Add a libc-backed path for safe_syscall() that make syscalls via libc's syscall(). This enables interposing syscalls via LD_PRELOAD when running static guest binaries under a dynamically linked qemu-user.
The assembly implementation (safe_syscall_base()) remains the default. A runtime switch or a set environment variable changes the behavior: Command line: -libc-syscall Environment: QEMU_LIBC_SYSCALL Signed-off-by: Balint Reczey <[email protected]> --- bsd-user/main.c | 11 +++++++ common-user/meson.build | 1 + common-user/safe-syscall.c | 57 +++++++++++++++++++++++++++++++++++++ docs/user/main.rst | 28 ++++++++++++++++-- include/user/safe-syscall.h | 25 +++++++++++----- linux-user/main.c | 9 ++++++ 6 files changed, 122 insertions(+), 9 deletions(-) create mode 100644 common-user/safe-syscall.c diff --git a/bsd-user/main.c b/bsd-user/main.c index 73aae8c327..9b3ff67859 100644 --- a/bsd-user/main.c +++ b/bsd-user/main.c @@ -38,6 +38,7 @@ #include "qemu/plugin.h" #include "user/guest-base.h" #include "user/page-protection.h" +#include "user/safe-syscall.h" #include "accel/accel-ops.h" #include "tcg/startup.h" #include "qemu/timer.h" @@ -166,6 +167,7 @@ static void usage(void) "-E var=value sets/modifies targets environment variable(s)\n" "-U var unsets targets environment variable(s)\n" "-B address set guest_base address to address\n" + "-libc-syscall use libc syscall() instead of assembly safe-syscall\n" "\n" "Debug options:\n" "-d item1[,...] enable logging of specified items\n" @@ -183,6 +185,8 @@ static void usage(void) "Environment variables:\n" "QEMU_STRACE Print system calls and arguments similar to the\n" " 'strace' program. Enable by setting to any value.\n" + "QEMU_LIBC_SYSCALL Use libc syscall() instead of assembly safe-syscall.\n" + " Enable by setting to any value.\n" "You can use -E and -U options to set/unset environment variables\n" "for target process. It is possible to provide several variables\n" "by repeating the option. For example:\n" @@ -310,6 +314,11 @@ int main(int argc, char **argv) qemu_add_opts(&qemu_trace_opts); qemu_plugin_add_opts(); + /* Check QEMU_LIBC_SYSCALL environment variable */ + if (getenv("QEMU_LIBC_SYSCALL")) { + qemu_use_libc_syscall = true; + } + optind = 1; for (;;) { if (optind >= argc) { @@ -380,6 +389,8 @@ int main(int argc, char **argv) have_guest_base = true; } else if (!strcmp(r, "drop-ld-preload")) { (void) envlist_unsetenv(envlist, "LD_PRELOAD"); + } else if (!strcmp(r, "libc-syscall")) { + qemu_use_libc_syscall = true; } else if (!strcmp(r, "seed")) { seed_optarg = optarg; } else if (!strcmp(r, "one-insn-per-tb")) { diff --git a/common-user/meson.build b/common-user/meson.build index ac9de5b9e3..d44ffe1f56 100644 --- a/common-user/meson.build +++ b/common-user/meson.build @@ -7,4 +7,5 @@ common_user_inc += include_directories('host/' / host_arch) user_ss.add(files( 'safe-syscall.S', 'safe-syscall-error.c', + 'safe-syscall.c', )) diff --git a/common-user/safe-syscall.c b/common-user/safe-syscall.c new file mode 100644 index 0000000000..d1476c3113 --- /dev/null +++ b/common-user/safe-syscall.c @@ -0,0 +1,57 @@ +/* + * safe-syscall.c: C implementation using libc's syscall() + * to handle signals occurring at the same time as system calls. + * + * Written by Balint Reczey <[email protected]> + * + * Copyright (C) 2025 Balint Reczey + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#if defined(__linux__) +# include "special-errno.h" +#elif defined(__FreeBSD__) +# include "errno_defs.h" +#endif +#include "user/safe-syscall.h" +#include <stdarg.h> +#include <unistd.h> +#include <sys/syscall.h> +#include "qemu/atomic.h" + +/* Global runtime toggle (default: false). */ +bool qemu_use_libc_syscall; + +/* + * libc-backed implementation: Make a system call via libc's syscall() + * if no guest signal is pending. + */ +long safe_syscall_libc(int *pending, long number, ...) +{ + va_list ap; + long arg1, arg2, arg3, arg4, arg5, arg6; + long ret; + + /* Check if a guest signal is pending */ + if (qatomic_read(pending)) { + errno = QEMU_ERESTARTSYS; + return -1; + } + + va_start(ap, number); + /* Extract up to 6 syscall arguments */ + arg1 = va_arg(ap, long); + arg2 = va_arg(ap, long); + arg3 = va_arg(ap, long); + arg4 = va_arg(ap, long); + arg5 = va_arg(ap, long); + arg6 = va_arg(ap, long); + va_end(ap); + + /* Make the actual system call using libc's syscall() */ + ret = syscall(number, arg1, arg2, arg3, arg4, arg5, arg6); + + return ret; +} diff --git a/docs/user/main.rst b/docs/user/main.rst index a8ddf91424..6b7e76dfe1 100644 --- a/docs/user/main.rst +++ b/docs/user/main.rst @@ -70,7 +70,7 @@ Command line options :: - qemu-i386 [-h] [-d] [-L path] [-s size] [-cpu