + array.nent * sizeof(struct kvm_cpuid_entry2))) + r = -EFAULT; out_free: - vfree(cpuid_entries); -out: + vfree(array.entries); return r; } -static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) -{ - struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - struct kvm_cpuid_entry2 *ej; - int j = i; - int nent = vcpu->arch.cpuid_nent; - - e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; - /* when no next entry is found, the current entry[i] is reselected */ - do { - j = (j + 1) % nent; - ej = &vcpu->arch.cpuid_entries[j]; - } while (ej->function != e->function); - - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - - return j; -} - -/* find an entry with matching function, matching index (if needed), and that - * should be read next (if it's stateful) */ -static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, - u32 function, u32 index) -{ - if (e->function != function) - return 0; - if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) - return 0; - if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && - !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) - return 0; - return 1; -} - struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index) { + struct kvm_cpuid_entry2 *e; int i; - struct kvm_cpuid_entry2 *best = NULL; for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - struct kvm_cpuid_entry2 *e; - e = &vcpu->arch.cpuid_entries[i]; - if (is_matching_cpuid_entry(e, function, index)) { - if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) - move_to_next_stateful_cpuid_entry(vcpu, i); - best = e; - break; - } + + if (e->function == function && (e->index == index || + !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + return e; } - return best; + return NULL; } EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* - * If the basic or extended CPUID leaf requested is higher than the - * maximum supported basic or extended leaf, respectively, then it is - * out of range. + * Intel CPUID semantics treats any query for an out-of-range leaf as if the + * highest basic leaf (i.e. CPUID.0H:EAX) were requested. AMD CPUID semantics + * returns all zeroes for any undefined leaf, whether or not the leaf is in + * range. Centaur/VIA follows Intel semantics. + * + * A leaf is considered out-of-range if its function is higher than the maximum + * supported leaf of its associated class or if its associated class does not + * exist. + * + * There are three primary classes to be considered, with their respective + * ranges described as "<base> - <top>[,<base2> - <top2>] inclusive. A primary + * class exists if a guest CPUID entry for its <base> leaf exists. For a given + * class, CPUID.<base>.EAX contains the max supported leaf for the class. + * + * - Basic: 0x00000000 - 0x3fffffff, 0x50000000 - 0x7fffffff + * - Hypervisor: 0x40000000 - 0x4fffffff + * - Extended: 0x80000000 - 0xbfffffff + * - Centaur: 0xc0000000 - 0xcfffffff + * + * The Hypervisor class is further subdivided into sub-classes that each act as + * their own indepdent class associated with a 0x100 byte range. E.g. if Qemu + * is advertising support for both HyperV and KVM, the resulting Hypervisor + * CPUID sub-classes are: + * + * - HyperV: 0x40000000 - 0x400000ff + * - KVM: 0x40000100 - 0x400001ff */ -static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function) +static struct kvm_cpuid_entry2 * +get_out_of_range_cpuid_entry(struct kvm_vcpu *vcpu, u32 *fn_ptr, u32 index) { - struct kvm_cpuid_entry2 *max; + struct kvm_cpuid_entry2 *basic, *class; + u32 function = *fn_ptr; + + basic = kvm_find_cpuid_entry(vcpu, 0, 0); + if (!basic) + return NULL; + + if (is_guest_vendor_amd(basic->ebx, basic->ecx, basic->edx) || + is_guest_vendor_hygon(basic->ebx, basic->ecx, basic->edx)) + return NULL; - max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - return max && function <= max->eax; + if (function >= 0x40000000 && function <= 0x4fffffff) + class = kvm_find_cpuid_entry(vcpu, function & 0xffffff00, 0); + else if (function >= 0xc0000000) + class = kvm_find_cpuid_entry(vcpu, 0xc0000000, 0); + else + class = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + + if (class && function <= class->eax) + return NULL; + + /* + * Leaf specific adjustments are also applied when redirecting to the + * max basic entry, e.g. if the max basic leaf is 0xb but there is no + * entry for CPUID.0xb.index (see below), then the output value for EDX + * needs to be pulled from CPUID.0xb.1. + */ + *fn_ptr = basic->eax; + + /* + * The class does not exist or the requested function is out of range; + * the effective CPUID entry is the max basic leaf. Note, the index of + * the original requested leaf is observed! + */ + return kvm_find_cpuid_entry(vcpu, basic->eax, index); } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, - u32 *ecx, u32 *edx, bool check_limit) + u32 *ecx, u32 *edx, bool exact_only) { - u32 function = *eax, index = *ecx; + u32 orig_function = *eax, function = *eax, index = *ecx; struct kvm_cpuid_entry2 *entry; - struct kvm_cpuid_entry2 *max; - bool found; + bool exact, used_max_basic = false; entry = kvm_find_cpuid_entry(vcpu, function, index); - found = entry; - /* - * Intel CPUID semantics treats any query for an out-of-range - * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were - * requested. AMD CPUID semantics returns all zeroes for any - * undefined leaf, whether or not the leaf is in range. - */ - if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) && - !cpuid_function_in_range(vcpu, function)) { - max = kvm_find_cpuid_entry(vcpu, 0, 0); - if (max) { - function = max->eax; - entry = kvm_find_cpuid_entry(vcpu, function, index); - } + exact = !!entry; + + if (!entry && !exact_only) { + entry = get_out_of_range_cpuid_entry(vcpu, &function, index); + used_max_basic = !!entry; } + if (entry) { *eax = entry->eax; *ebx = entry->ebx; @@ -1049,8 +1028,9 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, } } } - trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found); - return found; + trace_kvm_cpuid(orig_function, index, *eax, *ebx, *ecx, *edx, exact, + used_max_basic); + return exact; } EXPORT_SYMBOL_GPL(kvm_cpuid); @@ -1063,7 +1043,7 @@ int kvm_emulate_cpuid(struct kvm_vcpu *vcpu) eax = kvm_rax_read(vcpu); ecx = kvm_rcx_read(vcpu); - kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true); + kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, false); kvm_rax_write(vcpu, eax); kvm_rbx_write(vcpu, ebx); kvm_rcx_write(vcpu, ecx); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 7366c618aa04..63a70f6a3df3 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -6,8 +6,10 @@ #include <asm/cpu.h> #include <asm/processor.h> +extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly; +void kvm_set_cpu_caps(void); + int kvm_update_cpuid(struct kvm_vcpu *vcpu); -bool kvm_mpx_supported(void); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, @@ -23,7 +25,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, - u32 *ecx, u32 *edx, bool check_limit); + u32 *ecx, u32 *edx, bool exact_only); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); @@ -64,7 +66,7 @@ static const struct cpuid_reg reverse_cpuid[] = { * and can't be used by KVM to query/control guest capabilities. And obviously * the leaf being queried must have an entry in the lookup table. */ -static __always_inline void reverse_cpuid_check(unsigned x86_leaf) +static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); @@ -88,24 +90,18 @@ static __always_inline u32 __feature_bit(int x86_feature) #define feature_bit(name) __feature_bit(X86_FEATURE_##name) -static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned int x86_feature) { - unsigned x86_leaf = x86_feature / 32; + unsigned int x86_leaf = x86_feature / 32; reverse_cpuid_check(x86_leaf); return reverse_cpuid[x86_leaf]; } -static __always_inline int *guest_cpuid_get_register(struct kvm_vcpu *vcpu, unsigned x86_feature) +static __always_inline u32 *__cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, + u32 reg) { - struct kvm_cpuid_entry2 *entry; - const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); - - entry = kvm_find_cpuid_entry(vcpu, cpuid.function, cpuid.index); - if (!entry) - return NULL; - - switch (cpuid.reg) { + switch (reg) { case CPUID_EAX: return &entry->eax; case CPUID_EBX: @@ -120,9 +116,86 @@ static __always_inline int *guest_cpuid_get_register(struct kvm_vcpu *vcpu, unsi } } -static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_feature) +static __always_inline u32 *cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); + + return __cpuid_entry_get_reg(entry, cpuid.reg); +} + +static __always_inline u32 cpuid_entry_get(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + return *reg & __feature_bit(x86_feature); +} + +static __always_inline bool cpuid_entry_has(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + return cpuid_entry_get(entry, x86_feature); +} + +static __always_inline void cpuid_entry_clear(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + *reg &= ~__feature_bit(x86_feature); +} + +static __always_inline void cpuid_entry_set(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + *reg |= __feature_bit(x86_feature); +} + +static __always_inline void cpuid_entry_change(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature, + bool set) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + /* + * Open coded instead of using cpuid_entry_{clear,set}() to coerce the + * compiler into using CMOV instead of Jcc when possible. + */ + if (set) + *reg |= __feature_bit(x86_feature); + else + *reg &= ~__feature_bit(x86_feature); +} + +static __always_inline void cpuid_entry_override(struct kvm_cpuid_entry2 *entry, + enum cpuid_leafs leaf) +{ + u32 *reg = cpuid_entry_get_reg(entry, leaf * 32); + + BUILD_BUG_ON(leaf >= ARRAY_SIZE(kvm_cpu_caps)); + *reg = kvm_cpu_caps[leaf]; +} + +static __always_inline u32 *guest_cpuid_get_register(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - int *reg; + const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); + struct kvm_cpuid_entry2 *entry; + + entry = kvm_find_cpuid_entry(vcpu, cpuid.function, cpuid.index); + if (!entry) + return NULL; + + return __cpuid_entry_get_reg(entry, cpuid.reg); +} + +static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, + unsigned int x86_feature) +{ + u32 *reg; reg = guest_cpuid_get_register(vcpu, x86_feature); if (!reg) @@ -131,21 +204,24 @@ static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_ return *reg & __feature_bit(x86_feature); } -static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature) +static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - int *reg; + u32 *reg; reg = guest_cpuid_get_register(vcpu, x86_feature); if (reg) *reg &= ~__feature_bit(x86_feature); } -static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu) +static inline bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 0, 0); - return best && best->ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx; + return best && + (is_guest_vendor_amd(best->ebx, best->ecx, best->edx) || + is_guest_vendor_hygon(best->ebx, best->ecx, best->edx)); } static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) @@ -192,4 +268,39 @@ static inline bool cpuid_fault_enabled(struct kvm_vcpu *vcpu) MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; } +static __always_inline void kvm_cpu_cap_clear(unsigned int x86_feature) +{ + unsigned int x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); + kvm_cpu_caps[x86_leaf] &= ~__feature_bit(x86_feature); +} + +static __always_inline void kvm_cpu_cap_set(unsigned int x86_feature) +{ + unsigned int x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); + kvm_cpu_caps[x86_leaf] |= __feature_bit(x86_feature); +} + +static __always_inline u32 kvm_cpu_cap_get(unsigned int x86_feature) +{ + unsigned int x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); + return kvm_cpu_caps[x86_leaf] & __feature_bit(x86_feature); +} + +static __always_inline bool kvm_cpu_cap_has(unsigned int x86_feature) +{ + return !!kvm_cpu_cap_get(x86_feature); +} + +static __always_inline void kvm_cpu_cap_check_and_set(unsigned int x86_feature) +{ + if (boot_cpu_has(x86_feature)) + kvm_cpu_cap_set(x86_feature); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddbc61984227..bddaba9c68dd 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -20,7 +20,7 @@ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" -#include <asm/kvm_emulate.h> +#include "kvm_emulate.h" #include <linux/stringify.h> #include <asm/fpu/api.h> #include <asm/debugreg.h> @@ -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) \ @@ -673,6 +665,17 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector, ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg); } +static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt) +{ + return (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_LA57) ? 57 : 48; +} + +static inline bool emul_is_noncanonical_address(u64 la, + struct x86_emulate_ctxt *ctxt) +{ + return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la; +} + /* * x86 defines three classes of vector instructions: explicitly * aligned, explicitly unaligned, and the rest, which change behaviour @@ -2719,10 +2722,8 @@ static bool vendor_intel(struct x86_emulate_ctxt *ctxt) u32 eax, ebx, ecx, edx; eax = ecx = 0; - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx - && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx - && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true); + return is_guest_vendor_intel(ebx, ecx, edx); } static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) @@ -2739,36 +2740,18 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) eax = 0x00000000; ecx = 0x00000000; - ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); + ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true); /* - * Intel ("GenuineIntel") - * remark: Intel CPUs only support "syscall" in 64bit - * longmode. Also an 64bit guest with a - * 32bit compat-app running will #UD !! While this - * behaviour can be fixed (by emulating) into AMD - * response - CPUs of AMD can't behave like Intel. + * remark: Intel CPUs only support "syscall" in 64bit longmode. Also a + * 64bit guest with a 32bit compat-app running will #UD !! While this + * behaviour can be fixed (by emulating) into AMD response - CPUs of + * AMD can't behave like Intel. */ - if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && - ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && - edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) + if (is_guest_vendor_intel(ebx, ecx, edx)) return false; - /* AMD ("AuthenticAMD") */ - if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && - ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && - edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) - return true; - - /* AMD ("AMDisbetter!") */ - if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && - ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && - edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) - return true; - - /* Hygon ("HygonGenuine") */ - if (ebx == X86EMUL_CPUID_VENDOR_HygonGenuine_ebx && - ecx == X86EMUL_CPUID_VENDOR_HygonGenuine_ecx && - edx == X86EMUL_CPUID_VENDOR_HygonGenuine_edx) + if (is_guest_vendor_amd(ebx, ecx, edx) || + is_guest_vendor_hygon(ebx, ecx, edx)) return true; /* @@ -3988,7 +3971,7 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt) eax = reg_read(ctxt, VCPU_REGS_RAX); ecx = reg_read(ctxt, VCPU_REGS_RCX); - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true); + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); *reg_write(ctxt, VCPU_REGS_RAX) = eax; *reg_write(ctxt, VCPU_REGS_RBX) = ebx; *reg_write(ctxt, VCPU_REGS_RCX) = ecx; @@ -4258,7 +4241,7 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) eax = 0x80000008; ecx = 0; if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, - &edx, false)) + &edx, true)) maxphyaddr = eax & 0xff; else maxphyaddr = 36; @@ -5181,6 +5164,7 @@ 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 +5667,7 @@ 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/hyperv.c b/arch/x86/kvm/hyperv.c index a86fda7a1d03..bcefa9d4e57e 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1022,7 +1022,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return 1; - kvm_x86_ops->patch_hypercall(vcpu, instructions); + kvm_x86_ops.patch_hypercall(vcpu, instructions); ((unsigned char *)instructions)[3] = 0xc3; /* ret */ if (__copy_to_user((void __user *)addr, instructions, 4)) return 1; @@ -1607,7 +1607,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) * hypercall generates UD from non zero cpl and real mode * per HYPER-V spec */ - if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + if (kvm_x86_ops.get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -1800,8 +1800,8 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, }; int i, nent = ARRAY_SIZE(cpuid_entries); - if (kvm_x86_ops->nested_get_evmcs_version) - evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu); + if (kvm_x86_ops.nested_get_evmcs_version) + evmcs_ver = kvm_x86_ops.nested_get_evmcs_version(vcpu); /* Skip NESTED_FEATURES if eVMCS is not supported */ if (!evmcs_ver) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index b24c606ac04b..febca334c320 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -367,7 +367,7 @@ static void pit_load_count(struct kvm_pit *pit, int channel, u32 val) { struct kvm_kpit_state *ps = &pit->pit_state; - pr_debug("load_count val is %d, channel is %d\n", val, channel); + pr_debug("load_count val is %u, channel is %d\n", val, channel); /* * The largest possible initial count is 0; this is equivalent 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/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 58767020de41..62558b9bdda7 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -68,7 +68,7 @@ static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) return 0; if (!kvm_register_is_available(vcpu, reg)) - kvm_x86_ops->cache_reg(vcpu, reg); + kvm_x86_ops.cache_reg(vcpu, reg); return vcpu->arch.regs[reg]; } @@ -108,7 +108,7 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) might_sleep(); /* on svm */ if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) - kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR); + kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_PDPTR); return vcpu->arch.walk_mmu->pdptrs[index]; } @@ -117,7 +117,7 @@ static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; if (tmask & vcpu->arch.cr0_guest_owned_bits) - kvm_x86_ops->decache_cr0_guest_bits(vcpu); + kvm_x86_ops.decache_cr0_guest_bits(vcpu); return vcpu->arch.cr0 & mask; } @@ -130,14 +130,14 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR4_GUEST_BITS; if (tmask & vcpu->arch.cr4_guest_owned_bits) - kvm_x86_ops->decache_cr4_guest_bits(vcpu); + kvm_x86_ops.decache_cr4_guest_bits(vcpu); return vcpu->arch.cr4 & mask; } static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) - kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3); + kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR3); return vcpu->arch.cr3; } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 03946eb3e2b9..43c93ffa76ed 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -221,7 +221,7 @@ struct x86_emulate_ops { enum x86_intercept_stage stage); bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, - u32 *ecx, u32 *edx, bool check_limit); + u32 *ecx, u32 *edx, bool exact_only); bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt); @@ -292,7 +292,16 @@ 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 { + void *vcpu; const struct x86_emulate_ops *ops; /* Register state before/after emulation. */ @@ -311,6 +320,10 @@ struct x86_emulate_ctxt { bool have_exception; struct x86_exception exception; + /* GPA available */ + bool gpa_available; + gpa_t gpa_val; + /* * decode cache */ @@ -321,10 +334,10 @@ struct x86_emulate_ctxt { u8 intercept; u8 op_bytes; u8 ad_bytes; - 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, @@ -348,8 +361,12 @@ struct x86_emulate_ctxt { u8 seg_override; u64 d; unsigned long _eip; + + /* Here begins the usercopy section. */ + struct operand src; + struct operand src2; + struct operand dst; struct operand memop; - /* Fields above regs are cleared together. */ unsigned long _regs[NR_VCPU_REGS]; struct operand *memopp; struct fetch_cache fetch; @@ -378,6 +395,34 @@ struct x86_emulate_ctxt { #define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e #define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69 +#define X86EMUL_CPUID_VENDOR_CentaurHauls_ebx 0x746e6543 +#define X86EMUL_CPUID_VENDOR_CentaurHauls_ecx 0x736c7561 +#define X86EMUL_CPUID_VENDOR_CentaurHauls_edx 0x48727561 + +static inline bool is_guest_vendor_intel(u32 ebx, u32 ecx, u32 edx) +{ + return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && + ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && + edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; +} + +static inline bool is_guest_vendor_amd(u32 ebx, u32 ecx, u32 edx) +{ + return (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && + ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && + edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) || + (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && + ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && + edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx); +} + +static inline bool is_guest_vendor_hygon(u32 ebx, u32 ecx, u32 edx) +{ + return ebx == X86EMUL_CPUID_VENDOR_HygonGenuine_ebx && + ecx == X86EMUL_CPUID_VENDOR_HygonGenuine_ecx && + edx == X86EMUL_CPUID_VENDOR_HygonGenuine_edx; +} + enum x86_intercept_stage { X86_ICTP_NONE = 0, /* Allow zero-init to not match anything */ X86_ICPT_PRE_EXCEPT, diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index eafc631d305c..ca80daf8f878 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -164,14 +164,28 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } -static void recalculate_apic_map(struct kvm *kvm) +void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; int i; u32 max_id = 255; /* enough space for any xAPIC ID */ + if (!kvm->arch.apic_map_dirty) { + /* + * Read kvm->arch.apic_map_dirty before + * kvm->arch.apic_map + */ + smp_rmb(); + return; + } + mutex_lock(&kvm->arch.apic_map_lock); + if (!kvm->arch.apic_map_dirty) { + /* Someone else has updated the map. */ + mutex_unlock(&kvm->arch.apic_map_lock); + return; + } kvm_for_each_vcpu(i, vcpu, kvm) if (kvm_apic_present(vcpu)) @@ -236,6 +250,12 @@ out: old = rcu_dereference_protected(kvm->arch.apic_map, lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); + /* + * Write kvm->arch.apic_map before + * clearing apic->apic_map_dirty + */ + smp_wmb(); + kvm->arch.apic_map_dirty = false; mutex_unlock(&kvm->arch.apic_map_lock); if (old) @@ -257,20 +277,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) else static_key_slow_inc(&apic_sw_disabled.key); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { kvm_lapic_set_reg(apic, APIC_LDR, id); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) @@ -286,7 +306,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) @@ -294,11 +314,6 @@ static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) return !(kvm_lapic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); } -static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) -{ - return kvm_lapic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; -} - static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) { return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_ONESHOT; @@ -448,7 +463,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) if (unlikely(vcpu->arch.apicv_active)) { /* need to update RVI */ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); - kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_x86_ops.hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); } else { apic->irr_pending = false; @@ -473,7 +488,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * just set SVI. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops->hwapic_isr_update(vcpu, vec); + kvm_x86_ops.hwapic_isr_update(vcpu, vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -521,7 +536,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * and must be left alone. