kernel-ark/arch/x86/ia32/ia32_signal.c

499 lines
13 KiB
C
Raw Normal View History

/*
* linux/arch/x86_64/ia32/ia32_signal.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
* 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
* 2000-12-* x86-64 compatibility mode signal handling by Andi Kleen
*/
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/personality.h>
#include <linux/compat.h>
#include <linux/binfmts.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/ptrace.h>
#include <asm/ia32_unistd.h>
#include <asm/user32.h>
#include <asm/sigcontext32.h>
#include <asm/proto.h>
#include <asm/vdso.h>
#include <asm/sigframe.h>
#include <asm/sighandling.h>
x86: introducing asm/sys_ia32.h Impact: cleanup, avoid 44 sparse warnings, new file asm/sys_ia32.h Fixes following sparse warnings: CHECK arch/x86/ia32/sys_ia32.c arch/x86/ia32/sys_ia32.c:53:17: warning: symbol 'sys32_truncate64' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:60:17: warning: symbol 'sys32_ftruncate64' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:98:17: warning: symbol 'sys32_stat64' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:109:17: warning: symbol 'sys32_lstat64' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:119:17: warning: symbol 'sys32_fstat64' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:128:17: warning: symbol 'sys32_fstatat' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:164:17: warning: symbol 'sys32_mmap' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:195:17: warning: symbol 'sys32_mprotect' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:201:17: warning: symbol 'sys32_pipe' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:215:17: warning: symbol 'sys32_rt_sigaction' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:291:17: warning: symbol 'sys32_sigaction' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:330:17: warning: symbol 'sys32_rt_sigprocmask' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:370:17: warning: symbol 'sys32_alarm' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:383:17: warning: symbol 'sys32_old_select' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:393:17: warning: symbol 'sys32_waitpid' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:401:17: warning: symbol 'sys32_sysfs' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:406:17: warning: symbol 'sys32_sched_rr_get_interval' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:421:17: warning: symbol 'sys32_rt_sigpending' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:445:17: warning: symbol 'sys32_rt_sigqueueinfo' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:472:17: warning: symbol 'sys32_sysctl' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:517:17: warning: symbol 'sys32_pread' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:524:17: warning: symbol 'sys32_pwrite' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:532:17: warning: symbol 'sys32_personality' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:545:17: warning: symbol 'sys32_sendfile' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:565:17: warning: symbol 'sys32_mmap2' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:589:17: warning: symbol 'sys32_olduname' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:626:6: warning: symbol 'sys32_uname' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:641:6: warning: symbol 'sys32_ustat' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:663:17: warning: symbol 'sys32_execve' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:678:17: warning: symbol 'sys32_clone' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:693:6: warning: symbol 'sys32_lseek' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:698:6: warning: symbol 'sys32_kill' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:703:6: warning: symbol 'sys32_fadvise64_64' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:712:6: warning: symbol 'sys32_vm86_warning' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:726:6: warning: symbol 'sys32_lookup_dcookie' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:732:20: warning: symbol 'sys32_readahead' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:738:17: warning: symbol 'sys32_sync_file_range' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:746:17: warning: symbol 'sys32_fadvise64' was not declared. Should it be static? arch/x86/ia32/sys_ia32.c:753:17: warning: symbol 'sys32_fallocate' was not declared. Should it be static? CHECK arch/x86/ia32/ia32_signal.c arch/x86/ia32/ia32_signal.c:126:17: warning: symbol 'sys32_sigsuspend' was not declared. Should it be static? arch/x86/ia32/ia32_signal.c:141:17: warning: symbol 'sys32_sigaltstack' was not declared. Should it be static? arch/x86/ia32/ia32_signal.c:249:17: warning: symbol 'sys32_sigreturn' was not declared. Should it be static? arch/x86/ia32/ia32_signal.c:279:17: warning: symbol 'sys32_rt_sigreturn' was not declared. Should it be static? CHECK arch/x86/ia32/ipc32.c arch/x86/ia32/ipc32.c:12:17: warning: symbol 'sys32_ipc' was not declared. Should it be static? Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-27 16:07:10 +00:00
#include <asm/sys_ia32.h>
#include <asm/smap.h>
int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
{
int err = 0;
bool ia32 = test_thread_flag(TIF_IA32);
if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
return -EFAULT;
put_user_try {
/* If you change siginfo_t structure, please make sure that
this code is fixed accordingly.
