Linux: Add getdents64 system call

No 32-bit system call wrapper is added because the interface
is problematic because it cannot deal with 64-bit inode numbers
and 64-bit directory hashes.

A future commit will deprecate the undocumented getdirentries
and getdirentries64 functions.

Reviewed-by: Carlos O'Donell <carlos@redhat.com>

38 files changed, 282 insertions, 9 deletions

diff --git a/ChangeLog b/ChangeLog
index d988bc5309..55afdcbfbd 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,78 @@
+2019-06-07  Florian Weimer  <fweimer@redhat.com>
+
+	Linux: Add getdents64 system call.
+	* include/dirnent.h (getdents): Add comment and change buffer
+	argument type to void *.
+	(getdents64): Likewise.  Add hidden prototype.
+	* sysdeps/unix/sysv/linux/bits/Versions (GLIBC_2.30): Export
+	getdents64.
+	* sysdeps/unix/sysv/linux/Makefile [$(subdir) == dirent] (tests):
+	Add tst-getdents64.
+	* sysdeps/unix/sysv/linux/bits/unistd_ext.h (getdents64): Declare.
+	* sysdeps/unix/sysv/linux/getdents.c (__getdents): Change buffer
+	argument type to void *.
+	* sysdeps/unix/sysv/linux/getdents64.c (__getdents64): Likewise.
+	Add hidden definition and getdents64 alias.
+	* sysdeps/unix/sysv/linux/mips/mips64/getdents64.c (__getdents64):
+	Likewise.
+	* sysdeps/unix/sysv/linux/tst-getdents64.c: New file.
+	* manual/filesys.texi (Accessing Directories): Add Low-level
+	Directory Access node reference.
+	(Opening a Directory): Cross-reference it.
+	(Low-level Directory Access): New node.
+	* sysdeps/unix/sysv/linux/aarch64/libc.abilist (GLIBC_2.30): Add
+	getdents64.
+	* sysdeps/unix/sysv/linux/alpha/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/arm/libc.abilist (GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/csky/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/hppa/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/i386/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/ia64/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/m68k/coldfire/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/m68k/m680x0/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/microblaze/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/mips/mips32/fpu/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/mips/mips32/nofpu/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/mips/mips64/n32/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/mips/mips64/n64/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/nios2/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/powerpc/powerpc32/fpu/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/powerpc/powerpc32/nofpu/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/powerpc/powerpc64/be/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/powerpc/powerpc64/le/libc.abilist
+	(GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/riscv/rv64/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/s390/s390-32/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/s390/s390-64/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/sh/libc.abilist (GLIBC_2.30): Likewise.
+	* sysdeps/unix/sysv/linux/sparc/sparc32/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/sparc/sparc64/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/x86_64/64/libc.abilist (GLIBC_2.30):
+	Likewise.
+	* sysdeps/unix/sysv/linux/x86_64/x32/libc.abilist (GLIBC_2.30):
+	Likewise.
+
 2019-06-06  Paul A. Clarke  <pc@us.ibm.com>
 
 	* sysdeps/powerpc/fpu_control.h (_FPU_MASK_RC): New.
diff --git a/NEWS b/NEWS
index 31ead24851..00f9e855a2 100644
--- a/NEWS
+++ b/NEWS
@@ -20,7 +20,7 @@ Major new features:
   twalk function, but it passes an additional caller-supplied argument
   to the callback function.
 
-* On Linux, the gettid and tgkill functions have been added.
+* On Linux, the getdents64, gettid, and tgkill functions have been added.
 
