1 files changed, 186 insertions, 190 deletions

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;
 }