summaryrefslogtreecommitdiffstats
path: root/arch/um/os-Linux
diff options
context:
space:
mode:
Diffstat (limited to 'arch/um/os-Linux')
-rw-r--r--arch/um/os-Linux/Makefile2
-rw-r--r--arch/um/os-Linux/drivers/ethertap_kern.c2
-rw-r--r--arch/um/os-Linux/drivers/tuntap_kern.c2
-rw-r--r--arch/um/os-Linux/elf_aux.c1
-rw-r--r--arch/um/os-Linux/file.c104
-rw-r--r--arch/um/os-Linux/helper.c67
-rw-r--r--arch/um/os-Linux/internal.h20
-rw-r--r--arch/um/os-Linux/main.c39
-rw-r--r--arch/um/os-Linux/mem.c16
-rw-r--r--arch/um/os-Linux/process.c139
-rw-r--r--arch/um/os-Linux/registers.c11
-rw-r--r--arch/um/os-Linux/sigio.c349
-rw-r--r--arch/um/os-Linux/signal.c179
-rw-r--r--arch/um/os-Linux/skas/mem.c235
-rw-r--r--arch/um/os-Linux/skas/process.c376
-rw-r--r--arch/um/os-Linux/start_up.c5
-rw-r--r--arch/um/os-Linux/umid.c2
-rw-r--r--arch/um/os-Linux/util.c4
18 files changed, 692 insertions, 861 deletions
diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile
index 544e0b344c75..049dfa5bc9c6 100644
--- a/arch/um/os-Linux/Makefile
+++ b/arch/um/os-Linux/Makefile
@@ -12,6 +12,8 @@ obj-y = execvp.o file.o helper.o irq.o main.o mem.o process.o \
CFLAGS_signal.o += -Wframe-larger-than=4096
+CFLAGS_main.o += -Wno-frame-larger-than
+
obj-$(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) += elf_aux.o
USER_OBJS := $(user-objs-y) elf_aux.o execvp.o file.o helper.o irq.o \
diff --git a/arch/um/os-Linux/drivers/ethertap_kern.c b/arch/um/os-Linux/drivers/ethertap_kern.c
index 3182e759d8de..5e5ee40680ce 100644
--- a/arch/um/os-Linux/drivers/ethertap_kern.c
+++ b/arch/um/os-Linux/drivers/ethertap_kern.c
@@ -63,7 +63,7 @@ const struct net_kern_info ethertap_kern_info = {
.write = etap_write,
};
-int ethertap_setup(char *str, char **mac_out, void *data)
+static int ethertap_setup(char *str, char **mac_out, void *data)
{
struct ethertap_init *init = data;
diff --git a/arch/um/os-Linux/drivers/tuntap_kern.c b/arch/um/os-Linux/drivers/tuntap_kern.c
index adcb6717be6f..ff022d9cf0dd 100644
--- a/arch/um/os-Linux/drivers/tuntap_kern.c
+++ b/arch/um/os-Linux/drivers/tuntap_kern.c
@@ -53,7 +53,7 @@ const struct net_kern_info tuntap_kern_info = {
.write = tuntap_write,
};
-int tuntap_setup(char *str, char **mac_out, void *data)
+static int tuntap_setup(char *str, char **mac_out, void *data)
{
struct tuntap_init *init = data;
diff --git a/arch/um/os-Linux/elf_aux.c b/arch/um/os-Linux/elf_aux.c
index 344ac403fb5d..0a0f91cf4d6d 100644
--- a/arch/um/os-Linux/elf_aux.c
+++ b/arch/um/os-Linux/elf_aux.c
@@ -13,6 +13,7 @@
#include <init.h>
#include <elf_user.h>
#include <mem_user.h>
+#include "internal.h"
typedef Elf32_auxv_t elf_auxv_t;
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index fc4450db59bd..a0d01c68ce3e 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -17,6 +17,7 @@
#include <sys/stat.h>
#include <sys/sysmacros.h>
#include <sys/un.h>
+#include <sys/mman.h>
#include <sys/types.h>
#include <sys/eventfd.h>
#include <poll.h>
@@ -240,15 +241,19 @@ out:
return err;
}
-void os_close_file(int fd)
+int os_dup_file(int fd)
{
- close(fd);
+ int new_fd = dup(fd);
+
+ if (new_fd < 0)
+ return -errno;
+
+ return new_fd;
}
-int os_fsync_file(int fd)
+
+void os_close_file(int fd)
{
- if (fsync(fd) < 0)
- return -errno;
- return 0;
+ close(fd);
}
int os_seek_file(int fd, unsigned long long offset)
@@ -502,44 +507,51 @@ int os_shutdown_socket(int fd, int r, int w)
return 0;
}
-int os_rcv_fd(int fd, int *helper_pid_out)
+/**
+ * os_rcv_fd_msg - receive message with (optional) FDs
+ * @fd: the FD to receive from
+ * @fds: the array for FDs to write to
+ * @n_fds: number of FDs to receive (@fds array size)
+ * @data: the message buffer
+ * @data_len: the size of the message to receive
+ *
+ * Receive a message with FDs.
+ *
+ * Returns: the size of the received message, or an error code
+ */
+ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds,
+ void *data, size_t data_len)
{
- int new, n;
- char buf[CMSG_SPACE(sizeof(new))];
- struct msghdr msg;
+#define MAX_RCV_FDS 2
+ char buf[CMSG_SPACE(sizeof(*fds) * MAX_RCV_FDS)];
struct cmsghdr *cmsg;
- struct iovec iov;
-
- msg.msg_name = NULL;
- msg.msg_namelen = 0;
- iov = ((struct iovec) { .iov_base = helper_pid_out,
- .iov_len = sizeof(*helper_pid_out) });
- msg.msg_iov = &iov;
- msg.msg_iovlen = 1;
- msg.msg_control = buf;
- msg.msg_controllen = sizeof(buf);
- msg.msg_flags = 0;
+ struct iovec iov = {
+ .iov_base = data,
+ .iov_len = data_len,
+ };
+ struct msghdr msg = {
+ .msg_iov = &iov,
+ .msg_iovlen = 1,
+ .msg_control = buf,
+ .msg_controllen = CMSG_SPACE(sizeof(*fds) * n_fds),
+ };
+ int n;
+
+ if (n_fds > MAX_RCV_FDS)
+ return -EINVAL;
n = recvmsg(fd, &msg, 0);
if (n < 0)
return -errno;
- else if (n != iov.iov_len)
- *helper_pid_out = -1;
cmsg = CMSG_FIRSTHDR(&msg);
- if (cmsg == NULL) {
- printk(UM_KERN_ERR "rcv_fd didn't receive anything, "
- "error = %d\n", errno);
- return -1;
- }
- if ((cmsg->cmsg_level != SOL_SOCKET) ||
- (cmsg->cmsg_type != SCM_RIGHTS)) {
- printk(UM_KERN_ERR "rcv_fd didn't receive a descriptor\n");
- return -1;
- }
+ if (!cmsg ||
+ cmsg->cmsg_level != SOL_SOCKET ||
+ cmsg->cmsg_type != SCM_RIGHTS)
+ return n;
- new = ((int *) CMSG_DATA(cmsg))[0];
- return new;
+ memcpy(fds, CMSG_DATA(cmsg), cmsg->cmsg_len);
+ return n;
}
int os_create_unix_socket(const char *file, int len, int close_on_exec)
@@ -705,3 +717,25 @@ int os_poll(unsigned int n, const int *fds)
return -EIO;
}
+
+void *os_mmap_rw_shared(int fd, size_t size)
+{
+ void *res = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+
+ if (res == MAP_FAILED)
+ return NULL;
+
+ return res;
+}
+
+void *os_mremap_rw_shared(void *old_addr, size_t old_size, size_t new_size)
+{
+ void *res;
+
+ res = mremap(old_addr, old_size, new_size, MREMAP_MAYMOVE, NULL);
+
+ if (res == MAP_FAILED)
+ return NULL;
+
+ return res;
+}
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index 3cb8ac63be6e..89c2ad2a4e3a 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -8,6 +8,7 @@
#include <unistd.h>
#include <errno.h>
#include <sched.h>
+#include <pthread.h>
#include <linux/limits.h>
#include <sys/socket.h>
#include <sys/wait.h>
@@ -121,6 +122,10 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags,
unsigned long stack, sp;
int pid, status, err;
+ /* To share memory space, use os_run_helper_thread() instead. */
+ if (flags & CLONE_VM)
+ return -EINVAL;
+
stack = alloc_stack(0, __uml_cant_sleep());
if (stack == 0)
return -ENOMEM;
@@ -167,3 +172,65 @@ int helper_wait(int pid)
} else
return 0;
}
+
+struct os_helper_thread {
+ pthread_t handle;
+};
+
+int os_run_helper_thread(struct os_helper_thread **td_out,
+ void *(*routine)(void *), void *arg)
+{
+ struct os_helper_thread *td;
+ sigset_t sigset, oset;
+ int err, flags;
+
+ flags = __uml_cant_sleep() ? UM_GFP_ATOMIC : UM_GFP_KERNEL;
+ td = uml_kmalloc(sizeof(*td), flags);
+ if (!td)
+ return -ENOMEM;
+
+ sigfillset(&sigset);
+ if (sigprocmask(SIG_SETMASK, &sigset, &oset) < 0) {
+ err = -errno;
+ kfree(td);
+ return err;
+ }
+
+ err = pthread_create(&td->handle, NULL, routine, arg);
+
+ if (sigprocmask(SIG_SETMASK, &oset, NULL) < 0)
+ panic("Failed to restore the signal mask: %d", errno);
+
+ if (err != 0)
+ kfree(td);
+ else
+ *td_out = td;
+
+ return -err;
+}
+