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops->hwapic_isr_update(vcpu, + kvm_x86_ops.hwapic_isr_update(vcpu, apic_find_highest_isr(apic)); else { --apic->isr_count; @@ -627,9 +642,11 @@ 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; } @@ -657,7 +674,7 @@ static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; if (apic->vcpu->arch.apicv_active) - highest_irr = kvm_x86_ops->sync_pir_to_irr(apic->vcpu); + highest_irr = kvm_x86_ops.sync_pir_to_irr(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); if (highest_irr == -1 || (highest_irr & 0xF0) <= ppr) @@ -1046,11 +1063,8 @@ 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); } @@ -1080,9 +1094,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, result = 1; /* assumes that there are only KVM_APIC_INIT/SIPI */ apic->pending_events = (1UL << KVM_APIC_INIT); - /* make sure pending_events is visible before sending - * the request */ - smp_wmb(); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } @@ -1230,7 +1241,7 @@ void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector) } EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); -static void apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high) +void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high) { struct kvm_lapic_irq irq; @@ -1449,6 +1460,8 @@ 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) & @@ -1458,6 +1471,10 @@ 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; @@ -1719,7 +1736,7 @@ 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) @@ -1735,7 +1752,7 @@ static void cancel_hv_timer(struct kvm_lapic *apic) { WARN_ON(preemptible()); WARN_ON(!apic->lapic_timer.hv_timer_in_use); - kvm_x86_ops->cancel_hv_timer(apic->vcpu); + kvm_x86_ops.cancel_hv_timer(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; } @@ -1746,13 +1763,13 @@ static bool start_hv_timer(struct kvm_lapic *apic) bool expired; WARN_ON(preemptible()); - if (!kvm_x86_ops->set_hv_timer) + if (!kvm_x86_ops.set_hv_timer) return false; if (!ktimer->tscdeadline) return false; - if (kvm_x86_ops->set_hv_timer(vcpu, ktimer->tscdeadline, &expired)) + if (kvm_x86_ops.set_hv_timer(vcpu, ktimer->tscdeadline, &expired)) return false; ktimer->hv_timer_in_use = true; @@ -1915,7 +1932,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_DFR: if (!apic_x2apic_mode(apic)) { kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } else ret = 1; break; @@ -1944,7 +1961,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_ICR: /* No delay here, so we always clear the pending bit */ val &= ~(1 << 12); - apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2)); + kvm_apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2)); kvm_lapic_set_reg(apic, APIC_ICR, val); break; @@ -2021,6 +2038,8 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; } + kvm_recalculate_apic_map(apic->vcpu->kvm); + return ret; } EXPORT_SYMBOL_GPL(kvm_lapic_reg_write); @@ -2169,7 +2188,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) static_key_slow_dec_deferred(&apic_hw_disabled); } else { static_key_slow_inc(&apic_hw_disabled.key); - recalculate_apic_map(vcpu->kvm); + vcpu->kvm->arch.apic_map_dirty = true; } } @@ -2177,7 +2196,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) - kvm_x86_ops->set_virtual_apic_mode(vcpu); + kvm_x86_ops.set_virtual_apic_mode(vcpu); apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; @@ -2210,6 +2229,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) if (!apic) return; + vcpu->kvm->arch.apic_map_dirty = false; /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2254,13 +2274,15 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); if (vcpu->arch.apicv_active) { - kvm_x86_ops->apicv_post_state_restore(vcpu); - kvm_x86_ops->hwapic_irr_update(vcpu, -1); - kvm_x86_ops->hwapic_isr_update(vcpu, -1); + kvm_x86_ops.apicv_post_state_restore(vcpu); + kvm_x86_ops.hwapic_irr_update(vcpu, -1); + kvm_x86_ops.hwapic_isr_update(vcpu, -1); } vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; + + kvm_recalculate_apic_map(vcpu->kvm); } /* @@ -2482,17 +2504,18 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) struct kvm_lapic *apic = vcpu->arch.apic; int r; - kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); r = kvm_apic_state_fixup(vcpu, s, true); - if (r) + if (r) { + kvm_recalculate_apic_map(vcpu->kvm); return r; + } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); - recalculate_apic_map(vcpu->kvm); + kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); apic_update_ppr(apic); @@ -2504,10 +2527,10 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { - kvm_x86_ops->apicv_post_state_restore(vcpu); - kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_x86_ops.apicv_post_state_restore(vcpu); + kvm_x86_ops.hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); - kvm_x86_ops->hwapic_isr_update(vcpu, + kvm_x86_ops.hwapic_isr_update(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index ec6fbfe325cf..40ed6ed22751 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -78,6 +78,7 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); +void kvm_recalculate_apic_map(struct kvm *kvm); void kvm_apic_set_version(struct kvm_vcpu *vcpu); int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val); int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, @@ -95,6 +96,7 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); +void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index d55674f44a18..8a3b1bce722a 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -95,11 +95,24 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu)); } -static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu) +static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) { if (VALID_PAGE(vcpu->arch.mmu->root_hpa)) - vcpu->arch.mmu->set_cr3(vcpu, vcpu->arch.mmu->root_hpa | - kvm_get_active_pcid(vcpu)); + kvm_x86_ops.load_mmu_pgd(vcpu, vcpu->arch.mmu->root_hpa | + kvm_get_active_pcid(vcpu)); +} + +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault); + +static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u32 err, bool prefault) +{ +#ifdef CONFIG_RETPOLINE + if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault)) + return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault); +#endif + return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault); } /* @@ -157,8 +170,8 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned pte_access, unsigned pte_pkey, unsigned pfec) { - int cpl = kvm_x86_ops->get_cpl(vcpu); - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + int cpl = kvm_x86_ops.get_cpl(vcpu); + unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); /* * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1. diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7011a4e54866..8071952e9cf2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -19,6 +19,7 @@ #include "mmu.h" #include "x86.h" #include "kvm_cache_regs.h" +#include "kvm_emulate.h" #include "cpuid.h" #include <linux/kvm_host.h> @@ -86,6 +87,8 @@ __MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); */ bool tdp_enabled = false; +static int max_page_level __read_mostly; + enum { AUDIT_PRE_PAGE_FAULT, AUDIT_POST_PAGE_FAULT, @@ -215,17 +218,6 @@ struct kvm_shadow_walk_iterator { unsigned index; }; -static const union kvm_mmu_page_role mmu_base_role_mask = { - .cr0_wp = 1, - .gpte_is_8_bytes = 1, - .nxe = 1, - .smep_andnot_wp = 1, - .smap_andnot_wp = 1, - .smm = 1, - .guest_mode = 1, - .ad_disabled = 1, -}; - #define for_each_shadow_entry_using_root(_vcpu, _root, _addr, _walker) \ for (shadow_walk_init_using_root(&(_walker), (_vcpu), \ (_root), (_addr)); \ @@ -313,7 +305,7 @@ kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); static inline bool kvm_available_flush_tlb_with_range(void) { - return kvm_x86_ops->tlb_remote_flush_with_range; + return kvm_x86_ops.tlb_remote_flush_with_range; } static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, @@ -321,8 +313,8 @@ static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, { int ret = -ENOTSUPP; - if (range && kvm_x86_ops->tlb_remote_flush_with_range) - ret = kvm_x86_ops->tlb_remote_flush_with_range(kvm, range); + if (range && kvm_x86_ops.tlb_remote_flush_with_range) + ret = kvm_x86_ops.tlb_remote_flush_with_range(kvm, range); if (ret) kvm_flush_remote_tlbs(kvm); @@ -1650,7 +1642,7 @@ static bool spte_set_dirty(u64 *sptep) rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); /* - * Similar to the !kvm_x86_ops->slot_disable_log_dirty case, + * Similar to the !kvm_x86_ops.slot_disable_log_dirty case, * do not bother adding back write access to pages marked * SPTE_AD_WRPROT_ONLY_MASK. */ @@ -1739,8 +1731,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - if (kvm_x86_ops->enable_log_dirty_pt_masked) - kvm_x86_ops->enable_log_dirty_pt_masked(kvm, slot, gfn_offset, + if (kvm_x86_ops.enable_log_dirty_pt_masked) + kvm_x86_ops.enable_log_dirty_pt_masked(kvm, slot, gfn_offset, mask); else kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); @@ -1755,8 +1747,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, */ int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->write_log_dirty) - return kvm_x86_ops->write_log_dirty(vcpu); + if (kvm_x86_ops.write_log_dirty) + return kvm_x86_ops.write_log_dirty(vcpu); return 0; } @@ -3044,7 +3036,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (level > PT_PAGE_TABLE_LEVEL) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) - spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, + spte |= kvm_x86_ops.get_mt_mask(vcpu, gfn, kvm_is_mmio_pfn(pfn)); if (host_writable) @@ -3292,7 +3284,7 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, if (!slot) return PT_PAGE_TABLE_LEVEL; - max_level = min(max_level, kvm_x86_ops->get_lpage_level()); + max_level = min(max_level, max_page_level); for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) { linfo = lpage_info_slot(gfn, slot, max_level); if (!linfo->disallow_lpage) @@ -3568,8 +3560,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * write-protected for dirty-logging or access tracking. */ if ((error_code & PFERR_WRITE_MASK) && - spte_can_locklessly_be_made_writable(spte)) - { + spte_can_locklessly_be_made_writable(spte)) { new_spte |= PT_WRITABLE_MASK; /* @@ -3731,7 +3722,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root); } else BUG(); - vcpu->arch.mmu->root_cr3 = vcpu->arch.mmu->get_cr3(vcpu); + + /* root_cr3 is ignored for direct MMUs. */ + vcpu->arch.mmu->root_cr3 = 0; return 0; } @@ -3743,7 +3736,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) gfn_t root_gfn, root_cr3; int i; - root_cr3 = vcpu->arch.mmu->get_cr3(vcpu); + root_cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); root_gfn = root_cr3 >> PAGE_SHIFT; if (mmu_check_root(vcpu, root_gfn)) @@ -4080,7 +4073,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->direct_map; - arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); + arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); return kvm_setup_async_pf(vcpu, cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); @@ -4219,8 +4212,8 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); -static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - bool prefault) +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault) { int max_level; @@ -4252,6 +4245,14 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, context->nx = false; } +static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t cr3, + union kvm_mmu_page_role role) +{ + return (role.direct || cr3 == root->cr3) && + VALID_PAGE(root->hpa) && page_header(root->hpa) && + role.word == page_header(root->hpa)->role.word; +} + /* * Find out if a previously cached root matching the new CR3/role is available. * The current root is also inserted into the cache. @@ -4270,12 +4271,13 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3, root.cr3 = mmu->root_cr3; root.hpa = mmu->root_hpa; + if (is_root_usable(&root, new_cr3, new_role)) + return true; + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { swap(root, mmu->prev_roots[i]); - if (new_cr3 == root.cr3 && VALID_PAGE(root.hpa) && - page_header(root.hpa) != NULL && - new_role.word == page_header(root.hpa)->role.word) + if (is_root_usable(&root, new_cr3, new_role)) break; } @@ -4309,7 +4311,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, * accompanied by KVM_REQ_MMU_RELOAD, which will free * the root set here and allocate a new one. */ - kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); if (!skip_tlb_flush) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); @@ -4508,7 +4510,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, cpuid_maxphyaddr(vcpu), context->root_level, context->nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), - is_pse(vcpu), guest_cpuid_is_amd(vcpu)); + is_pse(vcpu), + guest_cpuid_is_amd_or_hygon(vcpu)); } static void @@ -4874,7 +4877,6 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); ext.cr4_pse = !!is_pse(vcpu); ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE); - ext.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57); ext.maxphyaddr = cpuid_maxphyaddr(vcpu); ext.valid = 1; @@ -4907,7 +4909,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only); role.base.ad_disabled = (shadow_accessed_mask == 0); - role.base.level = kvm_x86_ops->get_tdp_level(vcpu); + role.base.level = kvm_x86_ops.get_tdp_level(vcpu); role.base.direct = true; role.base.gpte_is_8_bytes = true; @@ -4920,19 +4922,17 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) union kvm_mmu_role new_role = kvm_calc_tdp_mmu_root_page_role(vcpu, false); - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == context->mmu_role.as_u64) return; context->mmu_role.as_u64 = new_role.as_u64; - context->page_fault = tdp_page_fault; + context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; - context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu); + context->shadow_root_level = kvm_x86_ops.get_tdp_level(vcpu); context->direct_map = true; - context->set_cr3 = kvm_x86_ops->set_tdp_cr3; - context->get_cr3 = get_cr3; + context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; @@ -4992,7 +4992,6 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) union kvm_mmu_role new_role = kvm_calc_shadow_mmu_root_page_role(vcpu, false); - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == context->mmu_role.as_u64) return; @@ -5012,14 +5011,14 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); static union kvm_mmu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, - bool execonly) + bool execonly, u8 level) { union kvm_mmu_role role = {0}; /* SMM flag is inherited from root_mmu */ role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; - role.base.level = PT64_ROOT_4LEVEL; + role.base.level = level; role.base.gpte_is_8_bytes = true; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; @@ -5043,17 +5042,17 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty, gpa_t new_eptp) { struct kvm_mmu *context = vcpu->arch.mmu; + u8 level = vmx_eptp_page_walk_level(new_eptp); union kvm_mmu_role new_role = kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty, - execonly); + execonly, level); __kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false); - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == context->mmu_role.as_u64) return; - context->shadow_root_level = PT64_ROOT_4LEVEL; + context->shadow_root_level = level; context->nx = true; context->ept_ad = accessed_dirty; @@ -5062,7 +5061,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->sync_page = ept_sync_page; context->invlpg = ept_invlpg; context->update_pte = ept_update_pte; - context->root_level = PT64_ROOT_4LEVEL; + context->root_level = level; context->direct_map = false; context->mmu_role.as_u64 = new_role.as_u64; @@ -5079,8 +5078,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) struct kvm_mmu *context = vcpu->arch.mmu; kvm_init_shadow_mmu(vcpu); - context->set_cr3 = kvm_x86_ops->set_cr3; - context->get_cr3 = get_cr3; + context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } @@ -5090,12 +5088,11 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false); struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == g_context->mmu_role.as_u64) return; g_context->mmu_role.as_u64 = new_role.as_u64; - g_context->get_cr3 = get_cr3; + g_context->get_guest_pgd = get_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; @@ -5185,8 +5182,8 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) kvm_mmu_sync_roots(vcpu); if (r) goto out; - kvm_mmu_load_cr3(vcpu); - kvm_x86_ops->tlb_flush(vcpu, true); + kvm_mmu_load_pgd(vcpu); + kvm_x86_ops.tlb_flush(vcpu, true); out: return r; } @@ -5329,6 +5326,22 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) return spte; } +/* + * Ignore various flags when determining if a SPTE can be immediately + * overwritten for the current MMU. + * - level: explicitly checked in mmu_pte_write_new_pte(), and will never + * match the current MMU role, as MMU's level tracks the root level. + * - access: updated based on the new guest PTE + * - quadrant: handled by get_written_sptes() + * - invalid: always false (loop only walks valid shadow pages) + */ +static const union kvm_mmu_page_role role_ign = { + .level = 0xf, + .access = 0x7, + .quadrant = 0x3, + .invalid = 0x1, +}; + static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes, struct kvm_page_track_notifier_node *node) @@ -5384,8 +5397,8 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte); if (gentry && - !((sp->role.word ^ base_role) - & mmu_base_role_mask.word) && rmap_can_add(vcpu)) + !((sp->role.word ^ base_role) & ~role_ign.word) && + rmap_can_add(vcpu)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); if (need_remote_flush(entry, *spte)) remote_flush = true; @@ -5416,18 +5429,12 @@ EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { - int r, emulation_type = 0; + int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->direct_map; if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) return RET_PF_RETRY; - /* With shadow page tables, fault_address contains a GVA or nGPA. */ - if (vcpu->arch.mmu->direct_map) { - vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2_or_gpa; - } - r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); @@ -5436,9 +5443,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), - false); + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, + lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); } @@ -5472,7 +5478,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) - emulation_type = EMULTYPE_ALLOW_RETRY; + emulation_type |= EMULTYPE_ALLOW_RETRY_PF; emulate: /* * On AMD platforms, under certain conditions insn_len may be zero on #NPF. @@ -5482,7 +5488,7 @@ emulate: * guest, with the exception of AMD Erratum 1096 which is unrecoverable. */ if (unlikely(insn && !insn_len)) { - if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu)) + if (!kvm_x86_ops.need_emulation_on_page_fault(vcpu)) return 1; } @@ -5517,7 +5523,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) if (VALID_PAGE(mmu->prev_roots[i].hpa)) mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); - kvm_x86_ops->tlb_flush_gva(vcpu, gva); + kvm_x86_ops.tlb_flush_gva(vcpu, gva); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); @@ -5542,7 +5548,7 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) } if (tlb_flush) - kvm_x86_ops->tlb_flush_gva(vcpu, gva); + kvm_x86_ops.tlb_flush_gva(vcpu, gva); ++vcpu->stat.invlpg; @@ -5554,18 +5560,25 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) } EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva); -void kvm_enable_tdp(void) +void kvm_configure_mmu(bool enable_tdp, int tdp_page_level) { - tdp_enabled = true; -} -EXPORT_SYMBOL_GPL(kvm_enable_tdp); + tdp_enabled = enable_tdp; -void kvm_disable_tdp(void) -{ - tdp_enabled = false; + /* + * max_page_level reflects the capabilities of KVM's MMU irrespective + * of kernel support, e.g. KVM may be capable of using 1GB pages when + * the kernel is not. But, KVM never creates a page size greater than + * what is used by the kernel for any given HVA, i.e. the kernel's + * capabilities are ultimately consulted by kvm_mmu_hugepage_adjust(). + */ + if (tdp_enabled) + max_page_level = tdp_page_level; + else if (boot_cpu_has(X86_FEATURE_GBPAGES)) + max_page_level = PT_PDPE_LEVEL; + else + max_page_level = PT_DIRECTORY_LEVEL; } -EXPORT_SYMBOL_GPL(kvm_disable_tdp); - +EXPORT_SYMBOL_GPL(kvm_configure_mmu); /* The return value indicates if tlb flush on all vcpus is needed. */ typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); @@ -5659,7 +5672,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can * skip allocating the PDP table. */ - if (tdp_enabled && kvm_x86_ops->get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) + if (tdp_enabled && kvm_x86_ops.get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32); @@ -5861,23 +5874,17 @@ static bool slot_rmap_write_protect(struct kvm *kvm, } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot) + struct kvm_memory_slot *memslot, + int start_level) { bool flush; spin_lock(&kvm->mmu_lock); - flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect, - false); + flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, + start_level, PT_MAX_HUGEPAGE_LEVEL, false); spin_unlock(&kvm->mmu_lock); /* - * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log() - * which do tlb flush out of mmu-lock should be serialized by - * kvm->slots_lock otherwise tlb flush would be missed. - */ - lockdep_assert_held(&kvm->slots_lock); - - /* * We can flush all the TLBs out of the mmu lock without TLB * corruption since we just change the spte from writable to * readonly so that we only need to care the case of changing @@ -5889,8 +5896,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, * on PT_WRITABLE_MASK anymore. */ if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, @@ -5942,6 +5948,21 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, spin_unlock(&kvm->mmu_lock); } +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + /* + * All current use cases for flushing the TLBs for a specific memslot + * are related to dirty logging, and do the TLB flush out of mmu_lock. + * The interaction between the various operations on memslot must be + * serialized by slots_locks to ensure the TLB flush from one operation + * is observed by any other operation on the same memslot. + */ + lockdep_assert_held(&kvm->slots_lock); + kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, + memslot->npages); +} + void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { @@ -5951,8 +5972,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); spin_unlock(&kvm->mmu_lock); - lockdep_assert_held(&kvm->slots_lock); - /* * It's also safe to flush TLBs out of mmu lock here as currently this * function is only used for dirty logging, in which case flushing TLB @@ -5960,8 +5979,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, * dirty_bitmap. */ if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); @@ -5975,12 +5993,8 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, false); spin_unlock(&kvm->mmu_lock); - /* see kvm_mmu_slot_remove_write_access */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); @@ -5993,12 +6007,8 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); spin_unlock(&kvm->mmu_lock); - lockdep_assert_held(&kvm->slots_lock); - - /* see kvm_mmu_slot_leaf_clear_dirty */ if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 3521e2d176f2..ddc1ec3bdacd 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -14,22 +14,18 @@ #include <linux/kvm_host.h> #include <linux/rculist.h> -#include <asm/kvm_host.h> #include <asm/kvm_page_track.h> #include "mmu.h" -void kvm_page_track_free_memslot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { int i; - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) - if (!dont || free->arch.gfn_track[i] != - dont->arch.gfn_track[i]) { - kvfree(free->arch.gfn_track[i]); - free->arch.gfn_track[i] = NULL; - } + for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { + kvfree(slot->arch.gfn_track[i]); + slot->arch.gfn_track[i] = NULL; + } } int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, @@ -48,7 +44,7 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, return 0; track_free: - kvm_page_track_free_memslot(slot, NULL); + kvm_page_track_free_memslot(slot); return -ENOMEM; } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 4e1ef0473663..9bdf9b7d9a96 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -33,7 +33,7 @@ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #define CMPXCHG cmpxchg #else #define CMPXCHG cmpxchg64 @@ -66,7 +66,7 @@ #define PT_GUEST_ACCESSED_SHIFT 8 #define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad) #define CMPXCHG cmpxchg64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #else #error Invalid PTTYPE value #endif @@ -333,7 +333,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: walker->level = mmu->root_level; - pte = mmu->get_cr3(vcpu); + pte = mmu->get_guest_pgd(vcpu); have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 @@ -400,7 +400,7 @@ retry_walk: goto error; ptep_user = (pt_element_t __user *)((void *)host_addr + offset); - if (unlikely(__copy_from_user(&pte, ptep_user, sizeof(pte)))) + if (unlikely(__get_user(pte, ptep_user))) goto error; walker->ptep_user[walker->level - 1] = ptep_user; 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/pmu.c b/arch/x86/kvm/pmu.c index bcc6a73d6628..a5078841bdac 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -111,7 +111,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, .config = config, }; - attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc); + attr.sample_period = get_sample_period(pmc, pmc->counter); if (in_tx) attr.config |= HSW_IN_TX; @@ -158,7 +158,7 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) /* recalibrate sample period and check if it's accepted by perf core */ if (perf_event_period(pmc->perf_event, - (-pmc->counter) & pmc_bitmask(pmc))) + get_sample_period(pmc, pmc->counter))) return false; /* reuse perf_event to serve as pmc_reprogram_counter() does*/ @@ -211,7 +211,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) ARCH_PERFMON_EVENTSEL_CMASK | HSW_IN_TX | HSW_IN_TX_CHECKPOINTED))) { - config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc), + config = kvm_x86_ops.pmu_ops->find_arch_event(pmc_to_pmu(pmc), event_select, unit_mask); if (config != PERF_COUNT_HW_MAX) @@ -265,7 +265,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) pmc->current_config = (u64)ctrl; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, - kvm_x86_ops->pmu_ops->find_fixed_event(idx), + kvm_x86_ops.pmu_ops->find_fixed_event(idx), !(en_field & 0x2), /* exclude user */ !(en_field & 0x1), /* exclude kernel */ pmi, false, false); @@ -274,7 +274,7 @@ EXPORT_SYMBOL_GPL(reprogram_fixed_counter); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) { - struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx); + struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx); if (!pmc) return; @@ -296,7 +296,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) int bit; for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { - struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); + struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, bit); if (unlikely(!pmc || !pmc->perf_event)) { clear_bit(bit, pmu->reprogram_pmi); @@ -318,7 +318,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) /* check if idx is a valid index to access PMU */ int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { - return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); + return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } bool is_vmware_backdoor_pmc(u32 pmc_idx) @@ -368,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); - pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask); + pmc = kvm_x86_ops.pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask); if (!pmc) return 1; @@ -384,14 +384,14 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) || - kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); + return kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr) || + kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, msr); } static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr); + struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr); if (pmc) __set_bit(pmc->idx, pmu->pmc_in_use); @@ -399,13 +399,13 @@ static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { - return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data); + return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr, data); } int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index); - return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); + return kvm_x86_ops.pmu_ops->set_msr(vcpu, msr_info); } /* refresh PMU settings. This function generally is called when underlying @@ -414,7 +414,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { - kvm_x86_ops->pmu_ops->refresh(vcpu); + kvm_x86_ops.pmu_ops->refresh(vcpu); } void kvm_pmu_reset(struct kvm_vcpu *vcpu) @@ -422,7 +422,7 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); irq_work_sync(&pmu->irq_work); - kvm_x86_ops->pmu_ops->reset(vcpu); + kvm_x86_ops.pmu_ops->reset(vcpu); } void kvm_pmu_init(struct kvm_vcpu *vcpu) @@ -430,7 +430,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); memset(pmu, 0, sizeof(*pmu)); - kvm_x86_ops->pmu_ops->init(vcpu); + kvm_x86_ops.pmu_ops->init(vcpu); init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); pmu->event_count = 0; pmu->need_cleanup = false; @@ -462,7 +462,7 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) pmu->pmc_in_use, X86_PMC_IDX_MAX); for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) { - pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i); + pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, i); if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc)) pmc_stop_counter(pmc); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 13332984b6d5..a6c78a797cb1 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -88,7 +88,7 @@ static inline bool pmc_is_fixed(struct kvm_pmc *pmc) static inline bool pmc_is_enabled(struct kvm_pmc *pmc) { - return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); + return kvm_x86_ops.pmu_ops->pmc_is_enabled(pmc); } static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, @@ -129,6 +129,15 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) return NULL; } +static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) +{ + u64 sample_period = (-counter_value) & pmc_bitmask(pmc); + + if (!sample_period) + sample_period = pmc_bitmask(pmc) + 1; + return sample_period; +} + void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a3e32d61d60c..851e9cc79930 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 @@ -519,10 +522,31 @@ static void recalc_intercepts(struct vcpu_svm *svm) h = &svm->nested.hsave->control; g = &svm->nested; - c->intercept_cr = h->intercept_cr | g->intercept_cr; - c->intercept_dr = h->intercept_dr | g->intercept_dr; - c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions; - c->intercept = h->intercept | g->intercept; + c->intercept_cr = h->intercept_cr; + c->intercept_dr = h->intercept_dr; + c->intercept_exceptions = h->intercept_exceptions; + c->intercept = h->intercept; + + if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { + /* We only want the cr8 intercept bits of L1 */ + c->intercept_cr &= ~(1U << INTERCEPT_CR8_READ); + c->intercept_cr &= ~(1U << INTERCEPT_CR8_WRITE); + + /* + * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not + * affect any interrupt we may want to inject; therefore, + * interrupt window vmexits are irrelevant to L0. + */ + c->intercept &= ~(1ULL << INTERCEPT_VINTR); + } + + /* We don't want to see VMMCALLs from a nested guest */ + c->intercept &= ~(1ULL << INTERCEPT_VMMCALL); + + c->intercept_cr |= g->intercept_cr; + c->intercept_dr |= g->intercept_dr; + c->intercept_exceptions |= g->intercept_exceptions; + c->intercept |= g->intercept; } static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm) @@ -627,6 +651,11 @@ static inline void clr_intercept(struct vcpu_svm *svm, int bit) recalc_intercepts(svm); } +static inline bool is_intercept(struct vcpu_svm *svm, int bit) +{ + return (svm->vmcb->control.intercept & (1ULL << bit)) != 0; +} + static inline bool vgif_enabled(struct vcpu_svm *svm) { return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK); @@ -1005,33 +1034,32 @@ 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; } @@ -1207,6 +1235,7 @@ static int avic_ga_log_notifier(u32 ga_tag) u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); + trace_kvm_avic_ga_log(vm_id, vcpu_id); spin_lock_irqsave(&svm_vm_data_hash_lock, flags); hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) { @@ -1350,6 +1379,47 @@ 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 void svm_set_cpu_caps(void) +{ + kvm_set_cpu_caps(); + + supported_xss = 0; + + /* CPUID 0x80000001 and 0x8000000A (SVM features) */ + if (nested) { + kvm_cpu_cap_set(X86_FEATURE_SVM); + + if (nrips) + kvm_cpu_cap_set(X86_FEATURE_NRIPS); + + if (npt_enabled) + kvm_cpu_cap_set(X86_FEATURE_NPT); + } + + /* CPUID 0x80000008 */ + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1368,6 +1438,8 @@ static __init int svm_hardware_setup(void) init_msrpm_offsets(); + supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -1415,16 +1487,11 @@ static __init int svm_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; - if (npt_enabled && !npt) { - printk(KERN_INFO "kvm: Nested Paging disabled\n"); + if (npt_enabled && !npt) npt_enabled = false; - } - if (npt_enabled) { - printk(KERN_INFO "kvm: Nested Paging enabled\n"); - kvm_enable_tdp(); - } else - kvm_disable_tdp(); + kvm_configure_mmu(npt_enabled, PT_PDPE_LEVEL); + pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); if (nrips) { if (!boot_cpu_has(X86_FEATURE_NRIPS)) @@ -1460,32 +1527,15 @@ static __init int svm_hardware_setup(void) pr_info("Virtual GIF supported\n"); } + svm_set_cpu_caps(); + 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; @@ -1933,32 +1983,11 @@ 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); } -static struct kvm *svm_vm_alloc(void) -{ - struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm), - GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); - return &kvm_svm->kvm; -} - -static void svm_vm_free(struct kvm *kvm) -{ - vfree(to_kvm_svm(kvm)); -} - static void sev_vm_destroy(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -1971,6 +2000,13 @@ 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. */ @@ -2175,7 +2211,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; - vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; @@ -2187,7 +2222,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) } init_vmcb(svm); - kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true); + kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, false); kvm_rdx_write(vcpu, eax); if (kvm_vcpu_apicv_active(vcpu) && !init_event) @@ -2197,8 +2232,9 @@ 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); @@ -2266,6 +2302,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) init_vmcb(svm); svm_init_osvw(vcpu); + vcpu->arch.microcode_version = 0x01000065; return 0; @@ -2419,14 +2456,38 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } +static inline void svm_enable_vintr(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control; + + /* The following fields are ignored when AVIC is enabled */ + WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu)); + + /* + * This is just a dummy VINTR to actually cause a vmexit to happen. + * Actual injection of virtual interrupts happens through EVENTINJ. + */ + control = &svm->vmcb->control; + control->int_vector = 0x0; + control->int_ctl &= ~V_INTR_PRIO_MASK; + control->int_ctl |= V_IRQ_MASK | + ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); + mark_dirty(svm->vmcb, VMCB_INTR); +} + static void svm_set_vintr(struct vcpu_svm *svm) { set_intercept(svm, INTERCEPT_VINTR); + if (is_intercept(svm, INTERCEPT_VINTR)) + svm_enable_vintr(svm); } static void svm_clear_vintr(struct vcpu_svm *svm) { clr_intercept(svm, INTERCEPT_VINTR); + + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + mark_dirty(svm->vmcb, VMCB_INTR); } static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) @@ -2982,15 +3043,6 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) return pdpte; } -static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, - unsigned long root) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->control.nested_cr3 = __sme_set(root); - mark_dirty(svm->vmcb, VMCB_NPT); -} - static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, struct x86_exception *fault) { @@ -3026,8 +3078,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu = &vcpu->arch.guest_mmu; kvm_init_shadow_mmu(vcpu); - vcpu->arch.mmu->set_cr3 = nested_svm_set_tdp_cr3; - vcpu->arch.mmu->get_cr3 = nested_svm_get_tdp_cr3; + vcpu->arch.mmu->get_guest_pgd = nested_svm_get_tdp_cr3; vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu->shadow_root_level = get_npt_level(vcpu); @@ -3088,43 +3139,36 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, return vmexit; } -/* This function returns true if it is save to enable the irq window */ -static inline bool nested_svm_intr(struct vcpu_svm *svm) +static void nested_svm_intr(struct vcpu_svm *svm) { - if (!is_guest_mode(&svm->vcpu)) - return true; - - if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - return true; - - if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) - return false; - - /* - * if vmexit was already requested (by intercepted exception - * for instance) do not overwrite it with "external interrupt" - * vmexit. - */ - if (svm->nested.exit_required) - return false; - svm->vmcb->control.exit_code = SVM_EXIT_INTR; svm->vmcb->control.exit_info_1 = 0; svm->vmcb->control.exit_info_2 = 0; - if (svm->nested.intercept & 1ULL) { - /* - * The #vmexit can't be emulated here directly because this - * code path runs with irqs and preemption disabled. A - * #vmexit emulation might sleep. Only signal request for - * the #vmexit here. - */ - svm->nested.exit_required = true; - trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); - return false; + /* nested_svm_vmexit this gets called afterwards from handle_exit */ + svm->nested.exit_required = true; + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); +} + +static bool nested_exit_on_intr(struct vcpu_svm *svm) +{ + return (svm->nested.intercept & 1ULL); +} + +static int svm_check_nested_events(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool block_nested_events = + kvm_event_needs_reinjection(vcpu) || svm->nested.exit_required; + + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(svm)) { + if (block_nested_events) + return -EBUSY; + nested_svm_intr(svm); + return 0; } - return true; + return 0; } /* This function returns true if it is save to enable the nmi window */ @@ -3243,9 +3287,6 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_CONTINUE; } -/* - * If this function returns true, this #vmexit was already handled - */ static int nested_svm_intercept(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; @@ -3520,6 +3561,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) static bool nested_vmcb_checks(struct vmcb *vmcb) { + if ((vmcb->save.efer & EFER_SVME) == 0) + return false; + if ((vmcb->control.intercept & (1ULL << INTERCEPT_VMRUN)) == 0) return false; @@ -3536,6 +3580,10 @@ static bool nested_vmcb_checks(struct vmcb *vmcb) static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, struct vmcb *nested_vmcb, struct kvm_host_map *map) { + bool evaluate_pending_interrupts = + is_intercept(svm, INTERCEPT_VINTR) || + is_intercept(svm, INTERCEPT_IRET); + if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) svm->vcpu.arch.hflags |= HF_HIF_MASK; else @@ -3595,15 +3643,6 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; - if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { - /* We only want the cr8 intercept bits of the guest */ - clr_cr_intercept(svm, INTERCEPT_CR8_READ); - clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); - } - - /* We don't want to see VMMCALLs from a nested guest */ - clr_intercept(svm, INTERCEPT_VMMCALL); - svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset; svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset; @@ -3631,7 +3670,21 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm->nested.vmcb = vmcb_gpa; + /* + * If L1 had a pending IRQ/NMI before executing VMRUN, + * which wasn't delivered because it was disallowed (e.g. + * interrupts disabled), L0 needs to evaluate if this pending + * event should cause an exit from L2 to L1 or be delivered + * directly to L2. + * + * Usually this would be handled by the processor noticing an + * IRQ/NMI window request. However, VMRUN can unblock interrupts + * by implicitly setting GIF, so force L0 to perform pending event + * evaluation by requesting a KVM_REQ_EVENT. + */ enable_gif(svm); + if (unlikely(evaluate_pending_interrupts)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); mark_all_dirty(svm->vmcb); } @@ -3833,11 +3886,8 @@ static int clgi_interception(struct vcpu_svm *svm) disable_gif(svm); /* After a CLGI no interrupts should come */ - if (!kvm_vcpu_apicv_active(&svm->vcpu)) { + if (!kvm_vcpu_apicv_active(&svm->vcpu)) svm_clear_vintr(svm); - svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; - mark_dirty(svm->vmcb, VMCB_INTR); - } return ret; } @@ -5123,19 +5173,6 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) ++vcpu->stat.nmi_injections; } -static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) -{ - struct vmcb_control_area *control; - - /* The following fields are ignored when AVIC is enabled */ - control = &svm->vmcb->control; - control->int_vector = irq; - control->int_ctl &= ~V_INTR_PRIO_MASK; - control->int_ctl |= V_IRQ_MASK | - ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); - mark_dirty(svm->vmcb, VMCB_INTR); -} - static void svm_set_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5232,6 +5269,9 @@ 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 +5295,11 @@ 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 +5311,8 @@ 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) @@ -5516,18 +5561,15 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - int ret; if (!gif_set(svm) || (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) return 0; - ret = !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF); - - if (is_guest_mode(vcpu)) - return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK); - - return ret; + if (is_guest_mode(vcpu) && (svm->vcpu.arch.hflags & HF_VINTR_MASK)) + return !!(svm->vcpu.arch.hflags & HF_HIF_MASK); + else + return !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF); } static void enable_irq_window(struct kvm_vcpu *vcpu) @@ -5542,7 +5584,7 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) * enabled, the STGI interception will not occur. Enable the irq * window under the assumption that the hardware will set the GIF. */ - if ((vgif_enabled(svm) || gif_set(svm)) && nested_svm_intr(svm)) { + if (vgif_enabled(svm) || gif_set(svm)) { /* * IRQ window is not needed when AVIC is enabled, * unless we have pending ExtINT since it cannot be injected @@ -5551,7 +5593,6 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) */ svm_toggle_avic_for_irq_window(vcpu, false); svm_set_vintr(svm); - svm_inject_irq(svm, 0x0); } } @@ -5937,24 +5978,30 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(svm_vcpu_run); -static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) +static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); + bool update_guest_cr3 = true; + unsigned long cr3; - svm->vmcb->save.cr3 = __sme_set(root); - mark_dirty(svm->vmcb, VMCB_CR); -} - -static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) -{ - struct vcpu_svm *svm = to_svm(vcpu); + cr3 = __sme_set(root); + if (npt_enabled) { + svm->vmcb->control.nested_cr3 = cr3; + mark_dirty(svm->vmcb, VMCB_NPT); - svm->vmcb->control.nested_cr3 = __sme_set(root); - mark_dirty(svm->vmcb, VMCB_NPT); + /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ + if (is_guest_mode(vcpu)) + update_guest_cr3 = false; + else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + cr3 = vcpu->arch.cr3; + else /* CR3 is already up-to-date. */ + update_guest_cr3 = false; + } - /* Also sync guest cr3 here in case we live migrate */ - svm->vmcb->save.cr3 = kvm_read_cr3(vcpu); - mark_dirty(svm->vmcb, VMCB_CR); + if (update_guest_cr3) { + svm->vmcb->save.cr3 = cr3; + mark_dirty(svm->vmcb, VMCB_CR); + } } static int is_disabled(void) @@ -6016,12 +6063,19 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) boot_cpu_has(X86_FEATURE_XSAVES); /* Update nrips enabled cache */ - svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); + svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && + guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); if (!kvm_vcpu_apicv_active(vcpu)) return; - guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC); + /* + * AVIC does not work with an x2APIC mode guest. If the X2APIC feature + * is exposed to the guest, disable AVIC. + */ + if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC)) + kvm_request_apicv_update(vcpu->kvm, false, + APICV_INHIBIT_REASON_X2APIC); /* * Currently, AVIC does not work with nested virtualization. @@ -6032,88 +6086,11 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) APICV_INHIBIT_REASON_NESTED); } -#define F feature_bit - -static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) -{ - switch (func) { - case 0x1: - if (avic) - entry->ecx &= ~F(X2APIC); - break; - case 0x80000001: - if (nested) - entry->ecx |= (1 << 2); /* Set SVM bit */ - break; - case 0x80000008: - if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->ebx |= F(VIRT_SSBD); - break; - case 0x8000000A: - entry->eax = 1; /* SVM revision 1 */ - entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper - ASID emulation to nested SVM */ - entry->ecx = 0; /* Reserved */ - entry->edx = 0; /* Per default do not support any - additional features */ - - /* Support next_rip if host supports it */ - if (boot_cpu_has(X86_FEATURE_NRIPS)) - entry->edx |= F(NRIPS); - - /* Support NPT for the guest if enabled */ - if (npt_enabled) - entry->edx |= F(NPT); - - } -} - -static int svm_get_lpage_level(void) -{ - return PT_PDPE_LEVEL; -} - -static bool svm_rdtscp_supported(void) -{ - return boot_cpu_has(X86_FEATURE_RDTSCP); -} - -static bool svm_invpcid_supported(void) -{ - return false; -} - -static bool svm_mpx_supported(void) -{ - return false; -} - -static bool svm_xsaves_supported(void) -{ - return boot_cpu_has(X86_FEATURE_XSAVES); -} - -static bool svm_umip_emulated(void) -{ - return false; -} - -static bool svm_pt_supported(void) -{ - return false; -} - static bool svm_has_wbinvd_exit(void) { return true; } -static bool svm_pku_supported(void) -{ - return false; -} - #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -6180,7 +6157,8 @@ static const struct __x86_intercept { static int svm_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, - enum x86_intercept_stage stage) + enum x86_intercept_stage stage, + struct x86_exception *exception) { struct vcpu_svm *svm = to_svm(vcpu); int vmexit, ret = X86EMUL_CONTINUE; @@ -6303,7 +6281,8 @@ 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 +7127,9 @@ 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 +7257,13 @@ 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); @@ -7351,7 +7340,7 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) * TODO: Last condition latch INIT signals on vCPU when * vCPU is in guest-mode and vmcb12 defines intercept on INIT. * To properly emulate the INIT intercept, SVM should implement - * kvm_x86_ops->check_nested_events() and call nested_svm_vmexit() + * kvm_x86_ops.check_nested_events() and call nested_svm_vmexit() * there if an INIT signal is pending. */ return !gif_set(svm) || @@ -7364,7 +7353,8 @@ static bool svm_check_apicv_inhibit_reasons(ulong bit) BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | - BIT(APICV_INHIBIT_REASON_PIT_REINJ); + BIT(APICV_INHIBIT_REASON_PIT_REINJ) | + BIT(APICV_INHIBIT_REASON_X2APIC); return supported & BIT(bit); } @@ -7374,12 +7364,8 @@ static void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) avic_update_access_page(kvm, activate); } -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, - .check_processor_compatibility = svm_check_processor_compat, +static struct kvm_x86_ops svm_x86_ops __initdata = { + .hardware_unsetup = svm_hardware_teardown, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, @@ -7389,8 +7375,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vcpu_free = svm_free_vcpu, .vcpu_reset = svm_vcpu_reset, - .vm_alloc = svm_vm_alloc, - .vm_free = svm_vm_free, + .vm_size = sizeof(struct kvm_svm), .vm_init = svm_vm_init, .vm_destroy = svm_vm_destroy, @@ -7412,7 +7397,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, - .set_cr3 = svm_set_cr3, .set_cr4 = svm_set_cr4, .set_efer = svm_set_efer, .get_idt = svm_get_idt, @@ -7433,6 +7417,7 @@ 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, @@ -7464,26 +7449,14 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_exit_info = svm_get_exit_info, - .get_lpage_level = svm_get_lpage_level, - .cpuid_update = svm_cpuid_update, - .rdtscp_supported = svm_rdtscp_supported, - .invpcid_supported = svm_invpcid_supported, - .mpx_supported = svm_mpx_supported, - .xsaves_supported = svm_xsaves_supported, - .umip_emulated = svm_umip_emulated, - .pt_supported = svm_pt_supported, - .pku_supported = svm_pku_supported, - - .set_supported_cpuid = svm_set_supported_cpuid, - .has_wbinvd_exit = svm_has_wbinvd_exit, .read_l1_tsc_offset = svm_read_l1_tsc_offset, .write_l1_tsc_offset = svm_write_l1_tsc_offset, - .set_tdp_cr3 = set_tdp_cr3, + .load_mmu_pgd = svm_load_mmu_pgd, .check_intercept = svm_check_intercept, .handle_exit_irqoff = svm_handle_exit_irqoff, @@ -7513,11 +7486,22 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, .apic_init_signal_blocked = svm_apic_init_signal_blocked, + + .check_nested_events = svm_check_nested_events, +}; + +static struct kvm_x86_init_ops svm_init_ops __initdata = { + .cpu_has_kvm_support = has_svm, + .disabled_by_bios = is_disabled, + .hardware_setup = svm_hardware_setup, + .check_processor_compatibility = svm_check_processor_compat, + + .runtime_ops = &svm_x86_ops, }; static int __init svm_init(void) { - return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm), + return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), THIS_MODULE); } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index f194dd058470..249062f24b94 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -151,32 +151,38 @@ TRACE_EVENT(kvm_fast_mmio, * Tracepoint for cpuid. */ TRACE_EVENT(kvm_cpuid, - TP_PROTO(unsigned int function, unsigned long rax, unsigned long rbx, - unsigned long rcx, unsigned long rdx, bool found), - TP_ARGS(function, rax, rbx, rcx, rdx, found), + TP_PROTO(unsigned int function, unsigned int index, unsigned long rax, + unsigned long rbx, unsigned long rcx, unsigned long rdx, + bool found, bool used_max_basic), + TP_ARGS(function, index, rax, rbx, rcx, rdx, found, used_max_basic), TP_STRUCT__entry( __field( unsigned int, function ) + __field( unsigned int, index ) __field( unsigned long, rax ) __field( unsigned long, rbx ) __field( unsigned long, rcx ) __field( unsigned long, rdx ) __field( bool, found ) + __field( bool, used_max_basic ) ), TP_fast_assign( __entry->function = function; + __entry->index = index; __entry->rax = rax; __entry->rbx = rbx; __entry->rcx = rcx; __entry->rdx = rdx; __entry->found = found; + __entry->used_max_basic = used_max_basic; ), - TP_printk("func %x rax %lx rbx %lx rcx %lx rdx %lx, cpuid entry %s", - __entry->function, __entry->rax, + TP_printk("func %x idx %x rax %lx rbx %lx rcx %lx rdx %lx, cpuid entry %s%s", + __entry->function, __entry->index, __entry->rax, __entry->rbx, __entry->rcx, __entry->rdx, - __entry->found ? "found" : "not found") + __entry->found ? "found" : "not found", + __entry->used_max_basic ? ", used max basic" : "") ); #define AREG(x) { APIC_##x, "APIC_" #x } @@ -240,7 +246,7 @@ TRACE_EVENT(kvm_exit, __entry->guest_rip = kvm_rip_read(vcpu); __entry->isa = isa; __entry->vcpu_id = vcpu->vcpu_id; - kvm_x86_ops->get_exit_info(vcpu, &__entry->info1, + kvm_x86_ops.get_exit_info(vcpu, &__entry->info1, &__entry->info2); ), @@ -744,14 +750,14 @@ TRACE_EVENT(kvm_emulate_insn, ), TP_fast_assign( - __entry->csbase = kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS); - __entry->len = vcpu->arch.emulate_ctxt.fetch.ptr - - vcpu->arch.emulate_ctxt.fetch.data; - __entry->rip = vcpu->arch.emulate_ctxt._eip - __entry->len; + __entry->csbase = kvm_x86_ops.get_segment_base(vcpu, VCPU_SREG_CS); + __entry->len = vcpu->arch.emulate_ctxt->fetch.ptr + - vcpu->arch.emulate_ctxt->fetch.data; + __entry->rip = vcpu->arch.emulate_ctxt->_eip - __entry->len; memcpy(__entry->insn, - vcpu->arch.emulate_ctxt.fetch.data, + vcpu->arch.emulate_ctxt->fetch.data, 15); - __entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt.mode); + __entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt->mode); __entry->failed = failed; ), @@ -815,8 +821,8 @@ TRACE_EVENT(kvm_write_tsc_offset, #ifdef CONFIG_X86_64 #define host_clocks \ - {VCLOCK_NONE, "none"}, \ - {VCLOCK_TSC, "tsc"} \ + {VDSO_CLOCKMODE_NONE, "none"}, \ + {VDSO_CLOCKMODE_TSC, "tsc"} \ TRACE_EVENT(kvm_update_master_clock, TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched), @@ -1367,6 +1373,24 @@ TRACE_EVENT(kvm_avic_unaccelerated_access, __entry->vec) ); +TRACE_EVENT(kvm_avic_ga_log, + TP_PROTO(u32 vmid, u32 vcpuid), + TP_ARGS(vmid, vcpuid), + + TP_STRUCT__entry( + __field(u32, vmid) + __field(u32, vcpuid) + ), + + TP_fast_assign( + __entry->vmid = vmid; + __entry->vcpuid = vcpuid; + ), + + TP_printk("vmid=%u, vcpuid=%u", + __entry->vmid, __entry->vcpuid) +); + TRACE_EVENT(kvm_hv_timer_state, TP_PROTO(unsigned int vcpu_id, unsigned int hv_timer_in_use), TP_ARGS(vcpu_id, hv_timer_in_use), diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 283bdb7071af..8903475f751e 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 @@ -100,7 +101,7 @@ static inline bool cpu_has_load_perf_global_ctrl(void) (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); } -static inline bool vmx_mpx_supported(void) +static inline bool cpu_has_vmx_mpx(void) { return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS); @@ -145,11 +146,6 @@ static inline bool vmx_umip_emulated(void) SECONDARY_EXEC_DESC; } -static inline bool vmx_pku_supported(void) -{ - return boot_cpu_has(X86_FEATURE_PKU); -} - static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -353,4 +349,22 @@ static inline bool cpu_has_vmx_intel_pt(void) (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } +/* + * Processor Trace can operate in one of three modes: + * a. system-wide: trace both host/guest and output to host buffer + * b. host-only: only trace host and output to host buffer + * c. host-guest: trace host and guest simultaneously and output to their + * respective buffer + * + * KVM currently only supports (a) and (c). + */ +static inline bool vmx_pt_mode_is_system(void) +{ + return pt_mode == PT_MODE_SYSTEM; +} +static inline bool vmx_pt_mode_is_host_guest(void) +{ + return pt_mode == PT_MODE_HOST_GUEST; +} + #endif /* __KVM_X86_VMX_CAPS_H */ diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 6de47f2569c9..e5f7a7ebf27d 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -198,6 +198,13 @@ static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {} static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ +enum nested_evmptrld_status { + EVMPTRLD_DISABLED, + EVMPTRLD_SUCCEEDED, + EVMPTRLD_VMFAIL, + EVMPTRLD_ERROR, +}; + bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 657c2eda357c..de232306561a 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; } @@ -353,9 +353,8 @@ static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT, nested_ept_ad_enabled(vcpu), - nested_ept_get_cr3(vcpu)); - vcpu->arch.mmu->set_cr3 = vmx_set_cr3; - vcpu->arch.mmu->get_cr3 = nested_ept_get_cr3; + nested_ept_get_eptp(vcpu)); + vcpu->arch.mmu->get_guest_pgd = nested_ept_get_eptp; vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault; vcpu->arch.mmu->get_pdptr = kvm_pdptr_read; @@ -544,7 +543,8 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { +static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) +{ int msr; for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { @@ -1909,20 +1909,21 @@ static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) * This is an equivalent of the nested hypervisor executing the vmptrld * instruction. */ -static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, - bool from_launch) +static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( + struct kvm_vcpu *vcpu, bool from_launch) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; if (likely(!vmx->nested.enlightened_vmcs_enabled)) - return 1; + return EVMPTRLD_DISABLED; if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) - return 1; + return EVMPTRLD_DISABLED; - 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; @@ -1930,7 +1931,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa), &vmx->nested.hv_evmcs_map)) - return 0; + return EVMPTRLD_ERROR; vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva; @@ -1959,7 +1960,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) && (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) { nested_release_evmcs(vcpu); - return 0; + return EVMPTRLD_VMFAIL; } vmx->nested.dirty_vmcs12 = true; @@ -1981,28 +1982,20 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, } /* - * Clean fields data can't de used on VMLAUNCH and when we switch + * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ if (from_launch || evmcs_gpa_changed) vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - return 1; + return EVMPTRLD_SUCCEEDED; } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * hv_evmcs may end up being not mapped after migration (when - * L2 was running), map it here to make sure vmcs12 changes are - * properly reflected. - */ - if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs) - nested_vmx_handle_enlightened_vmptrld(vcpu, false); - if (vmx->nested.hv_evmcs) { copy_vmcs12_to_enlightened(vmx); /* All fields are clean */ @@ -2473,9 +2466,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * If L1 use EPT, then L0 needs to execute INVEPT on * EPTP02 instead of EPTP01. Therefore, delay TLB * flush until vmcs02->eptp is fully updated by - * KVM_REQ_LOAD_CR3. Note that this assumes + * KVM_REQ_LOAD_MMU_PGD. Note that this assumes * KVM_REQ_TLB_FLUSH is evaluated after - * KVM_REQ_LOAD_CR3 in vcpu_enter_guest(). + * KVM_REQ_LOAD_MMU_PGD in