 * Minguo (Republic of China) calendar support has been added as an
   alternative calendar for the following locales: zh_TW, cmn_TW, hak_TW,
diff --git a/include/dirent.h b/include/dirent.h
index 400835eefe..3736803bce 100644
--- a/include/dirent.h
+++ b/include/dirent.h
@@ -35,10 +35,14 @@ extern __ssize_t __getdirentries (int __fd, char *__restrict __buf,
 				size_t __nbytes,
 				__off_t *__restrict __basep)
      __THROW __nonnull ((2, 4));
-extern __ssize_t __getdents (int __fd, char *__buf, size_t __nbytes)
-     attribute_hidden;
-extern __ssize_t __getdents64 (int __fd, char *__buf, size_t __nbytes)
+
+/* These functions are only implemented on Linux.  The public
+   interface for getdents64 is declared in <unistd.h>.  */
+extern __ssize_t __getdents (int __fd, void *__buf, size_t __nbytes)
      attribute_hidden;
+extern __ssize_t __getdents64 (int __fd, void *__buf, size_t __nbytes);
+libc_hidden_proto (__getdents64)
+
 extern int __alphasort64 (const struct dirent64 **a, const struct dirent64 **b)
      __attribute_pure__;
 extern int __versionsort64 (const struct dirent64 **a,
diff --git a/manual/filesys.texi b/manual/filesys.texi
index 28480e7608..513319418a 100644
--- a/manual/filesys.texi
+++ b/manual/filesys.texi
@@ -242,6 +242,7 @@ here to the stream facilities for ordinary files, described in
 * Scanning Directory Content::  Get entries for user selected subset of
                                  contents in given directory.
 * Simple Directory Lister Mark II::  Revised version of the program.
+* Low-level Directory Access::  AS-Safe functions for directory access.
 @end menu
 
 @node Directory Entries
@@ -360,6 +361,10 @@ You shouldn't ever allocate objects of the @code{struct dirent} or
 you.  Instead, you refer to these objects using the pointers returned by
 the following functions.
 
+Directory streams are a high-level interface.  On Linux, alternative
+interfaces for accessing directories using file descriptors are
+available.  @xref{Low-level Directory Access}.
+
 @deftypefun {DIR *} opendir (const char *@var{dirname})
 @standards{POSIX.1, dirent.h}
 @safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{} @acsfd{}}}
@@ -826,6 +831,39 @@ After the call the returned entries are available for direct use.
 Note the simple selector function in this example.  Since we want to see
 all directory entries we always return @code{1}.
 
+@node Low-level Directory Access
+@subsection Low-level Directory Access
+
+The stream-based directory functions are not AS-Safe and cannot be
+used after @code{vfork}.  @xref{POSIX Safety Concepts}.  The functions
+below provide an alternative that can be used in these contexts.
+
+Directory data is obtained from a file descriptor, as created by the
+@code{open} function, with or without the @code{O_DIRECTORY} flag.
+@xref{Opening and Closing Files}.
+
+@deftypefun ssize_t getdents64 (int @var{fd}, void *@var{buffer}, size_t @var{length})
+@standards{Linux, unistd.h}
+@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
+The @code{getdents64} function reads at most @var{length} bytes of
+directory entry data from the file descriptor @var{fd} and stores it
+into the byte array starting at @var{buffer}.
+
+On success, the function returns the number of bytes written to the
+buffer.  This number is zero if @var{fd} is already at the end of the
+directory stream.  On error, the function returns @code{-1} and sets
+@code{errno} to the appropriate error code.
+
+The data is stored as a sequence of @code{struct dirent64} records,
+which can be traversed using the @code{d_reclen} member.  The buffer
+should be large enough to hold the largest possible directory entry.
+Note that some file systems support file names longer than
+@code{NAME_MAX} bytes (e.g., because they support up to 255 Unicode
+characters), so a buffer size of at least 1024 is recommended.
+
+This function is specific to Linux.
+@end deftypefun
+
 