It should never copy any pad contained in the structure
to avoid security leaks, but must copy the generic
3 ints plus the relevant union member. */
put_user_ex(from->si_signo, &to->si_signo);
put_user_ex(from->si_errno, &to->si_errno);
put_user_ex((short)from->si_code, &to->si_code);
if (from->si_code < 0) {
put_user_ex(from->si_pid, &to->si_pid);
put_user_ex(from->si_uid, &to->si_uid);
put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
} else {
/*
* First 32bits of unions are always present:
* si_pid === si_band === si_tid === si_addr(LS half)
*/
put_user_ex(from->_sifields._pad[0],
&to->_sifields._pad[0]);
switch (from->si_code >> 16) {
case __SI_FAULT >> 16:
break;
signal, x86: add SIGSYS info and make it synchronous. This change enables SIGSYS, defines _sigfields._sigsys, and adds x86 (compat) arch support. _sigsys defines fields which allow a signal handler to receive the triggering system call number, the relevant AUDIT_ARCH_* value for that number, and the address of the callsite. SIGSYS is added to the SYNCHRONOUS_MASK because it is desirable for it to have setup_frame() called for it. The goal is to ensure that ucontext_t reflects the machine state from the time-of-syscall and not from another signal handler. The first consumer of SIGSYS would be seccomp filter. In particular, a filter program could specify a new return value, SECCOMP_RET_TRAP, which would result in the system call being denied and the calling thread signaled. This also means that implementing arch-specific support can be dependent upon HAVE_ARCH_SECCOMP_FILTER. Suggested-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Will Drewry <wad@chromium.org> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: H. Peter Anvin <hpa@zytor.com> Acked-by: Eric Paris <eparis@redhat.com> v18: - added acked by, rebase v17: - rebase and reviewed-by addition v14: - rebase/nochanges v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc v12: - reworded changelog (oleg@redhat.com) v11: - fix dropped words in the change description - added fallback copy_siginfo support. - added __ARCH_SIGSYS define to allow stepped arch support. v10: - first version based on suggestion Signed-off-by: James Morris <james.l.morris@oracle.com>
2012-04-12 21:48:00 +00:00
case __SI_SYS >> 16:
put_user_ex(from->si_syscall, &to->si_syscall);
put_user_ex(from->si_arch, &to->si_arch);
break;
case __SI_CHLD >> 16:
if (ia32) {
put_user_ex(from->si_utime, &to->si_utime);
put_user_ex(from->si_stime, &to->si_stime);
} else {
put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
}
put_user_ex(from->si_status, &to->si_status);
/* FALL THROUGH */
default:
case __SI_KILL >> 16:
put_user_ex(from->si_uid, &to->si_uid);
break;
case __SI_POLL >> 16:
put_user_ex(from->si_fd, &to->si_fd);
break;
case __SI_TIMER >> 16:
put_user_ex(from->si_overrun, &to->si_overrun);
put_user_ex(ptr_to_compat(from->si_ptr),
&to->si_ptr);
break;
/* This is not generated by the kernel as of now. */
case __SI_RT >> 16:
case __SI_MESGQ >> 16:
put_user_ex(from->si_uid, &to->si_uid);
put_user_ex(from->si_int, &to->si_int);
break;
}
}
} put_user_catch(err);
return err;
}
int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
{
int err = 0;
u32 ptr32;
if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
return -EFAULT;
get_user_try {
get_user_ex(to->si_signo, &from->si_signo);
get_user_ex(to->si_errno, &from->si_errno);
get_user_ex(to->si_code, &from->si_code);
get_user_ex(to->si_pid, &from->si_pid);
get_user_ex(to->si_uid, &from->si_uid);
get_user_ex(ptr32, &from->si_ptr);
to->si_ptr = compat_ptr(ptr32);
} get_user_catch(err);
return err;
}
/*
* Do a signal return; undo the signal stack.
