diff options
Diffstat (limited to 'arch/um/os-Linux/skas')
| -rw-r--r-- | arch/um/os-Linux/skas/Makefile | 10 | ||||
| -rw-r--r-- | arch/um/os-Linux/skas/mem.c | 206 | ||||
| -rw-r--r-- | arch/um/os-Linux/skas/process.c | 732 |
3 files changed, 948 insertions, 0 deletions
diff --git a/arch/um/os-Linux/skas/Makefile b/arch/um/os-Linux/skas/Makefile new file mode 100644 index 0000000000..75f11989d2 --- /dev/null +++ b/arch/um/os-Linux/skas/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{linux.intel,addtoit}.com) +# + +obj-y := mem.o process.o + +USER_OBJS := $(obj-y) + +include $(srctree)/arch/um/scripts/Makefile.rules diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c new file mode 100644 index 0000000000..953fb10f3f --- /dev/null +++ b/arch/um/os-Linux/skas/mem.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + */ + +#include <stddef.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <sys/mman.h> +#include <init.h> +#include <as-layout.h> +#include <mm_id.h> +#include <os.h> +#include <ptrace_user.h> +#include <registers.h> +#include <skas.h> +#include <sysdep/ptrace.h> +#include <sysdep/stub.h> + +extern char batch_syscall_stub[], __syscall_stub_start[]; + +extern void wait_stub_done(int pid); + +static inline unsigned long *check_init_stack(struct mm_id * mm_idp, + unsigned long *stack) +{ + if (stack == NULL) { + stack = (unsigned long *) mm_idp->stack + 2; + *stack = 0; + } + return stack; +} + +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) __syscall_stub_start); + syscall_regs[REGS_SP_INDEX] = STUB_DATA; + + return 0; +} + +__initcall(init_syscall_regs); + +static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr) +{ + int n, i; + long ret, offset; + unsigned long * data; + unsigned long * syscall; + int err, pid = mm_idp->u.pid; + + n = ptrace_setregs(pid, syscall_regs); + if (n < 0) { + printk(UM_KERN_ERR "Registers - \n"); + for (i = 0; i < MAX_REG_NR; i++) + printk(UM_KERN_ERR "\t%d\t0x%lx\n", i, syscall_regs[i]); + panic("%s : PTRACE_SETREGS failed, errno = %d\n", + __func__, -n); + } + + err = ptrace(PTRACE_CONT, pid, 0, 0); + if (err) + panic("Failed to continue stub, pid = %d, errno = %d\n", pid, + errno); + + 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) + */ + 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; + + *addr = check_init_stack(mm_idp, NULL); + + return ret; +} + +long run_syscall_stub(struct mm_id * mm_idp, int syscall, + unsigned long *args, long expected, void **addr, + int done) +{ + 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; + return 0; + } + + return do_syscall_stub(mm_idp, addr); +} + +long syscall_stub_data(struct mm_id * mm_idp, + unsigned long *data, int data_count, + void **addr, void **stub_addr) +{ + 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; + } + + 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; +} + +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) +{ + int ret; + unsigned long args[] = { virt, len, prot, + MAP_SHARED | MAP_FIXED, phys_fd, + MMAP_OFFSET(offset) }; + + ret = run_syscall_stub(mm_idp, STUB_MMAP_NR, args, virt, + data, done); + + return ret; +} + +int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len, + int done, void **data) +{ + int ret; + unsigned long args[] = { (unsigned long) addr, len, 0, 0, 0, + 0 }; + + ret = run_syscall_stub(mm_idp, __NR_munmap, args, 0, + data, done); + + return ret; +} + +int protect(struct mm_id * mm_idp, unsigned long addr, unsigned long len, + unsigned int prot, int done, void **data) +{ + int ret; + unsigned long args[] = { addr, len, prot, 0, 0, 0 }; + + ret = run_syscall_stub(mm_idp, __NR_mprotect, args, 0, + data, done); + + return ret; +} diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c new file mode 100644 index 0000000000..9464833e74 --- /dev/null +++ b/arch/um/os-Linux/skas/process.c @@ -0,0 +1,732 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) + * Copyright (C) 2002- 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + */ + +#include <stdlib.h> +#include <stdbool.h> +#include <unistd.h> +#include <sched.h> +#include <errno.