 @node Working with Directory Trees
 @section Working with Directory Trees
diff --git a/sysdeps/unix/sysv/linux/Makefile b/sysdeps/unix/sysv/linux/Makefile
index d2f0b60ea9..afcdc658b5 100644
--- a/sysdeps/unix/sysv/linux/Makefile
+++ b/sysdeps/unix/sysv/linux/Makefile
@@ -188,6 +188,7 @@ inhibit-glue = yes
 
 ifeq ($(subdir),dirent)
 sysdep_routines += getdirentries getdirentries64
+tests += tst-getdents64
 tests-internal += tst-readdir64-compat
 endif
 
diff --git a/sysdeps/unix/sysv/linux/Versions b/sysdeps/unix/sysv/linux/Versions
index c7137e2c2c..1ca102a9e2 100644
--- a/sysdeps/unix/sysv/linux/Versions
+++ b/sysdeps/unix/sysv/linux/Versions
@@ -175,7 +175,7 @@ libc {
     getcpu;
   }
   GLIBC_2.30 {
-    gettid; tgkill;
+    getdents64; gettid; tgkill;
   }
   GLIBC_PRIVATE {
     # functions used in other libraries
diff --git a/sysdeps/unix/sysv/linux/aarch64/libc.abilist b/sysdeps/unix/sysv/linux/aarch64/libc.abilist
index 324909d553..a4c31932cb 100644
--- a/sysdeps/unix/sysv/linux/aarch64/libc.abilist
+++ b/sysdeps/unix/sysv/linux/aarch64/libc.abilist
@@ -2141,6 +2141,7 @@ GLIBC_2.28 thrd_yield F
 GLIBC_2.29 getcpu F
 GLIBC_2.29 posix_spawn_file_actions_addchdir_np F
 GLIBC_2.29 posix_spawn_file_actions_addfchdir_np F
+GLIBC_2.30 getdents64 F
 GLIBC_2.30 gettid F
 GLIBC_2.30 tgkill F
 GLIBC_2.30 twalk_r F
diff --git a/sysdeps/unix/sysv/linux/alpha/libc.abilist b/sysdeps/unix/sysv/linux/alpha/libc.abilist
index 084e475569..fe85a35620 100644
--- a/sysdeps/unix/sysv/linux/alpha/libc.abilist
+++ b/sysdeps/unix/sysv/linux/alpha/libc.abilist
@@ -2216,6 +2216,7 @@ GLIBC_2.30 __nldbl_vwarn F
 GLIBC_2.30 __nldbl_vwarnx F
 GLIBC_2.30 __nldbl_warn F
 GLIBC_2.30 __nldbl_warnx F
+GLIBC_2.30 getdents64 F
 GLIBC_2.30 gettid F
 GLIBC_2.30 tgkill F
 GLIBC_2.30 twalk_r F
diff --git a/sysdeps/unix/sysv/linux/arm/libc.abilist b/sysdeps/unix/sysv/linux/arm/libc.abilist
index f58d16e210..bc3df8dcea 100644
--- a/sysdeps/unix/sysv/linux/arm/libc.abilist
+++ b/sysdeps/unix/sysv/linux/arm/libc.abilist
@@ -126,6 +126,7 @@ GLIBC_2.28 thrd_yield F
 GLIBC_2.29 getcpu F
 GLIBC_2.29 posix_spawn_file_actions_addchdir_np F
 GLIBC_2.29 posix_spawn_file_actions_addfchdir_np F
+GLIBC_2.30 getdents64 F
 GLIBC_2.30 gettid F
 GLIBC_2.30 tgkill F
 GLIBC_2.30 twalk_r F
diff --git a/sysdeps/unix/sysv/linux/bits/unistd_ext.h b/sysdeps/unix/sysv/linux/bits/unistd_ext.h
index 0061172f23..6e7b2bb83d 100644
--- a/sysdeps/unix/sysv/linux/bits/unistd_ext.h
+++ b/sysdeps/unix/sysv/linux/bits/unistd_ext.h
@@ -22,6 +22,12 @@
 