+void os_kill_helper_thread(struct os_helper_thread *td)
+{
+ pthread_cancel(td->handle);
+ pthread_join(td->handle, NULL);
+ kfree(td);
+}
+
+void os_fix_helper_thread_signals(void)
+{
+ sigset_t sigset;
+
+ sigemptyset(&sigset);
+
+ sigaddset(&sigset, SIGWINCH);
+ sigaddset(&sigset, SIGPIPE);
+ sigaddset(&sigset, SIGPROF);
+ sigaddset(&sigset, SIGINT);
+ sigaddset(&sigset, SIGTERM);
+ sigaddset(&sigset, SIGCHLD);
+ sigaddset(&sigset, SIGALRM);
+ sigaddset(&sigset, SIGIO);
+ sigaddset(&sigset, SIGUSR1);
+
+ pthread_sigmask(SIG_SETMASK, &sigset, NULL);
+}
diff --git a/arch/um/os-Linux/internal.h b/arch/um/os-Linux/internal.h
new file mode 100644
index 000000000000..317fca190c2b
--- /dev/null
+++ b/arch/um/os-Linux/internal.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_OS_LINUX_INTERNAL_H
+#define __UM_OS_LINUX_INTERNAL_H
+
+/*
+ * elf_aux.c
+ */
+void scan_elf_aux(char **envp);
+
+/*
+ * mem.c
+ */
+void check_tmpexec(void);
+
+/*
+ * skas/process.c
+ */
+void wait_stub_done(int pid);
+
+#endif /* __UM_OS_LINUX_INTERNAL_H */
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index c8a42ecbd7a2..3c63ce19e3bf 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -11,19 +11,19 @@
#include <signal.h>
#include <string.h>
#include <sys/resource.h>
+#include <sys/personality.h>
#include <as-layout.h>
#include <init.h>
#include <kern_util.h>
#include <os.h>
#include <um_malloc.h>
+#include "internal.h"
-#define PGD_BOUND (4 * 1024 * 1024)
#define STACKSIZE (8 * 1024 * 1024)
-#define THREAD_NAME_LEN (256)
long elf_aux_hwcap;
-static void set_stklim(void)
+static void __init set_stklim(void)
{
struct rlimit lim;
@@ -46,7 +46,7 @@ static void last_ditch_exit(int sig)
exit(1);
}
-static void install_fatal_handler(int sig)
+static void __init install_fatal_handler(int sig)
{
struct sigaction action;
@@ -71,7 +71,7 @@ static void install_fatal_handler(int sig)
#define UML_LIB_PATH ":" OS_LIB_PATH "/uml"
-static void setup_env_path(void)
+static void __init setup_env_path(void)
{
char *new_path = NULL;
char *old_path = NULL;
@@ -102,13 +102,26 @@ static void setup_env_path(void)
}
}
-extern void scan_elf_aux( char **envp);
-
int __init main(int argc, char **argv, char **envp)
{
char **new_argv;
int ret, i, err;
+ /* Disable randomization and re-exec if it was changed successfully */
+ ret = personality(PER_LINUX | ADDR_NO_RANDOMIZE);
+ if (ret >= 0 && (ret & (PER_LINUX | ADDR_NO_RANDOMIZE)) !=
+ (PER_LINUX | ADDR_NO_RANDOMIZE)) {
+ char buf[4096] = {};
+ ssize_t ret;
+
+ ret = readlink("/proc/self/exe", buf, sizeof(buf));
+ if (ret < 0 || ret >= sizeof(buf)) {
+ perror("readlink failure");
+ exit(1);
+ }
+ execve(buf, argv, envp);
+ }
+
set_stklim();
setup_env_path();
@@ -141,7 +154,7 @@ int __init main(int argc, char **argv, char **envp)
#endif
change_sig(SIGPIPE, 0);
- ret = linux_main(argc, argv);
+ ret = linux_main(argc, argv, envp);
/*
* Disable SIGPROF - I have no idea why libc doesn't do this or turn
@@ -183,6 +196,12 @@ int __init main(int argc, char **argv, char **envp)
}
extern void *__real_malloc(int);
+extern void __real_free(void *);
+
+/* workaround for -Wmissing-prototypes warnings */
+void *__wrap_malloc(int size);
+void *__wrap_calloc(int n, int size);
+void __wrap_free(void *ptr);
void *__wrap_malloc(int size)
{
@@ -215,10 +234,6 @@ void *__wrap_calloc(int n, int size)
return ptr;
}
-extern void __real_free(void *);
-
-extern unsigned long high_physmem;
-
void __wrap_free(void *ptr)
{
unsigned long addr = (unsigned long) ptr;
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index 8530b2e08604..72f302f4d197 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -15,7 +15,9 @@
#include <sys/vfs.h>
#include <linux/magic.h>
#include <init.h>
+#include <kern_util.h>
#include <os.h>
+#include "internal.h"
/*
* kasan_map_memory - maps memory from @start with a size of @len.
@@ -37,10 +39,22 @@ void kasan_map_memory(void *start, size_t len)
strerror(errno));
exit(1);
}
+
+ if (madvise(start, len, MADV_DONTDUMP)) {
+ os_info("Couldn't set MAD_DONTDUMP on shadow memory: %s\n.",
+ strerror(errno));
+ exit(1);
+ }
+
+ if (madvise(start, len, MADV_DONTFORK)) {
+ os_info("Couldn't set MADV_DONTFORK on shadow memory: %s\n.",
+ strerror(errno));
+ exit(1);
+ }
}
/* Set by make_tempfile() during early boot. */
-static char *tempdir = NULL;
+char *tempdir = NULL;
/* Check if dir is on tmpfs. Return 0 if yes, -1 if no or error. */
static int __init check_tmpfs(const char *dir)
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index e52dd37ddadc..184566edeee9 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -12,94 +12,18 @@
#include <fcntl.h>
#include <sys/mman.h>
#include <sys/ptrace.h>
+#include <sys/prctl.h>
#include <sys/wait.h>
#include <asm/unistd.h>
#include <init.h>
#include <longjmp.h>
#include <os.h>
-#define ARBITRARY_ADDR -1
-#define FAILURE_PID -1
-
-#define STAT_PATH_LEN sizeof("/proc/#######/stat\0")
-#define COMM_SCANF "%*[^)])"
-
-unsigned long os_process_pc(int pid)
-{
- char proc_stat[STAT_PATH_LEN], buf[256];
- unsigned long pc = ARBITRARY_ADDR;
- int fd, err;
-
- sprintf(proc_stat, "/proc/%d/stat", pid);
- fd = open(proc_stat, O_RDONLY, 0);
- if (fd < 0) {
- printk(UM_KERN_ERR "os_process_pc - couldn't open '%s', "
- "errno = %d\n", proc_stat, errno);
- goto out;
- }
- CATCH_EINTR(err = read(fd, buf, sizeof(buf)));
- if (err < 0) {
- printk(UM_KERN_ERR "os_process_pc - couldn't read '%s', "
- "err = %d\n", proc_stat, errno);
- goto out_close;
- }
- os_close_file(fd);
- pc = ARBITRARY_ADDR;
- if (sscanf(buf, "%*d " COMM_SCANF " %*c %*d %*d %*d %*d %*d %*d %*d "
- "%*d %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d "
- "%*d %*d %*d %*d %*d %lu", &pc) != 1)
- printk(UM_KERN_ERR "os_process_pc - couldn't find pc in '%s'\n",
- buf);
- out_close:
- close(fd);
- out:
- return pc;
-}
-
-int os_process_parent(int pid)
-{
- char stat[STAT_PATH_LEN];
- char data[256];
- int parent = FAILURE_PID, n, fd;
-
- if (pid == -1)
- return parent;
-
- snprintf(stat, sizeof(stat), "/proc/%d/stat", pid);
- fd = open(stat, O_RDONLY, 0);
- if (fd < 0) {
- printk(UM_KERN_ERR "Couldn't open '%s', errno = %d\n", stat,
- errno);
- return parent;
- }
-
- CATCH_EINTR(n = read(fd, data, sizeof(data)));
- close(fd);
-
- if (n < 0) {
- printk(UM_KERN_ERR "Couldn't read '%s', errno = %d\n", stat,
- errno);
- return parent;
- }
-
- parent = FAILURE_PID;
- n = sscanf(data, "%*d " COMM_SCANF " %*c %d", &parent);
- if (n != 1)
- printk(UM_KERN_ERR "Failed to scan '%s'\n", data);
-
- return parent;
-}
-
void os_alarm_process(int pid)
{
kill(pid, SIGALRM);
}
-void os_stop_process(int pid)
-{
- kill(pid, SIGSTOP);
-}
-
void os_kill_process(int pid, int reap_child)
{
kill(pid, SIGKILL);
@@ -130,11 +54,6 @@ int os_getpid(void)
return syscall(__NR_getpid);
}
-int os_getpgrp(void)
-{
- return getpgrp();
-}
-
int os_map_memory(void *virt, int fd, unsigned long long off, unsigned long len,
int r, int w, int x)
{
@@ -223,57 +142,6 @@ out:
return ok;
}
-static int os_page_mincore(void *addr)
-{
- char vec[2];
- int ret;
-
- ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
- if (ret < 0) {
- if (errno == ENOMEM || errno == EINVAL)
- return 0;
- else
- return -errno;
- }
-
- return vec[0] & 1;
-}
-
-int os_mincore(void *addr, unsigned long len)
