diff options
-rw-r--r-- | arch/Kconfig | 3 | ||||
-rw-r--r-- | include/linux/entry-common.h | 121 | ||||
-rw-r--r-- | kernel/Makefile | 1 | ||||
-rw-r--r-- | kernel/entry/Makefile | 12 | ||||
-rw-r--r-- | kernel/entry/common.c | 88 |
5 files changed, 225 insertions, 0 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 8cc35dc556c7..852a527f418f 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -27,6 +27,9 @@ config HAVE_IMA_KEXEC config HOTPLUG_SMT bool +config GENERIC_ENTRY + bool + config OPROFILE tristate "OProfile system profiling" depends on PROFILING diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h new file mode 100644 index 000000000000..42fc8e4632bb --- /dev/null +++ b/include/linux/entry-common.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_ENTRYCOMMON_H +#define __LINUX_ENTRYCOMMON_H + +#include <linux/tracehook.h> +#include <linux/syscalls.h> +#include <linux/seccomp.h> +#include <linux/sched.h> + +#include <asm/entry-common.h> + +/* + * Define dummy _TIF work flags if not defined by the architecture or for + * disabled functionality. + */ +#ifndef _TIF_SYSCALL_EMU +# define _TIF_SYSCALL_EMU (0) +#endif + +#ifndef _TIF_SYSCALL_TRACEPOINT +# define _TIF_SYSCALL_TRACEPOINT (0) +#endif + +#ifndef _TIF_SECCOMP +# define _TIF_SECCOMP (0) +#endif + +#ifndef _TIF_SYSCALL_AUDIT +# define _TIF_SYSCALL_AUDIT (0) +#endif + +/* + * TIF flags handled in syscall_enter_from_usermode() + */ +#ifndef ARCH_SYSCALL_ENTER_WORK +# define ARCH_SYSCALL_ENTER_WORK (0) +#endif + +#define SYSCALL_ENTER_WORK \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU | \ + ARCH_SYSCALL_ENTER_WORK) + +/** + * arch_check_user_regs - Architecture specific sanity check for user mode regs + * @regs: Pointer to currents pt_regs + * + * Defaults to an empty implementation. Can be replaced by architecture + * specific code. + * + * Invoked from syscall_enter_from_user_mode() in the non-instrumentable + * section. Use __always_inline so the compiler cannot push it out of line + * and make it instrumentable. + */ +static __always_inline void arch_check_user_regs(struct pt_regs *regs); + +#ifndef arch_check_user_regs +static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} +#endif + +/** + * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry() + * @regs: Pointer to currents pt_regs + * + * Returns: 0 on success or an error code to skip the syscall. + * + * Defaults to tracehook_report_syscall_entry(). Can be replaced by + * architecture specific code. + * + * Invoked from syscall_enter_from_user_mode() + */ +static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs); + +#ifndef arch_syscall_enter_tracehook +static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs) +{ + return tracehook_report_syscall_entry(regs); +} +#endif + +/** + * syscall_enter_from_user_mode - Check and handle work before invoking + * a syscall + * @regs: Pointer to currents pt_regs + * @syscall: The syscall number + * + * Invoked from architecture specific syscall entry code with interrupts + * disabled. The calling code has to be non-instrumentable. When the + * function returns all state is correct and the subsequent functions can be + * instrumented. + * + * Returns: The original or a modified syscall number + * + * If the returned syscall number is -1 then the syscall should be + * skipped. In this case the caller may invoke syscall_set_error() or + * syscall_set_return_value() first. If neither of those are called and -1 + * is returned, then the syscall will fail with ENOSYS. + * + * The following functionality is handled here: + * + * 1) Establish state (lockdep, RCU (context tracking), tracing) + * 2) TIF flag dependent invocations of arch_syscall_enter_tracehook(), + * __secure_computing(), trace_sys_enter() + * 3) Invocation of audit_syscall_entry() + */ +long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall); + +/** + * irqentry_enter_from_user_mode - Establish state before invoking the irq handler + * @regs: Pointer to currents pt_regs + * + * Invoked from architecture specific entry code with interrupts disabled. + * Can only be called when the interrupt entry came from user mode. The + * calling code must be non-instrumentable. When the function returns all + * state is correct and the subsequent functions can be instrumented. + * + * The function establishes state (lockdep, RCU (context tracking), tracing) + */ +void irqentry_enter_from_user_mode(struct pt_regs *regs); + +#endif diff --git a/kernel/Makefile b/kernel/Makefile index f3218bc5ec69..fde2000d0d0d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -48,6 +48,7 @@ obj-y += irq/ obj-y += rcu/ obj-y += livepatch/ obj-y += dma/ +obj-y += entry/ obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o obj-$(CONFIG_FREEZER) += freezer.o diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile new file mode 100644 index 000000000000..c207d202bf3a --- /dev/null +++ b/kernel/entry/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Prevent the noinstr section from being pestered by sanitizer and other goodies +# as long as these things cannot be disabled per function. +KASAN_SANITIZE := n +UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n + +CFLAGS_REMOVE_common.o = -fstack-protector -fstack-protector-strong +CFLAGS_common.o += -fno-stack-protector + +obj-$(CONFIG_GENERIC_ENTRY) += common.o diff --git a/kernel/entry/common.c b/kernel/entry/common.c new file mode 100644 index 000000000000..1d636dee2fec --- /dev/null +++ b/kernel/entry/common.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/context_tracking.h> +#include <linux/entry-common.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +/** + * enter_from_user_mode - Establish state when coming from user mode + * + * Syscall/interrupt entry disables interrupts, but user mode is traced as + * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. + * + * 1) Tell lockdep that interrupts are disabled + * 2) Invoke context tracking if enabled to reactivate RCU + * 3) Trace interrupts off state + */ +static __always_inline void enter_from_user_mode(struct pt_regs *regs) +{ + arch_check_user_regs(regs); + lockdep_hardirqs_off(CALLER_ADDR0); + + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit_irqoff(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + +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]); + } +} + +static long syscall_trace_enter(struct pt_regs *regs, long syscall, + unsigned long ti_work) +{ + long ret = 0; + + /* Handle ptrace */ + if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) { + ret = arch_syscall_enter_tracehook(regs); + if (ret || (ti_work & _TIF_SYSCALL_EMU)) + return -1L; + } + + /* Do seccomp after ptrace, to catch any tracer changes. */ + if (ti_work & _TIF_SECCOMP) { + ret = __secure_computing(NULL); + if (ret == -1L) + return ret; + } + + if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT)) + trace_sys_enter(regs, syscall); + + syscall_enter_audit(regs, syscall); + + return ret ? : syscall; +} + +noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) +{ + unsigned long ti_work; + + enter_from_user_mode(regs); + instrumentation_begin(); + + local_irq_enable(); + ti_work = READ_ONCE(current_thread_info()->flags); + if (ti_work & SYSCALL_ENTER_WORK) + syscall = syscall_trace_enter(regs, syscall, ti_work); + instrumentation_end(); + + return syscall; +} + +noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs) +{ + enter_from_user_mode(regs); +} |