Por que o rmdir e desvincula duas chamadas do sistema separadas?

Question

Aqui está algo que me fez pensar por um tempo:

[15:40:50][/tmp]$ mkdir a
[15:40:52][/tmp]$ strace rmdir a
execve("/usr/bin/rmdir", ["rmdir", "a"], [/* 78 vars */]) = 0
brk(0)                                  = 0x11bb000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7ff3772c3000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=245801, ...}) = 0
mmap(NULL, 245801, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7ff377286000
close(3)                                = 0
open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "7ELF
[15:40:50][/tmp]$ mkdir a
[15:40:52][/tmp]$ strace rmdir a
execve("/usr/bin/rmdir", ["rmdir", "a"], [/* 78 vars */]) = 0
brk(0)                                  = 0x11bb000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7ff3772c3000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=245801, ...}) = 0
mmap(NULL, 245801, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7ff377286000
close(3)                                = 0
open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "7ELF%pre%%pre%%pre%%pre%%pre%%pre%%pre%%pre%%pre%>%pre%%pre%%pre%%pre%p28<%pre%%pre%%pre%"..., 832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=2100672, ...}) = 0
mmap(0x3c38e00000, 3924576, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x3c38e00000
mprotect(0x3c38fb4000, 2097152, PROT_NONE) = 0
mmap(0x3c391b4000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1b4000) = 0x3c391b4000
mmap(0x3c391ba000, 16992, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x3c391ba000
close(3)                                = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7ff377285000
mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7ff377283000
arch_prctl(ARCH_SET_FS, 0x7ff377283740) = 0
mprotect(0x609000, 4096, PROT_READ)     = 0
mprotect(0x3c391b4000, 16384, PROT_READ) = 0
mprotect(0x3c38c1f000, 4096, PROT_READ) = 0
munmap(0x7ff377286000, 245801)          = 0
brk(0)                                  = 0x11bb000
brk(0x11dc000)                          = 0x11dc000
brk(0)                                  = 0x11dc000
open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=106070960, ...}) = 0
mmap(NULL, 106070960, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7ff370d5a000
close(3)                                = 0
rmdir("a")                              = 0
close(1)                                = 0
close(2)                                = 0
exit_group(0)                           = ?
+++ exited with 0 +++
[15:40:55][/tmp]$ touch a
[15:41:16][/tmp]$ strace rm a
execve("/usr/bin/rm", ["rm", "a"], [/* 78 vars */]) = 0
brk(0)                                  = 0xfa8000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f3b2388a000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=245801, ...}) = 0
mmap(NULL, 245801, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f3b2384d000
close(3)                                = 0
open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "7ELF%pre%%pre%%pre%%pre%%pre%%pre%%pre%%pre%%pre%>%pre%%pre%%pre%%pre%p28<%pre%%pre%%pre%"..., 832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=2100672, ...}) = 0
mmap(0x3c38e00000, 3924576, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x3c38e00000
mprotect(0x3c38fb4000, 2097152, PROT_NONE) = 0
mmap(0x3c391b4000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1b4000) = 0x3c391b4000
mmap(0x3c391ba000, 16992, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x3c391ba000
close(3)                                = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f3b2384c000
mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f3b2384a000
arch_prctl(ARCH_SET_FS, 0x7f3b2384a740) = 0
mprotect(0x60d000, 4096, PROT_READ)     = 0
mprotect(0x3c391b4000, 16384, PROT_READ) = 0
mprotect(0x3c38c1f000, 4096, PROT_READ) = 0
munmap(0x7f3b2384d000, 245801)          = 0
brk(0)                                  = 0xfa8000
brk(0xfc9000)                           = 0xfc9000
brk(0)                                  = 0xfc9000
open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=106070960, ...}) = 0
mmap(NULL, 106070960, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f3b1d321000
close(3)                                = 0
ioctl(0, SNDCTL_TMR_TIMEBASE or SNDRV_TIMER_IOCTL_NEXT_DEVICE or TCGETS, {B38400 opost isig icanon echo ...}) = 0
newfstatat(AT_FDCWD, "a", {st_mode=S_IFREG|0664, st_size=0, ...}, AT_SYMLINK_NOFOLLOW) = 0
geteuid()                               = 1000
newfstatat(AT_FDCWD, "a", {st_mode=S_IFREG|0664, st_size=0, ...}, AT_SYMLINK_NOFOLLOW) = 0
faccessat(AT_FDCWD, "a", W_OK)          = 0
unlinkat(AT_FDCWD, "a", 0)              = 0
lseek(0, 0, SEEK_CUR)                   = -1 ESPIPE (Illegal seek)
close(0)                                = 0
close(1)                                = 0
close(2)                                = 0
exit_group(0)                           = ?
+++ exited with 0 +++
%pre%%pre%%pre%%pre%%pre%%pre%%pre%%pre%>%pre%%pre%%pre%%pre%p28<%pre%%pre%%pre%"..., 832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=2100672, ...}) = 0
mmap(0x3c38e00000, 3924576, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x3c38e00000
mprotect(0x3c38fb4000, 2097152, PROT_NONE) = 0
mmap(0x3c391b4000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1b4000) = 0x3c391b4000
mmap(0x3c391ba000, 16992, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x3c391ba000
close(3)                                = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7ff377285000
mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7ff377283000
arch_prctl(ARCH_SET_FS, 0x7ff377283740) = 0
mprotect(0x609000, 4096, PROT_READ)     = 0
mprotect(0x3c391b4000, 16384, PROT_READ) = 0
mprotect(0x3c38c1f000, 4096, PROT_READ) = 0
munmap(0x7ff377286000, 245801)          = 0
brk(0)                                  = 0x11bb000
brk(0x11dc000)                          = 0x11dc000
brk(0)                                  = 0x11dc000
open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=106070960, ...}) = 0
mmap(NULL, 106070960, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7ff370d5a000
close(3)                                = 0
rmdir("a")                              = 0
close(1)                                = 0
close(2)                                = 0
exit_group(0)                           = ?
+++ exited with 0 +++
[15:40:55][/tmp]$ touch a
[15:41:16][/tmp]$ strace rm a
execve("/usr/bin/rm", ["rm", "a"], [/* 78 vars */]) = 0
brk(0)                                  = 0xfa8000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f3b2388a000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=245801, ...}) = 0
mmap(NULL, 245801, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f3b2384d000
close(3)                                = 0
open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "7ELF%pre%%pre%%pre%%pre%%pre%%pre%%pre%%pre%%pre%>%pre%%pre%%pre%%pre%p28<%pre%%pre%%pre%"..., 832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=2100672, ...}) = 0
mmap(0x3c38e00000, 3924576, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x3c38e00000
mprotect(0x3c38fb4000, 2097152, PROT_NONE) = 0
mmap(0x3c391b4000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1b4000) = 0x3c391b4000
mmap(0x3c391ba000, 16992, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x3c391ba000
close(3)                                = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f3b2384c000
mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f3b2384a000
arch_prctl(ARCH_SET_FS, 0x7f3b2384a740) = 0
mprotect(0x60d000, 4096, PROT_READ)     = 0
mprotect(0x3c391b4000, 16384, PROT_READ) = 0
mprotect(0x3c38c1f000, 4096, PROT_READ) = 0
munmap(0x7f3b2384d000, 245801)          = 0
brk(0)                                  = 0xfa8000
brk(0xfc9000)                           = 0xfc9000
brk(0)                                  = 0xfc9000
open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=106070960, ...}) = 0
mmap(NULL, 106070960, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f3b1d321000
close(3)                                = 0
ioctl(0, SNDCTL_TMR_TIMEBASE or SNDRV_TIMER_IOCTL_NEXT_DEVICE or TCGETS, {B38400 opost isig icanon echo ...}) = 0
newfstatat(AT_FDCWD, "a", {st_mode=S_IFREG|0664, st_size=0, ...}, AT_SYMLINK_NOFOLLOW) = 0
geteuid()                               = 1000
newfstatat(AT_FDCWD, "a", {st_mode=S_IFREG|0664, st_size=0, ...}, AT_SYMLINK_NOFOLLOW) = 0
faccessat(AT_FDCWD, "a", W_OK)          = 0
unlinkat(AT_FDCWD, "a", 0)              = 0
lseek(0, 0, SEEK_CUR)                   = -1 ESPIPE (Illegal seek)
close(0)                                = 0
close(1)                                = 0
close(2)                                = 0
exit_group(0)                           = ?
+++ exited with 0 +++