-{
- char *vec;
- int ret, i;
-
- if (len <= UM_KERN_PAGE_SIZE)
- return os_page_mincore(addr);
-
- vec = calloc(1, (len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE);
- if (!vec)
- return -ENOMEM;
-
- ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
- if (ret < 0) {
- if (errno == ENOMEM || errno == EINVAL)
- ret = 0;
- else
- ret = -errno;
-
- goto out;
- }
-
- for (i = 0; i < ((len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE); i++) {
- if (!(vec[i] & 1)) {
- ret = 0;
- goto out;
- }
- }
-
- ret = 1;
-out:
- free(vec);
- return ret;
-}
-
void init_new_thread_signals(void)
{
set_handler(SIGSEGV);
@@ -285,3 +153,8 @@ void init_new_thread_signals(void)
set_handler(SIGIO);
signal(SIGWINCH, SIG_IGN);
}
+
+void os_set_pdeathsig(void)
+{
+ prctl(PR_SET_PDEATHSIG, SIGKILL);
+}
diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c
index bd80b921add0..d7ca148807b2 100644
--- a/arch/um/os-Linux/registers.c
+++ b/arch/um/os-Linux/registers.c
@@ -10,11 +10,12 @@
#include <sysdep/ptrace.h>
#include <sysdep/ptrace_user.h>
#include <registers.h>
+#include <stdlib.h>
/* This is set once at boot time and not changed thereafter */
static unsigned long exec_regs[MAX_REG_NR];
-static unsigned long exec_fp_regs[FP_SIZE];
+static unsigned long *exec_fp_regs;
int init_pid_registers(int pid)
{
@@ -24,7 +25,11 @@ int init_pid_registers(int pid)
if (err < 0)
return -errno;
- arch_init_registers(pid);
+ err = arch_init_registers(pid);
+ if (err < 0)
+ return err;
+
+ exec_fp_regs = malloc(host_fp_size);
get_fp_registers(pid, exec_fp_regs);
return 0;
}
@@ -34,5 +39,5 @@ void get_safe_registers(unsigned long *regs, unsigned long *fp_regs)
memcpy(regs, exec_regs, sizeof(exec_regs));
if (fp_regs)
- memcpy(fp_regs, exec_fp_regs, sizeof(exec_fp_regs));
+ memcpy(fp_regs, exec_fp_regs, host_fp_size);
}
diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c
index 9e71794839e8..a05a6ecee756 100644
--- a/arch/um/os-Linux/sigio.c
+++ b/arch/um/os-Linux/sigio.c
@@ -11,6 +11,7 @@
#include <sched.h>
#include <signal.h>
#include <string.h>
+#include <sys/epoll.h>
#include <kern_util.h>
#include <init.h>
#include <os.h>
@@ -21,183 +22,51 @@
* Protected by sigio_lock(), also used by sigio_cleanup, which is an
* exitcall.
*/
-static int write_sigio_pid = -1;
-static unsigned long write_sigio_stack;
+static struct os_helper_thread *write_sigio_td;
-/*
- * These arrays are initialized before the sigio thread is started, and
- * the descriptors closed after it is killed. So, it can't see them change.
- * On the UML side, they are changed under the sigio_lock.
- */
-#define SIGIO_FDS_INIT {-1, -1}
-
-static int write_sigio_fds[2] = SIGIO_FDS_INIT;
-static int sigio_private[2] = SIGIO_FDS_INIT;
+static int epollfd = -1;
-struct pollfds {
- struct pollfd *poll;
- int size;
- int used;
-};
+#define MAX_EPOLL_EVENTS 64
-/*
- * Protected by sigio_lock(). Used by the sigio thread, but the UML thread
- * synchronizes with it.
- */
-static struct pollfds current_poll;
-static struct pollfds next_poll;
-static struct pollfds all_sigio_fds;
+static struct epoll_event epoll_events[MAX_EPOLL_EVENTS];
-static int write_sigio_thread(void *unused)
+static void *write_sigio_thread(void *unused)
{
- struct pollfds *fds, tmp;
- struct pollfd *p;
- int i, n, respond_fd;
- char c;
+ int pid = getpid();
+ int r;
+
+ os_fix_helper_thread_signals();
- os_fix_helper_signals();
- fds = &current_poll;
while (1) {
- n = poll(fds->poll, fds->used, -1);
- if (n < 0) {
+ r = epoll_wait(epollfd, epoll_events, MAX_EPOLL_EVENTS, -1);
+ if (r < 0) {
if (errno == EINTR)
continue;
- printk(UM_KERN_ERR "write_sigio_thread : poll returned "
- "%d, errno = %d\n", n, errno);
- }
- for (i = 0; i < fds->used; i++) {
- p = &fds->poll[i];
- if (p->revents == 0)
- continue;
- if (p->fd == sigio_private[1]) {
- CATCH_EINTR(n = read(sigio_private[1], &c,
- sizeof(c)));
- if (n != sizeof(c))
- printk(UM_KERN_ERR
- "write_sigio_thread : "
- "read on socket failed, "
- "err = %d\n", errno);
- tmp = current_poll;
- current_poll = next_poll;
- next_poll = tmp;
- respond_fd = sigio_private[1];
- }
- else {
- respond_fd = write_sigio_fds[1];
- fds->used--;
- memmove(&fds->poll[i], &fds->poll[i + 1],
- (fds->used - i) * sizeof(*fds->poll));
- }
-
- CATCH_EINTR(n = write(respond_fd, &c, sizeof(c)));
- if (n != sizeof(c))
- printk(UM_KERN_ERR "write_sigio_thread : "
- "write on socket failed, err = %d\n",
- errno);
+ printk(UM_KERN_ERR "%s: epoll_wait failed, errno = %d\n",
+ __func__, errno);
}
- }
-
- return 0;
-}
-
-static int need_poll(struct pollfds *polls, int n)
-{
- struct pollfd *new;
-
- if (n <= polls->size)
- return 0;
-
- new = uml_kmalloc(n * sizeof(struct pollfd), UM_GFP_ATOMIC);
- if (new == NULL) {
- printk(UM_KERN_ERR "need_poll : failed to allocate new "
- "pollfds\n");
- return -ENOMEM;
- }
-
- memcpy(new, polls->poll, polls->used * sizeof(struct pollfd));
- kfree(polls->poll);
-
- polls->poll = new;
- polls->size = n;
- return 0;
-}
-
-/*
- * Must be called with sigio_lock held, because it's needed by the marked
- * critical section.
- */
-static void update_thread(void)
-{
- unsigned long flags;
- int n;
- char c;
- flags = um_set_signals_trace(0);
- CATCH_EINTR(n = write(sigio_private[0], &c, sizeof(c)));
- if (n != sizeof(c)) {
- printk(UM_KERN_ERR "update_thread : write failed, err = %d\n",
- errno);
- goto fail;
+ CATCH_EINTR(r = tgkill(pid, pid, SIGIO));
+ if (r < 0)
+ printk(UM_KERN_ERR "%s: tgkill failed, errno = %d\n",
+ __func__, errno);
}
- CATCH_EINTR(n = read(sigio_private[0], &c, sizeof(c)));
- if (n != sizeof(c)) {
- printk(UM_KERN_ERR "update_thread : read failed, err = %d\n",
- errno);
- goto fail;
- }
-
- um_set_signals_trace(flags);
- return;
- fail:
- /* Critical section start */
- if (write_sigio_pid != -1) {
- os_kill_process(write_sigio_pid, 1);
- free_stack(write_sigio_stack, 0);
- }
- write_sigio_pid = -1;
- close(sigio_private[0]);
- close(sigio_private[1]);
- close(write_sigio_fds[0]);
- close(write_sigio_fds[1]);
- /* Critical section end */
- um_set_signals_trace(flags);
+ return NULL;
}
int __add_sigio_fd(int fd)
{
- struct pollfd *p;
- int err, i, n;
-
- for (i = 0; i < all_sigio_fds.used; i++) {
- if (all_sigio_fds.poll[i].fd == fd)
- break;
- }
- if (i == all_sigio_fds.used)
- return -ENOSPC;
-
- p = &all_sigio_fds.poll[i];
-
- for (i = 0; i < current_poll.used; i++) {
- if (current_poll.poll[i].fd == fd)
- return 0;
- }
-
- n = current_poll.used;
- err = need_poll(&next_poll, n + 1);
- if (err)
- return err;
-
- memcpy(next_poll.poll, current_poll.poll,
- current_poll.used * sizeof(struct pollfd));
- next_poll.poll[n] = *p;
- next_poll.used = n + 1;
- update_thread();
-
- return 0;
+ struct epoll_event event = {
+ .data.fd = fd,
+ .events = EPOLLIN | EPOLLET,
+ };
+ int r;
+
+ CATCH_EINTR(r = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &event));
+ return r < 0 ? -errno : 0;
}
-
int add_sigio_fd(int fd)
{
int err;
@@ -211,38 +80,11 @@ int add_sigio_fd(int fd)
int __ignore_sigio_fd(int fd)
{
- struct pollfd *p;
- int err, i, n = 0;
-
- /*
- * This is called from exitcalls elsewhere in UML - if
- * sigio_cleanup has already run, then update_thread will hang
- * or fail because the thread is no longer running.
