[Qemu-devel] [PATCH 16/17] Prefer glibc over direct syscalls

[riku . voipio]

From: Riku Voipio <address@hidden>

The openat/*at syscalls are incredibly common with modern coreutils,
calling them directly via syscalls breaks for example fakeroot. Use
glibc stubs whenever directly available and provide old syscall
calling for people still using older libc.

Patch originally from Mika Westerberg, Adapted to
apply to current trunk and cleaned up by Riku Voipio.

Signed-off-by: Riku Voipio <address@hidden>
---
 configure            |   53 +++++++++
 linux-user/syscall.c |  314 ++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 306 insertions(+), 61 deletions(-)

diff --git a/configure b/configure
index 8b0a378..9b882f8 100755
--- a/configure
+++ b/configure
@@ -1111,6 +1111,53 @@ EOF
   fi
 fi
 
+#
+# Check for xxxat() functions when we are building linux-user
+# emulator.  This is done because older glibc versions don't
+# have syscall stubs for these implemented.
+#
+atfile=no
+if [ "$linux_user" = "yes" ] ; then
+  cat > $TMPC << EOF
+#define _ATFILE_SOURCE
+#include <sys/types.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+int
+main(void)
+{
+       /* try to unlink nonexisting file */
+       return (unlinkat(AT_FDCWD, "nonexistent_file", 0));
+}
+EOF
+  if $cc $ARCH_CFLAGS -o $TMPE $TMPC 2> /dev/null ; then
+    atfile=yes
+  fi
+fi
+
+# Check for initofy functions when we are building linux-user
+# emulator.  This is done because older glibc versions don't
+# have syscall stubs for these implemented.  In that case we
+# don't provide them even if kernel supports them.
+#
+inotify=no
+if [ "$linux_user" = "yes" ] ; then
+  cat > $TMPC << EOF
+#include <sys/inotify.h>
+
+int
+main(void)
+{
+       /* try to start inotify */
+       return inotify_init(void);
+}
+EOF
+  if $cc $ARCH_CFLAGS -o $TMPE $TMPC 2> /dev/null ; then
+    inotify=yes
+  fi
+fi
+
 # Check if tools are available to build documentation.
 if [ -x "`which texi2html 2>/dev/null`" ] && \
    [ -x "`which pod2man 2>/dev/null`" ]; then
@@ -1491,6 +1538,12 @@ if test "$curses" = "yes" ; then
   echo "CONFIG_CURSES=yes" >> $config_mak
   echo "CURSES_LIBS=-lcurses" >> $config_mak
 fi
+if test "$atfile" = "yes" ; then
+  echo "#define CONFIG_ATFILE 1" >> $config_h
+fi
+if test "$inotify" = "yes" ; then
+  echo "#define CONFIG_INOTIFY 1" >> $config_h
+fi
 if test "$brlapi" = "yes" ; then
   echo "CONFIG_BRLAPI=yes" >> $config_mak
   echo "#define CONFIG_BRLAPI 1" >> $config_h
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 81366f7..17f7cdb 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -53,6 +53,7 @@
 #include <sys/statfs.h>
 #include <utime.h>
 #include <sys/sysinfo.h>
+#include <sys/utsname.h>
 //#include <sys/user.h>
 #include <netinet/ip.h>
 #include <netinet/tcp.h>
@@ -200,7 +201,229 @@ static int gettid(void) {
     return -ENOSYS;
 }
 #endif
-_syscall1(int,sys_uname,struct new_utsname *,buf)
+#if TARGET_ABI_BITS == 32
+_syscall3(int, sys_getdents, uint, fd, struct linux_dirent *, dirp, uint, 
count);
+#endif
+#if defined(TARGET_NR_getdents64) && defined(__NR_getdents64)
+_syscall3(int, sys_getdents64, uint, fd, struct linux_dirent64 *, dirp, uint, 
count);
+#endif
+_syscall2(int, sys_getpriority, int, which, int, who);
+#if !defined (__x86_64__)
+_syscall5(int, _llseek,  uint,  fd, ulong, hi, ulong, lo,
+          loff_t *, res, uint, wh);
+#endif
+_syscall3(int,sys_rt_sigqueueinfo,int,pid,int,sig,siginfo_t *,uinfo)
+_syscall3(int,sys_syslog,int,type,char*,bufp,int,len)
+#if defined(TARGET_NR_tgkill) && defined(__NR_tgkill)