 #ifdef __USE_GNU
 
+/* Read from the directory descriptor FD into LENGTH bytes at BUFFER.
+   Return the number of bytes read on success (0 for end of
+   directory), and -1 for failure.  */
+extern ssize_t getdents64 (int __fd, void *__buffer, size_t __length)
+  __THROW __nonnull ((2));
+
 /* Return the kernel thread ID (TID) of the current thread.  The
    returned value is not subject to caching.  Most Linux system calls
    accept a TID in place of a PID.  Using the TID to change properties
diff --git a/sysdeps/unix/sysv/linux/csky/libc.abilist b/sysdeps/unix/sysv/linux/csky/libc.abilist
index 38f6abaa30..9b3cee65bb 100644
--- a/sysdeps/unix/sysv/linux/csky/libc.abilist
+++ b/sysdeps/unix/sysv/linux/csky/libc.abilist
@@ -2085,6 +2085,7 @@ GLIBC_2.29 xdrstdio_create F
 GLIBC_2.29 xencrypt F
 GLIBC_2.29 xprt_register F
 GLIBC_2.29 xprt_unregister F
+GLIBC_2.30 getdents64 F
 GLIBC_2.30 gettid F
 GLIBC_2.30 tgkill F
 GLIBC_2.30 twalk_r F
diff --git a/sysdeps/unix/sysv/linux/getdents.c b/sysdeps/unix/sysv/linux/getdents.c
index e796d9354b..3eec4c4221 100644
--- a/sysdeps/unix/sysv/linux/getdents.c
+++ b/sysdeps/unix/sysv/linux/getdents.c
@@ -31,8 +31,10 @@
 /* Pack the dirent64 struct down into 32-bit offset/inode fields, and
    ensure that no overflow occurs.  */
 ssize_t
-__getdents (int fd, char *buf, size_t nbytes)
+__getdents (int fd, void *buf0, size_t nbytes)
 {
+  char *buf = buf0;
+
   union
   {
     /* For !_DIRENT_MATCHES_DIRENT64 kernel 'linux_dirent64' has the same
diff --git a/sysdeps/unix/sysv/linux/getdents64.c b/sysdeps/unix/sysv/linux/getdents64.c
index 0786a15195..a6dd22106d 100644
--- a/sysdeps/unix/sysv/linux/getdents64.c
+++ b/sysdeps/unix/sysv/linux/getdents64.c
@@ -20,12 +20,14 @@
 #include <dirent.h>
 #include <errno.h>
 
-/* The kernel struct linux_dirent64 matches the 'struct getdents64' type.  */
+/* The kernel struct linux_dirent64 matches the 'struct dirent64' type.  */
 ssize_t
-__getdents64 (int fd, char *buf, size_t nbytes)
+__getdents64 (int fd, void *buf, size_t nbytes)
 {
   return INLINE_SYSCALL_CALL (getdents64, fd, buf, nbytes);
 }
+libc_hidden_def (__getdents64)
+weak_alias (__getdents64, getdents64)
 
 #if _DIRENT_MATCHES_DIRENT64
 strong_alias (__getdents64, __getdents)
diff --git a/sysdeps/unix/sysv/linux/hppa/libc.abilist b/sysdeps/unix/sysv/linux/hppa/libc.abilist
index eb628f907b..75edece94a 100644
--- a/sysdeps/unix/sysv/linux/hppa/libc.abilist
+++ b/sysdeps/unix/sysv/linux/hppa/libc.abilist
@@ -2037,6 +2037,7 @@ GLIBC_2.3.4 setipv4sourcefilter F
 GLIBC_2.3.4 setsourcefilter F
 GLIBC_2.3.4 xdr_quad_t F
 GLIBC_2.3.4 xdr_u_quad_t F
+GLIBC_2.30 getdents64 F
 GLIBC_2.30 gettid F
 GLIBC_2.30 tgkill F
 GLIBC_2.30 twalk_r F
diff --git a/sysdeps/unix/sysv/linux/i386/libc.abilist b/sysdeps/unix/sysv/linux/i386/libc.abilist
index 6f240d9a59..edeaf8e722 100644
--- a/sysdeps/unix/sysv/linux/i386/libc.abilist
+++ b/sysdeps/unix/sysv/linux/i386/libc.abilist
@@ -2203,6 +