- */
- if (write_sigio_pid == -1)
- return -EIO;
-
- for (i = 0; i < current_poll.used; i++) {
- if (current_poll.poll[i].fd == fd)
- break;
- }
- if (i == current_poll.used)
- return -ENOENT;
-
- err = need_poll(&next_poll, current_poll.used - 1);
- if (err)
- return err;
-
- for (i = 0; i < current_poll.used; i++) {
- p = &current_poll.poll[i];
- if (p->fd != fd)
- next_poll.poll[n++] = *p;
- }
- next_poll.used = current_poll.used - 1;
-
- update_thread();
+ struct epoll_event event;
+ int r;
- return 0;
+ CATCH_EINTR(r = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, &event));
+ return r < 0 ? -errno : 0;
}
int ignore_sigio_fd(int fd)
@@ -256,125 +98,37 @@ int ignore_sigio_fd(int fd)
return err;
}
-static struct pollfd *setup_initial_poll(int fd)
-{
- struct pollfd *p;
-
- p = uml_kmalloc(sizeof(struct pollfd), UM_GFP_KERNEL);
- if (p == NULL) {
- printk(UM_KERN_ERR "setup_initial_poll : failed to allocate "
- "poll\n");
- return NULL;
- }
- *p = ((struct pollfd) { .fd = fd,
- .events = POLLIN,
- .revents = 0 });
- return p;
-}
-
static void write_sigio_workaround(void)
{
- struct pollfd *p;
int err;
- int l_write_sigio_fds[2];
- int l_sigio_private[2];
- int l_write_sigio_pid;
- /* We call this *tons* of times - and most ones we must just fail. */
sigio_lock();
- l_write_sigio_pid = write_sigio_pid;
- sigio_unlock();
-
- if (l_write_sigio_pid != -1)
- return;
+ if (write_sigio_td)
+ goto out;
- err = os_pipe(l_write_sigio_fds, 1, 1);
- if (err < 0) {
- printk(UM_KERN_ERR "write_sigio_workaround - os_pipe 1 failed, "
- "err = %d\n", -err);
- return;
+ epollfd = epoll_create(MAX_EPOLL_EVENTS);
+ if (epollfd < 0) {
+ printk(UM_KERN_ERR "%s: epoll_create failed, errno = %d\n",
+ __func__, errno);
+ goto out;
}
- err = os_pipe(l_sigio_private, 1, 1);
+
+ err = os_run_helper_thread(&write_sigio_td, write_sigio_thread, NULL);
if (err < 0) {
- printk(UM_KERN_ERR "write_sigio_workaround - os_pipe 2 failed, "
- "err = %d\n", -err);
- goto out_close1;
+ printk(UM_KERN_ERR "%s: os_run_helper_thread failed, errno = %d\n",
+ __func__, -err);
+ close(epollfd);
+ epollfd = -1;
+ goto out;
}
- p = setup_initial_poll(l_sigio_private[1]);
- if (!p)
- goto out_close2;
-
- sigio_lock();
-
- /*
- * Did we race? Don't try to optimize this, please, it's not so likely
- * to happen, and no more than once at the boot.
- */
- if (write_sigio_pid != -1)
- goto out_free;
-
- current_poll = ((struct pollfds) { .poll = p,
- .used = 1,
- .size = 1 });
-
- if (write_sigio_irq(l_write_sigio_fds[0]))
- goto out_clear_poll;
-
- memcpy(write_sigio_fds, l_write_sigio_fds, sizeof(l_write_sigio_fds));
- memcpy(sigio_private, l_sigio_private, sizeof(l_sigio_private));
-
- write_sigio_pid = run_helper_thread(write_sigio_thread, NULL,
- CLONE_FILES | CLONE_VM,
- &write_sigio_stack);
-
- if (write_sigio_pid < 0)
- goto out_clear;
-
- sigio_unlock();
- return;
-
-out_clear:
- write_sigio_pid = -1;
- write_sigio_fds[0] = -1;
- write_sigio_fds[1] = -1;
- sigio_private[0] = -1;
- sigio_private[1] = -1;
-out_clear_poll:
- current_poll = ((struct pollfds) { .poll = NULL,
- .size = 0,
- .used = 0 });
-out_free:
+out:
sigio_unlock();
- kfree(p);
-out_close2:
- close(l_sigio_private[0]);
- close(l_sigio_private[1]);
-out_close1:
- close(l_write_sigio_fds[0]);
- close(l_write_sigio_fds[1]);
}
-void sigio_broken(int fd)
+void sigio_broken(void)
{
- int err;
-
write_sigio_workaround();
-
- sigio_lock();
- err = need_poll(&all_sigio_fds, all_sigio_fds.used + 1);
- if (err) {
- printk(UM_KERN_ERR "maybe_sigio_broken - failed to add pollfd "
- "for descriptor %d\n", fd);
- goto out;
- }
-
- all_sigio_fds.poll[all_sigio_fds.used++] =
- ((struct pollfd) { .fd = fd,
- .events = POLLIN,
- .revents = 0 });
-out:
- sigio_unlock();
}
/* Changed during early boot */
@@ -388,17 +142,16 @@ void maybe_sigio_broken(int fd)
if (pty_output_sigio)
return;
- sigio_broken(fd);
+ sigio_broken();
}
static void sigio_cleanup(void)
{
- if (write_sigio_pid == -1)
+ if (!write_sigio_td)
return;
- os_kill_process(write_sigio_pid, 1);
- free_stack(write_sigio_stack, 0);
- write_sigio_pid = -1;
+ os_kill_helper_thread(write_sigio_td);
+ write_sigio_td = NULL;
}
__uml_exitcall(sigio_cleanup);
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 24a403a70a02..e71e5b4878d1 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -8,6 +8,7 @@
#include <stdlib.h>
#include <stdarg.h>
+#include <stdbool.h>
#include <errno.h>
#include <signal.h>
#include <string.h>
@@ -20,12 +21,12 @@
#include <sys/ucontext.h>
#include <timetravel.h>
-void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
+void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *, void *mc) = {
[SIGTRAP] = relay_signal,
[SIGFPE] = relay_signal,
[SIGILL] = relay_signal,
[SIGWINCH] = winch,
- [SIGBUS] = bus_handler,
+ [SIGBUS] = relay_signal,
[SIGSEGV] = segv_handler,
[SIGIO] = sigio_handler,
};
@@ -46,7 +47,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
if ((sig != SIGIO) && (sig != SIGWINCH))
unblock_signals_trace();
- (*sig_info[sig])(sig, si, &r);
+ (*sig_info[sig])(sig, si, &r, mc);
errno = save_errno;
}
@@ -64,26 +65,37 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
#define SIGALRM_MASK (1 << SIGALRM_BIT)
int signals_enabled;
-#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
-static int signals_blocked;
-#else
-#define signals_blocked 0
+#if IS_ENABLED(CONFIG_UML_TIME_TRAVEL_SUPPORT)
+static int signals_blocked, signals_blocked_pending;
#endif
static unsigned int signals_pending;
static unsigned int signals_active = 0;
-void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
+static void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
{
int enabled = signals_enabled;
- if ((signals_blocked || !enabled) && (sig == SIGIO)) {
+#if IS_ENABLED(CONFIG_UML_TIME_TRAVEL_SUPPORT)
+ if ((signals_blocked ||
+ __atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) &&
+ (sig == SIGIO)) {
+ /* increment so unblock will do another round */
+ __atomic_add_fetch(&signals_blocked_pending, 1,
+ __ATOMIC_SEQ_CST);
+ return;
+ }
+#endif
+
+ if (!enabled && (sig == SIGIO)) {
/*
* In TT_MODE_EXTERNAL, need to still call time-travel
- * handlers unless signals are also blocked for the
- * external time message processing. This will mark
- * signals_pending by itself (only if necessary.)
+ * handlers. This will mark signals_pending by itself
+ * (only if necessary.)