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/wait.h> +#include <asm/unistd.h> +#include <as-layout.h> +#include <init.h> +#include <kern_util.h> +#include <mem.h> +#include <os.h> +#include <ptrace_user.h> +#include <registers.h> +#include <skas.h> +#include <sysdep/stub.h> +#include <linux/threads.h> + +int is_skas_winch(int pid, int fd, void *data) +{ + return pid == getpgrp(); +} + +static const char *ptrace_reg_name(int idx) +{ +#define R(n) case HOST_##n: return #n + + switch (idx) { +#ifdef __x86_64__ + R(BX); + R(CX); + R(DI); + R(SI); + R(DX); + R(BP); + R(AX); + R(R8); + R(R9); + R(R10); + R(R11); + R(R12); + R(R13); + R(R14); + R(R15); + R(ORIG_AX); + R(CS); + R(SS); + R(EFLAGS); +#elif defined(__i386__) + R(IP); + R(SP); + R(EFLAGS); + R(AX); + R(BX); + R(CX); + R(DX); + R(SI); + R(DI); + R(BP); + R(CS); + R(SS); + R(DS); + R(FS); + R(ES); + R(GS); + R(ORIG_AX); +#endif + } + return ""; +} + +static int ptrace_dump_regs(int pid) +{ + unsigned long regs[MAX_REG_NR]; + int i; + + if (ptrace(PTRACE_GETREGS, pid, 0, regs) < 0) + return -errno; + + printk(UM_KERN_ERR "Stub registers -\n"); + for (i = 0; i < ARRAY_SIZE(regs); i++) { + const char *regname = ptrace_reg_name(i); + + printk(UM_KERN_ERR "\t%s\t(%2d): %lx\n", regname, i, regs[i]); + } + + return 0; +} + +/* + * Signals that are OK to receive in the stub - we'll just continue it. + * SIGWINCH will happen when UML is inside a detached screen. + */ +#define STUB_SIG_MASK ((1 << SIGALRM) | (1 << SIGWINCH)) + +/* Signals that the stub will finish with - anything else is an error */ +#define STUB_DONE_MASK (1 << SIGTRAP) + +void wait_stub_done(int pid) +{ + int n, status, err; + + while (1) { + CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL)); + if ((n < 0) || !WIFSTOPPED(status)) + goto bad_wait; + + if (((1 << WSTOPSIG(status)) & STUB_SIG_MASK) == 0) + break; + + err = ptrace(PTRACE_CONT, pid, 0, 0); + if (err) { + printk(UM_KERN_ERR "%s : continue failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + } + + if (((1 << WSTOPSIG(status)) & STUB_DONE_MASK) != 0) + return; + +bad_wait: + err = ptrace_dump_regs(pid); + if (err) + printk(UM_KERN_ERR "Failed to get registers from stub, errno = %d\n", + -err); + printk(UM_KERN_ERR "%s : failed to wait for SIGTRAP, pid = %d, n = %d, errno = %d, status = 0x%x\n", + __func__, pid, n, errno, status); + fatal_sigsegv(); +} + +extern unsigned long current_stub_stack(void); + +static void get_skas_faultinfo(int pid, struct faultinfo *fi, unsigned long *aux_fp_regs) +{ + 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, " + "errno = %d\n", pid, errno); + fatal_sigsegv(); + } + wait_stub_done(pid); + + /* + * faultinfo is prepared by the stub_segv_handler at start of + * 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) +{ + get_skas_faultinfo(pid, ®s->faultinfo, aux_fp_regs); + segv(regs->faultinfo, 0, 1, NULL); +} + +/* + * To use the same value of using_sysemu as the caller, ask it that value + * (in local_using_sysemu + */ +static void handle_trap(int pid, struct uml_pt_regs *regs, + int local_using_sysemu) +{ + int err, status; + + if ((UPT_IP(regs) >= STUB_START) && (UPT_IP(regs) < STUB_END)) + fatal_sigsegv(); + + if (!local_using_sysemu) + { + err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET, + __NR_getpid); + if (err < 0) { + printk(UM_KERN_ERR "%s - nullifying syscall failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + + err = ptrace(PTRACE_SYSCALL, pid, 0, 0); + if (err < 0) { + printk(UM_KERN_ERR "%s - continuing to end of syscall failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + + CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL)); + if ((err < 0) || !WIFSTOPPED(status) || + (WSTOPSIG(status) != SIGTRAP + 0x80)) { + err = ptrace_dump_regs(pid); + if (err) + printk(UM_KERN_ERR "Failed to get registers from process, errno = %d\n", + -err); + printk(UM_KERN_ERR "%s - failed to wait at end of syscall, errno = %d, status = %d\n", + __func__, errno, status); + fatal_sigsegv(); + } + } + + handle_syscall(regs); +} + +extern char __syscall_stub_start[]; + +/** + * userspace_tramp() - userspace trampoline + * @stack: pointer to the new userspace stack page, can be NULL, if? FIXME: + * + * 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 userspace_tramp(void *stack) +{ + void *addr; + int fd; + unsigned long long offset; + + 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) { + printk(UM_KERN_ERR "mapping mmap stub at 0x%lx failed, errno = %d\n", + STUB_CODE, errno); + exit(1); + } + + if (stack != NULL) { + 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) { + printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n", + STUB_DATA, errno); + exit(1); + } + } + if (stack != NULL) { + struct sigaction sa; + + unsigned long v = STUB_CODE + + (unsigned long) stub_segv_handler - + (unsigned long) __syscall_stub_start; + + 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 *) v; + sa.sa_restorer = NULL; + if (sigaction(SIGSEGV, &sa, NULL) < 0) { + printk(UM_KERN_ERR "%s - setting SIGSEGV handler failed - errno = %d\n", + __func__, errno); + exit(1); + } + } + + kill(os_getpid(), SIGSTOP); + return 0; +} + +int userspace_pid[NR_CPUS]; +int kill_userspace_mm[NR_CPUS]; + +/** + * start_userspace() - prepare a new userspace process + * @stub_stack: pointer to the stub stack. Can be NULL, if? FIXME: + * + * Setups a new temporary stack page that is used while userspace_tramp() runs + * Clones the kernel process into a new userspace process, with FDs only. + * + * Return: When positive: the process id of the new userspace process, + * when negative: an error number. + * FIXME: can PIDs become negative?! + */ +int start_userspace(unsigned long stub_stack) +{ + void *stack; + unsigned long sp; + int pid, status, n, flags, err; + + /* setup a temporary stack page */ + stack = mmap(NULL, UM_KERN_PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (stack == MAP_FAILED) { + err = -errno; + printk(UM_KERN_ERR "%s : mmap failed, errno = %d\n", + __func__, errno); + return err; + } + + /* 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); + if (pid < 0) { + err = -errno; + printk(UM_KERN_ERR "%s : clone failed, errno = %d\n", + __func__, errno); + return err; + } + + do { + CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL)); + if (n < 0) { + err = -errno; + printk(UM_KERN_ERR "%s : wait failed, errno = %d\n", + __func__, errno); + goto out_kill; + } + } while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM)); + + if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) { + err = -EINVAL; + printk(UM_KERN_ERR "%s : expected SIGSTOP, got status = %d\n", + __func__, status); + goto out_kill; + } + + if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL, + (void *) PTRACE_O_TRACESYSGOOD) < 0) { + err = -errno; + printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n", + __func__, errno); + goto out_kill; + } + + if (munmap(stack, UM_KERN_PAGE_SIZE) < 0) { + err = -errno; + printk(UM_KERN_ERR "%s : munmap failed, errno = %d\n", + __func__, errno); + goto out_kill; + } + + return pid; + + out_kill: + os_kill_ptraced_process(pid, 1); + return err; +} + +void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) +{ + int err, status, op, pid = userspace_pid[0]; + /* To prevent races if using_sysemu changes under us.*/ + int local_using_sysemu; + siginfo_t si; + + /* Handle any immediate reschedules or signals */ + interrupt_end(); + + while (1) { + if (kill_userspace_mm[0]) + fatal_sigsegv(); + + /* + * This can legitimately fail if the process loads a + * bogus value into a segment register. It will + * segfault and PTRACE_GETREGS will read that value + * out of the process. However, PTRACE_SETREGS will + * fail. In this case, there is nothing to do but + * just kill the process. + */ + if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) { + printk(UM_KERN_ERR "%s - ptrace set regs failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + + if (put_fp_registers(pid, regs->fp)) { + printk(UM_KERN_ERR "%s - ptrace set fp regs failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + + /* Now we set local_using_sysemu to be used for one loop */ + local_using_sysemu = get_using_sysemu(); + + op = SELECT_PTRACE_OPERATION(local_using_sysemu, + singlestepping(NULL)); + + if (ptrace(op, pid, 0, 0)) { + printk(UM_KERN_ERR "%s - ptrace continue failed, op = %d, errno = %d\n", + __func__, op, errno); + fatal_sigsegv(); + } + + CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL)); + if (err < 0) { + printk(UM_KERN_ERR "%s - wait failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + + regs->is_user = 1; + if (ptrace(PTRACE_GETREGS, pid, 0, regs->gp)) { + printk(UM_KERN_ERR "%s - PTRACE_GETREGS failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + + if (get_fp_registers(pid, regs->fp)) { + printk(UM_KERN_ERR "%s - get_fp_registers failed, errno = %d\n", + __func__, errno); + fatal_sigsegv(); + } + + UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */ + + if (WIFSTOPPED(status)) { + int sig = WSTOPSIG(status); + + /* These signal handlers need the si argument. + * The SIGIO and SIGALARM handlers which constitute the + * majority of invocations, do not use it. + */ + switch (sig) { + case SIGSEGV: + case SIGTRAP: + case SIGILL: + case SIGBUS: + case SIGFPE: + case SIGWINCH: + ptrace(PTRACE_GETSIGINFO, pid, 0, (struct siginfo *)&si); + break; + } + + switch (sig) { + case SIGSEGV: + if (PTRACE_FULL_FAULTINFO) { + get_skas_faultinfo(pid, + ®s->faultinfo, aux_fp_regs); + (*sig_info[SIGSEGV])(SIGSEGV, (struct siginfo *)&si, + regs); + } + else handle_segv(pid, regs, aux_fp_regs); + break; + case SIGTRAP + 0x80: + handle_trap(pid, regs, local_using_sysemu); + break; + case SIGTRAP: + relay_signal(SIGTRAP, (struct siginfo *)&si, regs); + break; + case SIGALRM: + break; + case SIGIO: + case SIGILL: + case SIGBUS: + case SIGFPE: + case SIGWINCH: + block_signals_trace(); + (*sig_info[sig])(sig, (struct siginfo *)&si, regs); + unblock_signals_trace(); + break; + default: + printk(UM_KERN_ERR "%s - child stopped with signal %d\n", + __func__, sig); + fatal_sigsegv(); + } + pid = userspace_pid[0]; + interrupt_end(); + + /* Avoid -ERESTARTSYS handling in host */ + if (PT_SYSCALL_NR_OFFSET != PT_SYSCALL_RET_OFFSET) + PT_SYSCALL_NR(regs->gp) = -1; + } + } +} + +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_OLDSETOPTIONS, pid, NULL, + (void *)PTRACE_O_TRACESYSGOOD) < 0) { + err = -errno; + printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS 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; + (*buf)[0].JB_SP = (unsigned long) stack + UM_THREAD_SIZE - + sizeof(void *); +} + +#define INIT_JMP_NEW_THREAD 0 +#define INIT_JMP_CALLBACK 1 +#define INIT_JMP_HALT 2 +#define INIT_JMP_REBOOT 3 + +void switch_threads(jmp_buf *me, jmp_buf *you) +{ + if (UML_SETJMP(me) == 0) + UML_LONGJMP(you, 1); +} + +static jmp_buf initial_jmpbuf; + +/* XXX Make these percpu */ +static void (*cb_proc)(void *arg); +static void *cb_arg; +static jmp_buf *cb_back; + +int start_idle_thread(void *stack, jmp_buf *switch_buf) +{ + int n; + + set_handler(SIGWINCH); + + /* + * Can't use UML_SETJMP or UML_LONGJMP here because they save + * and restore signals, with the possible side-effect of + * trying to handle any signals which came when they were + * blocked, which can't be done on this stack. + * Signals must be blocked when jumping back here and restored + * after returning to the jumper. + */ + n = setjmp(initial_jmpbuf); + switch (n) { + case INIT_JMP_NEW_THREAD: + (*switch_buf)[0].JB_IP = (unsigned long) uml_finishsetup; + (*switch_buf)[0].JB_SP = (unsigned long) stack + + UM_THREAD_SIZE - sizeof(void *); + break; + case INIT_JMP_CALLBACK: + (*cb_proc)(cb_arg); + longjmp(*cb_back, 1); + break; + case INIT_JMP_HALT: + kmalloc_ok = 0; + return 0; + case INIT_JMP_REBOOT: + kmalloc_ok = 0; + return 1; + default: + printk(UM_KERN_ERR "Bad sigsetjmp return in %s - %d\n", + __func__, n); + fatal_sigsegv(); + } + longjmp(*switch_buf, 1); + + /* unreachable */ + printk(UM_KERN_ERR "impossible long jump!"); + fatal_sigsegv(); + return 0; +} + +void initial_thread_cb_skas(void (*proc)(void *), void *arg) +{ + jmp_buf here; + + cb_proc = proc; + cb_arg = arg; + cb_back = &here; + + block_signals_trace(); + if (UML_SETJMP(&here) == 0) + UML_LONGJMP(&initial_jmpbuf, INIT_JMP_CALLBACK); + unblock_signals_trace(); + + cb_proc = NULL; + cb_arg = NULL; + cb_back = NULL; +} + +void halt_skas(void) +{ + block_signals_trace(); + UML_LONGJMP(&initial_jmpbuf, INIT_JMP_HALT); +} + +static bool noreboot; + +static int __init noreboot_cmd_param(char *str, int *add) +{ + noreboot = true; + return 0; +} + +__uml_setup("noreboot", noreboot_cmd_param, +"noreboot\n" +" Rather than rebooting, exit always, akin to QEMU's -no-reboot option.\n" +" This is useful if you're using CONFIG_PANIC_TIMEOUT in order to catch\n" +" crashes in CI\n"); + +void reboot_skas(void) +{ + block_signals_trace(); + UML_LONGJMP(&initial_jmpbuf, noreboot ? INIT_JMP_HALT : INIT_JMP_REBOOT); +} + +void __switch_mm(struct mm_id *mm_idp) +{ + userspace_pid[0] = mm_idp->u.pid; + kill_userspace_mm[0] = mm_idp->kill; +} |