*/
#define loadsegment_gs(v) load_gs_index(v)
#define loadsegment_fs(v) loadsegment(fs, v)
#define loadsegment_ds(v) loadsegment(ds, v)
#define loadsegment_es(v) loadsegment(es, v)
#define get_user_seg(seg) ({ unsigned int v; savesegment(seg, v); v; })
#define set_user_seg(seg, v) loadsegment_##seg(v)
#define COPY(x) { \
get_user_ex(regs->x, &sc->x); \
}
#define GET_SEG(seg) ({ \
unsigned short tmp; \
get_user_ex(tmp, &sc->seg); \
tmp; \
})
#define COPY_SEG_CPL3(seg) do { \
regs->seg = GET_SEG(seg) | 3; \
} while (0)
#define RELOAD_SEG(seg) { \
unsigned int pre = GET_SEG(seg); \
unsigned int cur = get_user_seg(seg); \
pre |= 3; \
if (pre != cur) \
set_user_seg(seg, pre); \
}
static int ia32_restore_sigcontext(struct pt_regs *regs,
struct sigcontext_ia32 __user *sc)
{
unsigned int tmpflags, err = 0;
void __user *buf;
u32 tmp;
/* Always make any pending restarted system calls return -EINTR */
all arches, signal: move restart_block to struct task_struct If an attacker can cause a controlled kernel stack overflow, overwriting the restart block is a very juicy exploit target. This is because the restart_block is held in the same memory allocation as the kernel stack. Moving the restart block to struct task_struct prevents this exploit by making the restart_block harder to locate. Note that there are other fields in thread_info that are also easy targets, at least on some architectures. It's also a decent simplification, since the restart code is more or less identical on all architectures. [james.hogan@imgtec.com: metag: align thread_info::supervisor_stack] Signed-off-by: Andy Lutomirski <luto@amacapital.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: David Miller <davem@davemloft.net> Acked-by: Richard Weinberger <richard@nod.at> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Steven Miao <realmz6@gmail.com> Cc: Mark Salter <msalter@redhat.com> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Tested-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Chris Zankel <chris@zankel.net> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Guenter Roeck <linux@roeck-us.net> Signed-off-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 23:01:14 +00:00
current->restart_block.fn = do_no_restart_syscall;
get_user_try {
/*
* Reload fs and gs if they have changed in the signal
* handler. This does not handle long fs/gs base changes in
* the handler, but does not clobber them at least in the
* normal case.
*/
RELOAD_SEG(gs);
RELOAD_SEG(fs);
RELOAD_SEG(ds);
RELOAD_SEG(es);
COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
COPY(dx); COPY(cx); COPY(ip); COPY(ax);
/* Don't touch extended registers */
COPY_SEG_CPL3(cs);
COPY_SEG_CPL3(ss);
get_user_ex(tmpflags, &sc->flags);
regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
/* disable syscall checks */
regs->orig_ax = -1;
get_user_ex(tmp, &sc->fpstate);
buf = compat_ptr(tmp);
} get_user_catch(err);
err |= fpu__restore_sig(buf, 1);
force_iret();
return err;
}
asmlinkage long sys32_sigreturn(void)
{
struct pt_regs *regs = current_pt_regs();
struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
sigset_t set;
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__get_user(set.sig[0], &frame->sc.oldmask)
|| (_COMPAT_NSIG_WORDS > 1
&& __copy_from_user((((char *) &set.sig) + 4),
&frame->extramask,
sizeof(frame->extramask))))
goto badframe;
set_current_blocked(&set);
if (ia32_restore_sigcontext(regs, &frame->sc))
goto badframe;
return regs->ax;
badframe:
signal_fault(regs, frame, "32bit sigreturn");
return 0;
}
asmlinkage long sys32_rt_sigreturn(void)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe_ia32 __user *frame;
sigset_t set;
frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
goto badframe;
set_current_blocked(&set);
if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext))
goto badframe;
if (compat_restore_altstack(&frame->uc.uc_stack))
goto badframe;
return regs->ax;
badframe:
signal_fault(regs, frame, "32bit rt sigreturn");
return 0;
}
/*
* Set up a signal frame.
*/
static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
void __user *fpstate,
struct pt_regs *regs, unsigned int mask)
{
int err = 0;
put_user_try {
put_user_ex(get_user_seg(gs), (unsigned int __user *)&sc->gs);
put_user_ex(get_user_seg(fs), (unsigned int __user *)&sc->fs);
put_user_ex(get_user_seg(ds), (unsigned int __user *)&sc->ds);
put_user_ex(get_user_seg(es), (unsigned int __user *)&sc->es);
put_user_ex(regs->di, &sc->di);
put_user_ex(regs->si, &sc->si);
put_user_ex(regs->bp, &sc->bp);
put_user_ex(regs->sp, &sc->sp);
put_user_ex(regs->bx, &sc->bx);
put_user_ex(regs->dx, &sc->dx);
put_user_ex(regs->cx, &sc->cx);
put_user_ex(regs->ax, &sc->ax);
put_user_ex(current->thread.trap_nr, &sc->trapno);
put_user_ex(current->thread.error_code, &sc->err);
put_user_ex(regs->ip, &sc->ip);
put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
put_user_ex(regs->flags, &sc->flags);
put_user_ex(regs->sp, &sc->sp_at_signal);
put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
put_user_ex(ptr_to_compat(fpstate), &sc->fpstate);
/* non-iBCS2 extensions.. */
put_user_ex(mask, &sc->oldmask);
put_user_ex(current->thread.cr2, &sc->cr2);
} put_user_catch(err);
return err;
}
/*
* Determine which stack to use..
