x86/entry/64: Call all native slow-path syscalls with full pt-regs

This removes all of the remaining asm syscall stubs except for
stub_ptregs_64.  Entries in the main syscall table are now all
callable from C.

The resulting asm is every bit as ridiculous as it looks.  The
next few patches will clean it up.  This patch is here to let
reviewers rest their brains and for bisection.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a6b3801be0d505d50aefabda02d3b93efbfc9c73.1454022279.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f1c8f150728ee80c6cffc10ce3471367aff163e1..f7050a5d9dbc121139fdc3ed5901d2313cdd8e91 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -253,7 +253,6 @@ tracesys:
         * the value it wants us to use in the table lookup.
         */
        RESTORE_C_REGS_EXCEPT_RAX
-       RESTORE_EXTRA_REGS
 #if __SYSCALL_MASK == ~0
        cmpq    $__NR_syscall_max, %rax
 #else
@@ -264,6 +263,7 @@ tracesys:
        movq    %r10, %rcx                      /* fixup for C */
        call    *sys_call_table(, %rax, 8)
        movq    %rax, RAX(%rsp)
+       RESTORE_EXTRA_REGS
 1:
        /* Use IRET because user could have changed pt_regs->foo */
 
@@ -384,83 +384,6 @@ END(ptregs_\func)
 #define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym)
 #include <asm/syscalls_64.h>
 
-       .macro FORK_LIKE func
-ENTRY(stub_\func)
-       SAVE_EXTRA_REGS 8
-       jmp     sys_\func
-END(stub_\func)
-       .endm
-
-       FORK_LIKE  clone
-       FORK_LIKE  fork
-       FORK_LIKE  vfork
-
-ENTRY(stub_execve)
-       call    sys_execve
-return_from_execve:
-       testl   %eax, %eax
-       jz      1f
-       /* exec failed, can use fast SYSRET code path in this case */
-       ret
-1:
-       /* must use IRET code path (pt_regs->cs may have changed) */
-       addq    $8, %rsp
-       ZERO_EXTRA_REGS
-       movq    %rax, RAX(%rsp)
-       jmp     int_ret_from_sys_call
-END(stub_execve)
-/*
- * Remaining execve stubs are only 7 bytes long.
- * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
- */
-       .align  8
-GLOBAL(stub_execveat)
-       call    sys_execveat
-       jmp     return_from_execve
-END(stub_execveat)
-
-#if defined(CONFIG_X86_X32_ABI)
-       .align  8
-GLOBAL(stub_x32_execve)
-       call    compat_sys_execve
-       jmp     return_from_execve
-END(stub_x32_execve)
-       .align  8
-GLOBAL(stub_x32_execveat)
-       call    compat_sys_execveat
-       jmp     return_from_execve
-END(stub_x32_execveat)
-#endif
-
-/*
- * sigreturn is special because it needs to restore all registers on return.
- * This cannot be done with SYSRET, so use the IRET return path instead.
- */
-ENTRY(stub_rt_sigreturn)
-       /*
-        * SAVE_EXTRA_REGS result is not normally needed:
-        * sigreturn overwrites all pt_regs->GPREGS.
-        * But sigreturn can fail (!), and there is no easy way to detect that.
-        * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
-        * we SAVE_EXTRA_REGS here.
-        */
-       SAVE_EXTRA_REGS 8
-       call    sys_rt_sigreturn
-return_from_stub:
-       addq    $8, %rsp
-       RESTORE_EXTRA_REGS
-       movq    %rax, RAX(%rsp)
-       jmp     int_ret_from_sys_call
-END(stub_rt_sigreturn)
-
-#ifdef CONFIG_X86_X32_ABI
-ENTRY(stub_x32_rt_sigreturn)
-       SAVE_EXTRA_REGS 8
-       call    sys32_x32_rt_sigreturn
-       jmp     return_from_stub
-END(stub_x32_rt_sigreturn)
-#endif
-
 /*
  * A newly forked process directly context switches into this address.
  *

diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5de342a729d0b0b8efc19497edc0365aae2fcb01..dcf107ce2cd4a4302bc3f805eaf4ade334da3cae 100644 (file)
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -21,7 +21,7 @@
 12     common  brk                     sys_brk
 13     64      rt_sigaction            sys_rt_sigaction
 14     common  rt_sigprocmask          sys_rt_sigprocmask
-15     64      rt_sigreturn            stub_rt_sigreturn/ptregs
+15     64      rt_sigreturn            sys_rt_sigreturn/ptregs
 16     64      ioctl                   sys_ioctl
 17     common  pread64                 sys_pread64
 18     common  pwrite64                sys_pwrite64
@@ -62,10 +62,10 @@
 53     common  socketpair              sys_socketpair
 54     64      setsockopt              sys_setsockopt
 55     64      getsockopt              sys_getsockopt
-56     common  clone                   stub_clone/ptregs
-57     common  fork                    stub_fork/ptregs
-58     common  vfork                   stub_vfork/ptregs
-59     64      execve                  stub_execve/ptregs
+56     common  clone                   sys_clone/ptregs
+57     common  fork                    sys_fork/ptregs
+58     common  vfork                   sys_vfork/ptregs
+59     64      execve                  sys_execve/ptregs
 60     common  exit                    sys_exit
 61     common  wait4                   sys_wait4
 62     common  kill                    sys_kill
@@ -328,7 +328,7 @@
 319    common  memfd_create            sys_memfd_create
 320    common  kexec_file_load         sys_kexec_file_load
 321    common  bpf                     sys_bpf
-322    64      execveat                stub_execveat/ptregs
+322    64      execveat                sys_execveat/ptregs
 323    common  userfaultfd             sys_userfaultfd
 324    common  membarrier              sys_membarrier
 325    common  mlock2                  sys_mlock2
@@ -339,14 +339,14 @@
 # for native 64-bit operation.
 #
 512    x32     rt_sigaction            compat_sys_rt_sigaction
-513    x32     rt_sigreturn            stub_x32_rt_sigreturn
+513    x32     rt_sigreturn            sys32_x32_rt_sigreturn
 514    x32     ioctl                   compat_sys_ioctl
 515    x32     readv                   compat_sys_readv
 516    x32     writev                  compat_sys_writev
 517    x32     recvfrom                compat_sys_recvfrom
 518    x32     sendmsg                 compat_sys_sendmsg
 519    x32     recvmsg                 compat_sys_recvmsg
-520    x32     execve                  stub_x32_execve/ptregs
+520    x32     execve                  compat_sys_execve/ptregs
 521    x32     ptrace                  compat_sys_ptrace
 522    x32     rt_sigpending           compat_sys_rt_sigpending
 523    x32     rt_sigtimedwait         compat_sys_rt_sigtimedwait
@@ -371,4 +371,4 @@
 542    x32     getsockopt              compat_sys_getsockopt
 543    x32     io_setup                compat_sys_io_setup
 544    x32     io_submit               compat_sys_io_submit
-545    x32     execveat                stub_x32_execveat/ptregs
+545    x32     execveat                compat_sys_execveat/ptregs