+_syscall3(int,sys_tgkill,int,tgid,int,pid,int,sig)
+#endif
+#if defined(TARGET_NR_tkill) && defined(__NR_tkill)
+_syscall2(int,sys_tkill,int,tid,int,sig)
+#endif
+#ifdef __NR_exit_group
+_syscall1(int,exit_group,int,error_code)
+#endif
+#if defined(TARGET_NR_set_tid_address) && defined(__NR_set_tid_address)
+_syscall1(int,set_tid_address,int *,tidptr)
+#endif
+#if defined(USE_NPTL)
+#if defined(TARGET_NR_futex) && defined(__NR_futex)
+_syscall6(int,sys_futex,int *,uaddr,int,op,int,val,
+          const struct timespec *,timeout,int *,uaddr2,int,val3)
+#endif
+#endif
+
+static bitmask_transtbl fcntl_flags_tbl[] = {
+  { TARGET_O_ACCMODE,   TARGET_O_WRONLY,    O_ACCMODE,   O_WRONLY,    },
+  { TARGET_O_ACCMODE,   TARGET_O_RDWR,      O_ACCMODE,   O_RDWR,      },
+  { TARGET_O_CREAT,     TARGET_O_CREAT,     O_CREAT,     O_CREAT,     },
+  { TARGET_O_EXCL,      TARGET_O_EXCL,      O_EXCL,      O_EXCL,      },
+  { TARGET_O_NOCTTY,    TARGET_O_NOCTTY,    O_NOCTTY,    O_NOCTTY,    },
+  { TARGET_O_TRUNC,     TARGET_O_TRUNC,     O_TRUNC,     O_TRUNC,     },
+  { TARGET_O_APPEND,    TARGET_O_APPEND,    O_APPEND,    O_APPEND,    },
+  { TARGET_O_NONBLOCK,  TARGET_O_NONBLOCK,  O_NONBLOCK,  O_NONBLOCK,  },
+  { TARGET_O_SYNC,      TARGET_O_SYNC,      O_SYNC,      O_SYNC,      },
+  { TARGET_FASYNC,      TARGET_FASYNC,      FASYNC,      FASYNC,      },
+  { TARGET_O_DIRECTORY, TARGET_O_DIRECTORY, O_DIRECTORY, O_DIRECTORY, },
+  { TARGET_O_NOFOLLOW,  TARGET_O_NOFOLLOW,  O_NOFOLLOW,  O_NOFOLLOW,  },
+  { TARGET_O_LARGEFILE, TARGET_O_LARGEFILE, O_LARGEFILE, O_LARGEFILE, },
+#if defined(O_DIRECT)
+  { TARGET_O_DIRECT,    TARGET_O_DIRECT,    O_DIRECT,    O_DIRECT,    },
+#endif
+  { 0, 0, 0, 0 }
+};
+
+#define COPY_UTSNAME_FIELD(dest, src) \
+  do { \
+      /* __NEW_UTS_LEN doesn't include terminating null */ \
+      (void) strncpy((dest), (src), __NEW_UTS_LEN); \
+      (dest)[__NEW_UTS_LEN] = '\0'; \
+  } while (0)
+
+static int sys_uname(struct new_utsname *buf)
+{
+  struct utsname uts_buf;
+
+  if (uname(&uts_buf) < 0)
+      return (-1);
+
+  /*
+   * Just in case these have some differences, we
+   * translate utsname to new_utsname (which is the
+   * struct linux kernel uses).
+   */
+
+  bzero(buf, sizeof (*buf));
+  COPY_UTSNAME_FIELD(buf->sysname, uts_buf.sysname);
+  COPY_UTSNAME_FIELD(buf->nodename, uts_buf.nodename);
+  COPY_UTSNAME_FIELD(buf->release, uts_buf.release);
+  COPY_UTSNAME_FIELD(buf->version, uts_buf.version);
+  COPY_UTSNAME_FIELD(buf->machine, uts_buf.machine);
+#ifdef _GNU_SOURCE
+  COPY_UTSNAME_FIELD(buf->domainname, uts_buf.domainname);
+#endif
+  return (0);
+
+#undef COPY_UTSNAME_FIELD
+}
+
+static int sys_getcwd1(char *buf, size_t size)
+{
+  if (getcwd(buf, size) == NULL) {
+      /* getcwd() sets errno */
+      return (-1);
+  }
+  return (0);
+}
+
+#ifdef CONFIG_ATFILE
+/*
+ * Host system seems to have atfile syscall stubs available.  We
+ * now enable them one by one as specified by target syscall_nr.h.
+ */
+
+#ifdef TARGET_NR_faccessat
+static int sys_faccessat(int dirfd, const char *pathname, int mode, int flags)
+{
+  return (faccessat(dirfd, pathname, mode, flags));
+}
+#endif
+#ifdef TARGET_NR_fchmodat
+static int sys_fchmodat(int dirfd, const char *pathname, mode_t mode, int 
flags)
+{
+  return (fchmodat(dirfd, pathname, mode, flags));
+}
+#endif
+#ifdef TARGET_NR_fchownat
+static int sys_fchownat(int dirfd, const char *pathname, uid_t owner,
+    gid_t group, int flags)
+{
+  return (fchownat(dirfd, pathname, owner, group, flags));
+}
+#endif