*/
static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
size_t frame_size,
void __user **fpstate)
{
struct fpu *fpu = &current->thread.fpu;
unsigned long sp;
/* Default to using normal stack */
sp = regs->sp;
/* This is the X/Open sanctioned signal stack switching. */
if (ksig->ka.sa.sa_flags & SA_ONSTACK)
sp = sigsp(sp, ksig);
/* This is the legacy signal stack switching. */
else if ((regs->ss & 0xffff) != __USER32_DS &&
!(ksig->ka.sa.sa_flags & SA_RESTORER) &&
ksig->ka.sa.sa_restorer)
sp = (unsigned long) ksig->ka.sa.sa_restorer;
if (fpu->fpstate_active) {
x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels Currently for x86 and x86_32 binaries, fpstate in the user sigframe is copied to/from the fpstate in the task struct. And in the case of signal delivery for x86_64 binaries, if the fpstate is live in the CPU registers, then the live state is copied directly to the user sigframe. Otherwise fpstate in the task struct is copied to the user sigframe. During restore, fpstate in the user sigframe is restored directly to the live CPU registers. Historically, different code paths led to different bugs. For example, x86_64 code path was not preemption safe till recently. Also there is lot of code duplication for support of new features like xsave etc. Unify signal handling code paths for x86 and x86_64 kernels. New strategy is as follows: Signal delivery: Both for 32/64-bit frames, align the core math frame area to 64bytes as needed by xsave (this where the main fpu/extended state gets copied to and excludes the legacy compatibility fsave header for the 32-bit [f]xsave frames). If the state is live, copy the register state directly to the user frame. If not live, copy the state in the thread struct to the user frame. And for 32-bit [f]xsave frames, construct the fsave header separately before the actual [f]xsave area. Signal return: As the 32-bit frames with [f]xstate has an additional 'fsave' header, copy everything back from the user sigframe to the fpstate in the task structure and reconstruct the fxstate from the 'fsave' header (Also user passed pointers may not be correctly aligned for any attempt to directly restore any partial state). At the next fpstate usage, everything will be restored to the live CPU registers. For all the 64-bit frames and the 32-bit fsave frame, restore the state from the user sigframe directly to the live CPU registers. 64-bit signals always restored the math frame directly, so we can expect the math frame pointer to be correctly aligned. For 32-bit fsave frames, there are no alignment requirements, so we can restore the state directly. "lat_sig catch" microbenchmark numbers (for x86, x86_64, x86_32 binaries) are with in the noise range with this change. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Link: http://lkml.kernel.org/r/1343171129-2747-4-git-send-email-suresh.b.siddha@intel.com [ Merged in compilation fix ] Link: http://lkml.kernel.org/r/1344544736.8326.17.camel@sbsiddha-desk.sc.intel.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-07-24 23:05:29 +00:00
unsigned long fx_aligned, math_size;
sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
*fpstate = (struct _fpstate_ia32 __user *) sp;
if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels Currently for x86 and x86_32 binaries, fpstate in the user sigframe is copied to/from the fpstate in the task struct. And in the case of signal delivery for x86_64 binaries, if the fpstate is live in the CPU registers, then the live state is copied directly to the user sigframe. Otherwise fpstate in the task struct is copied to the user sigframe. During restore, fpstate in the user sigframe is restored directly to the live CPU registers. Historically, different code paths led to different bugs. For example, x86_64 code path was not preemption safe till recently. Also there is lot of code duplication for support of new features like xsave etc. Unify signal handling code paths for x86 and x86_64 kernels. New strategy is as follows: Signal delivery: Both for 32/64-bit frames, align the core math frame area to 64bytes as needed by xsave (this where the main fpu/extended state gets copied to and excludes the legacy compatibility fsave header for the 32-bit [f]xsave frames). If the state is live, copy the register state directly to the user frame. If not live, copy the state in the thread struct to the user frame. And for 32-bit [f]xsave frames, construct the fsave header separately before the actual [f]xsave area. Signal return: As the 32-bit frames with [f]xstate has an additional 'fsave' header, copy everything back from the user sigframe to the fpstate in the task structure and reconstruct the fxstate from the 'fsave' header (Also user passed pointers may not be correctly aligned for any attempt to directly restore any partial state). At the next fpstate usage, everything will be restored to the live CPU registers. For all the 64-bit frames and the 32-bit fsave frame, restore the state from the user sigframe directly to the live CPU registers. 