+ * Note we won't get here if signals are hard-blocked
+ * (which is handled above), in that case the hard-
+ * unblock will handle things.
*/
- if (!signals_blocked && time_travel_mode == TT_MODE_EXTERNAL)
+ if (time_travel_mode == TT_MODE_EXTERNAL)
sigio_run_timetravel_handlers();
else
signals_pending |= SIGIO_MASK;
@@ -108,7 +120,7 @@ static void timer_real_alarm_handler(mcontext_t *mc)
timer_handler(SIGALRM, NULL, &regs);
}
-void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc)
+static void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc)
{
int enabled;
@@ -178,43 +190,8 @@ static void hard_handler(int sig, siginfo_t *si, void *p)
{
ucontext_t *uc = p;
mcontext_t *mc = &uc->uc_mcontext;
- unsigned long pending = 1UL << sig;
-
- do {
- int nested, bail;
-
- /*
- * pending comes back with one bit set for each
- * interrupt that arrived while setting up the stack,
- * plus a bit for this interrupt, plus the zero bit is
- * set if this is a nested interrupt.
- * If bail is true, then we interrupted another
- * handler setting up the stack. In this case, we
- * have to return, and the upper handler will deal
- * with this interrupt.
- */
- bail = to_irq_stack(&pending);
- if (bail)
- return;
-
- nested = pending & 1;
- pending &= ~1;
- while ((sig = ffs(pending)) != 0){
- sig--;
- pending &= ~(1 << sig);
- (*handlers[sig])(sig, (struct siginfo *)si, mc);
- }
-
- /*
- * Again, pending comes back with a mask of signals
- * that arrived while tearing down the stack. If this
- * is non-zero, we just go back, set up the stack
- * again, and handle the new interrupts.
- */
- if (!nested)
- pending = from_irq_stack(nested);
- } while (pending);
+ (*handlers[sig])(sig, (struct siginfo *)si, mc);
}
void set_handler(int sig)
@@ -285,7 +262,7 @@ void unblock_signals(void)
return;
signals_enabled = 1;
-#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
+#if IS_ENABLED(CONFIG_UML_TIME_TRAVEL_SUPPORT)
deliver_time_travel_irqs();
#endif
@@ -377,43 +354,101 @@ int um_set_signals_trace(int enable)
return ret;
}
-#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
+#if IS_ENABLED(CONFIG_UML_TIME_TRAVEL_SUPPORT)
void mark_sigio_pending(void)
{
+ /*
+ * It would seem that this should be atomic so
+ * it isn't a read-modify-write with a signal
+ * that could happen in the middle, losing the
+ * value set by the signal.
+ *
+ * However, this function is only called when in
+ * time-travel=ext simulation mode, in which case
+ * the only signal ever pending is SIGIO, which
+ * is blocked while this can be called, and the
+ * timer signal (SIGALRM) cannot happen.
+ */
signals_pending |= SIGIO_MASK;
}
void block_signals_hard(void)
{
- if (signals_blocked)
- return;
- signals_blocked = 1;
+ signals_blocked++;
barrier();
}
void unblock_signals_hard(void)
{
+ static bool unblocking;
+
if (!signals_blocked)
+ panic("unblocking signals while not blocked");
+
+ if (--signals_blocked)
return;
- /* Must be set to 0 before we check the pending bits etc. */
- signals_blocked = 0;
+ /*
+ * Must be set to 0 before we check pending so the
+ * SIGIO handler will run as normal unless we're still
+ * going to process signals_blocked_pending.
+ */
barrier();
- if (signals_pending && signals_enabled) {
- /* this is a bit inefficient, but that's not really important */
- block_signals();
- unblock_signals();
- } else if (signals_pending & SIGIO_MASK) {
- /* we need to run time-travel handlers even if not enabled */
- sigio_run_timetravel_handlers();
- }
-}
-#endif
+ /*
+ * Note that block_signals_hard()/unblock_signals_hard() can be called
+ * within the unblock_signals()/sigio_run_timetravel_handlers() below.
+ * This would still be prone to race conditions since it's actually a
+ * call _within_ e.g. vu_req_read_message(), where we observed this
+ * issue, which loops. Thus, if the inner call handles the recorded
+ * pending signals, we can get out of the inner call with the real
+ * signal hander no longer blocked, and still have a race. Thus don't
+ * handle unblocking in the inner call, if it happens, but only in
+ * the outermost call - 'unblocking' serves as an ownership for the
+ * signals_blocked_pending decrement.
+ */
+ if (unblocking)
+ return;
+ unblocking = true;
-int os_is_signal_stack(void)
-{
- stack_t ss;
- sigaltstack(NULL, &ss);
+ while (__atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) {
+ if (signals_enabled) {
+ /* signals are enabled so we can touch this */
+ signals_pending |= SIGIO_MASK;
+ /*
+ * this is a bit inefficient, but that's
+ * not really important
+ */
+ block_signals();
+ unblock_signals();
+ } else {
+ /*
+ * we need to run time-travel handlers even
+ * if not enabled
+ */
+ sigio_run_timetravel_handlers();
+ }
- return ss.ss_flags & SS_ONSTACK;
+ /*
+ * The decrement of signals_blocked_pending must be atomic so
+ * that the signal handler will either happen before or after
+ * the decrement, not during a read-modify-write:
+ * - If it happens before, it can increment it and we'll
+ * decrement it and do another round in the loop.
+ * - If it happens after it'll see 0 for both signals_blocked
+ * and signals_blocked_pending and thus run the handler as
+ * usual (subject to signals_enabled, but that's unrelated.)
+ *
+ * Note that a call to unblock_signals_hard() within the calls
+ * to unblock_signals() or sigio_run_timetravel_handlers() above
+ * will do nothing due to the 'unblocking' state, so this cannot
+ * underflow as the only one decrementing will be the outermost
+ * one.
+ */
+ if (__atomic_sub_fetch(&signals_blocked_pending, 1,
+ __ATOMIC_SEQ_CST) < 0)
+ panic("signals_blocked_pending underflow");
+ }
+
+ unblocking = false;
}
+#endif
diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c
index 953fb10f3f93..d7f1814b0e5a 100644
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
+ * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net>
* Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
*/
@@ -17,10 +18,32 @@
#include <skas.h>
#include <sysdep/ptrace.h>
#include <sysdep/stub.h>
+#include "../internal.h"
-extern char batch_syscall_stub[], __syscall_stub_start[];
+extern char __syscall_stub_start[];
-extern void wait_stub_done(int pid);
+void syscall_stub_dump_error(struct mm_id *mm_idp)
+{
+ struct stub_data *proc_data = (void *)mm_idp->stack;
+ struct stub_syscall *sc;
+
+ if (proc_data->syscall_data_len < 0 ||
+ proc_data->syscall_data_len >= ARRAY_SIZE(proc_data->syscall_data))
+ panic("Syscall data was corrupted by stub (len is: %d, expected maximum: %d)!",
+ proc_data->syscall_data_len,
+ mm_idp->syscall_data_len);
+
+ sc = &proc_data->syscall_data[proc_data->syscall_data_len];
+
+ printk(UM_KERN_ERR "%s : length = %d, last offset = %d",
+ __func__, mm_idp->syscall_data_len,
+ proc_data->syscall_data_len);
+ printk(UM_KERN_ERR "%s : stub syscall type %d failed, return value = 0x%lx\n",
+ __func__, sc->syscall, proc_data->err);
+
+ print_hex_dump(UM_KERN_ERR, " syscall data: ", 0,
+ 16, 4, sc, sizeof(*sc), 0);
+}
static inline unsigned long *check_init_stack(struct mm_id * mm_idp,
unsigned long *stack)
@@ -37,23 +60,25 @@ static unsigned long syscall_regs[MAX_REG_NR];
static int __init init_syscall_regs(void)
{
get_safe_registers(syscall_regs, NULL);
+
syscall_regs[REGS_IP_INDEX] = STUB_CODE +
- ((unsigned long) batch_syscall_stub -
+ ((unsigned long) stub_syscall_handler -
(unsigned long) __syscall_stub_start);
- syscall_regs[REGS_SP_INDEX] = STUB_DATA;
+ syscall_regs[REGS_SP_INDEX] = STUB_DATA +
+ offsetof(struct stub_data, sigstack) +
+ sizeof(((struct stub_data *) 0)->sigstack) -
+ sizeof(void *);
return 0;
}
__initcall(init_syscall_regs);
-static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr)
+static inline long do_syscall_stub(struct mm_id *mm_idp)
{
+ struct stub_data *proc_data = (void *)mm_idp->stack;
int n, i;
- long ret, offset;
- unsigned long * data;
- unsigned long * syscall;
- int err, pid = mm_idp->u.pid;
+ int err, pid = mm_idp->pid;
n = ptrace_setregs(pid, syscall_regs);
if (n < 0) {
@@ -64,6 +89,9 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr)
__func__, -n);
}
+ /* Inform process how much we have filled in. */
+ proc_data->syscall_data_len = mm_idp->syscall_data_len;
+
err = ptrace(PTRACE_CONT, pid, 0, 0);
if (err)
panic("Failed to continue stub, pid = %d, errno = %d\n", pid,
@@ -72,135 +100,120 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr)
wait_stub_done(pid);
/*
- * When the stub stops, we find the following values on the
- * beginning of the stack:
- * (long )return_value
- * (long )offset to failed sycall-data (0, if no error)
+ * proc_data->err will be non-zero if there was an (unexpected) error.
