diff options
Diffstat (limited to 'linux-user/syscall.c')
| -rw-r--r-- | linux-user/syscall.c | 175 |
1 files changed, 109 insertions, 66 deletions
diff --git a/linux-user/syscall.c b/linux-user/syscall.c index a6c426d73c..27871641f4 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -22,6 +22,8 @@ #include "qemu/path.h" #include "qemu/memfd.h" #include "qemu/queue.h" +#include "qemu/plugin.h" +#include "target_mman.h" #include <elf.h> #include <endian.h> #include <grp.h> @@ -168,9 +170,13 @@ #define CLONE_IGNORED_FLAGS \ (CLONE_DETACHED | CLONE_IO) +#ifndef CLONE_PIDFD +# define CLONE_PIDFD 0x00001000 +#endif + /* Flags for fork which we can implement within QEMU itself */ #define CLONE_OPTIONAL_FORK_FLAGS \ - (CLONE_SETTLS | CLONE_PARENT_SETTID | \ + (CLONE_SETTLS | CLONE_PARENT_SETTID | CLONE_PIDFD | \ CLONE_CHILD_CLEARTID | CLONE_CHILD_SETTID) /* Flags for thread creation which we can implement within QEMU itself */ @@ -795,49 +801,52 @@ static inline int host_to_target_sock_type(int host_type) } static abi_ulong target_brk; -static abi_ulong target_original_brk; static abi_ulong brk_page; void target_set_brk(abi_ulong new_brk) { - target_original_brk = target_brk = HOST_PAGE_ALIGN(new_brk); + target_brk = new_brk; brk_page = HOST_PAGE_ALIGN(target_brk); } -//#define DEBUGF_BRK(message, args...) do { fprintf(stderr, (message), ## args); } while (0) -#define DEBUGF_BRK(message, args...) - /* do_brk() must return target values and target errnos. */ -abi_long do_brk(abi_ulong new_brk) +abi_long do_brk(abi_ulong brk_val) { abi_long mapped_addr; abi_ulong new_alloc_size; + abi_ulong new_brk, new_host_brk_page; /* brk pointers are always untagged */ - DEBUGF_BRK("do_brk(" TARGET_ABI_FMT_lx ") -> ", new_brk); - - if (!new_brk) { - DEBUGF_BRK(TARGET_ABI_FMT_lx " (!new_brk)\n", target_brk); + /* return old brk value if brk_val unchanged or zero */ + if (!brk_val || brk_val == target_brk) { return target_brk; } - if (new_brk < target_original_brk) { - DEBUGF_BRK(TARGET_ABI_FMT_lx " (new_brk < target_original_brk)\n", - target_brk); + + new_brk = TARGET_PAGE_ALIGN(brk_val); + new_host_brk_page = HOST_PAGE_ALIGN(brk_val); + + /* brk_val and old target_brk might be on the same page */ + if (new_brk == TARGET_PAGE_ALIGN(target_brk)) { + if (brk_val > target_brk) { + /* empty remaining bytes in (possibly larger) host page */ + memset(g2h_untagged(target_brk), 0, new_host_brk_page - target_brk); + } + target_brk = brk_val; return target_brk; } - /* If the new brk is less than the highest page reserved to the - * target heap allocation, set it and we're almost done... */ - if (new_brk <= brk_page) { - /* Heap contents are initialized to zero, as for anonymous - * mapped pages. */ - if (new_brk > target_brk) { - memset(g2h_untagged(target_brk), 0, new_brk - target_brk); - } - target_brk = new_brk; - DEBUGF_BRK(TARGET_ABI_FMT_lx " (new_brk <= brk_page)\n", target_brk); - return target_brk; + /* Release heap if necesary */ + if (new_brk < target_brk) { + /* empty remaining bytes in (possibly larger) host page */ + memset(g2h_untagged(brk_val), 0, new_host_brk_page - brk_val); + + /* free unused host pages and set new brk_page */ + target_munmap(new_host_brk_page, brk_page - new_host_brk_page); + brk_page = new_host_brk_page; + + target_brk = brk_val; + return target_brk; } /* We need to allocate more memory after the brk... Note that @@ -846,10 +855,14 @@ abi_long do_brk(abi_ulong new_brk) * itself); instead we treat "mapped but at wrong address" as * a failure and unmap again. */ - new_alloc_size = HOST_PAGE_ALIGN(new_brk - brk_page); - mapped_addr = get_errno(target_mmap(brk_page, new_alloc_size, + new_alloc_size = new_host_brk_page - brk_page; + if (new_alloc_size) { + mapped_addr = get_errno(target_mmap(brk_page, new_alloc_size, PROT_READ|PROT_WRITE, MAP_ANON|MAP_PRIVATE, 0, 0)); + } else { + mapped_addr = brk_page; + } if (mapped_addr == brk_page) { /* Heap contents are initialized to zero, as for anonymous @@ -861,10 +874,8 @@ abi_long do_brk(abi_ulong new_brk) * then shrunken). */ memset(g2h_untagged(target_brk), 0, brk_page - target_brk); - target_brk = new_brk; - brk_page = HOST_PAGE_ALIGN(target_brk); - DEBUGF_BRK(TARGET_ABI_FMT_lx " (mapped_addr == brk_page)\n", - target_brk); + target_brk = brk_val; + brk_page = new_host_brk_page; return target_brk; } else if (mapped_addr != -1) { /* Mapped but at wrong address, meaning there wasn't actually @@ -872,10 +883,6 @@ abi_long do_brk(abi_ulong new_brk) */ target_munmap(mapped_addr, new_alloc_size); mapped_addr = -1; - DEBUGF_BRK(TARGET_ABI_FMT_lx " (mapped_addr != -1)\n", target_brk); - } - else { - DEBUGF_BRK(TARGET_ABI_FMT_lx " (otherwise)\n", target_brk); } #if defined(TARGET_ALPHA) @@ -1713,6 +1720,11 @@ static inline abi_long target_to_host_sockaddr(int fd, struct sockaddr *addr, lladdr = (struct target_sockaddr_ll *)addr; lladdr->sll_ifindex = tswap32(lladdr->sll_ifindex); lladdr->sll_hatype = tswap16(lladdr->sll_hatype); + } else if (sa_family == AF_INET6) { + struct sockaddr_in6 *in6addr; + + in6addr = (struct sockaddr_in6 *)addr; + in6addr->sin6_scope_id = tswap32(in6addr->sin6_scope_id); } unlock_user(target_saddr, target_addr, 0); @@ -6723,6 +6735,17 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp, return -TARGET_EINVAL; } +#if !defined(__NR_pidfd_open) || !defined(TARGET_NR_pidfd_open) + if (flags & CLONE_PIDFD) { + return -TARGET_EINVAL; + } +#endif + + /* Can not allow CLONE_PIDFD with CLONE_PARENT_SETTID */ + if ((flags & CLONE_PIDFD) && (flags & CLONE_PARENT_SETTID)) { + return -TARGET_EINVAL; + } + if (block_signals()) { return -QEMU_ERESTARTSYS; } @@ -6750,6 +6773,20 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp, ts->child_tidptr = child_tidptr; } else { cpu_clone_regs_parent(env, flags); + if (flags & CLONE_PIDFD) { + int pid_fd = 0; +#if defined(__NR_pidfd_open) && defined(TARGET_NR_pidfd_open) + int pid_child = ret; + pid_fd = pidfd_open(pid_child, 0); + if (pid_fd >= 0) { + fcntl(pid_fd, F_SETFD, fcntl(pid_fd, F_GETFL) + | FD_CLOEXEC); + } else { + pid_fd = 0; + } +#endif + put_user_u32(pid_fd, parent_tidptr); + } fork_end(0); } g_assert(!cpu_in_exclusive_context(cpu)); @@ -7606,6 +7643,14 @@ static inline int target_to_host_mlockall_arg(int arg) } #endif +static inline int target_to_host_msync_arg(abi_long arg) +{ + return ((arg & TARGET_MS_ASYNC) ? MS_ASYNC : 0) | + ((arg & TARGET_MS_INVALIDATE) ? MS_INVALIDATE : 0) | + ((arg & TARGET_MS_SYNC) ? MS_SYNC : 0) | + (arg & ~(TARGET_MS_ASYNC | TARGET_MS_INVALIDATE | TARGET_MS_SYNC)); +} + #if (defined(TARGET_NR_stat64) || defined(TARGET_NR_lstat64) || \ defined(TARGET_NR_fstat64) || defined(TARGET_NR_fstatat64) || \ defined(TARGET_NR_newfstatat)) @@ -8079,6 +8124,9 @@ static int open_self_stat(CPUArchState *cpu_env, int fd) gchar *bin = g_strrstr(ts->bprm->argv[0], "/"); bin = bin ? bin + 1 : ts->bprm->argv[0]; g_string_printf(buf, "(%.15s) ", bin); + } else if (i == 2) { + /* task state */ + g_string_assign(buf, "R "); /* we are running right now */ } else if (i == 3) { /* ppid */ g_string_printf(buf, FMT_pid " ", getppid()); @@ -9989,18 +10037,13 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1, /* Short circuit this for the magic exe check. */ ret = -TARGET_EINVAL; } else if (is_proc_myself((const char *)p, "exe")) { - char real[PATH_MAX], *temp; - temp = realpath(exec_path, real); - /* Return value is # of bytes that we wrote to the buffer. */ - if (temp == NULL) { - ret = get_errno(-1); - } else { - /* Don't worry about sign mismatch as earlier mapping - * logic would have thrown a bad address error. */ - ret = MIN(strlen(real), arg3); - /* We cannot NUL terminate the string. */ - memcpy(p2, real, ret); - } + /* + * Don't worry about sign mismatch as earlier mapping + * logic would have thrown a bad address error. + */ + ret = MIN(strlen(exec_path), arg3); + /* We cannot NUL terminate the string. */ + memcpy(p2, exec_path, ret); } else { ret = get_errno(readlink(path(p), p2, arg3)); } @@ -10021,18 +10064,13 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1, /* Short circuit this for the magic exe check. */ ret = -TARGET_EINVAL; } else if (is_proc_myself((const char *)p, "exe")) { - char real[PATH_MAX], *temp; - temp = realpath(exec_path, real); - /* Return value is # of bytes that we wrote to the buffer. */ - if (temp == NULL) { - ret = get_errno(-1); - } else { - /* Don't worry about sign mismatch as earlier mapping - * logic would have thrown a bad address error. */ - ret = MIN(strlen(real), arg4); - /* We cannot NUL terminate the string. */ - memcpy(p2, real, ret); - } + /* + * Don't worry about sign mismatch as earlier mapping + * logic would have thrown a bad address error. + */ + ret = MIN(strlen(exec_path), arg4); + /* We cannot NUL terminate the string. */ + memcpy(p2, exec_path, ret); } else { ret = get_errno(readlinkat(arg1, path(p), p2, arg4)); } @@ -10129,7 +10167,8 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1, /* ??? msync/mlock/munlock are broken for softmmu. */ #ifdef TARGET_NR_msync case TARGET_NR_msync: - return get_errno(msync(g2h(cpu, arg1), arg2, arg3)); + return get_errno(msync(g2h(cpu, arg1), arg2, + target_to_host_msync_arg(arg3))); #endif #ifdef TARGET_NR_mlock case TARGET_NR_mlock: @@ -12886,8 +12925,8 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1, if (!lock_user_struct(VERIFY_READ, target_rnew, arg3, 1)) { return -TARGET_EFAULT; } - rnew.rlim_cur = tswap64(target_rnew->rlim_cur); - rnew.rlim_max = tswap64(target_rnew->rlim_max); + __get_user(rnew.rlim_cur, &target_rnew->rlim_cur); + __get_user(rnew.rlim_max, &target_rnew->rlim_max); unlock_user_struct(target_rnew, arg3, 0); rnewp = &rnew; } @@ -12897,8 +12936,8 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1, if (!lock_user_struct(VERIFY_WRITE, target_rold, arg4, 1)) { return -TARGET_EFAULT; } - target_rold->rlim_cur = tswap64(rold.rlim_cur); - target_rold->rlim_max = tswap64(rold.rlim_max); + __put_user(rold.rlim_cur, &target_rold->rlim_cur); + __put_user(rold.rlim_max, &target_rold->rlim_max); unlock_user_struct(target_rold, arg4, 1); } return ret; @@ -13118,8 +13157,12 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1, #if defined(TARGET_NR_timerfd_create) && defined(CONFIG_TIMERFD) case TARGET_NR_timerfd_create: - return get_errno(timerfd_create(arg1, - target_to_host_bitmask(arg2, fcntl_flags_tbl))); + ret = get_errno(timerfd_create(arg1, + target_to_host_bitmask(arg2, fcntl_flags_tbl))); + if (ret >= 0) { + fd_trans_register(ret, &target_timerfd_trans); + } + return ret; #endif #if defined(TARGET_NR_timerfd_gettime) && defined(CONFIG_TIMERFD) |