linux/arch/x86/kernel/signal.c
Linus Torvalds 1423e2660c Fixes and improvements for FPU handling on x86:
- Prevent sigaltstack out of bounds writes. The kernel unconditionally
     writes the FPU state to the alternate stack without checking whether
     the stack is large enough to accomodate it.
 
     Check the alternate stack size before doing so and in case it's too
     small force a SIGSEGV instead of silently corrupting user space data.
 
   - MINSIGSTKZ and SIGSTKSZ are constants in signal.h and have never been
     updated despite the fact that the FPU state which is stored on the
     signal stack has grown over time which causes trouble in the field
     when AVX512 is available on a CPU. The kernel does not expose the
     minimum requirements for the alternate stack size depending on the
     available and enabled CPU features.
 
     ARM already added an aux vector AT_MINSIGSTKSZ for the same reason.
     Add it to x86 as well
 
   - A major cleanup of the x86 FPU code. The recent discoveries of XSTATE
     related issues unearthed quite some inconsistencies, duplicated code
     and other issues.
 
     The fine granular overhaul addresses this, makes the code more robust
     and maintainable, which allows to integrate upcoming XSTATE related
     features in sane ways.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAmDlcpETHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoeP5D/4i+AgYYeiMLgGb+NS7iaKPfoWo6LIz
 y3qdTSA0DQaIYbYivWwRO/g0GYdDMXDWeZalFi7eGnVI8O3eOog+22Zrf/y0UINB
 KJHdYd4ApWHhs401022y5hexrWQvnV8w1yQCuj/zLm6eC+AVhdwt2AY+IBoRrdUj
 wqY97B/4rJNsBvvqTDn9EeDrJA2y0y0Suc7AhIp2BGMI+dpIdxys8RJDamXNWyDL
 gJf0YRgUoiIn3AHKb+fgv60AoxfC175NSg/5/y/scFNXqVlW0Up4YCb7pqG9o2Ga
 f3XvtWfbw1N5PmUYjFkALwEkzGUbM3v0RA3xLY2j2WlWm9fBPPy59dt+i/h/VKyA
 GrA7i7lcIqX8dfVH6XkrReZBkRDSB6t9SZTvV54jAz5fcIZO2Rg++UFUvI/R6GKK
 XCcxukYaArwo+IG62iqDszS3gfLGhcor/cviOeULRC5zMUIO4Jah+IhDnifmShtC
 M5s9QzrwIRD/XMewGRQmvkiN4kBfE7jFoBQr1J9leCXJKrM+2JQmMzVInuubTQIq
 SdlKOaAIn7xtekz+6XdFG9Gmhck0PCLMJMOLNvQkKWI3KqGLRZ+dAWKK0vsCizAx
 0BA7ZeB9w9lFT+D8mQCX77JvW9+VNwyfwIOLIrJRHk3VqVpS5qvoiFTLGJJBdZx4
 /TbbRZu7nXDN2w==
 =Mq1m
 -----END PGP SIGNATURE-----

Merge tag 'x86-fpu-2021-07-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fpu updates from Thomas Gleixner:
 "Fixes and improvements for FPU handling on x86:

   - Prevent sigaltstack out of bounds writes.

     The kernel unconditionally writes the FPU state to the alternate
     stack without checking whether the stack is large enough to
     accomodate it.

     Check the alternate stack size before doing so and in case it's too
     small force a SIGSEGV instead of silently corrupting user space
     data.

   - MINSIGSTKZ and SIGSTKSZ are constants in signal.h and have never
     been updated despite the fact that the FPU state which is stored on
     the signal stack has grown over time which causes trouble in the
     field when AVX512 is available on a CPU. The kernel does not expose
     the minimum requirements for the alternate stack size depending on
     the available and enabled CPU features.

     ARM already added an aux vector AT_MINSIGSTKSZ for the same reason.
     Add it to x86 as well.

   - A major cleanup of the x86 FPU code. The recent discoveries of
     XSTATE related issues unearthed quite some inconsistencies,
     duplicated code and other issues.