+ * In that case, syscall_data_len points to the last executed syscall,
+ * otherwise it will be zero (but we do not need to rely on that).
*/
- ret = *((unsigned long *) mm_idp->stack);
- offset = *((unsigned long *) mm_idp->stack + 1);
- if (offset) {
- data = (unsigned long *)(mm_idp->stack + offset - STUB_DATA);
- printk(UM_KERN_ERR "%s : ret = %ld, offset = %ld, data = %p\n",
- __func__, ret, offset, data);
- syscall = (unsigned long *)((unsigned long)data + data[0]);
- printk(UM_KERN_ERR "%s: syscall %ld failed, return value = 0x%lx, expected return value = 0x%lx\n",
- __func__, syscall[0], ret, syscall[7]);
- printk(UM_KERN_ERR " syscall parameters: 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
- syscall[1], syscall[2], syscall[3],
- syscall[4], syscall[5], syscall[6]);
- for (n = 1; n < data[0]/sizeof(long); n++) {
- if (n == 1)
- printk(UM_KERN_ERR " additional syscall data:");
- if (n % 4 == 1)
- printk("\n" UM_KERN_ERR " ");
- printk(" 0x%lx", data[n]);
- }
- if (n > 1)
- printk("\n");
- }
- else ret = 0;
+ if (proc_data->err < 0) {
+ syscall_stub_dump_error(mm_idp);
- *addr = check_init_stack(mm_idp, NULL);
+ /* Store error code in case someone tries to add more syscalls */
+ mm_idp->syscall_data_len = proc_data->err;
+ } else {
+ mm_idp->syscall_data_len = 0;
+ }
- return ret;
+ return mm_idp->syscall_data_len;
}
-long run_syscall_stub(struct mm_id * mm_idp, int syscall,
- unsigned long *args, long expected, void **addr,
- int done)
+int syscall_stub_flush(struct mm_id *mm_idp)
{
- unsigned long *stack = check_init_stack(mm_idp, *addr);
-
- *stack += sizeof(long);
- stack += *stack / sizeof(long);
-
- *stack++ = syscall;
- *stack++ = args[0];
- *stack++ = args[1];
- *stack++ = args[2];
- *stack++ = args[3];
- *stack++ = args[4];
- *stack++ = args[5];
- *stack++ = expected;
- *stack = 0;
-
- if (!done && ((((unsigned long) stack) & ~UM_KERN_PAGE_MASK) <
- UM_KERN_PAGE_SIZE - 10 * sizeof(long))) {
- *addr = stack;
+ int res;
+
+ if (mm_idp->syscall_data_len == 0)
return 0;
+
+ /* If an error happened already, report it and reset the state. */
+ if (mm_idp->syscall_data_len < 0) {
+ res = mm_idp->syscall_data_len;
+ mm_idp->syscall_data_len = 0;
+ return res;
}
- return do_syscall_stub(mm_idp, addr);
+ res = do_syscall_stub(mm_idp);
+ mm_idp->syscall_data_len = 0;
+
+ return res;
}
-long syscall_stub_data(struct mm_id * mm_idp,
- unsigned long *data, int data_count,
- void **addr, void **stub_addr)
+struct stub_syscall *syscall_stub_alloc(struct mm_id *mm_idp)
{
- unsigned long *stack;
- int ret = 0;
-
- /*
- * If *addr still is uninitialized, it *must* contain NULL.
- * Thus in this case do_syscall_stub correctly won't be called.
- */
- if ((((unsigned long) *addr) & ~UM_KERN_PAGE_MASK) >=
- UM_KERN_PAGE_SIZE - (10 + data_count) * sizeof(long)) {
- ret = do_syscall_stub(mm_idp, addr);
- /* in case of error, don't overwrite data on stack */
- if (ret)
- return ret;
+ struct stub_syscall *sc;
+ struct stub_data *proc_data = (struct stub_data *) mm_idp->stack;
+
+ if (mm_idp->syscall_data_len > 0 &&
+ mm_idp->syscall_data_len == ARRAY_SIZE(proc_data->syscall_data))
+ do_syscall_stub(mm_idp);
+
+ if (mm_idp->syscall_data_len < 0) {
+ /* Return dummy to retain error state. */
+ sc = &proc_data->syscall_data[0];
+ } else {
+ sc = &proc_data->syscall_data[mm_idp->syscall_data_len];
+ mm_idp->syscall_data_len += 1;
}
+ memset(sc, 0, sizeof(*sc));
- stack = check_init_stack(mm_idp, *addr);
- *addr = stack;
-
- *stack = data_count * sizeof(long);
-
- memcpy(stack + 1, data, data_count * sizeof(long));
-
- *stub_addr = (void *)(((unsigned long)(stack + 1) &
- ~UM_KERN_PAGE_MASK) + STUB_DATA);
-
- return 0;
+ return sc;
}
-int map(struct mm_id * mm_idp, unsigned long virt, unsigned long len, int prot,
- int phys_fd, unsigned long long offset, int done, void **data)
+static struct stub_syscall *syscall_stub_get_previous(struct mm_id *mm_idp,
+ int syscall_type,
+ unsigned long virt)
{
- int ret;
- unsigned long args[] = { virt, len, prot,
- MAP_SHARED | MAP_FIXED, phys_fd,
- MMAP_OFFSET(offset) };
+ if (mm_idp->syscall_data_len > 0) {
+ struct stub_data *proc_data = (void *) mm_idp->stack;
+ struct stub_syscall *sc;
+
+ sc = &proc_data->syscall_data[mm_idp->syscall_data_len - 1];
- ret = run_syscall_stub(mm_idp, STUB_MMAP_NR, args, virt,
- data, done);
+ if (sc->syscall == syscall_type &&
+ sc->mem.addr + sc->mem.length == virt)
+ return sc;
+ }
- return ret;
+ return NULL;
}
-int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len,
- int done, void **data)
+int map(struct mm_id *mm_idp, unsigned long virt, unsigned long len, int prot,
+ int phys_fd, unsigned long long offset)
{
- int ret;
- unsigned long args[] = { (unsigned long) addr, len, 0, 0, 0,
- 0 };
+ struct stub_syscall *sc;
- ret = run_syscall_stub(mm_idp, __NR_munmap, args, 0,
- data, done);
+ /* Compress with previous syscall if that is possible */
+ sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MMAP, virt);
+ if (sc && sc->mem.prot == prot && sc->mem.fd == phys_fd &&
+ sc->mem.offset == MMAP_OFFSET(offset - sc->mem.length)) {
+ sc->mem.length += len;
+ return 0;
+ }
+
+ sc = syscall_stub_alloc(mm_idp);
+ sc->syscall = STUB_SYSCALL_MMAP;
+ sc->mem.addr = virt;
+ sc->mem.length = len;
+ sc->mem.prot = prot;
+ sc->mem.fd = phys_fd;
+ sc->mem.offset = MMAP_OFFSET(offset);
- return ret;
+ return 0;
}
-int protect(struct mm_id * mm_idp, unsigned long addr, unsigned long len,
- unsigned int prot, int done, void **data)
+int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len)
{
- int ret;
- unsigned long args[] = { addr, len, prot, 0, 0, 0 };
+ struct stub_syscall *sc;
- ret = run_syscall_stub(mm_idp, __NR_mprotect, args, 0,
- data, done);
+ /* Compress with previous syscall if that is possible */
+ sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MUNMAP, addr);
+ if (sc) {
+ sc->mem.length += len;
+ return 0;
+ }
+
+ sc = syscall_stub_alloc(mm_idp);
+ sc->syscall = STUB_SYSCALL_MUNMAP;
+ sc->mem.addr = addr;
+ sc->mem.length = len;
- return ret;
+ return 0;
}
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 1f5c3f2523d1..ae2aea062f06 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -10,8 +10,11 @@
#include <sched.h>
#include <errno.h>
#include <string.h>
+#include <fcntl.h>
+#include <mem_user.h>
#include <sys/mman.h>
#include <sys/wait.h>
+#include <sys/stat.h>
#include <asm/unistd.h>
#include <as-layout.h>
#include <init.h>
@@ -23,6 +26,8 @@
#include <skas.h>
#include <sysdep/stub.h>
#include <linux/threads.h>
+#include <timetravel.h>
+#include "../internal.h"
int is_skas_winch(int pid, int fd, void *data)
{
@@ -139,16 +144,10 @@ bad_wait:
extern unsigned long current_stub_stack(void);
-static void get_skas_faultinfo(int pid, struct faultinfo *fi, unsigned long *aux_fp_regs)
+static void get_skas_faultinfo(int pid, struct faultinfo *fi)
{
int err;
- err = get_fp_registers(pid, aux_fp_regs);
- if (err < 0) {
- printk(UM_KERN_ERR "save_fp_registers returned %d\n",
- err);
- fatal_sigsegv();
- }
err = ptrace(PTRACE_CONT, pid, 0, SIGSEGV);
if (err) {
printk(UM_KERN_ERR "Failed to continue stub, pid = %d, "
@@ -162,19 +161,12 @@ static void get_skas_faultinfo(int pid, struct faultinfo *fi, unsigned long *aux
* the stub stack page. We just have to copy it.