model] [-g endpoint] [-B offset] [-R size] program [arguments...] + qemu-i386 [-h] [-d] [-L path] [-s size] [-cpu model] [-g endpoint] [-B offset] [-R size] [-libc-syscall] program [arguments...] ``-h`` Print the help @@ -101,6 +101,15 @@ Command line options bytes). \"G\", \"M\", and \"k\" suffixes may be used when specifying the size. +``-libc-syscall`` + Use the host C library's ``syscall()`` entry point for guest system calls + instead of QEMU's built-in safe-syscall trampoline. By default this option + is disabled and QEMU uses its internal assembly implementation for + performance and precise control of signal-restart semantics. This switch is + primarily intended for debugging and integration scenarios (for example + when interposing on ``syscall()`` via ``LD_PRELOAD``). Available on Linux + and BSD user-mode builds. + Debug options: ``-d item1,...`` @@ -135,6 +144,10 @@ QEMU_STRACE format are printed with information for six arguments. Many flag-style arguments don't have decoders and will show up as numbers. +QEMU_LIBC_SYSCALL + When set to a non-empty value, behave as if ``-libc-syscall`` was specified + on the command line. Defaults to disabled. + Other binaries ~~~~~~~~~~~~~~ @@ -231,7 +244,7 @@ Command line options :: - qemu-sparc64 [-h] [-d] [-L path] [-s size] [-bsd type] program [arguments...] + qemu-sparc64 [-h] [-d] [-L path] [-s size] [-bsd type] [-libc-syscall] program [arguments...] ``-h`` Print the help @@ -256,6 +269,11 @@ Command line options Set the type of the emulated BSD Operating system. Valid values are FreeBSD, NetBSD and OpenBSD (default). +``-libc-syscall`` + Use the host C library's ``syscall()`` entry point for guest system calls + instead of QEMU's built-in safe-syscall trampoline. See the Linux user-mode + option of the same name for details. Defaults to disabled. + Debug options: ``-d item1,...`` @@ -266,3 +284,9 @@ Debug options: Run the emulation with one guest instruction per translation block. This slows down emulation a lot, but can be useful in some situations, such as when trying to analyse the logs produced by the ``-d`` option. + +Environment variables: + +QEMU_LIBC_SYSCALL + When set to a non-empty value, behave as if ``-libc-syscall`` was specified + on the command line. Defaults to disabled. diff --git a/include/user/safe-syscall.h b/include/user/safe-syscall.h index aa075f4d5c..02a95c24e9 100644 --- a/include/user/safe-syscall.h +++ b/include/user/safe-syscall.h @@ -125,16 +125,27 @@ * kinds of restartability. */ -/* The core part of this function is implemented in assembly */ -long safe_syscall_base(int *pending, long number, ...); -long safe_syscall_set_errno_tail(int value); +/* + * The core part remains implemented in assembly; a C dispatcher selects + * runtime path. + */ +extern long safe_syscall_base(int *pending, long number, ...); +extern long safe_syscall_set_errno_tail(int value); +extern long safe_syscall_libc(int *pending, long number, ...); +extern bool qemu_use_libc_syscall; -/* These are defined by the safe-syscall.inc.S file */ +/* + * These symbols are defined for compatibility with signal handling code. + * In the C implementation, they are dummy symbols. + */ extern char safe_syscall_start[]; extern char safe_syscall_end[]; -#define safe_syscall(...) \ - safe_syscall_base(&get_task_state(thread_cpu)->signal_pending, \ - __VA_ARGS__) +#define safe_syscall(...) \ + (qemu_use_libc_syscall ? \ + safe_syscall_libc(&get_task_state(thread_cpu)->signal_pending, \ + __VA_ARGS__) : \ + safe_syscall_base(&get_task_state(thread_cpu)->signal_pending, \ + __VA_ARGS__)) #endif diff --git a/linux-user/main.c b/linux-user/main.c index db751c0757..de2a20efb4 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -40,6 +40,7 @@ #include "qemu/plugin.h" #include "user/guest-base.h" #include "user/page-protection.h" +#include "user/safe-syscall.h" #include "exec/gdbstub.h" #include "gdbstub/user.h" #include "accel/accel-ops.h" @@ -456,6 +457,12 @@ static void handle_arg_jitdump(const char *arg) perf_enable_jitdump(); } +static void handle_arg_libc_syscall(const char *arg) +{ + /* Enable libc-backed syscall implementation */ + qemu_use_libc_syscall = true; +} + static QemuPluginList plugins = QTAILQ_HEAD_INITIALIZER(plugins); #ifdef CONFIG_PLUGIN @@ -534,6 +541,8 @@ static const struct qemu_argument arg_table[] = { "", "Generate a /tmp/perf-${pid}.map file for perf"}, {"jitdump", "QEMU_JITDUMP", false, handle_arg_jitdump, "", "Generate a jit-${pid}.dump file for perf"}, + {"libc-syscall", "QEMU_LIBC_SYSCALL", false, handle_arg_libc_syscall, + "", "use libc syscall() instead of assembly safe-syscall"}, {NULL, NULL, false, NULL, NULL, NULL} }; -- 2.43.0