Por que existem chamadas de sistema separadas para remover um diretório e arquivos? Por que essas duas operações seriam semanticamente distintas?

    

Answer 1

Diretórios são especiais no sentido de que dentro de um diretório você pode ter referências a vários arquivos e diretórios, então, se você remover o diretório pai, todos esses arquivos perderão seu ponto de referência de onde eles podem ser acessados, o mesmo com processo . Para esses casos, rmdir() tem verificações diferentes, que são diferentes de unlink() :

• Se o diretório não estiver vazio. Se um diretório não estiver vazio, ele não poderá removê-lo até que o conteúdo seja unlink 'd / removed.

     ENOTEMPTY
        pathname contains entries other than . and .. ; or, pathname has
        ..  as its final component.  POSIX.1-2001 also allows EEXIST for
        this condition.
  

• Se o diretório estiver em uso. Se um processo perder seu diretório atual, isso pode levar a problemas e comportamentos indefinidos. É melhor preveni-los.

     EBUSY  pathname  is currently in use by the system or some process that
        prevents its removal.  On Linux this means pathname is currently
        used  as  a  mount point or is the root directory of the calling
        process.
  

No caso de unlink() , essas verificações não existem. Na verdade, você pode excluir o nome de um arquivo com unlink() e o processo que ainda está usando / fazendo referência a ele, pode modificá-lo sem problemas. O arquivo existe até que o descritor de arquivo exista, apenas inacessível ao novo processo (a menos que você saiba onde procurar). Isso faz parte da magia das mãos coloridas do arco-íris dos sistemas de arquivos * NIX.

Agora, há o unlinkat() que se comporta como unlink() ou rmdir(2) dependendo do caminho que você espera.