diff options
Diffstat (limited to 'kernel/entry')
| -rw-r--r-- | kernel/entry/Makefile | 8 | ||||
| -rw-r--r-- | kernel/entry/common.c | 340 | ||||
| -rw-r--r-- | kernel/entry/common.h | 7 | ||||
| -rw-r--r-- | kernel/entry/syscall-common.c | 23 | ||||
| -rw-r--r-- | kernel/entry/syscall_user_dispatch.c | 40 | ||||
| -rw-r--r-- | kernel/entry/virt.c (renamed from kernel/entry/kvm.c) | 15 |
6 files changed, 129 insertions, 304 deletions
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile index 095c775e001e..2333d70802e4 100644 --- a/kernel/entry/Makefile +++ b/kernel/entry/Makefile @@ -6,8 +6,12 @@ KASAN_SANITIZE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Branch profiling isn't noinstr-safe +ccflags-$(CONFIG_TRACE_BRANCH_PROFILING) += -DDISABLE_BRANCH_PROFILING + CFLAGS_REMOVE_common.o = -fstack-protector -fstack-protector-strong CFLAGS_common.o += -fno-stack-protector -obj-$(CONFIG_GENERIC_ENTRY) += common.o syscall_user_dispatch.o -obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK) += kvm.o +obj-$(CONFIG_GENERIC_IRQ_ENTRY) += common.o +obj-$(CONFIG_GENERIC_SYSCALL) += syscall-common.o syscall_user_dispatch.o +obj-$(CONFIG_VIRT_XFER_TO_GUEST_WORK) += virt.o diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e33691d5adf7..19d2244a9fef 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -1,105 +1,58 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/context_tracking.h> -#include <linux/entry-common.h> +#include <linux/irq-entry-common.h> #include <linux/resume_user_mode.h> #include <linux/highmem.h> #include <linux/jump_label.h> #include <linux/kmsan.h> #include <linux/livepatch.h> -#include <linux/audit.h> #include <linux/tick.h> -#include "common.h" - -#define CREATE_TRACE_POINTS -#include <trace/events/syscalls.h> - -static inline void syscall_enter_audit(struct pt_regs *regs, long syscall) -{ - if (unlikely(audit_context())) { - unsigned long args[6]; - - syscall_get_arguments(current, regs, args); - audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]); - } -} - -long syscall_trace_enter(struct pt_regs *regs, long syscall, - unsigned long work) -{ - long ret = 0; - - /* - * Handle Syscall User Dispatch. This must comes first, since - * the ABI here can be something that doesn't make sense for - * other syscall_work features. - */ - if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) { - if (syscall_user_dispatch(regs)) - return -1L; - } - - /* Handle ptrace */ - if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) { - ret = ptrace_report_syscall_entry(regs); - if (ret || (work & SYSCALL_WORK_SYSCALL_EMU)) - return -1L; - } - - /* Do seccomp after ptrace, to catch any tracer changes. */ - if (work & SYSCALL_WORK_SECCOMP) { - ret = __secure_computing(NULL); - if (ret == -1L) - return ret; - } - - /* Either of the above might have changed the syscall number */ - syscall = syscall_get_nr(current, regs); - - if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) { - trace_sys_enter(regs, syscall); - /* - * Probes or BPF hooks in the tracepoint may have changed the - * system call number as well. - */ - syscall = syscall_get_nr(current, regs); - } - - syscall_enter_audit(regs, syscall); - - return ret ? : syscall; -} - -noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs) -{ - enter_from_user_mode(regs); - instrumentation_begin(); - local_irq_enable(); - instrumentation_end(); -} - /* Workaround to allow gradual conversion of architecture code */ void __weak arch_do_signal_or_restart(struct pt_regs *regs) { } -/** - * exit_to_user_mode_loop - do any pending work before leaving to user space - * @regs: Pointer to pt_regs on entry stack - * @ti_work: TIF work flags as read by the caller +#ifdef CONFIG_HAVE_GENERIC_TIF_BITS +#define EXIT_TO_USER_MODE_WORK_LOOP (EXIT_TO_USER_MODE_WORK & ~_TIF_RSEQ) +#else +#define EXIT_TO_USER_MODE_WORK_LOOP (EXIT_TO_USER_MODE_WORK) +#endif + +/* TIF bits, which prevent a time slice extension. */ +#ifdef CONFIG_PREEMPT_RT +/* + * Since rseq slice ext has a direct correlation to the worst case + * scheduling latency (schedule is delayed after all), only have it affect + * LAZY reschedules on PREEMPT_RT for now. + * + * However, since this delay is only applicable to userspace, a value + * for rseq_slice_extension_nsec that is strictly less than the worst case + * kernel space preempt_disable() region, should mean the scheduling latency + * is not affected, even for !LAZY. + * + * However, since this value depends on the hardware