+#ifdef __NR_fstatat64
+static int sys_fstatat64(int dirfd, const char *pathname, struct stat *buf,
+    int flags)
+{
+  return (fstatat(dirfd, pathname, buf, flags));
+}
+#endif
+#ifdef __NR_newfstatat
+static int sys_newfstatat(int dirfd, const char *pathname, struct stat *buf,
+    int flags)
+{
+  return (fstatat(dirfd, pathname, buf, flags));
+}
+#endif
+#ifdef TARGET_NR_futimesat
+static int sys_futimesat(int dirfd, const char *pathname,
+    const struct timeval times[2])
+{
+  return (futimesat(dirfd, pathname, times));
+}
+#endif
+#ifdef TARGET_NR_linkat
+static int sys_linkat(int olddirfd, const char *oldpath,
+    int newdirfd, const char *newpath, int flags)
+{
+  return (linkat(olddirfd, oldpath, newdirfd, newpath, flags));
+}
+#endif
+#ifdef TARGET_NR_mkdirat
+static int sys_mkdirat(int dirfd, const char *pathname, mode_t mode)
+{
+  return (mkdirat(dirfd, pathname, mode));
+}
+#endif
+#ifdef TARGET_NR_mknodat
+static int sys_mknodat(int dirfd, const char *pathname, mode_t mode,
+    dev_t dev)
+{
+  return (mknodat(dirfd, pathname, mode, dev));
+}
+#endif
+#ifdef TARGET_NR_openat
+static int sys_openat(int dirfd, const char *pathname, int flags, ...)
+{
+  /*
+   * open(2) has extra parameter 'mode' when called with
+   * flag O_CREAT.
+   */
+  if ((flags & O_CREAT) != 0) {
+      va_list ap;
+      mode_t mode;
+
+      /*
+       * Get the 'mode' parameter and translate it to
+       * host bits.
+       */
+      va_start(ap, flags);
+      mode = va_arg(ap, mode_t);
+      mode = target_to_host_bitmask(mode, fcntl_flags_tbl);
+      va_end(ap);
+
+      return (openat(dirfd, pathname, flags, mode));
+  }
+  return (openat(dirfd, pathname, flags));
+}
+#endif
+#ifdef TARGET_NR_readlinkat
+static int sys_readlinkat(int dirfd, const char *pathname, char *buf, size_t 
bufsiz)
+{
+  return (readlinkat(dirfd, pathname, buf, bufsiz));
+}
+#endif
+#ifdef TARGET_NR_renameat
+static int sys_renameat(int olddirfd, const char *oldpath,
+    int newdirfd, const char *newpath)
+{
+  return (renameat(olddirfd, oldpath, newdirfd, newpath));
+}
+#endif
+#ifdef TARGET_NR_symlinkat
+static int sys_symlinkat(const char *oldpath, int newdirfd, const char 
*newpath)
+{
+  return (symlinkat(oldpath, newdirfd, newpath));
+}
+#endif
+#ifdef TARGET_NR_unlinkat
+static int sys_unlinkat(int dirfd, const char *pathname, int flags)
+{
+  return (unlinkat(dirfd, pathname, flags));
+}
+#endif
+#ifdef TARGET_NR_utimensat
+static int sys_utimensat(int dirfd, const char *pathname,
+    const struct timespec times[2], int flags)
+{
+  return (utimensat(dirfd, pathname, times, flags));
+}
+#endif
+#else /* !CONFIG_ATFILE */
+
+/*
+ * Try direct syscalls instead
+ */
 #if defined(TARGET_NR_faccessat) && defined(__NR_faccessat)
 _syscall4(int,sys_faccessat,int,dirfd,const char *,pathname,int,mode,int,flags)
 #endif
@@ -221,21 +444,14 @@ _syscall4(int,sys_fstatat64,int,dirfd,const char 
*,pathname,
 _syscall3(int,sys_futimesat,int,dirfd,const char *,pathname,
          const struct timeval *,times)
 #endif
-_syscall2(int,sys_getcwd1,char *,buf,size_t,size)
-#if TARGET_ABI_BITS == 32
-_syscall3(int, sys_getdents, uint, fd, struct linux_dirent *, dirp, uint, 
count);
-#endif
-#if defined(TARGET_NR_getdents64) && defined(__NR_getdents64)
-_syscall3(int, sys_getdents64, uint, fd, struct linux_dirent64 *, dirp, uint, 
count);
-#endif
-_syscall2(int, sys_getpriority, int, which, int, who);
-#if !defined (__x86_64__)
-_syscall5(int, _llseek,  uint,  fd, ulong, hi, ulong, lo,
-          loff_t *, res, uint, wh);