64-bit signals always restored the math frame directly, so we can expect the math frame pointer to be correctly aligned. For 32-bit fsave frames, there are no alignment requirements, so we can restore the state directly. "lat_sig catch" microbenchmark numbers (for x86, x86_64, x86_32 binaries) are with in the noise range with this change. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Link: http://lkml.kernel.org/r/1343171129-2747-4-git-send-email-suresh.b.siddha@intel.com [ Merged in compilation fix ] Link: http://lkml.kernel.org/r/1344544736.8326.17.camel@sbsiddha-desk.sc.intel.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-07-24 23:05:29 +00:00
math_size) < 0)
return (void __user *) -1L;
}
sp -= frame_size;
/* Align the stack pointer according to the i386 ABI,
* i.e. so that on function entry ((sp + 4) & 15) == 0. */
sp = ((sp + 4) & -16ul) - 4;
return (void __user *) sp;
}
int ia32_setup_frame(int sig, struct ksignal *ksig,
compat_sigset_t *set, struct pt_regs *regs)
{
struct sigframe_ia32 __user *frame;
void __user *restorer;
int err = 0;
void __user *fpstate = NULL;
/* copy_to_user optimizes that into a single 8 byte store */
static const struct {
u16 poplmovl;
u32 val;
u16 int80;
} __attribute__((packed)) code = {
0xb858, /* popl %eax ; movl $...,%eax */
__NR_ia32_sigreturn,
0x80cd, /* int $0x80 */
};
frame = get_sigframe(ksig, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
if (__put_user(sig, &frame->sig))
return -EFAULT;
if (ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]))
return -EFAULT;
if (_COMPAT_NSIG_WORDS > 1) {
if (__copy_to_user(frame->extramask, &set->sig[1],
sizeof(frame->extramask)))
return -EFAULT;
}
if (ksig->ka.sa.sa_flags & SA_RESTORER) {
restorer = ksig->ka.sa.sa_restorer;
} else {
/* Return stub is in 32bit vsyscall page */
if (current->mm->context.vdso)
x86, vdso: Reimplement vdso.so preparation in build-time C Currently, vdso.so files are prepared and analyzed by a combination of objcopy, nm, some linker script tricks, and some simple ELF parsers in the kernel. Replace all of that with plain C code that runs at build time. All five vdso images now generate .c files that are compiled and linked in to the kernel image. This should cause only one userspace-visible change: the loaded vDSO images are stripped more heavily than they used to be. Everything outside the loadable segment is dropped. In particular, this causes the section table and section name strings to be missing. This should be fine: real dynamic loaders don't load or inspect these tables anyway. The result is roughly equivalent to eu-strip's --strip-sections option. The purpose of this change is to enable the vvar and hpet mappings to be moved to the page following the vDSO load segment. Currently, it is possible for the section table to extend into the page after the load segment, so, if we map it, it risks overlapping the vvar or hpet page. This happens whenever the load segment is just under a multiple of PAGE_SIZE. The only real subtlety here is that the old code had a C file with inline assembler that did 'call VDSO32_vsyscall' and a linker script that defined 'VDSO32_vsyscall = __kernel_vsyscall'. This most likely worked by accident: the linker script entry defines a symbol associated with an address as opposed to an alias for the real dynamic symbol __kernel_vsyscall. That caused ld to relocate the reference at link time instead of leaving an interposable dynamic relocation. Since the VDSO32_vsyscall hack is no longer needed, I now use 'call __kernel_vsyscall', and I added -Bsymbolic to make it work. vdso2c will generate an error and abort the build if the resulting image contains any dynamic relocations, so we won't silently generate bad vdso images. (Dynamic relocations are a problem because nothing will even attempt to relocate the vdso.) Signed-off-by: Andy Lutomirski <luto@amacapital.net> Link: http://lkml.kernel.org/r/2c4fcf45524162a34d87fdda1eb046b2a5cecee7.1399317206.git.luto@amacapital.net Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2014-05-05 19:19:34 +00:00
restorer = current->mm->context.vdso +
selected_vdso32->sym___kernel_sigreturn;
else
restorer = &frame->retcode;
}
put_user_try {
put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
/*
* These are actually not used anymore, but left because some
* gdb versions depend on them as a marker.