at hand, it cannot be + * pre-determined in any sensible way. Hence punt on this problem for now. */ -__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs, - unsigned long ti_work) +# define TIF_SLICE_EXT_SCHED (_TIF_NEED_RESCHED_LAZY) +#else +# define TIF_SLICE_EXT_SCHED (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) +#endif +#define TIF_SLICE_EXT_DENY (EXIT_TO_USER_MODE_WORK & ~TIF_SLICE_EXT_SCHED) + +static __always_inline unsigned long __exit_to_user_mode_loop(struct pt_regs *regs, + unsigned long ti_work) { /* * Before returning to user space ensure that all pending work * items have been completed. */ - while (ti_work & EXIT_TO_USER_MODE_WORK) { + while (ti_work & EXIT_TO_USER_MODE_WORK_LOOP) { - local_irq_enable_exit_to_user(ti_work); + local_irq_enable(); - if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) - schedule(); + if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) { + if (!rseq_grant_slice_extension(ti_work, TIF_SLICE_EXT_DENY)) + schedule(); + } if (ti_work & _TIF_UPROBE) uprobe_notify_resume(regs); @@ -121,7 +74,7 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs, * might have changed while interrupts and preemption was * enabled above. */ - local_irq_disable_exit_to_user(); + local_irq_disable(); /* Check if any of the above work has queued a deferred wakeup */ tick_nohz_user_enter_prepare(); @@ -133,172 +86,50 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs, return ti_work; } -/* - * If SYSCALL_EMU is set, then the only reason to report is when - * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall - * instruction has been already reported in syscall_enter_from_user_mode(). - */ -static inline bool report_single_step(unsigned long work) -{ - if (work & SYSCALL_WORK_SYSCALL_EMU) - return false; - - return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP; -} - -static void syscall_exit_work(struct pt_regs *regs, unsigned long work) -{ - bool step; - - /* - * If the syscall was rolled back due to syscall user dispatching, - * then the tracers below are not invoked for the same reason as - * the entry side was not invoked in syscall_trace_enter(): The ABI - * of these syscalls is unknown. - */ - if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) { - if (unlikely(current->syscall_dispatch.on_dispatch)) { - current->syscall_dispatch.on_dispatch = false; - return; - } - } - - audit_syscall_exit(regs); - - if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT) - trace_sys_exit(regs, syscall_get_return_value(current, regs)); - - step = report_single_step(work); - if (step || work & SYSCALL_WORK_SYSCALL_TRACE) - ptrace_report_syscall_exit(regs, step); -} - -/* - * Syscall specific exit to user mode preparation. Runs with interrupts - * enabled. +/** + * exit_to_user_mode_loop - do any pending work before leaving to user space + * @regs: Pointer to pt_regs on entry stack + * @ti_work: TIF work flags as read by the caller */ -static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs) +__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs, + unsigned long ti_work) { - unsigned long work = READ_ONCE(current_thread_info()->syscall_work); - unsigned long nr = syscall_get_nr(current, regs); - - CT_WARN_ON(ct_state() != CT_STATE_KERNEL); + for (;;) { + ti_work = __exit_to_user_mode_loop(regs, ti_work); - if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { - if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr)) - local_irq_enable(); + if (likely(!rseq_exit_to_user_mode_restart(regs, ti_work))) + return ti_work; + ti_work = read_thread_flags(); } - - rseq_syscall(regs); - - /* - * Do one-time syscall specific work. If these work items are - * enabled, we want to run them exactly once per syscall exit with - * interrupts enabled. - */ - if (unlikely(work & SYSCALL_WORK_EXIT)) - syscall_exit_work(regs, work); -} - -static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *regs) -{ - syscall_exit_to_user_mode_prepare(regs); - local_irq_disable_exit_to_user(); - exit_to_user_mode_prepare(regs); -} - -void syscall_exit_to_user_mode_work(struct pt_regs *regs) -{ - __syscall_exit_to_user_mode_work(regs); -} - -__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs) -{ - instrumentation_begin(); - __syscall_exit_to_user_mode_work(regs); - instrumentation_end(); - exit_to_user_mode(); -} - -noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs) -{ - enter_from_user_mode(regs); -} - -noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs) -{ - instrumentation_begin(); - exit_to_user_mode_prepare(regs); - instrumentation_end(); - exit_to_user_mode(); } noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) { - irqentry_state_t ret = { - .exit_rcu = false, - }; - if (user_mode(regs)) { + irqentry_state_t ret = { + .exit_rcu = false, + }; + irqentry_enter_from_user_mode(regs); return ret; } - /* - * If this entry hit the idle task invoke ct_irq_enter() whether - * RCU is watching or not. - * - * Interrupts can nest when the first interrupt invokes softirq - * processing on return which enables interrupts. - * - * Scheduler ticks in the idle task can mark quiescent state and - * terminate a grace period, if and only if the timer interrupt is - * not nested into another interrupt. - * - * Checking for rcu_is_watching() here would prevent the nesting - * interrupt to invoke ct_irq_enter(). If that nested interrupt is - * the tick then rcu_flavor_sched_clock_irq() would wrongfully - * assume that it is the first interrupt and eventually claim - * quiescent state and end grace periods prematurely. - * - * Unconditionally invoke ct_irq_enter() so RCU state stays - * consistent. - * - * TINY_RCU does not support EQS, so let the compiler eliminate - * this part when enabled. - */ - if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) { - /* - * If RCU is not watching then the same careful - * sequence vs. lockdep and tracing is required - * as in irqentry_enter_from_user_mode(). - */ - lockdep_hardirqs_off(CALLER_ADDR0); - ct_irq_enter(); - instrumentation_begin(); - kmsan_unpoison_entry_regs(regs); - trace_hardirqs_off_finish(); - instrumentation_end(); - - ret.exit_rcu = true; - return ret; - } + return irqentry_enter_from_kernel_mode(regs); +} - /* - * If RCU is watching then RCU only wants to check whether it needs - * to restart the tick in NOHZ mode. rcu_irq_enter_check_tick() - * already contains a warning when RCU is not watching, so no point - * in having another one here. - */ - lockdep_hardirqs_off(CALLER_ADDR0); - instrumentation_begin(); - kmsan_unpoison_entry_regs(regs); - rcu_irq_enter_check_tick(); - trace_hardirqs_off_finish(); - instrumentation_end(); +/** + * arch_irqentry_exit_need_resched - Architecture specific need resched function + * + * Invoked from raw_irqentry_exit_cond_resched() to check if resched is needed. + * Defaults return true. + * + * The main purpose is to permit arch to avoid preemption of a task from an IRQ. + */ +static inline bool arch_irqentry_exit_need_resched(void); - return ret; -} +#ifndef arch_irqentry_exit_need_resched +static inline bool arch_irqentry_exit_need_resched(void) { return true; } +#endif void raw_irqentry_exit_cond_resched(void) { @@ -307,7 +138,7 @@ void raw_irqentry_exit_cond_resched(void) rcu_irq_exit_check_preempt(); if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) WARN_ON_ONCE(!on_thread_stack()); - if (need_resched()) + if (need_resched() && arch_irqentry_exit_need_resched()) preempt_schedule_irq(); } } @@ -327,43 +158,10 @@ void dynamic_irqentry_exit_cond_resched(void) noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state) { - lockdep_assert_irqs_disabled(); - - /* Check whether this returns to user mode */ - if (user_mode(regs)) { + if (user_mode(regs)) irqentry_exit_to_user_mode(regs); - } else if (!regs_irqs_disabled(regs)) { - /* - * If RCU was not watching on entry this needs to be done - * carefully and needs the same ordering of lockdep/tracing - * and RCU as the return to user mode path. - */ - if (state.exit_rcu) { - instrumentation_begin(); - /* Tell the tracer that IRET will enable interrupts */ - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(); - instrumentation_end(); - ct_irq_exit(); - lockdep_hardirqs_on(CALLER_ADDR0); - return; - } - - instrumentation_begin(); - if (IS_ENABLED(CONFIG_PREEMPTION)) - irqentry_exit_cond_resched(); - - /* Covers both tracing and lockdep */ - trace_hardirqs_on(); - instrumentation_end(); - } else { - /* - * IRQ flags state is correct already. Just tell RCU if it - * was not watching on entry. - */ - if (state.exit_rcu) - ct_irq_exit(); - } + else + irqentry_exit_to_kernel_mode(regs, state); } irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs) diff --git a/kernel/entry/common.h b/kernel/entry/common.h deleted file mode 100644 index f6e6d02f07fe..000000000000 --- a/kernel/entry/common.