+#if (defined(TARGET_NR_newfstatat) || defined(TARGET_NR_fstatat64) ) && \
+        defined(__NR_newfstatat)
+_syscall4(int,sys_newfstatat,int,dirfd,const char *,pathname,
+          struct stat *,buf,int,flags)
 #endif
 #if defined(TARGET_NR_linkat) && defined(__NR_linkat)
 _syscall5(int,sys_linkat,int,olddirfd,const char *,oldpath,
-         int,newdirfd,const char *,newpath,int,flags)
+      int,newdirfd,const char *,newpath,int,flags)
 #endif
 #if defined(TARGET_NR_mkdirat) && defined(__NR_mkdirat)
 _syscall3(int,sys_mkdirat,int,dirfd,const char *,pathname,mode_t,mode)
@@ -244,11 +460,6 @@ _syscall3(int,sys_mkdirat,int,dirfd,const char 
*,pathname,mode_t,mode)
 _syscall4(int,sys_mknodat,int,dirfd,const char *,pathname,
           mode_t,mode,dev_t,dev)
 #endif
-#if (defined(TARGET_NR_newfstatat) || defined(TARGET_NR_fstatat64) ) && \
-        defined(__NR_newfstatat)
-_syscall4(int,sys_newfstatat,int,dirfd,const char *,pathname,
-          struct stat *,buf,int,flags)
-#endif
 #if defined(TARGET_NR_openat) && defined(__NR_openat)
 _syscall4(int,sys_openat,int,dirfd,const char *,pathname,int,flags,mode_t,mode)
 #endif
@@ -260,24 +471,10 @@ _syscall4(int,sys_readlinkat,int,dirfd,const char 
*,pathname,
 _syscall4(int,sys_renameat,int,olddirfd,const char *,oldpath,
           int,newdirfd,const char *,newpath)
 #endif
-_syscall3(int,sys_rt_sigqueueinfo,int,pid,int,sig,siginfo_t *,uinfo)
 #if defined(TARGET_NR_symlinkat) && defined(__NR_symlinkat)
 _syscall3(int,sys_symlinkat,const char *,oldpath,
           int,newdirfd,const char *,newpath)
 #endif
-_syscall3(int,sys_syslog,int,type,char*,bufp,int,len)
-#if defined(TARGET_NR_tgkill) && defined(__NR_tgkill)
-_syscall3(int,sys_tgkill,int,tgid,int,pid,int,sig)
-#endif
-#if defined(TARGET_NR_tkill) && defined(__NR_tkill)
-_syscall2(int,sys_tkill,int,tid,int,sig)
-#endif
-#ifdef __NR_exit_group
-_syscall1(int,exit_group,int,error_code)
-#endif
-#if defined(TARGET_NR_set_tid_address) && defined(__NR_set_tid_address)
-_syscall1(int,set_tid_address,int *,tidptr)
-#endif
 #if defined(TARGET_NR_unlinkat) && defined(__NR_unlinkat)
 _syscall3(int,sys_unlinkat,int,dirfd,const char *,pathname,int,flags)
 #endif
@@ -285,21 +482,36 @@ _syscall3(int,sys_unlinkat,int,dirfd,const char 
*,pathname,int,flags)
 _syscall4(int,sys_utimensat,int,dirfd,const char *,pathname,
           const struct timespec *,tsp,int,flags)
 #endif
+
+#endif /* CONFIG_ATFILE */
+
+#ifdef CONFIG_INOTIFY
+
 #if defined(TARGET_NR_inotify_init) && defined(__NR_inotify_init)
-_syscall0(int,sys_inotify_init)
+static int sys_inotify_init(void)
+{
+  return (inotify_init());
+}
 #endif
 #if defined(TARGET_NR_inotify_add_watch) && defined(__NR_inotify_add_watch)
-_syscall3(int,sys_inotify_add_watch,int,fd,const char *,pathname,uint32_t,mask)
+static int sys_inotify_add_watch(int fd,const char *pathname, int32_t mask)
+{
+  return (inotify_add_watch(fd, pathname, mask));
+}
 #endif
 #if defined(TARGET_NR_inotify_rm_watch) && defined(__NR_inotify_rm_watch)
-_syscall2(int,sys_inotify_rm_watch,int,fd,uint32_t,wd)
-#endif
-#if defined(USE_NPTL)
-#if defined(TARGET_NR_futex) && defined(__NR_futex)
-_syscall6(int,sys_futex,int *,uaddr,int,op,int,val,
-          const struct timespec *,timeout,int *,uaddr2,int,val3)
-#endif
+static int sys_inotify_rm_watch(int fd, int32_t wd)
+{
+  return (inotify_rm_watch(fd,pathname, wd));
+}
 #endif
+#else
+/* Userspace can usually survive runtime without inotify */
+#undef TARGET_NR_inotify_init
+#undef TARGET_NR_inotify_add_watch
+#undef TARGET_NR_inotify_rm_watch
+#endif /* CONFIG_INOTIFY  */
+
 