*/
put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
} put_user_catch(err);
if (err)
return -EFAULT;
/* Set up registers for signal handler */
regs->sp = (unsigned long) frame;
regs->ip = (unsigned long) ksig->ka.sa.sa_handler;
/* Make -mregparm=3 work */
regs->ax = sig;
regs->dx = 0;
regs->cx = 0;
loadsegment(ds, __USER32_DS);
loadsegment(es, __USER32_DS);
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
return 0;
}
int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
compat_sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe_ia32 __user *frame;
void __user *restorer;
int err = 0;
void __user *fpstate = NULL;
/* __copy_to_user optimizes that into a single 8 byte store */
static const struct {
u8 movl;
u32 val;
u16 int80;
u8 pad;
} __attribute__((packed)) code = {
0xb8,
__NR_ia32_rt_sigreturn,
0x80cd,
0,
};
frame = get_sigframe(ksig, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
put_user_try {
put_user_ex(sig, &frame->sig);
put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo);
put_user_ex(ptr_to_compat(&frame->uc), &frame->puc);
/* Create the ucontext. */
if (cpu_has_xsave)
put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
if (ksig->ka.sa.sa_flags & SA_RESTORER)
restorer = ksig->ka.sa.sa_restorer;
else
x86, vdso: Reimplement vdso.so preparation in build-time C Currently, vdso.so files are prepared and analyzed by a combination of objcopy, nm, some linker script tricks, and some simple ELF parsers in the kernel. Replace all of that with plain C code that runs at build time. All five vdso images now generate .c files that are compiled and linked in to the kernel image. This should cause only one userspace-visible change: the loaded vDSO images are stripped more heavily than they used to be. Everything outside the loadable segment is dropped. In particular, this causes the section table and section name strings to be missing. This should be fine: real dynamic loaders don't load or inspect these tables anyway. The result is roughly equivalent to eu-strip's --strip-sections option. The purpose of this change is to enable the vvar and hpet mappings to be moved to the page following the vDSO load segment. Currently, it is possible for the section table to extend into the page after the load segment, so, if we map it, it risks overlapping the vvar or hpet page. This happens whenever the load segment is just under a multiple of PAGE_SIZE. The only real subtlety here is that the old code had a C file with inline assembler that did 'call VDSO32_vsyscall' and a linker script that defined 'VDSO32_vsyscall = __kernel_vsyscall'. This most likely worked by accident: the linker script entry defines a symbol associated with an address as opposed to an alias for the real dynamic symbol __kernel_vsyscall. That caused ld to relocate the reference at link time instead of leaving an interposable dynamic relocation. Since the VDSO32_vsyscall hack is no longer needed, I now use 'call __kernel_vsyscall', and I added -Bsymbolic to make it work. vdso2c will generate an error and abort the build if the resulting image contains any dynamic relocations, so we won't silently generate bad vdso images. (Dynamic relocations are a problem because nothing will even attempt to relocate the vdso.) Signed-off-by: Andy Lutomirski <luto@amacapital.net> Link: http://lkml.kernel.org/r/2c4fcf45524162a34d87fdda1eb046b2a5cecee7.1399317206.git.luto@amacapital.net Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2014-05-05 19:19:34 +00:00
restorer = current->mm->context.vdso +
selected_vdso32->sym___kernel_rt_sigreturn;
put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
/*
* Not actually used anymore, but left because some gdb
* versions need it.
*/
put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
} put_user_catch(err);
err |= copy_siginfo_to_user32(&frame->info, &ksig->info);
err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
return -EFAULT;
/* Set up registers for signal handler */
regs->sp = (unsigned long) frame;
regs->ip = (unsigned long) ksig->ka.sa.sa_handler;
/* Make -mregparm=3 work */
regs->ax = sig;
regs->dx = (unsigned long) &frame->info;
regs->cx = (unsigned long) &frame->uc;
loadsegment(ds, __USER32_DS);
loadsegment(es, __USER32_DS);
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
return 0;
}