vcpu_enter_guest(). */ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } @@ -2520,7 +2513,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 * on nested VM-Exit, which can occur without actually running L2 and - * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * thus without hitting vmx_load_mmu_pgd(), e.g. if L1 is entering L2 with * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the * transition to HLT instead of running L2. */ @@ -2562,13 +2555,13 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) return 0; } -static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) +static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) { struct vcpu_vmx *vmx = to_vmx(vcpu); int maxphyaddr = cpuid_maxphyaddr(vcpu); /* Check for memory type validity */ - switch (address & VMX_EPTP_MT_MASK) { + switch (new_eptp & VMX_EPTP_MT_MASK) { case VMX_EPTP_MT_UC: if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT))) return false; @@ -2581,16 +2574,26 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) return false; } - /* only 4 levels page-walk length are valid */ - if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)) + /* Page-walk levels validity. */ + switch (new_eptp & VMX_EPTP_PWL_MASK) { + case VMX_EPTP_PWL_5: + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT))) + return false; + break; + case VMX_EPTP_PWL_4: + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT))) + return false; + break; + default: return false; + } /* Reserved bits should not be set */ - if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f))) + if (CC(new_eptp >> maxphyaddr || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ - if (address & VMX_EPTP_AD_ENABLE_BIT) { + if (new_eptp & VMX_EPTP_AD_ENABLE_BIT) { if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT))) return false; } @@ -2639,7 +2642,7 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, return -EINVAL; if (nested_cpu_has_ept(vmcs12) && - CC(!valid_ept_address(vcpu, vmcs12->ept_pointer))) + CC(!nested_vmx_check_eptp(vcpu, vmcs12->ept_pointer))) return -EINVAL; if (nested_cpu_has_vmfunc(vmcs12)) { @@ -2959,7 +2962,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) /* * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS, * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to - * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e. + * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e. * there is no need to preserve other bits or save/restore the field. */ vmcs_writel(GUEST_RFLAGS, 0); @@ -3051,6 +3054,27 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) struct page *page; u64 hpa; + /* + * hv_evmcs may end up being not mapped after migration (when + * L2 was running), map it here to make sure vmcs12 changes are + * properly reflected. + */ + if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs) { + enum nested_evmptrld_status evmptrld_status = + nested_vmx_handle_enlightened_vmptrld(vcpu, false); + + if (evmptrld_status == EVMPTRLD_VMFAIL || + evmptrld_status == EVMPTRLD_ERROR) { + pr_debug_ratelimited("%s: enlightened vmptrld failed\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; + } + } + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * Translate L1 physical address to host physical @@ -3160,10 +3184,10 @@ 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) @@ -3314,12 +3338,18 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) enum nvmx_vmentry_status status; struct vcpu_vmx *vmx = to_vmx(vcpu); u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); + enum nested_evmptrld_status evmptrld_status; if (!nested_vmx_check_permission(vcpu)) return 1; - if (!nested_vmx_handle_enlightened_vmptrld(vcpu, launch)) + evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, launch); + if (evmptrld_status == EVMPTRLD_ERROR) { + kvm_queue_exception(vcpu, UD_VECTOR); return 1; + } else if (evmptrld_status == EVMPTRLD_VMFAIL) { + return nested_vmx_failInvalid(vcpu); + } if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull) return nested_vmx_failInvalid(vcpu); @@ -3497,7 +3527,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, } -static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gfn_t gfn; @@ -3575,25 +3605,80 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } -static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) +/* + * Returns true if a debug trap is pending delivery. + * + * In KVM, debug traps bear an exception payload. As such, the class of a #DB + * exception may be inferred from the presence of an exception payload. + */ +static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.exception.pending && + vcpu->arch.exception.nr == DB_VECTOR && + vcpu->arch.exception.payload; +} + +/* + * Certain VM-exits set the 'pending debug exceptions' field to indicate a + * recognized #DB (data or single-step) that has yet to be delivered. Since KVM + * represents these debug traps with a payload that is said to be compatible + * with the 'pending debug exceptions' field, write the payload to the VMCS + * field if a VM-exit is delivered before the debug trap. + */ +static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) +{ + if (vmx_pending_dbg_trap(vcpu)) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vcpu->arch.exception.payload); +} + +static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); 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) return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); clear_bit(KVM_APIC_INIT, &apic->pending_events); nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); return 0; } + /* + * Process any exceptions that are not debug traps before MTF. + */ if (vcpu->arch.exception.pending && - nested_vmx_check_exception(vcpu, &exit_qual)) { + !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)) { if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); @@ -3623,8 +3708,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - if ((kvm_cpu_has_interrupt(vcpu) || external_intr) && - nested_exit_on_intr(vcpu)) { + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); @@ -3967,7 +4051,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * * If vmcs12 uses EPT, we need to execute this flush on EPTP01 * and therefore we request the TLB flush to happen only after VMCS EPTP - * has been set by KVM_REQ_LOAD_CR3. + * has been set by KVM_REQ_LOAD_MMU_PGD. */ if (enable_vpid && (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) { @@ -4272,17 +4356,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - /* - * TODO: SDM says that with acknowledge interrupt on - * exit, bit 31 of the VM-exit interrupt information - * (valid interrupt) is always set to 1 on - * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't - * need kvm_cpu_has_interrupt(). See the commit - * message for details. - */ - if (nested_exit_intr_ack_set(vcpu) && - exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - kvm_cpu_has_interrupt(vcpu)) { + if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + nested_exit_intr_ack_set(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | @@ -4326,7 +4401,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, * Decode the memory-address operand of a vmx instruction, as recorded on an * exit caused by such an instruction (run by a guest hypervisor). * On success, returns 0. When the operand is invalid, returns 1 and throws - * #UD or #GP. + * #UD, #GP, or #SS. */ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret) @@ -4367,7 +4442,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, if (base_is_valid) off += kvm_register_read(vcpu, base_reg); if (index_is_valid) - off += kvm_register_read(vcpu, index_reg)<<scaling; + off += kvm_register_read(vcpu, index_reg) << scaling; vmx_get_segment(vcpu, &s, seg_reg); /* @@ -4460,7 +4535,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) return; vmx = to_vmx(vcpu); - if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { + if (kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; vmx->nested.msrs.exit_ctls_high |= @@ -4546,7 +4621,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) vmx->nested.vmcs02_initialized = false; vmx->nested.vmxon = true; - if (pt_mode == PT_MODE_HOST_GUEST) { + if (vmx_pt_mode_is_host_guest()) { vmx->pt_desc.guest.ctl = 0; pt_update_intercept_for_msr(vmx); } @@ -5178,7 +5253,7 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { u32 index = kvm_rcx_read(vcpu); - u64 address; + u64 new_eptp; bool accessed_dirty; struct kvm_mmu *mmu = vcpu->arch.walk_mmu; @@ -5191,23 +5266,23 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT, - &address, index * 8, 8)) + &new_eptp, index * 8, 8)) return 1; - accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT); + accessed_dirty = !!(new_eptp & VMX_EPTP_AD_ENABLE_BIT); /* * If the (L2) guest does a vmfunc to the currently * active ept pointer, we don't have to do anything else */ - if (vmcs12->ept_pointer != address) { - if (!valid_ept_address(vcpu, address)) + if (vmcs12->ept_pointer != new_eptp) { + if (!nested_vmx_check_eptp(vcpu, new_eptp)) return 1; kvm_mmu_unload(vcpu); mmu->ept_ad = accessed_dirty; mmu->mmu_role.base.ad_disabled = !accessed_dirty; - vmcs12->ept_pointer = address; + vmcs12->ept_pointer = new_eptp; /* * TODO: Check what's the correct approach in case * mmu reload fails. Currently, we just let the next @@ -5256,24 +5331,17 @@ 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; @@ -5300,8 +5368,26 @@ 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. @@ -5457,8 +5543,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (vmx->nested.nested_run_pending) - return false; + WARN_ON_ONCE(vmx->nested.nested_run_pending); if (unlikely(vmx->fail)) { trace_kvm_nested_vmenter_failed( @@ -5467,19 +5552,6 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return true; } - /* - * The host physical addresses of some pages of guest memory - * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC - * Page). The CPU may write to these pages via their host - * physical address while L2 is running, bypassing any - * address-translation-based dirty tracking (e.g. EPT write - * protection). - * - * Mark them dirty on every exit from L2 to prevent them from - * getting out of sync with dirty tracking. - */ - nested_mark_vmcs12_pages_dirty(vcpu); - trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, vmcs_readl(EXIT_QUALIFICATION), vmx->idt_vectoring_info, @@ -5560,7 +5632,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_TRAP_FLAG: - return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); + return nested_cpu_has_mtf(vmcs12); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: @@ -5683,6 +5755,9 @@ 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; } } @@ -5834,10 +5909,12 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa); } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) { /* - * Sync eVMCS upon entry as we may not have - * HV_X64_MSR_VP_ASSIST_PAGE set up yet. + * nested_vmx_handle_enlightened_vmptrld() cannot be called + * directly from here as HV_X64_MSR_VP_ASSIST_PAGE may not be + * restored yet. EVMCS will be mapped from + * nested_get_vmcs12_pages(). */ - vmx->nested.need_vmcs12_to_shadow_sync = true; + kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu); } else { return -EINVAL; } @@ -5863,6 +5940,9 @@ 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) { @@ -5920,8 +6000,7 @@ 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 @@ -5948,7 +6027,7 @@ 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; @@ -6057,11 +6136,13 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, /* nested EPT: emulate EPT also to L1 */ msrs->secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; - msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT | - VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT; - if (cpu_has_vmx_ept_execute_only()) - msrs->ept_caps |= - VMX_EPT_EXECUTE_ONLY_BIT; + msrs->ept_caps = + VMX_EPT_PAGE_WALK_4_BIT | + VMX_EPT_PAGE_WALK_5_BIT | + VMX_EPTP_WB_BIT | + VMX_EPT_INVEPT_BIT | + VMX_EPT_EXECUTE_ONLY_BIT; + msrs->ept_caps &= ept_caps; msrs->ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT | @@ -6160,7 +6241,8 @@ void nested_vmx_hardware_unsetup(void) } } -__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) +__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops, + int (*exit_handlers[])(struct kvm_vcpu *)) { int i; @@ -6196,12 +6278,12 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; - kvm_x86_ops->check_nested_events = vmx_check_nested_events; - kvm_x86_ops->get_nested_state = vmx_get_nested_state; - kvm_x86_ops->set_nested_state = vmx_set_nested_state; - kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages; - kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs; - kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version; + ops->check_nested_events = vmx_check_nested_events; + ops->get_nested_state = vmx_get_nested_state; + ops->set_nested_state = vmx_set_nested_state; + ops->get_vmcs12_pages = nested_get_vmcs12_pages; + ops->nested_enable_evmcs = nested_enable_evmcs; + ops->nested_get_evmcs_version = nested_get_evmcs_version; return 0; } diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index fc874d4ead0f..ac56aefa49e3 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,10 +17,10 @@ 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 *)); +__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops, + int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, @@ -34,6 +34,9 @@ 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); +void nested_mark_vmcs12_pages_dirty(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) { @@ -59,7 +62,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) vmx->nested.hv_evmcs; } -static inline unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) +static inline unsigned long nested_ept_get_eptp(struct kvm_vcpu *vcpu) { /* return the page table to be shadowed - in our case, EPT12 */ return get_vmcs12(vcpu)->ept_pointer; @@ -67,7 +70,7 @@ static inline unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) static inline bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu) { - return nested_ept_get_cr3(vcpu) & VMX_EPTP_AD_ENABLE_BIT; + return nested_ept_get_eptp(vcpu) & VMX_EPTP_AD_ENABLE_BIT; } /* @@ -175,6 +178,11 @@ 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/ops.h b/arch/x86/kvm/vmx/ops.h index 45eaedee2ac0..19717d0a1100 100644 --- a/arch/x86/kvm/vmx/ops.h +++ b/arch/x86/kvm/vmx/ops.h @@ -13,6 +13,8 @@ #define __ex(x) __kvm_handle_fault_on_reboot(x) asmlinkage void vmread_error(unsigned long field, bool fault); +__attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, + bool fault); void vmwrite_error(unsigned long field, unsigned long value); void vmclear_error(struct vmcs *vmcs, u64 phys_addr); void vmptrld_error(struct vmcs *vmcs, u64 phys_addr); @@ -70,15 +72,28 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) asm volatile("1: vmread %2, %1\n\t" ".byte 0x3e\n\t" /* branch taken hint */ "ja 3f\n\t" - "mov %2, %%" _ASM_ARG1 "\n\t" - "xor %%" _ASM_ARG2 ", %%" _ASM_ARG2 "\n\t" - "2: call vmread_error\n\t" - "xor %k1, %k1\n\t" + + /* + * VMREAD failed. Push '0' for @fault, push the failing + * @field, and bounce through the trampoline to preserve + * volatile registers. + */ + "push $0\n\t" + "push %2\n\t" + "2:call vmread_error_trampoline\n\t" + + /* + * Unwind the stack. Note, the trampoline zeros out the + * memory for @fault so that the result is '0' on error. + */ + "pop %2\n\t" + "pop %1\n\t" "3:\n\t" + /* VMREAD faulted. As above, except push '1' for @fault. */ ".pushsection .fixup, \"ax\"\n\t" - "4: mov %2, %%" _ASM_ARG1 "\n\t" - "mov $1, %%" _ASM_ARG2 "\n\t" + "4: push $1\n\t" + "push %2\n\t" "jmp 2b\n\t" ".popsection\n\t" _ASM_EXTABLE(1b, 4b) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index fd21cdb10b79..7c857737b438 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -263,9 +263,15 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); + if (pmc->perf_event) + perf_event_period(pmc->perf_event, + get_sample_period(pmc, data)); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); + if (pmc->perf_event) + perf_event_period(pmc->perf_event, + get_sample_period(pmc, data)); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) @@ -329,7 +335,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->global_ovf_ctrl_mask = pmu->global_ctrl_mask & ~(MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF | MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD); - if (kvm_x86_ops->pt_supported()) + if (vmx_pt_mode_is_host_guest()) pmu->global_ovf_ctrl_mask &= ~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 81ada2ce99e7..9651ba388ba9 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -135,12 +135,12 @@ SYM_FUNC_START(__vmx_vcpu_run) cmpb $0, %bl /* Load guest registers. Don't clobber flags. */ - mov VCPU_RBX(%_ASM_AX), %_ASM_BX mov VCPU_RCX(%_ASM_AX), %_ASM_CX mov VCPU_RDX(%_ASM_AX), %_ASM_DX + mov VCPU_RBX(%_ASM_AX), %_ASM_BX + mov VCPU_RBP(%_ASM_AX), %_ASM_BP mov VCPU_RSI(%_ASM_AX), %_ASM_SI mov VCPU_RDI(%_ASM_AX), %_ASM_DI - mov VCPU_RBP(%_ASM_AX), %_ASM_BP #ifdef CONFIG_X86_64 mov VCPU_R8 (%_ASM_AX), %r8 mov VCPU_R9 (%_ASM_AX), %r9 @@ -168,12 +168,12 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Save all guest registers, including RAX from the stack */ __ASM_SIZE(pop) VCPU_RAX(%_ASM_AX) - mov %_ASM_BX, VCPU_RBX(%_ASM_AX) mov %_ASM_CX, VCPU_RCX(%_ASM_AX) mov %_ASM_DX, VCPU_RDX(%_ASM_AX) + mov %_ASM_BX, VCPU_RBX(%_ASM_AX) + mov %_ASM_BP, VCPU_RBP(%_ASM_AX) mov %_ASM_SI, VCPU_RSI(%_ASM_AX) mov %_ASM_DI, VCPU_RDI(%_ASM_AX) - mov %_ASM_BP, VCPU_RBP(%_ASM_AX) #ifdef CONFIG_X86_64 mov %r8, VCPU_R8 (%_ASM_AX) mov %r9, VCPU_R9 (%_ASM_AX) @@ -197,12 +197,12 @@ SYM_FUNC_START(__vmx_vcpu_run) * free. RSP and RAX are exempt as RSP is restored by hardware during * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. */ -1: xor %ebx, %ebx - xor %ecx, %ecx +1: xor %ecx, %ecx xor %edx, %edx + xor %ebx, %ebx + xor %ebp, %ebp xor %esi, %esi xor %edi, %edi - xor %ebp, %ebp #ifdef CONFIG_X86_64 xor %r8d, %r8d xor %r9d, %r9d @@ -234,3 +234,61 @@ SYM_FUNC_START(__vmx_vcpu_run) 2: mov $1, %eax jmp 1b SYM_FUNC_END(__vmx_vcpu_run) + +/** + * vmread_error_trampoline - Trampoline from inline asm to vmread_error() + * @field: VMCS field encoding that failed + * @fault: %true if the VMREAD faulted, %false if it failed + + * Save and restore volatile registers across a call to vmread_error(). Note, + * all parameters are passed on the stack. + */ +SYM_FUNC_START(vmread_error_trampoline) + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP + + push %_ASM_AX + push %_ASM_CX + push %_ASM_DX +#ifdef CONFIG_X86_64 + push %rdi + push %rsi + push %r8 + push %r9 + push %r10 + push %r11 +#endif +#ifdef CONFIG_X86_64 + /* Load @field and @fault to arg1 and arg2 respectively. */ + mov 3*WORD_SIZE(%rbp), %_ASM_ARG2 + mov 2*WORD_SIZE(%rbp), %_ASM_ARG1 +#else + /* Parameters are passed on the stack for 32-bit (see asmlinkage). */ + push 3*WORD_SIZE(%ebp) + push 2*WORD_SIZE(%ebp) +#endif + + call vmread_error + +#ifndef CONFIG_X86_64 + add $8, %esp +#endif + + /* Zero out @fault, which will be popped into the result register. */ + _ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP) + +#ifdef CONFIG_X86_64 + pop %r11 + pop %r10 + pop %r9 + pop %r8 + pop %rsi + pop %rdi +#endif + pop %_ASM_DX + pop %_ASM_CX + pop %_ASM_AX + pop %_ASM_BP + + ret +SYM_FUNC_END(vmread_error_trampoline) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9a6664886f2e..91749f1254e8 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> @@ -41,6 +42,7 @@ #include <asm/mce.h> #include <asm/mmu_context.h> #include <asm/mshyperv.h> +#include <asm/mwait.h> #include <asm/spec-ctrl.h> #include <asm/virtext.h> #include <asm/vmx.h> @@ -64,11 +66,13 @@ 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 +99,7 @@ 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); /* @@ -433,7 +437,6 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; -u64 host_efer; static unsigned long host_idt_base; /* @@ -654,53 +657,16 @@ static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, return ret; } -void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) -{ - vmcs_clear(loaded_vmcs->vmcs); - if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) - vmcs_clear(loaded_vmcs->shadow_vmcs); - loaded_vmcs->cpu = -1; - loaded_vmcs->launched = 0; -} - #ifdef CONFIG_KEXEC_CORE -/* - * This bitmap is used to indicate whether the vmclear - * operation is enabled on all cpus. All disabled by - * default. - */ -static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; - -static inline void crash_enable_local_vmclear(int cpu) -{ - cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline void crash_disable_local_vmclear(int cpu) -{ - cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline int crash_local_vmclear_enabled(int cpu) -{ - return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - static void crash_vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; - if (!crash_local_vmclear_enabled(cpu)) - return; - list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); } -#else -static inline void crash_enable_local_vmclear(int cpu) { } -static inline void crash_disable_local_vmclear(int cpu) { } #endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) @@ -712,19 +678,24 @@ static void __loaded_vmcs_clear(void *arg) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; - crash_disable_local_vmclear(cpu); + + vmcs_clear(loaded_vmcs->vmcs); + if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) + vmcs_clear(loaded_vmcs->shadow_vmcs); + list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); /* - * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link - * is before setting loaded_vmcs->vcpu to -1 which is done in - * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist - * then adds the vmcs into percpu list before it is deleted. + * Ensure all writes to loaded_vmcs, including deleting it from its + * current percpu list, complete before setting loaded_vmcs->vcpu to + * -1, otherwise a different cpu can see vcpu == -1 first and add + * loaded_vmcs to its percpu list before it's deleted from this cpu's + * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs(). */ smp_wmb(); - loaded_vmcs_init(loaded_vmcs); - crash_enable_local_vmclear(cpu); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; } void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) @@ -808,7 +779,7 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu) if (to_vmx(vcpu)->rmode.vm86_active) eb = ~0; if (enable_ept) - eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ + eb &= ~(1u << PF_VECTOR); /* When we are running a nested L2 guest and L1 specified for it a * certain exception bitmap, we must trap the same exceptions and pass @@ -1059,7 +1030,7 @@ static unsigned long segment_base(u16 selector) static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) { - return (pt_mode == PT_MODE_HOST_GUEST) && + return vmx_pt_mode_is_host_guest() && !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); } @@ -1093,7 +1064,7 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) static void pt_guest_enter(struct vcpu_vmx *vmx) { - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) return; /* @@ -1110,7 +1081,7 @@ static void pt_guest_enter(struct vcpu_vmx *vmx) static void pt_guest_exit(struct vcpu_vmx *vmx) { - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) return; if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { @@ -1175,6 +1146,10 @@ 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; @@ -1339,18 +1314,17 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); local_irq_disable(); - crash_disable_local_vmclear(cpu); /* - * Read loaded_vmcs->cpu should be before fetching - * loaded_vmcs->loaded_vmcss_on_cpu_link. - * See the comments in __loaded_vmcs_clear(). + * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to + * this cpu's percpu list, otherwise it may not yet be deleted + * from its previous cpu's percpu list. Pairs with the + * smb_wmb() in __loaded_vmcs_clear(). */ smp_rmb(); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); - crash_enable_local_vmclear(cpu); local_irq_enable(); } @@ -1599,6 +1573,40 @@ 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) { /* @@ -1649,16 +1657,6 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) vmx_clear_hlt(vcpu); } -static bool vmx_rdtscp_supported(void) -{ - return cpu_has_vmx_rdtscp(); -} - -static bool vmx_invpcid_supported(void) -{ - return cpu_has_vmx_invpcid(); -} - /* * Swap MSR entry in host/guest MSR entry array. */ @@ -1866,24 +1864,24 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &msr_info->data); break; case MSR_IA32_RTIT_CTL: - if (pt_mode != PT_MODE_HOST_GUEST) + if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.ctl; break; case MSR_IA32_RTIT_STATUS: - if (pt_mode != PT_MODE_HOST_GUEST) + if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.status; break; case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) return 1; msr_info->data = vmx->pt_desc.guest.cr3_match; break; case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, @@ -1892,7 +1890,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.output_base; break; case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, @@ -1902,7 +1900,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_num_address_ranges))) return 1; @@ -2108,7 +2106,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || vmx_rtit_ctl_check(vcpu, data) || vmx->nested.vmxon) return 1; @@ -2224,18 +2222,33 @@ static __init int vmx_disabled_by_bios(void) !boot_cpu_has(X86_FEATURE_VMX); } -static void kvm_cpu_vmxon(u64 addr) +static int kvm_cpu_vmxon(u64 vmxon_pointer) { + u64 msr; + cr4_set_bits(X86_CR4_VMXE); intel_pt_handle_vmx(1); - asm volatile ("vmxon %0" : : "m"(addr)); + asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); + return 0; + +fault: + WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", + rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + intel_pt_handle_vmx(0); + cr4_clear_bits(X86_CR4_VMXE); + + return -EFAULT; } static int hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + int r; if (cr4_read_shadow() & X86_CR4_VMXE) return -EBUSY; @@ -2252,18 +2265,10 @@ static int hardware_enable(void) INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - /* - * Now we can enable the vmclear operation in kdump - * since the loaded_vmcss_on_cpu list on this cpu - * has been initialized. - * - * Though the cpu is not in VMX operation now, there - * is no problem to enable the vmclear operation - * for the loaded_vmcss_on_cpu list is empty! - */ - crash_enable_local_vmclear(cpu); + r = kvm_cpu_vmxon(phys_addr); + if (r) + return r; - kvm_cpu_vmxon(phys_addr); if (enable_ept) ept_sync_global(); @@ -2298,6 +2303,17 @@ 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 +2394,9 @@ 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) @@ -2563,9 +2580,12 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->vmcs) return -ENOMEM; + vmcs_clear(loaded_vmcs->vmcs); + loaded_vmcs->shadow_vmcs = NULL; loaded_vmcs->hv_timer_soft_disabled = false; - loaded_vmcs_init(loaded_vmcs); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; if (cpu_has_vmx_msr_bitmap()) { loaded_vmcs->msr_bitmap = (unsigned long *) @@ -2947,6 +2967,8 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return vmx_eptp_page_walk_level(nested_ept_get_eptp(vcpu)); if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -2966,7 +2988,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) return eptp; } -void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; @@ -2978,7 +3000,7 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) eptp = construct_eptp(vcpu, cr3); vmcs_write64(EPT_POINTER, eptp); - if (kvm_x86_ops->tlb_remote_flush) { + if (kvm_x86_ops.tlb_remote_flush) { spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); to_vmx(vcpu)->ept_pointer = eptp; to_kvm_vmx(kvm)->ept_pointers_match @@ -3815,24 +3837,29 @@ 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; } /* @@ -3978,7 +4005,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX); if (!cpu_need_virtualize_apic_accesses(vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; @@ -4033,7 +4060,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } } - if (vmx_rdtscp_supported()) { + if (cpu_has_vmx_rdtscp()) { bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP); if (!rdtscp_enabled) exec_control &= ~SECONDARY_EXEC_RDTSCP; @@ -4048,7 +4075,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } } - if (vmx_invpcid_supported()) { + if (cpu_has_vmx_invpcid()) { /* Exposing INVPCID only when PCID is exposed */ bool invpcid_enabled = guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) && @@ -4219,7 +4246,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (cpu_has_vmx_encls_vmexit()) vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); - if (pt_mode == PT_MODE_HOST_GUEST) { + if (vmx_pt_mode_is_host_guest()) { memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc)); /* Bit[6~0] are forced to 1, writes are ignored. */ vmx->pt_desc.guest.output_mask = 0x7F; @@ -4238,7 +4265,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->msr_ia32_umwait_control = 0; - vcpu->arch.microcode_version = 0x100000000ULL; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); @@ -4448,8 +4474,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - return (!to_vmx(vcpu)->nested.nested_run_pending && - vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + if (to_vmx(vcpu)->nested.nested_run_pending) + return false; + + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) + return true; + + return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } @@ -4505,7 +4536,6 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) case GP_VECTOR: case MF_VECTOR: return true; - break; } return false; } @@ -5282,7 +5312,6 @@ static void vmx_enable_tdp(void) VMX_EPT_RWX_MASK, 0ull); ept_set_mmio_spte_mask(); - kvm_enable_tdp(); } /* @@ -5815,8 +5844,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason)) - return nested_vmx_reflect_vmexit(vcpu, exit_reason); + if (is_guest_mode(vcpu)) { + /* + * The host physical addresses of some pages of guest memory + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + + if (nested_vmx_exit_reflected(vcpu, exit_reason)) + return nested_vmx_reflect_vmexit(vcpu, exit_reason); + } if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { dump_vmcs(); @@ -6176,15 +6220,13 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); /* if exit due to PF check for async PF */ - if (is_page_fault(vmx->exit_intr_info)) + if (is_page_fault(vmx->exit_intr_info)) { vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); - /* Handle machine checks before interrupts are enabled */ - if (is_machine_check(vmx->exit_intr_info)) + } else if (is_machine_check(vmx->exit_intr_info)) { kvm_machine_check(); - /* We need to handle NMIs before interrupts are enabled */ - if (is_nmi(vmx->exit_intr_info)) { + } else if (is_nmi(vmx->exit_intr_info)) { kvm_before_interrupt(&vmx->vcpu); asm("int $2"); kvm_after_interrupt(&vmx->vcpu); @@ -6228,7 +6270,7 @@ 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) ); @@ -6270,11 +6312,6 @@ static bool vmx_has_emulated_msr(int index) } } -static bool vmx_pt_supported(void) -{ - return pt_mode == PT_MODE_HOST_GUEST; -} - static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -6480,8 +6517,11 @@ 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]); @@ -6517,7 +6557,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_enter(vmx); - atomic_switch_perf_msrs(vmx); + if (vcpu_to_pmu(vcpu)->version) + atomic_switch_perf_msrs(vmx); atomic_switch_umwait_control_msr(vmx); if (enable_preemption_timer) @@ -6634,20 +6675,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_complete_interrupts(vmx); } -static struct kvm *vmx_vm_alloc(void) -{ - struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), - GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); - return &kvm_vmx->kvm; -} - -static void vmx_vm_free(struct kvm *kvm) -{ - kfree(kvm->arch.hyperv.hv_pa_pg); - vfree(to_kvm_vmx(kvm)); -} - static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6755,14 +6782,14 @@ 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)); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; + vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* @@ -6836,8 +6863,7 @@ 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()); @@ -6851,17 +6877,24 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) u8 cache; u64 ipat = 0; - /* For VT-d and EPT combination - * 1. MMIO: always map as UC - * 2. EPT with VT-d: - * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. - * b. VT-d with snooping control feature: snooping control feature of - * VT-d engine can guarantee the cache correctness. Just set it - * to WB to keep consistent with host. So the same as item 3. - * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep - * consistent with host MTRR + /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in + * memory aliases with conflicting memory types and sometimes MCEs. + * We have to be careful as to what are honored and when. + * + * For MMIO, guest CD/MTRR are ignored. The EPT memory type is set to + * UC. The effective memory type is UC or WC depending on guest PAT. + * This was historically the source of MCEs and we want to be + * conservative. + * + * When there is no need to deal with noncoherent DMA (e.g., no VT-d + * or VT-d has snoop control), guest CD/MTRR/PAT are all ignored. The + * EPT memory type is set to WB. The effective memory type is forced + * WB. + * + * Otherwise, we trust guest. Guest CD/MTRR/PAT are all honored. The + * EPT memory type is used to emulate guest CD/MTRR. */ + if (is_mmio) { cache = MTRR_TYPE_UNCACHABLE; goto exit; @@ -6888,15 +6921,6 @@ exit: return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; } -static int vmx_get_lpage_level(void) -{ - if (enable_ept && !cpu_has_vmx_ept_1g_page()) - return PT_DIRECTORY_LEVEL; - else - /* For shadow and EPT supported 1GB page */ - return PT_PDPE_LEVEL; -} - static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx) { /* @@ -7087,10 +7111,37 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) } } -static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) +static __init void vmx_set_cpu_caps(void) { - if (func == 1 && nested) - entry->ecx |= feature_bit(VMX); + kvm_set_cpu_caps(); + + /* CPUID 0x1 */ + if (nested) + kvm_cpu_cap_set(X86_FEATURE_VMX); + + /* CPUID 0x7 */ + if (kvm_mpx_supported()) + kvm_cpu_cap_check_and_set(X86_FEATURE_MPX); + if (cpu_has_vmx_invpcid()) + kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID); + if (vmx_pt_mode_is_host_guest()) + kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); + + /* PKU is not yet implemented for shadow paging. */ + if (enable_ept && boot_cpu_has(X86_FEATURE_OSPKE)) + kvm_cpu_cap_check_and_set(X86_FEATURE_PKU); + + if (vmx_umip_emulated()) + kvm_cpu_cap_set(X86_FEATURE_UMIP); + + /* CPUID 0xD.1 */ + supported_xss = 0; + if (!vmx_xsaves_supported()) + kvm_cpu_cap_clear(X86_FEATURE_XSAVES); + + /* CPUID 0x80000001 */ + if (!cpu_has_vmx_rdtscp()) + kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); } static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -7098,26 +7149,86 @@ 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) + enum x86_intercept_stage stage, + struct x86_exception *exception) { 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)) { + exception->vector = UD_VECTOR; + 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 @@ -7198,7 +7309,8 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) static void vmx_slot_enable_log_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); + if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) + kvm_mmu_slot_leaf_clear_dirty(kvm, slot); kvm_mmu_slot_largepage_remove_write_access(kvm, slot); } @@ -7381,7 +7493,7 @@ static void pi_post_block(struct kvm_vcpu *vcpu) static void vmx_post_block(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->set_hv_timer) + if (kvm_x86_ops.set_hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); pi_post_block(vcpu); @@ -7548,13 +7660,164 @@ static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->nested.vmxon; } +static void hardware_unsetup(void) +{ + if (nested) + nested_vmx_hardware_unsetup(); + + free_kvm_area(); +} + +static bool vmx_check_apicv_inhibit_reasons(ulong bit) +{ + ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_HYPERV); + + return supported & BIT(bit); +} + +static struct kvm_x86_ops vmx_x86_ops __initdata = { + .hardware_unsetup = hardware_unsetup, + + .hardware_enable = hardware_enable, + .hardware_disable = hardware_disable, + .cpu_has_accelerated_tpr = report_flexpriority, + .has_emulated_msr = vmx_has_emulated_msr, + + .vm_size = sizeof(struct kvm_vmx), + .vm_init = vmx_vm_init, + + .vcpu_create = vmx_create_vcpu, + .vcpu_free = vmx_free_vcpu, + .vcpu_reset = vmx_vcpu_reset, + + .prepare_guest_switch = vmx_prepare_switch_to_guest, + .vcpu_load = vmx_vcpu_load, + .vcpu_put = vmx_vcpu_put, + + .update_bp_intercept = update_exception_bitmap, + .get_msr_feature = vmx_get_msr_feature, + .get_msr = vmx_get_msr, + .set_msr = vmx_set_msr, + .get_segment_base = vmx_get_segment_base, + .get_segment = vmx_get_segment, + .set_segment = vmx_set_segment, + .get_cpl = vmx_get_cpl, + .get_cs_db_l_bits = vmx_get_cs_db_l_bits, + .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, + .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, + .set_cr0 = vmx_set_cr0, + .set_cr4 = vmx_set_cr4, + .set_efer = vmx_set_efer, + .get_idt = vmx_get_idt, + .set_idt = vmx_set_idt, + .get_gdt = vmx_get_gdt, + .set_gdt = vmx_set_gdt, + .get_dr6 = vmx_get_dr6, + .set_dr6 = vmx_set_dr6, + .set_dr7 = vmx_set_dr7, + .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, + .cache_reg = vmx_cache_reg, + .get_rflags = vmx_get_rflags, + .set_rflags = vmx_set_rflags, + + .tlb_flush = vmx_flush_tlb, + .tlb_flush_gva = vmx_flush_tlb_gva, + + .run = vmx_vcpu_run, + .handle_exit = vmx_handle_exit, + .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, + .set_irq = vmx_inject_irq, + .set_nmi = vmx_inject_nmi, + .queue_exception = vmx_queue_exception, + .cancel_injection = vmx_cancel_injection, + .interrupt_allowed = vmx_interrupt_allowed, + .nmi_allowed = vmx_nmi_allowed, + .get_nmi_mask = vmx_get_nmi_mask, + .set_nmi_mask = vmx_set_nmi_mask, + .enable_nmi_window = enable_nmi_window, + .enable_irq_window = enable_irq_window, + .update_cr8_intercept = update_cr8_intercept, + .set_virtual_apic_mode = vmx_set_virtual_apic_mode, + .set_apic_access_page_addr = vmx_set_apic_access_page_addr, + .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, + .load_eoi_exitmap = vmx_load_eoi_exitmap, + .apicv_post_state_restore = vmx_apicv_post_state_restore, + .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, + .hwapic_irr_update = vmx_hwapic_irr_update, + .hwapic_isr_update = vmx_hwapic_isr_update, + .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, + .sync_pir_to_irr = vmx_sync_pir_to_irr, + .deliver_posted_interrupt = vmx_deliver_posted_interrupt, + .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, + + .set_tss_addr = vmx_set_tss_addr, + .set_identity_map_addr = vmx_set_identity_map_addr, + .get_tdp_level = get_ept_level, + .get_mt_mask = vmx_get_mt_mask, + + .get_exit_info = vmx_get_exit_info, + + .cpuid_update = vmx_cpuid_update, + + .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + + .read_l1_tsc_offset = vmx_read_l1_tsc_offset, + .write_l1_tsc_offset = vmx_write_l1_tsc_offset, + + .load_mmu_pgd = vmx_load_mmu_pgd, + + .check_intercept = vmx_check_intercept, + .handle_exit_irqoff = vmx_handle_exit_irqoff, + + .request_immediate_exit = vmx_request_immediate_exit, + + .sched_in = vmx_sched_in, + + .slot_enable_log_dirty = vmx_slot_enable_log_dirty, + .slot_disable_log_dirty = vmx_slot_disable_log_dirty, + .flush_log_dirty = vmx_flush_log_dirty, + .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + .write_log_dirty = vmx_write_pml_buffer, + + .pre_block = vmx_pre_block, + .post_block = vmx_post_block, + + .pmu_ops = &intel_pmu_ops, + + .update_pi_irte = vmx_update_pi_irte, + +#ifdef CONFIG_X86_64 + .set_hv_timer = vmx_set_hv_timer, + .cancel_hv_timer = vmx_cancel_hv_timer, +#endif + + .setup_mce = vmx_setup_mce, + + .smi_allowed = vmx_smi_allowed, + .pre_enter_smm = vmx_pre_enter_smm, + .pre_leave_smm = vmx_pre_leave_smm, + .enable_smi_window = enable_smi_window, + + .check_nested_events = NULL, + .get_nested_state = NULL, + .set_nested_state = NULL, + .get_vmcs12_pages = NULL, + .nested_enable_evmcs = NULL, + .nested_get_evmcs_version = NULL, + .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, + .apic_init_signal_blocked = vmx_apic_init_signal_blocked, +}; + static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, i; - - rdmsrl_safe(MSR_EFER, &host_efer); + int r, i, ept_lpage_level; store_idt(&dt); host_idt_base = dt.address; @@ -7573,6 +7836,10 @@ static __init int hardware_setup(void) WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); } + if (!cpu_has_vmx_mpx()) + supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | + XFEATURE_MASK_BNDCSR); + if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; @@ -7601,19 +7868,16 @@ static __init int hardware_setup(void) * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) - kvm_x86_ops->set_apic_access_page_addr = NULL; + vmx_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) - kvm_x86_ops->update_cr8_intercept = NULL; - - if (enable_ept && !cpu_has_vmx_ept_2m_page()) - kvm_disable_largepages(); + vmx_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - kvm_x86_ops->tlb_remote_flush = hv_remote_flush_tlb; - kvm_x86_ops->tlb_remote_flush_with_range = + vmx_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; + vmx_x86_ops.tlb_remote_flush_with_range = hv_remote_flush_tlb_with_range; } #endif @@ -7628,7 +7892,7 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) { enable_apicv = 0; - kvm_x86_ops->sync_pir_to_irr = NULL; + vmx_x86_ops.sync_pir_to_irr = NULL; } if (cpu_has_vmx_tsc_scaling()) { @@ -7641,8 +7905,16 @@ static __init int hardware_setup(void) if (enable_ept) vmx_enable_tdp(); + + if (!enable_ept) + ept_lpage_level = 0; + else if (cpu_has_vmx_ept_1g_page()) + ept_lpage_level = PT_PDPE_LEVEL; + else if (cpu_has_vmx_ept_2m_page()) + ept_lpage_level = PT_DIRECTORY_LEVEL; else - kvm_disable_tdp(); + ept_lpage_level = PT_PAGE_TABLE_LEVEL; + kvm_configure_mmu(enable_ept, ept_lpage_level); /* * Only enable PML when hardware supports PML feature, and both EPT @@ -7652,10 +7924,10 @@ static __init int hardware_setup(void) enable_pml = 0; if (!enable_pml) { - kvm_x86_ops->slot_enable_log_dirty = NULL; - kvm_x86_ops->slot_disable_log_dirty = NULL; - kvm_x86_ops->flush_log_dirty = NULL; - kvm_x86_ops->enable_log_dirty_pt_masked = NULL; + vmx_x86_ops.slot_enable_log_dirty = NULL; + vmx_x86_ops.slot_disable_log_dirty = NULL; + vmx_x86_ops.flush_log_dirty = NULL; + vmx_x86_ops.enable_log_dirty_pt_masked = NULL; } if (!cpu_has_vmx_preemption_timer()) @@ -7683,9 +7955,9 @@ static __init int hardware_setup(void) } if (!enable_preemption_timer) { - kvm_x86_ops->set_hv_timer = NULL; - kvm_x86_ops->cancel_hv_timer = NULL; - kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; + vmx_x86_ops.set_hv_timer = NULL; + vmx_x86_ops.cancel_hv_timer = NULL; + vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } kvm_set_posted_intr_wakeup_handler(wakeup_handler); @@ -7699,186 +7971,29 @@ 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); + r = nested_vmx_hardware_setup(&vmx_x86_ops, + kvm_vmx_exit_handlers); if (r) return r; } + vmx_set_cpu_caps(); + r = alloc_kvm_area(); if (r) nested_vmx_hardware_unsetup(); return r; } -static __exit void hardware_unsetup(void) -{ - if (nested) - nested_vmx_hardware_unsetup(); - - free_kvm_area(); -} - -static bool vmx_check_apicv_inhibit_reasons(ulong bit) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_HYPERV); - - return supported & BIT(bit); -} - -static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { +static struct kvm_x86_init_ops vmx_init_ops __initdata = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, - .hardware_setup = hardware_setup, - .hardware_unsetup = hardware_unsetup, .check_processor_compatibility = vmx_check_processor_compat, - .hardware_enable = hardware_enable, - .hardware_disable = hardware_disable, - .cpu_has_accelerated_tpr = report_flexpriority, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_init = vmx_vm_init, - .vm_alloc = vmx_vm_alloc, - .vm_free = vmx_vm_free, - - .vcpu_create = vmx_create_vcpu, - .vcpu_free = vmx_free_vcpu, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_guest_switch = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .update_bp_intercept = update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, - .set_cr0 = vmx_set_cr0, - .set_cr3 = vmx_set_cr3, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .get_dr6 = vmx_get_dr6, - .set_dr6 = vmx_set_dr6, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - - .tlb_flush = vmx_flush_tlb, - .tlb_flush_gva = vmx_flush_tlb_gva, - - .run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .set_irq = vmx_inject_irq, - .set_nmi = vmx_inject_nmi, - .queue_exception = vmx_queue_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = enable_nmi_window, - .enable_irq_window = enable_irq_window, - .update_cr8_intercept = update_cr8_intercept, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, - .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_posted_interrupt = vmx_deliver_posted_interrupt, - .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_tdp_level = get_ept_level, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .get_lpage_level = vmx_get_lpage_level, - - .cpuid_update = vmx_cpuid_update, - - .rdtscp_supported = vmx_rdtscp_supported, - .invpcid_supported = vmx_invpcid_supported, - - .set_supported_cpuid = vmx_set_supported_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .read_l1_tsc_offset = vmx_read_l1_tsc_offset, - .write_l1_tsc_offset = vmx_write_l1_tsc_offset, - - .set_tdp_cr3 = vmx_set_cr3, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - .mpx_supported = vmx_mpx_supported, - .xsaves_supported = vmx_xsaves_supported, - .umip_emulated = vmx_umip_emulated, - .pt_supported = vmx_pt_supported, - .pku_supported = vmx_pku_supported, - - .request_immediate_exit = vmx_request_immediate_exit, - - .sched_in = vmx_sched_in, - - .slot_enable_log_dirty = vmx_slot_enable_log_dirty, - .slot_disable_log_dirty = vmx_slot_disable_log_dirty, - .flush_log_dirty = vmx_flush_log_dirty, - .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, - .write_log_dirty = vmx_write_pml_buffer, - - .pre_block = vmx_pre_block, - .post_block = vmx_post_block, - - .pmu_ops = &intel_pmu_ops, - - .update_pi_irte = vmx_update_pi_irte, - -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif - - .setup_mce = vmx_setup_mce, - - .smi_allowed = vmx_smi_allowed, - .pre_enter_smm = vmx_pre_enter_smm, - .pre_leave_smm = vmx_pre_leave_smm, - .enable_smi_window = enable_smi_window, + .hardware_setup = hardware_setup, - .check_nested_events = NULL, - .get_nested_state = NULL, - .set_nested_state = NULL, - .get_vmcs12_pages = NULL, - .nested_enable_evmcs = NULL, - .nested_get_evmcs_version = NULL, - .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, + .runtime_ops = &vmx_x86_ops, }; static void vmx_cleanup_l1d_flush(void) @@ -7965,7 +8080,7 @@ static int __init vmx_init(void) } #endif - r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), + r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) return r; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f42cf3dcd70..aab9df55336e 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -12,9 +12,6 @@ #include "vmcs.h" extern const u32 vmx_msr_index[]; -extern u64 host_efer; - -extern u32 get_umwait_control_msr(void); #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -150,6 +147,9 @@ 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; /* @@ -332,9 +332,9 @@ u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask); void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer); void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); void set_cr4_guest_host_mask(struct vcpu_vmx *vmx); +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3); void ept_save_pdptrs(struct kvm_vcpu *vcpu); void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -449,7 +449,7 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static inline u32 vmx_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ @@ -460,7 +460,7 @@ static inline u32 vmx_vmentry_ctrl(void) static inline u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ @@ -490,7 +490,6 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags); void free_vmcs(struct vmcs *vmcs); int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); -void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs); void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs); static inline struct vmcs *alloc_vmcs(bool shadow) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fbabb2f06273..b8124b562dea 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -22,6 +22,7 @@ #include "i8254.h" #include "tss.h" #include "kvm_cache_regs.h" +#include "kvm_emulate.h" #include "x86.h" #include "cpuid.h" #include "pmu.h" @@ -81,7 +82,7 @@ u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); #define emul_to_vcpu(ctxt) \ - container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt) + ((struct kvm_vcpu *)(ctxt)->vcpu) /* EFER defaults: * - enable syscall per default because its emulated by KVM @@ -109,7 +110,7 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); -struct kvm_x86_ops *kvm_x86_ops __read_mostly; +struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); static bool __read_mostly ignore_msrs = 0; @@ -180,7 +181,17 @@ struct kvm_shared_msrs { static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; static struct kvm_shared_msrs __percpu *shared_msrs; +#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ + | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ + | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ + | XFEATURE_MASK_PKRU) + +u64 __read_mostly host_efer; +EXPORT_SYMBOL_GPL(host_efer); + static u64 __read_mostly host_xss; +u64 __read_mostly supported_xss; +EXPORT_SYMBOL_GPL(supported_xss); struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, @@ -226,10 +237,25 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { }; u64 __read_mostly host_xcr0; +u64 __read_mostly supported_xcr0; +EXPORT_SYMBOL_GPL(supported_xcr0); struct kmem_cache *x86_fpu_cache; EXPORT_SYMBOL_GPL(x86_fpu_cache); +static struct kmem_cache *x86_emulator_cache; + +static struct kmem_cache *kvm_alloc_emulator_cache(void) +{ + unsigned int useroffset = offsetof(struct x86_emulate_ctxt, src); + unsigned int size = sizeof(struct x86_emulate_ctxt); + + return kmem_cache_create_usercopy("x86_emulator", size, + __alignof__(struct x86_emulate_ctxt), + SLAB_ACCOUNT, useroffset, + size - useroffset, NULL); +} + static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) @@ -350,6 +376,7 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } kvm_lapic_set_base(vcpu, msr_info->data); + kvm_recalculate_apic_map(vcpu->kvm); return 0; } EXPORT_SYMBOL_GPL(kvm_set_apic_base); @@ -438,6 +465,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * for #DB exceptions under VMX. */ vcpu->arch.dr6 ^= payload & DR6_RTM; + + /* + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. + */ + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = payload; @@ -490,19 +525,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; - /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). However, for ABI - * compatibility with KVM_GET_VCPU_EVENTS and - * KVM_SET_VCPU_EVENTS, we can't delay payload - * delivery unless userspace has enabled this - * functionality via the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD. - */ - if (!vcpu->kvm->arch.exception_payload_enabled || - !is_guest_mode(vcpu)) + if (!is_guest_mode(vcpu)) kvm_deliver_exception_payload(vcpu); return; } @@ -623,7 +646,7 @@ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { - if (kvm_x86_ops->get_cpl(vcpu) <= required_cpl) + if (kvm_x86_ops.get_cpl(vcpu) <= required_cpl) return true; kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; @@ -764,7 +787,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!is_pae(vcpu)) return 1; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); if (cs_l) return 1; } else @@ -777,7 +800,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) return 1; - kvm_x86_ops->set_cr0(vcpu, cr0); + kvm_x86_ops.set_cr0(vcpu, cr0); if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); @@ -873,7 +896,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - if (kvm_x86_ops->get_cpl(vcpu) != 0 || + if (kvm_x86_ops.get_cpl(vcpu) != 0 || __kvm_set_xcr(vcpu, index, xcr)) { kvm_inject_gp(vcpu, 0); return 1; @@ -907,10 +930,10 @@ static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) { u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - if (cpuid_ecx(0x7) & feature_bit(LA57)) + if (kvm_cpu_cap_has(X86_FEATURE_LA57)) reserved_bits &= ~X86_CR4_LA57; - if (kvm_x86_ops->umip_emulated()) + if (kvm_cpu_cap_has(X86_FEATURE_UMIP)) reserved_bits &= ~X86_CR4_UMIP; return reserved_bits; @@ -954,7 +977,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } - if (kvm_x86_ops->set_cr4(vcpu, cr4)) + if (kvm_x86_ops.set_cr4(vcpu, cr4)) return 1; if (((cr4 ^ old_cr4) & pdptr_bits) || @@ -1038,7 +1061,7 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu) static void kvm_update_dr6(struct kvm_vcpu *vcpu) { if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - kvm_x86_ops->set_dr6(vcpu, vcpu->arch.dr6); + kvm_x86_ops.set_dr6(vcpu, vcpu->arch.dr6); } static void kvm_update_dr7(struct kvm_vcpu *vcpu) @@ -1049,7 +1072,7 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; - kvm_x86_ops->set_dr7(vcpu, dr7); + kvm_x86_ops.set_dr7(vcpu, dr7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; @@ -1119,7 +1142,7 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) *val = vcpu->arch.dr6; else - *val = kvm_x86_ops->get_dr6(vcpu); + *val = kvm_x86_ops.get_dr6(vcpu); break; case 5: /* fall through */ @@ -1354,7 +1377,7 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) rdmsrl_safe(msr->index, &msr->data); break; default: - if (kvm_x86_ops->get_msr_feature(msr)) + if (kvm_x86_ops.get_msr_feature(msr)) return 1; } return 0; @@ -1422,7 +1445,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; - kvm_x86_ops->set_efer(vcpu, efer); + kvm_x86_ops.set_efer(vcpu, efer); /* Update reserved bits */ if ((efer ^ old_efer) & EFER_NX) @@ -1478,7 +1501,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, msr.index = index; msr.host_initiated = host_initiated; - return kvm_x86_ops->set_msr(vcpu, &msr); + return kvm_x86_ops.set_msr(vcpu, &msr); } /* @@ -1496,7 +1519,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, msr.index = index; msr.host_initiated = host_initiated; - ret = kvm_x86_ops->get_msr(vcpu, &msr); + ret = kvm_x86_ops.get_msr(vcpu, &msr); if (!ret) *data = msr.data; return ret; @@ -1558,12 +1581,19 @@ 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)) { + data &= ~(1 << 12); + kvm_apic_send_ipi(vcpu->arch.apic, (u32)data, (u32)(data >> 32)); kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32)); - return