 extern int personality(int);
 extern int flock(int, int);
@@ -2841,26 +3053,6 @@ static bitmask_transtbl mmap_flags_tbl[] = {
        { 0, 0, 0, 0 }
 };
 
-static bitmask_transtbl fcntl_flags_tbl[] = {
-       { TARGET_O_ACCMODE,   TARGET_O_WRONLY,    O_ACCMODE,   O_WRONLY,    },
-       { TARGET_O_ACCMODE,   TARGET_O_RDWR,      O_ACCMODE,   O_RDWR,      },
-       { TARGET_O_CREAT,     TARGET_O_CREAT,     O_CREAT,     O_CREAT,     },
-       { TARGET_O_EXCL,      TARGET_O_EXCL,      O_EXCL,      O_EXCL,      },
-       { TARGET_O_NOCTTY,    TARGET_O_NOCTTY,    O_NOCTTY,    O_NOCTTY,    },
-       { TARGET_O_TRUNC,     TARGET_O_TRUNC,     O_TRUNC,     O_TRUNC,     },
-       { TARGET_O_APPEND,    TARGET_O_APPEND,    O_APPEND,    O_APPEND,    },
-       { TARGET_O_NONBLOCK,  TARGET_O_NONBLOCK,  O_NONBLOCK,  O_NONBLOCK,  },
-       { TARGET_O_SYNC,      TARGET_O_SYNC,      O_SYNC,      O_SYNC,      },
-       { TARGET_FASYNC,      TARGET_FASYNC,      FASYNC,      FASYNC,      },
-       { TARGET_O_DIRECTORY, TARGET_O_DIRECTORY, O_DIRECTORY, O_DIRECTORY, },
-       { TARGET_O_NOFOLLOW,  TARGET_O_NOFOLLOW,  O_NOFOLLOW,  O_NOFOLLOW,  },
-       { TARGET_O_LARGEFILE, TARGET_O_LARGEFILE, O_LARGEFILE, O_LARGEFILE, },
-#if defined(O_DIRECT)
-       { TARGET_O_DIRECT,    TARGET_O_DIRECT,    O_DIRECT,    O_DIRECT,    },
-#endif
-       { 0, 0, 0, 0 }
-};
-
 #if defined(TARGET_I386)
 
 /* NOTE: there is really one LDT for all the threads */
-- 
1.6.2.1