*/
memcpy(fi, (void *)current_stub_stack(), sizeof(*fi));
-
- err = put_fp_registers(pid, aux_fp_regs);
- if (err < 0) {
- printk(UM_KERN_ERR "put_fp_registers returned %d\n",
- err);
- fatal_sigsegv();
- }
}
-static void handle_segv(int pid, struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
+static void handle_segv(int pid, struct uml_pt_regs *regs)
{
- get_skas_faultinfo(pid, &regs->faultinfo, aux_fp_regs);
- segv(regs->faultinfo, 0, 1, NULL);
+ get_skas_faultinfo(pid, &regs->faultinfo);
+ segv(regs->faultinfo, 0, 1, NULL, NULL);
}
static void handle_trap(int pid, struct uml_pt_regs *regs)
@@ -187,72 +179,143 @@ static void handle_trap(int pid, struct uml_pt_regs *regs)
extern char __syscall_stub_start[];
-/**
- * userspace_tramp() - userspace trampoline
- * @stack: pointer to the new userspace stack page
- *
- * The userspace trampoline is used to setup a new userspace process in start_userspace() after it was clone()'ed.
- * This function will run on a temporary stack page.
- * It ptrace()'es itself, then
- * Two pages are mapped into the userspace address space:
- * - STUB_CODE (with EXEC), which contains the skas stub code
- * - STUB_DATA (with R/W), which contains a data page that is used to transfer certain data between the UML userspace process and the UML kernel.
- * Also for the userspace process a SIGSEGV handler is installed to catch pagefaults in the userspace process.
- * And last the process stops itself to give control to the UML kernel for this userspace process.
- *
- * Return: Always zero, otherwise the current userspace process is ended with non null exit() call
- */
+static int stub_exe_fd;
+
+#ifndef CLOSE_RANGE_CLOEXEC
+#define CLOSE_RANGE_CLOEXEC (1U << 2)
+#endif
+
static int userspace_tramp(void *stack)
{
- struct sigaction sa;
- void *addr;
- int fd;
+ char *const argv[] = { "uml-userspace", NULL };
+ int pipe_fds[2];
unsigned long long offset;
- unsigned long segv_handler = STUB_CODE +
- (unsigned long) stub_segv_handler -
- (unsigned long) __syscall_stub_start;
-
- ptrace(PTRACE_TRACEME, 0, 0, 0);
-
- signal(SIGTERM, SIG_DFL);
- signal(SIGWINCH, SIG_IGN);
-
- fd = phys_mapping(uml_to_phys(__syscall_stub_start), &offset);
- addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE,
- PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset);
- if (addr == MAP_FAILED) {
- os_info("mapping mmap stub at 0x%lx failed, errno = %d\n",
- STUB_CODE, errno);
- exit(1);
+ struct stub_init_data init_data = {
+ .stub_start = STUB_START,
+ .segv_handler = STUB_CODE +
+ (unsigned long) stub_segv_handler -
+ (unsigned long) __syscall_stub_start,
+ };
+ struct iomem_region *iomem;
+ int ret;
+
+ init_data.stub_code_fd = phys_mapping(uml_to_phys(__syscall_stub_start),
+ &offset);
+ init_data.stub_code_offset = MMAP_OFFSET(offset);
+
+ init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset);
+ init_data.stub_data_offset = MMAP_OFFSET(offset);
+
+ /*
+ * Avoid leaking unneeded FDs to the stub by setting CLOEXEC on all FDs
+ * and then unsetting it on all memory related FDs.
+ * This is not strictly necessary from a safety perspective.
+ */
+ syscall(__NR_close_range, 0, ~0U, CLOSE_RANGE_CLOEXEC);
+
+ fcntl(init_data.stub_data_fd, F_SETFD, 0);
+ for (iomem = iomem_regions; iomem; iomem = iomem->next)
+ fcntl(iomem->fd, F_SETFD, 0);
+
+ /* Create a pipe for init_data (no CLOEXEC) and dup2 to STDIN */
+ if (pipe(pipe_fds))
+ exit(2);
+
+ if (dup2(pipe_fds[0], 0) < 0)
+ exit(3);
+ close(pipe_fds[0]);
+
+ /* Write init_data and close write side */
+ ret = write(pipe_fds[1], &init_data, sizeof(init_data));
+ close(pipe_fds[1]);
+
+ if (ret != sizeof(init_data))
+ exit(4);
+
+ /* Raw execveat for compatibility with older libc versions */
+ syscall(__NR_execveat, stub_exe_fd, (unsigned long)"",
+ (unsigned long)argv, NULL, AT_EMPTY_PATH);
+
+ exit(5);
+}
+
+extern char stub_exe_start[];
+extern char stub_exe_end[];
+
+extern char *tempdir;
+
+#define STUB_EXE_NAME_TEMPLATE "/uml-userspace-XXXXXX"
+
+#ifndef MFD_EXEC
+#define MFD_EXEC 0x0010U
+#endif
+
+static int __init init_stub_exe_fd(void)
+{
+ size_t written = 0;
+ char *tmpfile = NULL;
+
+ stub_exe_fd = memfd_create("uml-userspace",
+ MFD_EXEC | MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+ if (stub_exe_fd < 0) {
+ printk(UM_KERN_INFO "Could not create executable memfd, using temporary file!");
+
+ tmpfile = malloc(strlen(tempdir) +
+ strlen(STUB_EXE_NAME_TEMPLATE) + 1);
+ if (tmpfile == NULL)
+ panic("Failed to allocate memory for stub binary name");
+
+ strcpy(tmpfile, tempdir);
+ strcat(tmpfile, STUB_EXE_NAME_TEMPLATE);
+
+ stub_exe_fd = mkstemp(tmpfile);
+ if (stub_exe_fd < 0)
+ panic("Could not create temporary file for stub binary: %d",
+ -errno);
}
- fd = phys_mapping(uml_to_phys(stack), &offset);
- addr = mmap((void *) STUB_DATA,
- STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_SHARED, fd, offset);
- if (addr == MAP_FAILED) {
- os_info("mapping segfault stack at 0x%lx failed, errno = %d\n",
- STUB_DATA, errno);
- exit(1);
+ while (written < stub_exe_end - stub_exe_start) {
+ ssize_t res = write(stub_exe_fd, stub_exe_start + written,
+ stub_exe_end - stub_exe_start - written);
+ if (res < 0) {
+ if (errno == EINTR)
+ continue;
+
+ if (tmpfile)
+ unlink(tmpfile);
+ panic("Failed write stub binary: %d", -errno);
+ }
+
+ written += res;
}
- set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
- sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
- sa.sa_sigaction = (void *) segv_handler;
- sa.sa_restorer = NULL;
- if (sigaction(SIGSEGV, &sa, NULL) < 0) {
- os_info("%s - setting SIGSEGV handler failed - errno = %d\n",
- __func__, errno);
- exit(1);
+ if (!tmpfile) {
+ fcntl(stub_exe_fd, F_ADD_SEALS,
+ F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_SEAL);
+ } else {
+ if (fchmod(stub_exe_fd, 00500) < 0) {
+ unlink(tmpfile);
+ panic("Could not make stub binary executable: %d",
+ -errno);
+ }
+
+ close(stub_exe_fd);
+ stub_exe_fd = open(tmpfile, O_RDONLY | O_CLOEXEC | O_NOFOLLOW);
+ if (stub_exe_fd < 0) {
+ unlink(tmpfile);
+ panic("Could not reopen stub binary: %d", -errno);
+ }
+
+ unlink(tmpfile);
+ free(tmpfile);
}
- kill(os_getpid(), SIGSTOP);
return 0;
}
+__initcall(init_stub_exe_fd);
int userspace_pid[NR_CPUS];
-int kill_userspace_mm[NR_CPUS];
/**
* start_userspace() - prepare a new userspace process
@@ -269,7 +332,7 @@ int start_userspace(unsigned long stub_stack)
{
void *stack;
unsigned long sp;
- int pid, status, n, flags, err;
+ int pid, status, n, err;
/* setup a temporary stack page */
stack = mmap(NULL, UM_KERN_PAGE_SIZE,
@@ -285,10 +348,10 @@ int start_userspace(unsigned long stub_stack)
/* set stack pointer to the end of the stack page, so it can grow downwards */
sp = (unsigned long)stack + UM_KERN_PAGE_SIZE;
- flags = CLONE_FILES | SIGCHLD;
-
/* clone into new userspace process */
- pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack);
+ pid = clone(userspace_tramp, (void *) sp,
+ CLONE_VFORK | CLONE_VM | SIGCHLD,
+ (void *)stub_stack);
if (pid < 0) {
err = -errno;
printk(UM_KERN_ERR "%s : clone failed, errno = %d\n",
@@ -335,7 +398,10 @@ int start_userspace(unsigned long stub_stack)
return err;
}
-void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
+int unscheduled_userspace_iterations;
+extern unsigned long tt_extra_sched_jiffies;
+
+void userspace(struct uml_pt_regs *regs)
{
int err, status, op, pid = userspace_pid[0];
siginfo_t si;
@@ -344,8 +410,43 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
interrupt_end();
while (1) {
- if (kill_userspace_mm[0])
+ /*
+ * When we are in time-travel mode, userspace can theoretically
+ * do a *lot* of work without being scheduled. The problem with
+ * this is that it will prevent kernel bookkeeping (primarily
+ * the RCU) from running and this can for example cause OOM
+ * situations.