kvm_lapic_reg_write(vcpu->arch.apic, APIC_ICR, (u32)data); + kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR, (u32)data); + trace_kvm_apic_write(APIC_ICR, (u32)data); + return 0; } return 1; @@ -1572,11 +1602,12 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); - u64 data = kvm_read_edx_eax(vcpu); + u64 data; int ret = 0; switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): + data = kvm_read_edx_eax(vcpu); ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); break; default: @@ -1635,7 +1666,7 @@ static void update_pvclock_gtod(struct timekeeper *tk) write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ - vdata->clock.vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->clock.vclock_mode = tk->tkr_mono.clock->vdso_clock_mode; vdata->clock.cycle_last = tk->tkr_mono.cycle_last; vdata->clock.mask = tk->tkr_mono.mask; vdata->clock.mult = tk->tkr_mono.mult; @@ -1643,7 +1674,7 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; vdata->clock.offset = tk->tkr_mono.base; - vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->archdata.vclock_mode; + vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->vdso_clock_mode; vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; vdata->raw_clock.mask = tk->tkr_raw.mask; vdata->raw_clock.mult = tk->tkr_raw.mult; @@ -1844,7 +1875,7 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) static inline int gtod_is_based_on_tsc(int mode) { - return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK; + return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) @@ -1877,7 +1908,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) { - u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + u64 curr_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } @@ -1919,7 +1950,7 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + u64 tsc_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); return tsc_offset + kvm_scale_tsc(vcpu, host_tsc); } @@ -1927,7 +1958,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { - vcpu->arch.tsc_offset = kvm_x86_ops->write_l1_tsc_offset(vcpu, offset); + vcpu->arch.tsc_offset = kvm_x86_ops.write_l1_tsc_offset(vcpu, offset); } static inline bool kvm_check_tsc_unstable(void) @@ -1937,7 +1968,7 @@ static inline bool kvm_check_tsc_unstable(void) * TSC is marked unstable when we're running on Hyper-V, * 'TSC page' clocksource is good. */ - if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK) + if (pvclock_gtod_data.clock.vclock_mode == VDSO_CLOCKMODE_HVCLOCK) return false; #endif return check_tsc_unstable(); @@ -2051,7 +2082,7 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc); static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { - u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + u64 tsc_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } @@ -2092,30 +2123,30 @@ static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, u64 tsc_pg_val; switch (clock->vclock_mode) { - case VCLOCK_HVCLOCK: + case VDSO_CLOCKMODE_HVCLOCK: tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(), tsc_timestamp); if (tsc_pg_val != U64_MAX) { /* TSC page valid */ - *mode = VCLOCK_HVCLOCK; + *mode = VDSO_CLOCKMODE_HVCLOCK; v = (tsc_pg_val - clock->cycle_last) & clock->mask; } else { /* TSC page invalid */ - *mode = VCLOCK_NONE; + *mode = VDSO_CLOCKMODE_NONE; } break; - case VCLOCK_TSC: - *mode = VCLOCK_TSC; + case VDSO_CLOCKMODE_TSC: + *mode = VDSO_CLOCKMODE_TSC; *tsc_timestamp = read_tsc(); v = (*tsc_timestamp - clock->cycle_last) & clock->mask; break; default: - *mode = VCLOCK_NONE; + *mode = VDSO_CLOCKMODE_NONE; } - if (*mode == VCLOCK_NONE) + if (*mode == VDSO_CLOCKMODE_NONE) *tsc_timestamp = v = 0; return v * clock->mult; @@ -2448,7 +2479,6 @@ 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(vcpu->hv_clock.system_time < 0); /* If the host uses TSC clocksource, then it is stable */ pvclock_flags = 0; @@ -2527,7 +2557,7 @@ static void kvmclock_sync_fn(struct work_struct *work) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd(vcpu)) + if (guest_cpuid_is_amd_or_hygon(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; @@ -2649,7 +2679,7 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa); + kvm_x86_ops.tlb_flush(vcpu, invalidate_gpa); } static void record_steal_time(struct kvm_vcpu *vcpu) @@ -2802,12 +2832,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; /* - * We do support PT if kvm_x86_ops->pt_supported(), but we do - * not support IA32_XSS[bit 8]. Guests will have to use - * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT - * MSRs. + * KVM supports exposing PT to the guest, but does not support + * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than + * XSAVES/XRSTORS to save/restore PT MSRs. */ - if (data != 0) + if (data & ~supported_xss) return 1; vcpu->arch.ia32_xss = data; break; @@ -3081,7 +3110,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); - break; case MSR_IA32_TSCDEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; @@ -3164,7 +3192,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); - break; case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow @@ -3369,10 +3396,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE); + r = kvm_x86_ops.has_emulated_msr(MSR_IA32_SMBASE); break; case KVM_CAP_VAPIC: - r = !kvm_x86_ops->cpu_has_accelerated_tpr(); + r = !kvm_x86_ops.cpu_has_accelerated_tpr(); break; case KVM_CAP_NR_VCPUS: r = KVM_SOFT_MAX_VCPUS; @@ -3399,14 +3426,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_X2APIC_API_VALID_FLAGS; break; case KVM_CAP_NESTED_STATE: - r = kvm_x86_ops->get_nested_state ? - kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0; + r = kvm_x86_ops.get_nested_state ? + kvm_x86_ops.get_nested_state(NULL, NULL, 0) : 0; break; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - r = kvm_x86_ops->enable_direct_tlbflush != NULL; + r = kvm_x86_ops.enable_direct_tlbflush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - r = kvm_x86_ops->nested_enable_evmcs != NULL; + r = kvm_x86_ops.nested_enable_evmcs != NULL; break; default: break; @@ -3468,7 +3495,7 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } - case KVM_X86_GET_MCE_CAP_SUPPORTED: { + case KVM_X86_GET_MCE_CAP_SUPPORTED: r = -EFAULT; if (copy_to_user(argp, &kvm_mce_cap_supported, sizeof(kvm_mce_cap_supported))) @@ -3500,9 +3527,9 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; - } default: r = -EINVAL; + break; } out: return r; @@ -3522,14 +3549,14 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { - if (kvm_x86_ops->has_wbinvd_exit()) + if (kvm_x86_ops.has_wbinvd_exit()) cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); else if (vcpu->cpu != -1 && vcpu->cpu != cpu) smp_call_function_single(vcpu->cpu, wbinvd_ipi, NULL, 1); } - kvm_x86_ops->vcpu_load(vcpu, cpu); + kvm_x86_ops.vcpu_load(vcpu, cpu); /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { @@ -3596,7 +3623,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) int idx; if (vcpu->preempted) - vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu); + vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu); /* * Disable page faults because we're in atomic context here. @@ -3615,7 +3642,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvm_steal_time_set_preempted(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); pagefault_enable(); - kvm_x86_ops->vcpu_put(vcpu); + kvm_x86_ops.vcpu_put(vcpu); vcpu->arch.last_host_tsc = rdtsc(); /* * If userspace has set any breakpoints or watchpoints, dr6 is restored @@ -3629,7 +3656,7 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { if (vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_x86_ops.sync_pir_to_irr(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -3737,7 +3764,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; - kvm_x86_ops->setup_mce(vcpu); + kvm_x86_ops.setup_mce(vcpu); out: return r; } @@ -3796,6 +3823,21 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, process_nmi(vcpu); /* + * In guest mode, payload delivery should be deferred, + * so that the L1 hypervisor can intercept #PF before + * CR2 is modified (or intercept #DB before DR6 is + * modified under nVMX). Unless the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of + * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we + * opportunistically defer the exception payload, deliver it if the + * capability hasn't been requested before processing a + * KVM_GET_VCPU_EVENTS. + */ + if (!vcpu->kvm->arch.exception_payload_enabled && + vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) + kvm_deliver_exception_payload(vcpu); + + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception @@ -3826,11 +3868,11 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; events->interrupt.soft = 0; - events->interrupt.shadow = kvm_x86_ops->get_interrupt_shadow(vcpu); + events->interrupt.shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending != 0; - events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + events->nmi.masked = kvm_x86_ops.get_nmi_mask(vcpu); events->nmi.pad = 0; events->sipi_vector = 0; /* never valid when reporting to user space */ @@ -3897,13 +3939,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) - kvm_x86_ops->set_interrupt_shadow(vcpu, + kvm_x86_ops.set_interrupt_shadow(vcpu, events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) vcpu->arch.nmi_pending = events->nmi.pending; - kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + kvm_x86_ops.set_nmi_mask(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) @@ -4090,8 +4132,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility * with old userspace. */ - if (xstate_bv & ~kvm_supported_xcr0() || - mxcsr & ~mxcsr_feature_mask) + if (xstate_bv & ~supported_xcr0 || mxcsr & ~mxcsr_feature_mask) return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { @@ -4178,9 +4219,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops->nested_enable_evmcs) + if (!kvm_x86_ops.nested_enable_evmcs) return -ENOTTY; - r = kvm_x86_ops->nested_enable_evmcs(vcpu, &vmcs_version); + r = kvm_x86_ops.nested_enable_evmcs(vcpu, &vmcs_version); if (!r) { user_ptr = (void __user *)(uintptr_t)cap->args[0]; if (copy_to_user(user_ptr, &vmcs_version, @@ -4189,10 +4230,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, } return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - if (!kvm_x86_ops->enable_direct_tlbflush) + if (!kvm_x86_ops.enable_direct_tlbflush) return -ENOTTY; - return kvm_x86_ops->enable_direct_tlbflush(vcpu); + return kvm_x86_ops.enable_direct_tlbflush(vcpu); default: return -EINVAL; @@ -4495,7 +4536,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_data_size; r = -EINVAL; - if (!kvm_x86_ops->get_nested_state) + if (!kvm_x86_ops.get_nested_state) break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); @@ -4503,7 +4544,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (get_user(user_data_size, &user_kvm_nested_state->size)) break; - r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, + r = kvm_x86_ops.get_nested_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) break; @@ -4525,7 +4566,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, int idx; r = -EINVAL; - if (!kvm_x86_ops->set_nested_state) + if (!kvm_x86_ops.set_nested_state) break; r = -EFAULT; @@ -4547,7 +4588,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + r = kvm_x86_ops.set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } @@ -4591,14 +4632,14 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; - ret = kvm_x86_ops->set_tss_addr(kvm, addr); + ret = kvm_x86_ops.set_tss_addr(kvm, addr); return ret; } static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { - return kvm_x86_ops->set_identity_map_addr(kvm, ident_addr); + return kvm_x86_ops.set_identity_map_addr(kvm, ident_addr); } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, @@ -4750,77 +4791,13 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, return 0; } -/** - * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot - * @kvm: kvm instance - * @log: slot id and address to which we copy the log - * - * Steps 1-4 below provide general overview of dirty page logging. See - * kvm_get_dirty_log_protect() function description for additional details. - * - * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we - * always flush the TLB (step 4) even if previous step failed and the dirty - * bitmap may be corrupt. Regardless of previous outcome the KVM logging API - * does not preclude user space subsequent dirty log read. Flushing TLB ensures - * writes will be marked dirty for next log read. - * - * 1. Take a snapshot of the bit and clear it if needed. - * 2. Write protect the corresponding page. - * 3. Copy the snapshot to the userspace. - * 4. Flush TLB's if needed. - */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - /* * Flush potentially hardware-cached dirty pages to dirty_bitmap. */ - if (kvm_x86_ops->flush_log_dirty) - kvm_x86_ops->flush_log_dirty(kvm); - - r = kvm_get_dirty_log_protect(kvm, log, &flush); - - /* - * All the TLBs can be flushed out of mmu lock, see the comments in - * kvm_mmu_slot_remove_write_access(). - */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->slots_lock); - return r; -} - -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) -{ - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - - /* - * Flush potentially hardware-cached dirty pages to dirty_bitmap. - */ - if (kvm_x86_ops->flush_log_dirty) - kvm_x86_ops->flush_log_dirty(kvm); - - r = kvm_clear_dirty_log_protect(kvm, log, &flush); - - /* - * All the TLBs can be flushed out of mmu lock, see the comments in - * kvm_mmu_slot_remove_write_access(). - */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->slots_lock); - return r; + if (kvm_x86_ops.flush_log_dirty) + kvm_x86_ops.flush_log_dirty(kvm); } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, @@ -5173,8 +5150,8 @@ set_identity_unlock: } case KVM_MEMORY_ENCRYPT_OP: { r = -ENOTTY; - if (kvm_x86_ops->mem_enc_op) - r = kvm_x86_ops->mem_enc_op(kvm, argp); + if (kvm_x86_ops.mem_enc_op) + r = kvm_x86_ops.mem_enc_op(kvm, argp); break; } case KVM_MEMORY_ENCRYPT_REG_REGION: { @@ -5185,8 +5162,8 @@ set_identity_unlock: goto out; r = -ENOTTY; - if (kvm_x86_ops->mem_enc_reg_region) - r = kvm_x86_ops->mem_enc_reg_region(kvm, ®ion); + if (kvm_x86_ops.mem_enc_reg_region) + r = kvm_x86_ops.mem_enc_reg_region(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { @@ -5197,8 +5174,8 @@ set_identity_unlock: goto out; r = -ENOTTY; - if (kvm_x86_ops->mem_enc_unreg_region) - r = kvm_x86_ops->mem_enc_unreg_region(kvm, ®ion); + if (kvm_x86_ops.mem_enc_unreg_region) + r = kvm_x86_ops.mem_enc_unreg_region(kvm, ®ion); break; } case KVM_HYPERV_EVENTFD: { @@ -5249,28 +5226,28 @@ static void kvm_init_msr_list(void) continue; break; case MSR_TSC_AUX: - if (!kvm_x86_ops->rdtscp_supported()) + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) continue; break; case MSR_IA32_RTIT_CTL: case MSR_IA32_RTIT_STATUS: - if (!kvm_x86_ops->pt_supported()) + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) continue; break; case MSR_IA32_RTIT_CR3_MATCH: - if (!kvm_x86_ops->pt_supported() || + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) continue; break; case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: - if (!kvm_x86_ops->pt_supported() || + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) continue; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { - if (!kvm_x86_ops->pt_supported() || + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; @@ -5293,7 +5270,7 @@ static void kvm_init_msr_list(void) } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i])) + if (!kvm_x86_ops.has_emulated_msr(emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; @@ -5356,13 +5333,13 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) static void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops->set_segment(vcpu, var, seg); + kvm_x86_ops.set_segment(vcpu, var, seg); } void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops->get_segment(vcpu, var, seg); + kvm_x86_ops.get_segment(vcpu, var, seg); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, @@ -5382,14 +5359,14 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5397,7 +5374,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5446,7 +5423,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; @@ -5471,7 +5448,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED @@ -5492,7 +5469,7 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = 0; - if (!system && kvm_x86_ops->get_cpl(vcpu) == 3) + if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); @@ -5545,7 +5522,7 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = PFERR_WRITE_MASK; - if (!system && kvm_x86_ops->get_cpl(vcpu) == 3) + if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -5608,7 +5585,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { - u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) + u32 access = ((kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* @@ -5727,7 +5704,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; /* * If the exit was due to a NPF we may already have a GPA. @@ -5736,10 +5713,9 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, * operation using rep will only have the initial GPA from the NPF * occurred. */ - if (vcpu->arch.gpa_available && - emulator_can_use_gpa(ctxt) && - (addr & ~PAGE_MASK) == (vcpu->arch.gpa_val & ~PAGE_MASK)) { - gpa = vcpu->arch.gpa_val; + if (ctxt->gpa_available && emulator_can_use_gpa(ctxt) && + (addr & ~PAGE_MASK) == (ctxt->gpa_val & ~PAGE_MASK)) { + gpa = ctxt->gpa_val; ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write); } else { ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); @@ -5959,11 +5935,9 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, return 0; } -static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, void *val, - unsigned int count) +static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, unsigned int count) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int ret; if (vcpu->arch.pio.count) @@ -5983,20 +5957,33 @@ data_avail: return 0; } -static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, - const void *val, unsigned int count) +static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + return emulator_pio_in(emul_to_vcpu(ctxt), size, port, val, count); +} + +static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, const void *val, + unsigned int count) +{ memcpy(vcpu->arch.pio_data, val, size * count); trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } +static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, + const void *val, unsigned int count) +{ + return emulator_pio_out(emul_to_vcpu(ctxt), size, port, val, count); +} + static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { - return kvm_x86_ops->get_segment_base(vcpu, seg); + return kvm_x86_ops.get_segment_base(vcpu, seg); } static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) @@ -6009,7 +5996,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; - if (kvm_x86_ops->has_wbinvd_exit()) { + if (kvm_x86_ops.has_wbinvd_exit()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); @@ -6114,27 +6101,27 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { - return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); + return kvm_x86_ops.get_cpl(emul_to_vcpu(ctxt)); } static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->get_gdt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.get_gdt(emul_to_vcpu(ctxt), dt); } static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->get_idt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.get_idt(emul_to_vcpu(ctxt), dt); } static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->set_gdt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.set_gdt(emul_to_vcpu(ctxt), dt); } static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->set_idt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.set_idt(emul_to_vcpu(ctxt), dt); } static unsigned long emulator_get_cached_segment_base( @@ -6256,13 +6243,15 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); + return kvm_x86_ops.check_intercept(emul_to_vcpu(ctxt), info, stage, + &ctxt->exception); } static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, + bool exact_only) { - return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit); + return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only); } static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt) @@ -6292,7 +6281,7 @@ static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulon static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { - kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked); + kvm_x86_ops.set_nmi_mask(emul_to_vcpu(ctxt), masked); } static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) @@ -6308,7 +6297,7 @@ static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_fla static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, const char *smstate) { - return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate); + return kvm_x86_ops.pre_leave_smm(emul_to_vcpu(ctxt), smstate); } static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) @@ -6370,7 +6359,7 @@ static const struct x86_emulate_ops emulate_ops = { static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { - u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu); + u32 int_shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); /* * an sti; sti; sequence only disable interrupts for the first * instruction. So, if the last instruction, be it emulated or @@ -6381,7 +6370,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { - kvm_x86_ops->set_interrupt_shadow(vcpu, mask); + kvm_x86_ops.set_interrupt_shadow(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -6389,7 +6378,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) static bool inject_emulated_exception(struct kvm_vcpu *vcpu) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; if (ctxt->exception.vector == PF_VECTOR) return kvm_propagate_fault(vcpu, &ctxt->exception); @@ -6401,13 +6390,31 @@ static bool inject_emulated_exception(struct kvm_vcpu *vcpu) return false; } +static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt; + + ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); + if (!ctxt) { + pr_err("kvm: failed to allocate vcpu's emulator\n"); + return NULL; + } + + ctxt->vcpu = vcpu; + ctxt->ops = &emulate_ops; + vcpu->arch.emulate_ctxt = ctxt; + + return ctxt; +} + static void init_emulate_ctxt(struct kvm_vcpu *vcpu) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + ctxt->gpa_available = false; ctxt->eflags = kvm_get_rflags(vcpu); ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; @@ -6427,7 +6434,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); @@ -6466,7 +6473,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) kvm_queue_exception(vcpu, UD_VECTOR); - if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { + if (!is_guest_mode(vcpu) && kvm_x86_ops.get_cpl(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; @@ -6483,10 +6490,11 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu))) + if (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) return false; if (!vcpu->arch.mmu->direct_map) { @@ -6574,10 +6582,11 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, */ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu))) + if (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) return false; if (x86_page_table_writing_insn(ctxt)) @@ -6645,10 +6654,10 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); int r; - r = kvm_x86_ops->skip_emulated_instruction(vcpu); + r = kvm_x86_ops.skip_emulated_instruction(vcpu); if (unlikely(!r)) return 0; @@ -6740,7 +6749,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len) { int r; - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; @@ -6830,8 +6839,19 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } restart: - /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2_or_gpa; + if (emulation_type & EMULTYPE_PF) { + /* Save the faulting GPA (cr2) in the address field */ + ctxt->exception.address = cr2_or_gpa; + + /* With shadow page tables, cr2 contains a GVA or nGPA. */ + if (vcpu->arch.mmu->direct_map) { + ctxt->gpa_available = true; + ctxt->gpa_val = cr2_or_gpa; + } + } else { + /* Sanitize the address out of an abundance of paranoia. */ + ctxt->exception.address = 0; + } r = x86_emulate_insn(ctxt); @@ -6872,7 +6892,7 @@ restart: r = 1; if (writeback) { - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; if (!ctxt->have_exception || @@ -6880,6 +6900,8 @@ 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); } @@ -6930,8 +6952,8 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_rax_read(vcpu); - int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, - size, port, &val, 1); + int ret = emulator_pio_out(vcpu, size, port, &val, 1); + if (ret) return ret; @@ -6967,11 +6989,10 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0; /* - * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform + * Since vcpu->arch.pio.count == 1 let emulator_pio_in perform * the copy and tracing */ - emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size, - vcpu->arch.pio.port, &val, 1); + emulator_pio_in(vcpu, vcpu->arch.pio.size, vcpu->arch.pio.port, &val, 1); kvm_rax_write(vcpu, val); return kvm_skip_emulated_instruction(vcpu); @@ -6986,8 +7007,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, /* For size less than 4 we merge, else we zero extend */ val = (size < 4) ? kvm_rax_read(vcpu) : 0; - ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port, - &val, 1); + ret = emulator_pio_in(vcpu, size, port, &val, 1); if (ret) { kvm_rax_write(vcpu, val); return ret; @@ -7177,14 +7197,16 @@ 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, @@ -7208,7 +7230,7 @@ static int kvm_is_user_mode(void) int user_mode = 3; if (__this_cpu_read(current_vcpu)) - user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu)); + user_mode = kvm_x86_ops.get_cpl(__this_cpu_read(current_vcpu)); return user_mode != 0; } @@ -7285,22 +7307,22 @@ static struct notifier_block pvclock_gtod_notifier = { int kvm_arch_init(void *opaque) { + struct kvm_x86_init_ops *ops = opaque; int r; - struct kvm_x86_ops *ops = opaque; - if (kvm_x86_ops) { + if (kvm_x86_ops.hardware_enable) { printk(KERN_ERR "kvm: already loaded the other module\n"); r = -EEXIST; goto out; } 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; } @@ -7325,18 +7347,22 @@ int kvm_arch_init(void *opaque) goto out; } + x86_emulator_cache = kvm_alloc_emulator_cache(); + if (!x86_emulator_cache) { + pr_err("kvm: failed to allocate cache for x86 emulator\n"); + goto out_free_x86_fpu_cache; + } + shared_msrs = alloc_percpu(struct kvm_shared_msrs); if (!shared_msrs) { printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n"); - goto out_free_x86_fpu_cache; + goto out_free_x86_emulator_cache; } r = kvm_mmu_module_init(); if (r) goto out_free_percpu; - kvm_x86_ops = ops; - kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, PT_PRESENT_MASK, 0, sme_me_mask); @@ -7344,8 +7370,10 @@ int kvm_arch_init(void *opaque) perf_register_guest_info_callbacks(&kvm_guest_cbs); - if (boot_cpu_has(X86_FEATURE_XSAVE)) + if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; + } kvm_lapic_init(); if (pi_inject_timer == -1) @@ -7361,6 +7389,8 @@ int kvm_arch_init(void *opaque) out_free_percpu: free_percpu(shared_msrs); +out_free_x86_emulator_cache: + kmem_cache_destroy(x86_emulator_cache); out_free_x86_fpu_cache: kmem_cache_destroy(x86_fpu_cache); out: @@ -7383,7 +7413,7 @@ void kvm_arch_exit(void) #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); #endif - kvm_x86_ops = NULL; + kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(shared_msrs); kmem_cache_destroy(x86_fpu_cache); @@ -7521,7 +7551,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (kvm_x86_ops->get_cpl(vcpu) != 0) { + if (kvm_x86_ops.get_cpl(vcpu) != 0) { ret = -KVM_EPERM; goto out; } @@ -7567,7 +7597,7 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); - kvm_x86_ops->patch_hypercall(vcpu, instruction); + kvm_x86_ops.patch_hypercall(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); @@ -7596,7 +7626,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) { int max_irr, tpr; - if (!kvm_x86_ops->update_cr8_intercept) + if (!kvm_x86_ops.update_cr8_intercept) return; if (!lapic_in_kernel(vcpu)) @@ -7615,17 +7645,17 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) tpr = kvm_lapic_get_cr8(vcpu); - kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); + kvm_x86_ops.update_cr8_intercept(vcpu, tpr, max_irr); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) +static int inject_pending_event(struct kvm_vcpu *vcpu) { int r; /* try to reinject previous events if any */ if (vcpu->arch.exception.injected) - kvm_x86_ops->queue_exception(vcpu); + kvm_x86_ops.queue_exception(vcpu); /* * Do not inject an NMI or interrupt if there is a pending * exception. Exceptions and interrupts are recognized at @@ -7642,9 +7672,9 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) */ else if (!vcpu->arch.exception.pending) { if (vcpu->arch.nmi_injected) - kvm_x86_ops->set_nmi(vcpu); + kvm_x86_ops.set_nmi(vcpu); else if (vcpu->arch.interrupt.injected) - kvm_x86_ops->set_irq(vcpu); + kvm_x86_ops.set_irq(vcpu); } /* @@ -7653,8 +7683,8 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * from L2 to L1 due to pending L1 events which require exit * from L2 to L1. */ - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) { + r = kvm_x86_ops.check_nested_events(vcpu); if (r != 0) return r; } @@ -7691,7 +7721,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } } - kvm_x86_ops->queue_exception(vcpu); + kvm_x86_ops.queue_exception(vcpu); } /* Don't consider new event if we re-injected an event */ @@ -7699,14 +7729,14 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) return 0; if (vcpu->arch.smi_pending && !is_smm(vcpu) && - kvm_x86_ops->smi_allowed(vcpu)) { + kvm_x86_ops.smi_allowed(vcpu)) { vcpu->arch.smi_pending = false; ++vcpu->arch.smi_count; enter_smm(vcpu); - } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + } else if (vcpu->arch.nmi_pending && kvm_x86_ops.nmi_allowed(vcpu)) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); + kvm_x86_ops.set_nmi(vcpu); } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* * Because interrupts can be injected asynchronously, we are @@ -7715,15 +7745,15 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * proposal and current concerns. Perhaps we should be setting * KVM_REQ_EVENT only on certain events and not unconditionally? */ - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) { + r = kvm_x86_ops.check_nested_events(vcpu); if (r != 0) return r; } - if (kvm_x86_ops->interrupt_allowed(vcpu)) { + if (kvm_x86_ops.interrupt_allowed(vcpu)) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); - kvm_x86_ops->set_irq(vcpu); + kvm_x86_ops.set_irq(vcpu); } } @@ -7739,7 +7769,7 @@ static void process_nmi(struct kvm_vcpu *vcpu) * If an NMI is already in progress, limit further NMIs to just one. * Otherwise, allow two (and we'll inject the first one immediately). */ - if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + if (kvm_x86_ops.get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) limit = 1; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); @@ -7829,11 +7859,11 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7f7c, seg.limit); put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); - kvm_x86_ops->get_gdt(vcpu, &dt); + kvm_x86_ops.get_gdt(vcpu, &dt); put_smstate(u32, buf, 0x7f74, dt.address); put_smstate(u32, buf, 0x7f70, dt.size); - kvm_x86_ops->get_idt(vcpu, &dt); + kvm_x86_ops.get_idt(vcpu, &dt); put_smstate(u32, buf, 0x7f58, dt.address); put_smstate(u32, buf, 0x7f54, dt.size); @@ -7883,7 +7913,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e94, seg.limit); put_smstate(u64, buf, 0x7e98, seg.base); - kvm_x86_ops->get_idt(vcpu, &dt); + kvm_x86_ops.get_idt(vcpu, &dt); put_smstate(u32, buf, 0x7e84, dt.size); put_smstate(u64, buf, 0x7e88, dt.address); @@ -7893,7 +7923,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e74, seg.limit); put_smstate(u64, buf, 0x7e78, seg.base); - kvm_x86_ops->get_gdt(vcpu, &dt); + kvm_x86_ops.get_gdt(vcpu, &dt); put_smstate(u32, buf, 0x7e64, dt.size); put_smstate(u64, buf, 0x7e68, dt.address); @@ -7923,28 +7953,28 @@ static void enter_smm(struct kvm_vcpu *vcpu) * vCPU state (e.g. leave guest mode) after we've saved the state into * the SMM state-save area. */ - kvm_x86_ops->pre_enter_smm(vcpu, buf); + kvm_x86_ops.pre_enter_smm(vcpu, buf); vcpu->arch.hflags |= HF_SMM_MASK; kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); - if (kvm_x86_ops->get_nmi_mask(vcpu)) + if (kvm_x86_ops.get_nmi_mask(vcpu)) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else - kvm_x86_ops->set_nmi_mask(vcpu, true); + kvm_x86_ops.set_nmi_mask(vcpu, true); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0x8000); cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); - kvm_x86_ops->set_cr0(vcpu, cr0); + kvm_x86_ops.set_cr0(vcpu, cr0); vcpu->arch.cr0 = cr0; - kvm_x86_ops->set_cr4(vcpu, 0); + kvm_x86_ops.set_cr4(vcpu, 0); /* Undocumented: IDT limit is set to zero on entry to SMM. */ dt.address = dt.size = 0; - kvm_x86_ops->set_idt(vcpu, &dt); + kvm_x86_ops.set_idt(vcpu, &dt); __kvm_set_dr(vcpu, 7, DR7_FIXED_1); @@ -7975,7 +8005,7 @@ static void enter_smm(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - kvm_x86_ops->set_efer(vcpu, 0); + kvm_x86_ops.set_efer(vcpu, 0); #endif kvm_update_cpuid(vcpu); @@ -8013,7 +8043,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); kvm_apic_update_apicv(vcpu); - kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); + kvm_x86_ops.refresh_apicv_exec_ctrl(vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -8026,23 +8056,30 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); */ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) { - if (!kvm_x86_ops->check_apicv_inhibit_reasons || - !kvm_x86_ops->check_apicv_inhibit_reasons(bit)) + unsigned long old, new, expected; + + if (!kvm_x86_ops.check_apicv_inhibit_reasons || + !kvm_x86_ops.check_apicv_inhibit_reasons(bit)) return; - if (activate) { - if (!test_and_clear_bit(bit, &kvm->arch.apicv_inhibit_reasons) || - !kvm_apicv_activated(kvm)) - return; - } else { - if (test_and_set_bit(bit, &kvm->arch.apicv_inhibit_reasons) || - kvm_apicv_activated(kvm)) - return; - } + old = READ_ONCE(kvm->arch.apicv_inhibit_reasons); + do { + expected = new = old; + if (activate) + __clear_bit(bit, &new); + else + __set_bit(bit, &new); + if (new == old) + break; + old = cmpxchg(&kvm->arch.apicv_inhibit_reasons, expected, new); + } while (old != expected); + + if (!!old == !!new) + return; trace_kvm_apicv_update_request(activate, bit); - if (kvm_x86_ops->pre_update_apicv_exec_ctrl) - kvm_x86_ops->pre_update_apicv_exec_ctrl(kvm, activate); + if (kvm_x86_ops.pre_update_apicv_exec_ctrl) + kvm_x86_ops.pre_update_apicv_exec_ctrl(kvm, activate); kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); } EXPORT_SYMBOL_GPL(kvm_request_apicv_update); @@ -8058,7 +8095,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { if (vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_x86_ops.sync_pir_to_irr(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -8078,7 +8115,7 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, vcpu_to_synic(vcpu)->vec_bitmap, 256); - kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_x86_ops.load_eoi_exitmap(vcpu, eoi_exit_bitmap); } int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, @@ -8105,13 +8142,13 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; - if (!kvm_x86_ops->set_apic_access_page_addr) + if (!kvm_x86_ops.set_apic_access_page_addr) return; page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (is_error_page(page)) return; - kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page)); + kvm_x86_ops.set_apic_access_page_addr(vcpu, page_to_phys(page)); /* * Do not pin apic access page in memory, the MMU notifier @@ -8143,7 +8180,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) { - if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) { + if (unlikely(!kvm_x86_ops.get_vmcs12_pages(vcpu))) { r = 0; goto out; } @@ -8163,8 +8200,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); - if (kvm_check_request(KVM_REQ_LOAD_CR3, vcpu)) - kvm_mmu_load_cr3(vcpu); + if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) + kvm_mmu_load_pgd(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_vcpu_flush_tlb(vcpu, true); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { @@ -8249,7 +8286,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - if (inject_pending_event(vcpu, req_int_win) != 0) + if (inject_pending_event(vcpu) != 0) req_immediate_exit = true; else { /* Enable SMI/NMI/IRQ window open exits if needed. @@ -8267,12 +8304,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * SMI. */ if (vcpu->arch.smi_pending && !is_smm(vcpu)) - if (!kvm_x86_ops->enable_smi_window(vcpu)) + if (!kvm_x86_ops.enable_smi_window(vcpu)) req_immediate_exit = true; if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); + kvm_x86_ops.enable_nmi_window(vcpu); if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + kvm_x86_ops.enable_irq_window(vcpu); WARN_ON(vcpu->arch.exception.pending); } @@ -8289,7 +8326,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); - kvm_x86_ops->prepare_guest_switch(vcpu); + kvm_x86_ops.prepare_guest_switch(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -8320,7 +8357,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * notified with kvm_vcpu_kick. */ if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_x86_ops.sync_pir_to_irr(vcpu); if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || need_resched() || signal_pending(current)) { @@ -8335,7 +8372,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_x86_ops->request_immediate_exit(vcpu); + kvm_x86_ops.request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); @@ -8355,7 +8392,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - kvm_x86_ops->run(vcpu); + kvm_x86_ops.run(vcpu); /* * Do this here before restoring debug registers on the host. And @@ -8365,7 +8402,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); - kvm_x86_ops->sync_dirty_debug_regs(vcpu); + kvm_x86_ops.sync_dirty_debug_regs(vcpu); kvm_update_dr0123(vcpu); kvm_update_dr6(vcpu); kvm_update_dr7(vcpu); @@ -8387,7 +8424,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops->handle_exit_irqoff(vcpu, &exit_fastpath); + kvm_x86_ops.handle_exit_irqoff(vcpu, &exit_fastpath); /* * Consume any pending interrupts, including the possible source of @@ -8430,12 +8467,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); - vcpu->arch.gpa_available = false; - r = kvm_x86_ops->handle_exit(vcpu, exit_fastpath); + r = kvm_x86_ops.handle_exit(vcpu, exit_fastpath); return r; cancel_injection: - kvm_x86_ops->cancel_injection(vcpu); + kvm_x86_ops.cancel_injection(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: @@ -8445,13 +8481,13 @@ out: static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu) && - (!kvm_x86_ops->pre_block || kvm_x86_ops->pre_block(vcpu) == 0)) { + (!kvm_x86_ops.pre_block || kvm_x86_ops.pre_block(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_x86_ops->post_block) - kvm_x86_ops->post_block(vcpu); + if (kvm_x86_ops.post_block) + kvm_x86_ops.post_block(vcpu); if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) return 1; @@ -8471,15 +8507,14 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) break; default: return -EINTR; - break; } return 1; } static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); + if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) + kvm_x86_ops.check_nested_events(vcpu); return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); @@ -8635,7 +8670,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) kvm_save_current_fpu(vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ + /* PKRU is separately restored in kvm_x86_ops.run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8740,7 +8775,7 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) * that usually, but some bad designed PV devices (vmware * backdoor interface) need this to work */ - emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt); + emulator_writeback_register_cache(vcpu->arch.emulate_ctxt); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; } regs->rax = kvm_rax_read(vcpu); @@ -8838,10 +8873,10 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - kvm_x86_ops->get_idt(vcpu, &dt); + kvm_x86_ops.get_idt(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; - kvm_x86_ops->get_gdt(vcpu, &dt); + kvm_x86_ops.get_gdt(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; @@ -8926,7 +8961,7 @@ out: int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); @@ -8942,7 +8977,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); - kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } EXPORT_SYMBOL_GPL(kvm_task_switch); @@ -8989,10 +9023,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) dt.size = sregs->idt.limit; dt.address = sregs->idt.base; - kvm_x86_ops->set_idt(vcpu, &dt); + kvm_x86_ops.set_idt(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; - kvm_x86_ops->set_gdt(vcpu, &dt); + kvm_x86_ops.set_gdt(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; @@ -9002,16 +9036,16 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_set_cr8(vcpu, sregs->cr8); mmu_reset_needed |= vcpu->arch.efer != sregs->efer; - kvm_x86_ops->set_efer(vcpu, sregs->efer); + kvm_x86_ops.set_efer(vcpu, sregs->efer); mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; - kvm_x86_ops->set_cr0(vcpu, sregs->cr0); + kvm_x86_ops.set_cr0(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)); - kvm_x86_ops->set_cr4(vcpu, sregs->cr4); + kvm_x86_ops.set_cr4(vcpu, sregs->cr4); if (cpuid_update_needed) kvm_update_cpuid(vcpu); @@ -9117,7 +9151,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops->update_bp_intercept(vcpu); + kvm_x86_ops.update_bp_intercept(vcpu); r = 0; @@ -9259,7 +9293,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct page *page; int r; - vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else @@ -9297,11 +9330,14 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) GFP_KERNEL_ACCOUNT)) goto fail_free_mce_banks; + if (!alloc_emulate_ctxt(vcpu)) + goto free_wbinvd_dirty_mask; + vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!vcpu->arch.user_fpu) { pr_err("kvm: failed to allocate userspace's fpu\n"); - goto free_wbinvd_dirty_mask; + goto free_emulate_ctxt; } vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, @@ -9326,7 +9362,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_hv_vcpu_init(vcpu); - r = kvm_x86_ops->vcpu_create(vcpu); + r = kvm_x86_ops.vcpu_create(vcpu); if (r) goto free_guest_fpu; @@ -9343,6 +9379,8 @@ free_guest_fpu: kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); free_user_fpu: kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); +free_emulate_ctxt: + kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_wbinvd_dirty_mask: free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fail_free_mce_banks: @@ -9377,11 +9415,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) mutex_unlock(&vcpu->mutex); - if (!kvmclock_periodic_sync) - return; - - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); + if (kvmclock_periodic_sync && vcpu->vcpu_idx == 0) + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, + KVMCLOCK_SYNC_PERIOD); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) @@ -9393,8 +9429,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); - kvm_x86_ops->vcpu_free(vcpu); + kvm_x86_ops.vcpu_free(vcpu); + kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); @@ -9480,7 +9517,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.ia32_xss = 0; - kvm_x86_ops->vcpu_reset(vcpu, init_event); + kvm_x86_ops.vcpu_reset(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -9505,7 +9542,7 @@ int kvm_arch_hardware_enable(void) bool stable, backwards_tsc = false; kvm_shared_msr_cpu_online(); - ret = kvm_x86_ops->hardware_enable(); + ret = kvm_x86_ops.hardware_enable(); if (ret != 0) return ret; @@ -9587,18 +9624,29 @@ int kvm_arch_hardware_enable(void) void kvm_arch_hardware_disable(void) { - kvm_x86_ops->hardware_disable(); + kvm_x86_ops.hardware_disable(); drop_user_return_notifiers(); } -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { + struct kvm_x86_init_ops *ops = opaque; int r; - r = kvm_x86_ops->hardware_setup(); + rdmsrl_safe(MSR_EFER, &host_efer); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + + r = ops->hardware_setup(); if (r != 0) return r; + memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) + supported_xss = 0; + cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); if (kvm_has_tsc_control) { @@ -9615,28 +9663,26 @@ int kvm_arch_hardware_setup(void) kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; } - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - kvm_init_msr_list(); return 0; } void kvm_arch_hardware_unsetup(void) { - kvm_x86_ops->hardware_unsetup(); + kvm_x86_ops.hardware_unsetup(); } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + struct kvm_x86_init_ops *ops = opaque; WARN_ON(!irqs_disabled()); if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) return -EIO; - return kvm_x86_ops->check_processor_compatibility(); + return ops->check_processor_compatibility(); } bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) @@ -9662,9 +9708,16 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) pmu->need_cleanup = true; kvm_make_request(KVM_REQ_PMU, vcpu); } - kvm_x86_ops->sched_in(vcpu, cpu); + kvm_x86_ops.sched_in(vcpu, cpu); } +void kvm_arch_free_vm(struct kvm *kvm) +{ + kfree(kvm->arch.hyperv.hv_pa_pg); + vfree(kvm); +} + + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { if (type) @@ -9699,7 +9752,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); - return kvm_x86_ops->vm_init(kvm); + return kvm_x86_ops.vm_init(kvm); } int kvm_arch_post_init_vm(struct kvm *kvm) @@ -9747,9 +9800,9 @@ void kvm_arch_sync_events(struct kvm *kvm) int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int i, r; - unsigned long hva; + unsigned long hva, uninitialized_var(old_npages); struct kvm_memslots *slots = kvm_memslots(kvm); - struct kvm_memory_slot *slot, old; + struct kvm_memory_slot *slot; /* Called with kvm->slots_lock held. */ if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) @@ -9757,7 +9810,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) slot = id_to_memslot(slots, id); if (size) { - if (slot->npages) + if (slot && slot->npages) return -EEXIST; /* @@ -9769,13 +9822,18 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) if (IS_ERR((void *)hva)) return PTR_ERR((void *)hva); } else { - if (!slot->npages) + if (!slot || !slot->npages) return 0; - hva = 0; + /* + * Stuff a non-canonical value to catch use-after-delete. This + * ends up being 0 on 32-bit KVM, but there's no better + * alternative. + */ + hva = (unsigned long)(0xdeadull << 48); + old_npages = slot->npages; } - old = *slot; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_userspace_memory_region m; @@ -9790,7 +9848,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } if (!size) - vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); + vm_munmap(hva, old_npages * PAGE_SIZE); return 0; } @@ -9817,8 +9875,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } - if (kvm_x86_ops->vm_destroy) - kvm_x86_ops->vm_destroy(kvm); + if (kvm_x86_ops.vm_destroy) + kvm_x86_ops.vm_destroy(kvm); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); @@ -9829,34 +9887,36 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_hv_destroy_vm(kvm); } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { - kvfree(free->arch.rmap[i]); - free->arch.rmap[i] = NULL; - } + kvfree(slot->arch.rmap[i]); + slot->arch.rmap[i] = NULL; + if (i == 0) continue; - if (!dont || free->arch.lpage_info[i - 1] != - dont->arch.lpage_info[i - 1]) { - kvfree(free->arch.lpage_info[i - 1]); - free->arch.lpage_info[i - 1] = NULL; - } + kvfree(slot->arch.lpage_info[i - 1]); + slot->arch.lpage_info[i - 1] = NULL; } - kvm_page_track_free_memslot(free, dont); + kvm_page_track_free_memslot(slot); } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, + unsigned long npages) { int i; + /* + * Clear out the previous array pointers for the KVM_MR_MOVE case. The + * old arrays will be freed by __kvm_set_memory_region() if installing + * the new memslot is successful. + */ + memset(&slot->arch, 0, sizeof(slot->arch)); + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; @@ -9887,11 +9947,9 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, ugfn = slot->userspace_addr >> PAGE_SHIFT; /* * If the gfn and userspace address are not aligned wrt each - * other, or if explicitly asked to, disable large page - * support for this slot + * other, disable large page support for this slot. */ - if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || - !kvm_largepages_enabled()) { + if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1)) { unsigned long j; for (j = 0; j < lpages; ++j) @@ -9938,6 +9996,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + return kvm_alloc_memslot_metadata(memslot, + mem->memory_size >> PAGE_SHIFT); return 0; } @@ -9946,14 +10007,14 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, { /* Still write protect RO slot */ if (new->flags & KVM_MEM_READONLY) { - kvm_mmu_slot_remove_write_access(kvm, new); + kvm_mmu_slot_remove_write_access(kvm, new, PT_PAGE_TABLE_LEVEL); return; } /* * Call kvm_x86_ops dirty logging hooks when they are valid. * - * kvm_x86_ops->slot_disable_log_dirty is called when: + * kvm_x86_ops.slot_disable_log_dirty is called when: * * - KVM_MR_CREATE with dirty logging is disabled * - KVM_MR_FLAGS_ONLY with dirty logging is disabled in new flag @@ -9965,7 +10026,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * any additional overhead from PML when guest is running with dirty * logging disabled for memory slots. * - * kvm_x86_ops->slot_enable_log_dirty is called when switching new slot + * kvm_x86_ops.slot_enable_log_dirty is called when switching new slot * to dirty logging mode. * * If kvm_x86_ops dirty logging hooks are invalid, use write protect. @@ -9981,19 +10042,32 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * See the comments in fast_page_fault(). */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { - if (kvm_x86_ops->slot_enable_log_dirty) - kvm_x86_ops->slot_enable_log_dirty(kvm, new); - else - kvm_mmu_slot_remove_write_access(kvm, new); + if (kvm_x86_ops.slot_enable_log_dirty) { + kvm_x86_ops.slot_enable_log_dirty(kvm, new); + } else { + int level = + kvm_dirty_log_manual_protect_and_init_set(kvm) ? + PT_DIRECTORY_LEVEL : PT_PAGE_TABLE_LEVEL; + + /* + * If we're with initial-all-set, we don't need + * to write protect any small page because + * they're reported as dirty already. However + * we still need to write-protect huge pages + * so that the page split can happen lazily on + * the first write to the huge page. + */ + kvm_mmu_slot_remove_write_access(kvm, new, level); + } } else { - if (kvm_x86_ops->slot_disable_log_dirty) - kvm_x86_ops->slot_disable_log_dirty(kvm, new); + if (kvm_x86_ops.slot_disable_log_dirty) + kvm_x86_ops.slot_disable_log_dirty(kvm, new); } } void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -10035,6 +10109,10 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, */ if (change != KVM_MR_DELETE) kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new); + + /* Free the arrays associated with the old memslot. */ + if (change == KVM_MR_MOVE) + kvm_arch_free_memslot(kvm, old); } void kvm_arch_flush_shadow_all(struct kvm *kvm) @@ -10051,8 +10129,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { return (is_guest_mode(vcpu) && - kvm_x86_ops->guest_apic_has_interrupt && - kvm_x86_ops->guest_apic_has_interrupt(vcpu)); + kvm_x86_ops.guest_apic_has_interrupt && + kvm_x86_ops.guest_apic_has_interrupt(vcpu)); } static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) @@ -10071,7 +10149,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && - kvm_x86_ops->nmi_allowed(vcpu))) + kvm_x86_ops.nmi_allowed(vcpu))) return true; if (kvm_test_request(KVM_REQ_SMI, vcpu) || @@ -10104,7 +10182,7 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; - if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu)) + if (vcpu->arch.apicv_active && kvm_x86_ops.dy_apicv_has_pending_interrupt(vcpu)) return true; return false; @@ -10122,7 +10200,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_x86_ops.interrupt_allowed(vcpu); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) @@ -10144,7 +10222,7 @@ unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; - rflags = kvm_x86_ops->get_rflags(vcpu); + rflags = kvm_x86_ops.get_rflags(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) rflags &= ~X86_EFLAGS_TF; return rflags; @@ -10156,7 +10234,7 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) rflags |= X86_EFLAGS_TF; - kvm_x86_ops->set_rflags(vcpu, rflags); + kvm_x86_ops.set_rflags(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) @@ -10179,10 +10257,10 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) return; if (!vcpu->arch.mmu->direct_map && - work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) + work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) @@ -10267,7 +10345,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || (vcpu->arch.apf.send_user_only && - kvm_x86_ops->get_cpl(vcpu) == 0)) + kvm_x86_ops.get_cpl(vcpu) == 0)) return false; return true; @@ -10287,7 +10365,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) * If interrupts are off we cannot even use an artificial * halt state. */ - return kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_x86_ops.interrupt_allowed(vcpu); } void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, @@ -10416,7 +10494,7 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, irqfd->producer = prod; - return kvm_x86_ops->update_pi_irte(irqfd->kvm, + return kvm_x86_ops.update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 1); } @@ -10436,7 +10514,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ - ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); + ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); @@ -10445,7 +10523,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); + return kvm_x86_ops.update_pi_irte(kvm, host_irq, guest_irq, set); } bool kvm_vector_hashing_enabled(void) @@ -10502,4 +10580,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 3624665acee4..b968acc0516f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -5,6 +5,7 @@ #include <linux/kvm_host.h> #include <asm/pvclock.h> #include "kvm_cache_regs.h" +#include "kvm_emulate.h" #define KVM_DEFAULT_PLE_GAP 128 #define KVM_VMX_DEFAULT_PLE_WINDOW 4096 @@ -96,7 +97,7 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu) if (!is_long_mode(vcpu)) return false; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); return cs_l; } @@ -149,11 +150,6 @@ static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48; } -static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt) -{ - return (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_LA57) ? 