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _COMMON_H -#define _COMMON_H - -bool syscall_user_dispatch(struct pt_regs *regs); - -#endif diff --git a/kernel/entry/syscall-common.c b/kernel/entry/syscall-common.c new file mode 100644 index 000000000000..cd4967a9c53e --- /dev/null +++ b/kernel/entry/syscall-common.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/entry-common.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +/* Out of line to prevent tracepoint code duplication */ + +long trace_syscall_enter(struct pt_regs *regs, long syscall) +{ + trace_sys_enter(regs, syscall); + /* + * Probes or BPF hooks in the tracepoint may have changed the + * system call number. Reread it. + */ + return syscall_get_nr(current, regs); +} + +void trace_syscall_exit(struct pt_regs *regs, long ret) +{ + trace_sys_exit(regs, ret); +} diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index 5340c5aa89e7..d89dffcc2d64 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -2,6 +2,8 @@ /* * Copyright (C) 2020 Collabora Ltd. */ + +#include <linux/entry-common.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/ptrace.h> @@ -15,8 +17,6 @@ #include <asm/syscall.h> -#include "common.h" - static void trigger_sigsys(struct pt_regs *regs) { struct kernel_siginfo info; @@ -78,7 +78,7 @@ static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned lon if (offset || len || selector) return -EINVAL; break; - case PR_SYS_DISPATCH_ON: + case PR_SYS_DISPATCH_EXCLUSIVE_ON: /* * Validate the direct dispatcher region just for basic * sanity against overflow and a 0-sized dispatcher @@ -87,30 +87,40 @@ static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned lon */ if (offset && offset + len <= offset) return -EINVAL; - + break; + case PR_SYS_DISPATCH_INCLUSIVE_ON: + if (len == 0 || offset + len <= offset) + return -EINVAL; /* - * access_ok() will clear memory tags for tagged addresses - * if current has memory tagging enabled. - - * To enable a tracer to set a tracees selector the - * selector address must be untagged for access_ok(), - * otherwise an untagged tracer will always fail to set a - * tagged tracees selector. + * Invert the range, the check in syscall_user_dispatch() + * supports wrap-around. */ - if (selector && !access_ok(untagged_addr(selector), sizeof(*selector))) - return -EFAULT; - + offset = offset + len; + len = -len; break; default: return -EINVAL; } + /* + * access_ok() will clear memory tags for tagged addresses + * if current has memory tagging enabled. + * + * To enable a tracer to set a tracees selector the + * selector address must be untagged for access_ok(), + * otherwise an untagged tracer will always fail to set a + * tagged tracees selector. + */ + if (mode != PR_SYS_DISPATCH_OFF && selector && + !access_ok(untagged_addr(selector), sizeof(*selector))) + return -EFAULT; + task->syscall_dispatch.selector = selector; task->syscall_dispatch.offset = offset; task->syscall_dispatch.len = len; task->syscall_dispatch.on_dispatch = false; - if (mode == PR_SYS_DISPATCH_ON) + if (mode != PR_SYS_DISPATCH_OFF) set_task_syscall_work(task, SYSCALL_USER_DISPATCH); else clear_task_syscall_work(task, SYSCALL_USER_DISPATCH); diff --git a/kernel/entry/kvm.c b/kernel/entry/virt.c index 8485f63863af..c52f99249763 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/virt.c @@ -1,17 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/entry-kvm.h> -#include <linux/kvm_host.h> +#include <linux/entry-virt.h> -static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) +static int xfer_to_guest_mode_work(unsigned long ti_work) { do { int ret; - if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { - kvm_handle_signal_exit(vcpu); + if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) return -EINTR; - } if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) schedule(); @@ -19,7 +16,7 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ti_work & _TIF_NOTIFY_RESUME) resume_user_mode_work(NULL); - ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work); + ret = arch_xfer_to_guest_mode_handle_work(ti_work); if (ret) return ret; @@ -28,7 +25,7 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) return 0; } -int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu) +int xfer_to_guest_mode_handle_work(void) { unsigned long ti_work; @@ -44,6 +41,6 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu) if (!(ti_work & XFER_TO_GUEST_MODE_WORK)) return 0; - return xfer_to_guest_mode_work(vcpu, ti_work); + return xfer_to_guest_mode_work(ti_work); } EXPORT_SYMBOL_GPL(xfer_to_guest_mode_handle_work); |