diff options
| author | Dominik Brodowski | 2018-03-06 22:18:08 +0100 |
|---|---|---|
| committer | Ingo Molnar | 2018-03-07 07:57:31 +0100 |
| commit | af52201d991624d2d5adce2c123805b3d42a8d4d (patch) | |
| tree | 6fcb0ec95c5ad0c7fff5dd51abb8df12c623dc53 /arch/x86/ia32 | |
| parent | 4ddb45db30851b2269101ee8969f079b028dd257 (diff) | |
x86/entry: Do not special-case clone(2) in compat entry
With the CPU renaming registers on its own, and all the overhead of the
syscall entry/exit, it is doubtful whether the compiled output of
mov %r8, %rax
mov %rcx, %r8
mov %rax, %rcx
jmpq sys_clone
is measurably slower than the hand-crafted version of
xchg %r8, %rcx
So get rid of this special case.
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: luto@amacapital.net
Cc: viro@zeniv.linux.org.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/ia32')
| -rw-r--r-- | arch/x86/ia32/sys_ia32.c | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 3bc03446ec44..6512498bbef6 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -233,3 +233,14 @@ COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); } + +/* + * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS + */ +COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, + unsigned long, newsp, int __user *, parent_tidptr, + unsigned long, tls_val, int __user *, child_tidptr) +{ + return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr, + tls_val); +} |