57 : 48; -} - static inline u64 get_canonical(u64 la, u8 vaddr_bits) { return ((int64_t)la << (64 - vaddr_bits)) >> (64 - vaddr_bits); @@ -164,12 +160,6 @@ static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la; } -static inline bool emul_is_noncanonical_address(u64 la, - struct x86_emulate_ctxt *ctxt) -{ - return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la; -} - static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, unsigned access) { @@ -247,7 +237,7 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) { - return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu); + return is_smm(vcpu) || kvm_x86_ops.apic_init_signal_blocked(vcpu); } void kvm_set_pending_timer(struct kvm_vcpu *vcpu); @@ -280,13 +270,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); -#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ - | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ - | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ - | XFEATURE_MASK_PKRU) extern u64 host_xcr0; +extern u64 supported_xcr0; +extern u64 supported_xss; -extern u64 kvm_supported_xcr0(void); +static inline bool kvm_mpx_supported(void) +{ + return (supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) + == (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); +} extern unsigned int min_timer_period_us; diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 53adc1762ec0..ec31f5b60323 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -366,7 +366,7 @@ AVXcode: 1 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv 1c: Grp20 (1A),(1C) 1d: -1e: +1e: Grp21 (1A) 1f: NOP Ev # 0x0f 0x20-0x2f 20: MOV Rd,Cd @@ -803,8 +803,8 @@ f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2) f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2) f2: ANDN Gy,By,Ey (v) f3: Grp17 (1A) -f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) -f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) +f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) | WRUSSD/Q My,Gy (66) +f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) | WRSSD/Q My,Gy f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) f9: MOVDIRI My,Gy @@ -970,7 +970,7 @@ GrpTable: Grp7 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv -5: rdpkru (110),(11B) | wrpkru (111),(11B) +5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B) 6: LMSW Ew 7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) EndTable @@ -1041,8 +1041,8 @@ GrpTable: Grp15 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) 4: XSAVE | ptwrite Ey (F3),(11B) -5: XRSTOR | lfence (11B) -6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) +5: XRSTOR | lfence (11B) | INCSSPD/Q Ry (F3),(11B) +6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) | CLRSSBSY Mq (F3) 7: clflush | clflushopt (66) | sfence (11B) EndTable @@ -1077,6 +1077,11 @@ GrpTable: Grp20 0: cldemote Mb EndTable +GrpTable: Grp21 +1: RDSSPD/Q Ry (F3),(11B) +7: ENDBR64 (F3),(010),(11B) | ENDBR32 (F3),(011),(11B) +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH 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/extable.c b/arch/x86/mm/extable.c index 30bb0bd3b1b8..b991aa4bdfae 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -80,18 +80,6 @@ __visible bool ex_handler_uaccess(const struct exception_table_entry *fixup, } EXPORT_SYMBOL(ex_handler_uaccess); -__visible bool ex_handler_ext(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) -{ - /* Special hack for uaccess_err */ - current->thread.uaccess_err = 1; - regs->ip = ex_fixup_addr(fixup); - return true; -} -EXPORT_SYMBOL(ex_handler_ext); - __visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fa4ea09593ab..859519f5b342 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: * @@ -1288,7 +1310,7 @@ void do_user_addr_fault(struct pt_regs *regs, struct task_struct *tsk; struct mm_struct *mm; vm_fault_t fault, major = 0; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; @@ -1442,27 +1464,23 @@ good_area: fault = handle_mm_fault(vma, address, flags); major |= fault & VM_FAULT_MAJOR; + /* Quick path to respond to signals */ + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + no_context(regs, hw_error_code, address, SIGBUS, + BUS_ADRERR); + return; + } + /* * If we need to retry the mmap_sem has already been released, * and if there is a fatal signal pending there is no guarantee * that we made any progress. Handle this case first. */ - if (unlikely(fault & VM_FAULT_RETRY)) { - /* Retry at most once */ - if (flags & FAULT_FLAG_ALLOW_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; - flags |= FAULT_FLAG_TRIED; - if (!fatal_signal_pending(tsk)) - goto retry; - } - - /* User mode? Just return to handle the fatal exception */ - if (flags & FAULT_FLAG_USER) - return; - - /* Not returning to user mode? Handle exceptions or die: */ - no_context(regs, hw_error_code, address, SIGBUS, BUS_ADRERR); - return; + if (unlikely((fault & VM_FAULT_RETRY) && + (flags & FAULT_FLAG_ALLOW_RETRY))) { + flags |= FAULT_FLAG_TRIED; + goto retry; } up_read(&mm->mmap_sem); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 23df4885bbed..de73992b8432 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -238,7 +238,11 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) } } -static inline int is_kernel_text(unsigned long addr) +/* + * The <linux/kallsyms.h> already defines is_kernel_text, + * using '__' prefix not to get in conflict. + */ +static inline int __is_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end) return 1; @@ -328,8 +332,8 @@ repeat: addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1; - if (is_kernel_text(addr) || - is_kernel_text(addr2)) + if (__is_kernel_text(addr) || + __is_kernel_text(addr2)) prot = PAGE_KERNEL_LARGE_EXEC; pages_2m++; @@ -354,7 +358,7 @@ repeat: */ pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR); - if (is_kernel_text(addr)) + if (__is_kernel_text(addr)) prot = PAGE_KERNEL_EXEC; pages_4k++; @@ -788,44 +792,6 @@ void __init mem_init(void) x86_init.hyper.init_after_bootmem(); mem_init_print_info(NULL); - printk(KERN_INFO "virtual kernel memory layout:\n" - " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" - " cpu_entry : 0x%08lx - 0x%08lx (%4ld kB)\n" -#ifdef CONFIG_HIGHMEM - " pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n" -#endif - " vmalloc : 0x%08lx - 0x%08lx (%4ld MB)\n" - " lowmem : 0x%08lx - 0x%08lx (%4ld MB)\n" - " .init : 0x%08lx - 0x%08lx (%4ld kB)\n" - " .data : 0x%08lx - 0x%08lx (%4ld kB)\n" - " .text : 0x%08lx - 0x%08lx (%4ld kB)\n", - FIXADDR_START, FIXADDR_TOP, - (FIXADDR_TOP - FIXADDR_START) >> 10, - - CPU_ENTRY_AREA_BASE, - CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE, - CPU_ENTRY_AREA_MAP_SIZE >> 10, - -#ifdef CONFIG_HIGHMEM - PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, - (LAST_PKMAP*PAGE_SIZE) >> 10, -#endif - - VMALLOC_START, VMALLOC_END, - (VMALLOC_END - VMALLOC_START) >> 20, - - (unsigned long)__va(0), (unsigned long)high_memory, - ((unsigned long)high_memory - (unsigned long)__va(0)) >> 20, - - (unsigned long)&__init_begin, (unsigned long)&__init_end, - ((unsigned long)&__init_end - - (unsigned long)&__init_begin) >> 10, - - (unsigned long)&_etext, (unsigned long)&_edata, - ((unsigned long)&_edata - (unsigned long)&_etext) >> 10, - - (unsigned long)&_text, (unsigned long)&_etext, - ((unsigned long)&_etext - (unsigned long)&_text) >> 10); /* * Check boundaries twice: Some fundamental inconsistencies can @@ -881,7 +847,7 @@ static void mark_nxdata_nx(void) */ unsigned long start = PFN_ALIGN(_etext); /* - * This comes from is_kernel_text upper limit. Also HPAGE where used: + * This comes from __is_kernel_text upper limit. Also HPAGE where used: */ unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index abbdecb75fad..0a14711d3a93 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -818,8 +818,7 @@ void __init paging_init(void) * will not set it back. */ node_clear_state(0, N_MEMORY); - if (N_MEMORY != N_NORMAL_MEMORY) - node_clear_state(0, N_NORMAL_MEMORY); + node_clear_state(0, N_NORMAL_MEMORY); zone_sizes_init(); } 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/kmmio.c b/arch/x86/mm/kmmio.c index 49d7814b59a9..9994353fb75d 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -260,7 +260,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) goto no_kmmio; } - ctx = &get_cpu_var(kmmio_ctx); + ctx = this_cpu_ptr(&kmmio_ctx); if (ctx->active) { if (page_base == ctx->addr) { /* @@ -285,7 +285,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) pr_emerg("previous hit was at 0x%08lx.\n", ctx->addr); disarm_kmmio_fault_page(faultpage); } - goto no_kmmio_ctx; + goto no_kmmio; } ctx->active++; @@ -314,11 +314,8 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) * the user should drop to single cpu before tracing. */ - put_cpu_var(kmmio_ctx); return 1; /* fault handled */ -no_kmmio_ctx: - put_cpu_var(kmmio_ctx); no_kmmio: rcu_read_unlock(); preempt_enable_no_resched(); @@ -333,7 +330,7 @@ no_kmmio: static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) { int ret = 0; - struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx); + struct kmmio_context *ctx = this_cpu_ptr(&kmmio_ctx); if (!ctx->active) { /* @@ -371,7 +368,6 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) if (!(regs->flags & X86_EFLAGS_TF)) ret = 1; out: - put_cpu_var(kmmio_ctx); return ret; } 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/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 7f1d2034df1e..c5174b4e318b 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -324,7 +324,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, 0, NULL, NUMA_NO_NODE); } -int __init setup_emu2phys_nid(int *dfl_phys_nid) +static int __init setup_emu2phys_nid(int *dfl_phys_nid) { int i, max_emu_nid = 0; diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index c4aedd00c1ba..6d5424069e2b 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -15,6 +15,7 @@ #include <linux/gfp.h> #include <linux/pci.h> #include <linux/vmalloc.h> +#include <linux/libnvdimm.h> #include <asm/e820/api.h> #include <asm/processor.h> @@ -304,11 +305,13 @@ void clflush_cache_range(void *vaddr, unsigned int size) } EXPORT_SYMBOL_GPL(clflush_cache_range); +#ifdef CONFIG_ARCH_HAS_PMEM_API void arch_invalidate_pmem(void *addr, size_t size) { clflush_cache_range(addr, size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); +#endif static void __cpa_flush_all(void *arg) { diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 44a9f068eee0..843aa10a4cb6 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -39,6 +39,7 @@ #include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/sections.h> +#include <asm/set_memory.h> #undef pr_fmt #define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt @@ -555,13 +556,6 @@ static inline bool pti_kernel_image_global_ok(void) } /* - * This is the only user for these and it is not arch-generic - * like the other set_memory.h functions. Just extern them. - */ -extern int set_memory_nonglobal(unsigned long addr, int numpages); -extern int set_memory_global(unsigned long addr, int numpages); - -/* * For some configurations, map all of kernel text into the user page * tables. This reduces TLB misses, especially on non-PCID systems. */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 9ba08e9abc09..5ea7c2cf7ab4 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1361,37 +1361,140 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, -(stack_size - i * 8)); } +static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, + struct bpf_prog *p, int stack_size, bool mod_ret) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (emit_call(&prog, __bpf_prog_enter, prog)) + return -EINVAL; + /* remember prog start time returned by __bpf_prog_enter */ + emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + + /* arg1: lea rdi, [rbp - stack_size] */ + EMIT4(0x48, 0x8D, 0x7D, -stack_size); + /* arg2: progs[i]->insnsi for interpreter */ + if (!p->jited) + emit_mov_imm64(&prog, BPF_REG_2, + (long) p->insnsi >> 32, + (u32) (long) p->insnsi); + /* call JITed bpf program or interpreter */ + if (emit_call(&prog, p->bpf_func, prog)) + return -EINVAL; + + /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + * of the previous call which is then passed on the stack to + * the next BPF program. + */ + if (mod_ret) + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, + (u32) (long) p); + /* arg2: mov rsi, rbx <- start time in nsec */ + emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); + if (emit_call(&prog, __bpf_prog_exit, prog)) + return -EINVAL; + + *pprog = prog; + return 0; +} + +static void emit_nops(u8 **pprog, unsigned int len) +{ + unsigned int i, noplen; + u8 *prog = *pprog; + int cnt = 0; + + while (len > 0) { + noplen = len; + + if (noplen > ASM_NOP_MAX) + noplen = ASM_NOP_MAX; + + for (i = 0; i < noplen; i++) + EMIT1(ideal_nops[noplen][i]); + len -= noplen; + } + + *pprog = prog; +} + +static void emit_align(u8 **pprog, u32 align) +{ + u8 *target, *prog = *pprog; + + target = PTR_ALIGN(prog, align); + if (target != prog) + emit_nops(&prog, target - prog); + + *pprog = prog; +} + +static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) +{ + u8 *prog = *pprog; + int cnt = 0; + s64 offset; + + offset = func - (ip + 2 + 4); + if (!is_simm32(offset)) { + pr_err("Target %p is out of range\n", func); + return -EINVAL; + } + EMIT2_off32(0x0F, jmp_cond + 0x10, offset); + *pprog = prog; + return 0; +} + static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, - struct bpf_prog **progs, int prog_cnt, int stack_size) + struct bpf_tramp_progs *tp, int stack_size) { + int i; u8 *prog = *pprog; - int cnt = 0, i; - for (i = 0; i < prog_cnt; i++) { - if (emit_call(&prog, __bpf_prog_enter, prog)) - return -EINVAL; - /* remember prog start time returned by __bpf_prog_enter */ - emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); - - /* arg1: lea rdi, [rbp - stack_size] */ - EMIT4(0x48, 0x8D, 0x7D, -stack_size); - /* arg2: progs[i]->insnsi for interpreter */ - if (!progs[i]->jited) - emit_mov_imm64(&prog, BPF_REG_2, - (long) progs[i]->insnsi >> 32, - (u32) (long) progs[i]->insnsi); - /* call JITed bpf program or interpreter */ - if (emit_call(&prog, progs[i]->bpf_func, prog)) + for (i = 0; i < tp->nr_progs; i++) { + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) return -EINVAL; + } + *pprog = prog; + return 0; +} + +static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, + struct bpf_tramp_progs *tp, int stack_size, + u8 **branches) +{ + u8 *prog = *pprog; + int i, cnt = 0; - /* arg1: mov rdi, progs[i] */ - emit_mov_imm64(&prog, BPF_REG_1, (long) progs[i] >> 32, - (u32) (long) progs[i]); - /* arg2: mov rsi, rbx <- start time in nsec */ - emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); - if (emit_call(&prog, __bpf_prog_exit, prog)) + /* The first fmod_ret program will receive a garbage return value. + * Set this to 0 to avoid confusing the program. + */ + emit_mov_imm32(&prog, false, BPF_REG_0, 0); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + for (i = 0; i < tp->nr_progs; i++) { + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, true)) return -EINVAL; + + /* mod_ret prog stored return value into [rbp - 8]. Emit: + * if (*(u64 *)(rbp - 8) != 0) + * goto do_fexit; + */ + /* cmp QWORD PTR [rbp - 0x8], 0x0 */ + EMIT4(0x48, 0x83, 0x7d, 0xf8); EMIT1(0x00); + + /* Save the location of the branch and Generate 6 nops + * (4 bytes for an offset and 2 bytes for the jump) These nops + * are replaced with a conditional jump once do_fexit (i.e. the + * start of the fexit invocation) is finalized. + */ + branches[i] = prog; + emit_nops(&prog, 4 + 2); } + *pprog = prog; return 0; } @@ -1458,12 +1561,15 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, */ int arch_prepare_bpf_trampoline(void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_prog **fentry_progs, int fentry_cnt, - struct bpf_prog **fexit_progs, int fexit_cnt, + struct bpf_tramp_progs *tprogs, void *orig_call) { - int cnt = 0, nr_args = m->nr_args; + int ret, i, cnt = 0, nr_args = m->nr_args; int stack_size = nr_args * 8; + struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY]; + struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT]; + struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; + u8 **branches = NULL; u8 *prog; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ @@ -1492,28 +1598,64 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, save_regs(m, &prog, nr_args, stack_size); - if (fentry_cnt) - if (invoke_bpf(m, &prog, fentry_progs, fentry_cnt, stack_size)) + if (fentry->nr_progs) + if (invoke_bpf(m, &prog, fentry, stack_size)) return -EINVAL; + if (fmod_ret->nr_progs) { + branches = kcalloc(fmod_ret->nr_progs, sizeof(u8 *), + GFP_KERNEL); + if (!branches) + return -ENOMEM; + + if (invoke_bpf_mod_ret(m, &prog, fmod_ret, stack_size, + branches)) { + ret = -EINVAL; + goto cleanup; + } + } + if (flags & BPF_TRAMP_F_CALL_ORIG) { - if (fentry_cnt) + if (fentry->nr_progs || fmod_ret->nr_progs) restore_regs(m, &prog, nr_args, stack_size); /* call original function */ - if (emit_call(&prog, orig_call, prog)) - return -EINVAL; + if (emit_call(&prog, orig_call, prog)) { + ret = -EINVAL; + goto cleanup; + } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); } - if (fexit_cnt) - if (invoke_bpf(m, &prog, fexit_progs, fexit_cnt, stack_size)) - return -EINVAL; + if (fmod_ret->nr_progs) { + /* From Intel 64 and IA-32 Architectures Optimization + * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler + * Coding Rule 11: All branch targets should be 16-byte + * aligned. + */ + emit_align(&prog, 16); + /* Update the branches saved in invoke_bpf_mod_ret with the + * aligned address of do_fexit. + */ + for (i = 0; i < fmod_ret->nr_progs; i++) + emit_cond_near_jump(&branches[i], prog, branches[i], + X86_JNE); + } + + if (fexit->nr_progs) + if (invoke_bpf(m, &prog, fexit, stack_size)) { + ret = -EINVAL; + goto cleanup; + } if (flags & BPF_TRAMP_F_RESTORE_REGS) restore_regs(m, &prog, nr_args, stack_size); + /* This needs to be done regardless. If there were fmod_ret programs, + * the return value is only updated on the stack and still needs to be + * restored to R0. + */ if (flags & BPF_TRAMP_F_CALL_ORIG) /* restore original return value back into RAX */ emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); @@ -1525,45 +1667,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ EMIT1(0xC3); /* ret */ /* Make sure the trampoline generation logic doesn't overflow */ - if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) - return -EFAULT; - return prog - (u8 *)image; -} - -static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) -{ - u8 *prog = *pprog; - int cnt = 0; - s64 offset; - - offset = func - (ip + 2 + 4); - if (!is_simm32(offset)) { - pr_err("Target %p is out of range\n", func); - return -EINVAL; - } - EMIT2_off32(0x0F, jmp_cond + 0x10, offset); - *pprog = prog; - return 0; -} - -static void emit_nops(u8 **pprog, unsigned int len) -{ - unsigned int i, noplen; - u8 *prog = *pprog; - int cnt = 0; - - while (len > 0) { - noplen = len; - - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - - for (i = 0; i < noplen; i++) - EMIT1(ideal_nops[noplen][i]); - len -= noplen; + if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { + ret = -EFAULT; + goto cleanup; } + ret = prog - (u8 *)image; - *pprog = prog; +cleanup: + kfree(branches); + return ret; } static int emit_fallback_jump(u8 **pprog) @@ -1588,7 +1700,7 @@ static int emit_fallback_jump(u8 **pprog) static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) { - u8 *jg_reloc, *jg_target, *prog = *pprog; + u8 *jg_reloc, *prog = *pprog; int pivot, err, jg_bytes = 1, cnt = 0; s64 jg_offset; @@ -1643,9 +1755,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) * Coding Rule 11: All branch targets should be 16-byte * aligned. */ - jg_target = PTR_ALIGN(prog, 16); - if (jg_target != prog) - emit_nops(&prog, jg_target - prog); + emit_align(&prog, 16); jg_offset = prog - jg_reloc; emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes); 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/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 99b6332ba540..b11ec5d8f8ac 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -71,5 +71,6 @@ $(obj)/realmode.relocs: $(obj)/realmode.elf FORCE KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP -D_WAKEUP \ -I$(srctree)/arch/x86/boot KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables GCOV_PROFILE := n UBSAN_SANITIZE := n diff --git a/arch/x86/realmode/rm/realmode.lds.S b/arch/x86/realmode/rm/realmode.lds.S index 64d135d1ee63..63aa51875ba0 100644 --- a/arch/x86/realmode/rm/realmode.lds.S +++ b/arch/x86/realmode/rm/realmode.lds.S @@ -71,7 +71,6 @@ SECTIONS /DISCARD/ : { *(.note*) *(.debug*) - *(.eh_frame*) } #include "pasyms.h" diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index a8985e1f7432..95d26a69088b 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -27,11 +27,6 @@ config X86_64 def_bool 64BIT select MODULES_USE_ELF_RELA -config ARCH_DEFCONFIG - string - default "arch/um/configs/i386_defconfig" if X86_32 - default "arch/um/configs/x86_64_defconfig" if X86_64 - config 3_LEVEL_PGTABLES bool "Three-level pagetables" if !64BIT default 64BIT diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 33c51c064c77..77f70b969d14 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -21,6 +21,7 @@ obj-y += checksum_32.o syscalls_32.o obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o +subarch-y += ../kernel/sys_ia32.o else diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 9649b5ad2ca2..2ed81e581755 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -7,7 +7,7 @@ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> -#include <generated/user_constants.h> +#include <asm/unistd.h> #include <asm/syscall.h> #define __NO_STUBS @@ -26,11 +26,11 @@ #define old_mmap sys_old_mmap -#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_I386(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_32.h> #undef __SYSCALL_I386 -#define __SYSCALL_I386(nr, sym, qual) [ nr ] = sym, +#define __SYSCALL_I386(nr, sym) [ nr ] = sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index c8bc7fb8cbd6..2e8544dafbb0 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -7,7 +7,7 @@ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> -#include <generated/user_constants.h> +#include <asm/unistd.h> #include <asm/syscall.h> #define __NO_STUBS @@ -36,11 +36,14 @@ #define stub_execveat sys_execveat #define stub_rt_sigreturn sys_rt_sigreturn -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_X32(nr, sym) +#define __SYSCALL_COMMON(nr, sym) __SYSCALL_64(nr, sym) + +#define __SYSCALL_64(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [ nr ] = sym, +#define __SYSCALL_64(nr, sym) [ nr ] = sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index 5b37b7f952dd..c51dd8363d25 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -9,18 +9,6 @@ #include <linux/ptrace.h> #include <asm/types.h> -#ifdef __i386__ -#define __SYSCALL_I386(nr, sym, qual) [nr] = 1, -static char syscalls[] = { -#include <asm/syscalls_32.h> -}; -#else -#define __SYSCALL_64(nr, sym, qual) [nr] = 1, -static char syscalls[] = { -#include <asm/syscalls_64.h> -}; -#endif - #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) @@ -94,7 +82,4 @@ void foo(void) DEFINE(UM_PROT_READ, PROT_READ); DEFINE(UM_PROT_WRITE, PROT_WRITE); DEFINE(UM_PROT_EXEC, PROT_EXEC); - - DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); - DEFINE(NR_syscalls, sizeof(syscalls)); } 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/x86/xen/time.c b/arch/x86/xen/time.c index befbdd8b17f0..c8897aad13cd 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -145,12 +145,19 @@ static struct notifier_block xen_pvclock_gtod_notifier = { .notifier_call = xen_pvclock_gtod_notify, }; +static int xen_cs_enable(struct clocksource *cs) +{ + vclocks_set_used(VDSO_CLOCKMODE_PVCLOCK); + return 0; +} + static struct clocksource xen_clocksource __read_mostly = { - .name = "xen", - .rating = 400, - .read = xen_clocksource_get_cycles, - .mask = ~0, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .name = "xen", + .rating = 400, + .read = xen_clocksource_get_cycles, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .enable = xen_cs_enable, }; /* @@ -412,12 +419,13 @@ void xen_restore_time_memory_area(void) ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t); /* - * We don't disable VCLOCK_PVCLOCK entirely if it fails to register the - * secondary time info with Xen or if we migrated to a host without the - * necessary flags. On both of these cases what happens is either - * process seeing a zeroed out pvti or seeing no PVCLOCK_TSC_STABLE_BIT - * bit set. Userspace checks the latter and if 0, it discards the data - * in pvti and fallbacks to a system call for a reliable timestamp. + * We don't disable VDSO_CLOCKMODE_PVCLOCK entirely if it fails to + * register the secondary time info with Xen or if we migrated to a + * host without the necessary flags. On both of these cases what + * happens is either process seeing a zeroed out pvti or seeing no + * PVCLOCK_TSC_STABLE_BIT bit set. Userspace checks the latter and + * if 0, it discards the data in pvti and fallbacks to a system + * call for a reliable timestamp. */ if (ret != 0) pr_notice("Cannot restore secondary vcpu_time_info (err %d)", @@ -443,7 +451,7 @@ static void xen_setup_vsyscall_time_info(void) ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t); if (ret) { - pr_notice("xen: VCLOCK_PVCLOCK not supported (err %d)\n", ret); + pr_notice("xen: VDSO_CLOCKMODE_PVCLOCK not supported (err %d)\n", ret); free_page((unsigned long)ti); return; } @@ -460,14 +468,14 @@ static void xen_setup_vsyscall_time_info(void) if (!ret) free_page((unsigned long)ti); - pr_notice("xen: VCLOCK_PVCLOCK not supported (tsc unstable)\n"); + pr_notice("xen: VDSO_CLOCKMODE_PVCLOCK not supported (tsc unstable)\n"); return; } xen_clock = ti; pvclock_set_pvti_cpu0_va(xen_clock); - xen_clocksource.archdata.vclock_mode = VCLOCK_PVCLOCK; + xen_clocksource.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; } static void __init xen_time_init(void) diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 271917c24b7f..9718e9593564 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -1,36 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h -generic-y += bug.h -generic-y += compat.h -generic-y += device.h -generic-y += div64.h -generic-y += dma-mapping.h -generic-y += emergency-restart.h -generic-y += exec.h generic-y += extable.h -generic-y += fb.h -generic-y += hardirq.h -generic-y += hw_irq.h -generic-y += irq_regs.h -generic-y += irq_work.h -generic-y += kdebug.h -generic-y += kmap_types.h -generic-y += kprobes.h generic-y += kvm_para.h -generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h -generic-y += mm-arch-hooks.h -generic-y += mmiowb.h generic-y += param.h -generic-y += percpu.h -generic-y += preempt.h generic-y += qrwlock.h generic-y += qspinlock.h -generic-y += sections.h -generic-y += topology.h -generic-y += trace_clock.h generic-y += user.h -generic-y += vga.h -generic-y += word-at-a-time.h -generic-y += xor.h 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/mm/fault.c b/arch/xtensa/mm/fault.c index bee30a77cd70..e7172bd53ced 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -43,7 +43,7 @@ void do_page_fault(struct pt_regs *regs) int is_write, is_exec; vm_fault_t fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned int flags = FAULT_FLAG_DEFAULT; code = SEGV_MAPERR; @@ -110,7 +110,7 @@ good_area: */ fault = handle_mm_fault(vma, address, flags); - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + if (fault_signal_pending(fault, regs)) return; if (unlikely(fault & VM_FAULT_ERROR)) { @@ -128,7 +128,6 @@ good_area: else current->min_flt++; if (fault & VM_FAULT_RETRY) { - flags &= ~FAULT_FLAG_ALLOW_RETRY; flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would 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); |