+ *
+ * This code accounts a jiffie against the scheduling clock
+ * after the defined userspace iterations in the same thread.
+ * By doing so the situation is effectively prevented.
+ */
+ if (time_travel_mode == TT_MODE_INFCPU ||
+ time_travel_mode == TT_MODE_EXTERNAL) {
+#ifdef CONFIG_UML_MAX_USERSPACE_ITERATIONS
+ if (CONFIG_UML_MAX_USERSPACE_ITERATIONS &&
+ unscheduled_userspace_iterations++ >
+ CONFIG_UML_MAX_USERSPACE_ITERATIONS) {
+ tt_extra_sched_jiffies += 1;
+ unscheduled_userspace_iterations = 0;
+ }
+#endif
+ }
+
+ time_travel_print_bc_msg();
+
+ current_mm_sync();
+
+ /* Flush out any pending syscalls */
+ err = syscall_stub_flush(current_mm_id());
+ if (err) {
+ if (err == -ENOMEM)
+ report_enomem();
+
+ printk(UM_KERN_ERR "%s - Error flushing stub syscalls: %d",
+ __func__, -err);
fatal_sigsegv();
+ }
/*
* This can legitimately fail if the process loads a
@@ -422,17 +523,17 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
case SIGSEGV:
if (PTRACE_FULL_FAULTINFO) {
get_skas_faultinfo(pid,
- &regs->faultinfo, aux_fp_regs);
+ &regs->faultinfo);
(*sig_info[SIGSEGV])(SIGSEGV, (struct siginfo *)&si,
- regs);
+ regs, NULL);
}
- else handle_segv(pid, regs, aux_fp_regs);
+ else handle_segv(pid, regs);
break;
case SIGTRAP + 0x80:
handle_trap(pid, regs);
break;
case SIGTRAP:
- relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
+ relay_signal(SIGTRAP, (struct siginfo *)&si, regs, NULL);
break;
case SIGALRM:
break;
@@ -442,7 +543,7 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
case SIGFPE:
case SIGWINCH:
block_signals_trace();
- (*sig_info[sig])(sig, (struct siginfo *)&si, regs);
+ (*sig_info[sig])(sig, (struct siginfo *)&si, regs, NULL);
unblock_signals_trace();
break;
default:
@@ -460,113 +561,6 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
}
}
-static unsigned long thread_regs[MAX_REG_NR];
-static unsigned long thread_fp_regs[FP_SIZE];
-
-static int __init init_thread_regs(void)
-{
- get_safe_registers(thread_regs, thread_fp_regs);
- /* Set parent's instruction pointer to start of clone-stub */
- thread_regs[REGS_IP_INDEX] = STUB_CODE +
- (unsigned long) stub_clone_handler -
- (unsigned long) __syscall_stub_start;
- thread_regs[REGS_SP_INDEX] = STUB_DATA + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE -
- sizeof(void *);
-#ifdef __SIGNAL_FRAMESIZE
- thread_regs[REGS_SP_INDEX] -= __SIGNAL_FRAMESIZE;
-#endif
- return 0;
-}
-
-__initcall(init_thread_regs);
-
-int copy_context_skas0(unsigned long new_stack, int pid)
-{
- int err;
- unsigned long current_stack = current_stub_stack();
- struct stub_data *data = (struct stub_data *) current_stack;
- struct stub_data *child_data = (struct stub_data *) new_stack;
- unsigned long long new_offset;
- int new_fd = phys_mapping(uml_to_phys((void *)new_stack), &new_offset);
-
- /*
- * prepare offset and fd of child's stack as argument for parent's
- * and child's mmap2 calls
- */
- *data = ((struct stub_data) {
- .offset = MMAP_OFFSET(new_offset),
- .fd = new_fd,
- .parent_err = -ESRCH,
- .child_err = 0,
- });
-
- *child_data = ((struct stub_data) {
- .child_err = -ESRCH,
- });
-
- err = ptrace_setregs(pid, thread_regs);
- if (err < 0) {
- err = -errno;
- printk(UM_KERN_ERR "%s : PTRACE_SETREGS failed, pid = %d, errno = %d\n",
- __func__, pid, -err);
- return err;
- }
-
- err = put_fp_registers(pid, thread_fp_regs);
- if (err < 0) {
- printk(UM_KERN_ERR "%s : put_fp_registers failed, pid = %d, err = %d\n",
- __func__, pid, err);
- return err;
- }
-
- /*
- * Wait, until parent has finished its work: read child's pid from
- * parent's stack, and check, if bad result.
- */
- err = ptrace(PTRACE_CONT, pid, 0, 0);
- if (err) {
- err = -errno;
- printk(UM_KERN_ERR "Failed to continue new process, pid = %d, errno = %d\n",
- pid, errno);
- return err;
- }
-
- wait_stub_done(pid);
-
- pid = data->parent_err;
- if (pid < 0) {
- printk(UM_KERN_ERR "%s - stub-parent reports error %d\n",
- __func__, -pid);
- return pid;
- }
-
- /*
- * Wait, until child has finished too: read child's result from
- * child's stack and check it.
- */
- wait_stub_done(pid);
- if (child_data->child_err != STUB_DATA) {
- printk(UM_KERN_ERR "%s - stub-child %d reports error %ld\n",
- __func__, pid, data->child_err);
- err = data->child_err;
- goto out_kill;
- }
-
- if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
- (void *)PTRACE_O_TRACESYSGOOD) < 0) {
- err = -errno;
- printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
- __func__, errno);
- goto out_kill;
- }
-
- return pid;
-
- out_kill:
- os_kill_ptraced_process(pid, 1);
- return err;
-}
-
void new_thread(void *stack, jmp_buf *buf, void (*handler)(void))
{
(*buf)[0].JB_IP = (unsigned long) handler;
@@ -581,6 +575,8 @@ void new_thread(void *stack, jmp_buf *buf, void (*handler)(void))
void switch_threads(jmp_buf *me, jmp_buf *you)
{
+ unscheduled_userspace_iterations = 0;
+
if (UML_SETJMP(me) == 0)
UML_LONGJMP(you, 1);
}
@@ -664,6 +660,7 @@ static bool noreboot;
static int __init noreboot_cmd_param(char *str, int *add)
{
+ *add = 0;
noreboot = true;
return 0;
}
@@ -682,6 +679,5 @@ void reboot_skas(void)
void __switch_mm(struct mm_id *mm_idp)
{
- userspace_pid[0] = mm_idp->u.pid;
- kill_userspace_mm[0] = mm_idp->kill;
+ userspace_pid[0] = mm_idp->pid;
}
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 8b0e98ab842c..93fc82c01aba 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -17,13 +17,16 @@
#include <sys/wait.h>
#include <sys/time.h>
#include <sys/resource.h>
+#include <asm/ldt.h>
#include <asm/unistd.h>
#include <init.h>
#include <os.h>
+#include <kern_util.h>
#include <mem_user.h>
#include <ptrace_user.h>
#include <registers.h>
#include <skas.h>
+#include "internal.h"
static void ptrace_child(void)
{
@@ -221,8 +224,6 @@ static void __init check_ptrace(void)
check_sysemu();
}
-extern void check_tmpexec(void);
-
static void __init check_coredump_limit(void)
{
struct rlimit lim;
diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c
index e09d65b05d1c..eb523ab1e218 100644
--- a/arch/um/os-Linux/umid.c
+++ b/arch/um/os-Linux/umid.c
@@ -358,6 +358,8 @@ char *get_umid(void)
static int __init set_uml_dir(char *name, int *add)
{
+ *add = 0;
+
if (*name == '\0') {
os_warn("uml_dir can't be an empty string\n");
return 0;
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index 1dca4ffbd572..4193e04d7e4a 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -52,8 +52,8 @@ void setup_machinename(char *machine_out)
struct utsname host;
uname(&host);
-#ifdef UML_CONFIG_UML_X86
-# ifndef UML_CONFIG_64BIT
+#if IS_ENABLED(CONFIG_UML_X86)
+# if !IS_ENABLED(CONFIG_64BIT)
if (!strcmp(host.machine, "x86_64")) {
strcpy(machine_out, "i686");
return;
generated by cgit v1.2.3 (git 2.46.0) at 2025-04-27 00:10:18 +0000