     The fine granular overhaul addresses this, makes the code more
     robust and maintainable, which allows to integrate upcoming XSTATE
     related features in sane ways"

* tag 'x86-fpu-2021-07-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (74 commits)
  x86/fpu/xstate: Clear xstate header in copy_xstate_to_uabi_buf() again
  x86/fpu/signal: Let xrstor handle the features to init
  x86/fpu/signal: Handle #PF in the direct restore path
  x86/fpu: Return proper error codes from user access functions
  x86/fpu/signal: Split out the direct restore code
  x86/fpu/signal: Sanitize copy_user_to_fpregs_zeroing()
  x86/fpu/signal: Sanitize the xstate check on sigframe
  x86/fpu/signal: Remove the legacy alignment check
  x86/fpu/signal: Move initial checks into fpu__restore_sig()
  x86/fpu: Mark init_fpstate __ro_after_init
  x86/pkru: Remove xstate fiddling from write_pkru()
  x86/fpu: Don't store PKRU in xstate in fpu_reset_fpstate()
  x86/fpu: Remove PKRU handling from switch_fpu_finish()
  x86/fpu: Mask PKRU from kernel XRSTOR[S] operations
  x86/fpu: Hook up PKRU into ptrace()
  x86/fpu: Add PKRU storage outside of task XSAVE buffer
  x86/fpu: Dont restore PKRU in fpregs_restore_userspace()
  x86/fpu: Rename xfeatures_mask_user() to xfeatures_mask_uabi()
  x86/fpu: Move FXSAVE_LEAK quirk info __copy_kernel_to_fpregs()
  x86/fpu: Rename __fpregs_load_activate() to fpregs_restore_userregs()
  ...
2021-07-07 11:12:01 -07:00

945 lines
25 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
*
* 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
* 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
* 2000-2002 x86-64 support by Andi Kleen
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/tracehook.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/personality.h>
#include <linux/uaccess.h>
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
#include <linux/context_tracking.h>
#include <linux/entry-common.h>
#include <linux/syscalls.h>
#include <asm/processor.h>
#include <asm/ucontext.h>
#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/vdso.h>
#include <asm/mce.h>
#include <asm/sighandling.h>
#include <asm/vm86.h>
#ifdef CONFIG_X86_64
#include <linux/compat.h>
#include <asm/proto.h>
#include <asm/ia32_unistd.h>
#endif /* CONFIG_X86_64 */
#include <asm/syscall.h>
#include <asm/sigframe.h>
#include <asm/signal.h>
#ifdef CONFIG_X86_64
/*
* If regs->ss will cause an IRET fault, change it. Otherwise leave it
* alone. Using this generally makes no sense unless
* user_64bit_mode(regs) would return true.
*/
static void force_valid_ss(struct pt_regs *regs)
{
u32 ar;
asm volatile ("lar %[old_ss], %[ar]\n\t"
"jz 1f\n\t" /* If invalid: */
"xorl %[ar], %[ar]\n\t" /* set ar = 0 */
"1:"
: [ar] "=r" (ar)
: [old_ss] "rm" ((u16)regs->ss));
/*
* For a valid 64-bit user context, we need DPL 3, type
* read-write data or read-write exp-down data, and S and P
* set. We can't use VERW because VERW doesn't check the
* P bit.
*/
ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK;
if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) &&
ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN))
regs->ss = __USER_DS;
}
# define CONTEXT_COPY_SIZE offsetof(struct sigcontext, reserved1)
#else
# define CONTEXT_COPY_SIZE sizeof(struct sigcontext)
#endif
static int restore_sigcontext(struct pt_regs *regs,
struct sigcontext __user *usc,
unsigned long uc_flags)
{
struct sigcontext sc;
/* Always make any pending restarted system calls return -EINTR */
current->restart_block.fn = do_no_restart_syscall;
if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE))
return -EFAULT;
#ifdef CONFIG_X86_32
set_user_gs(regs, sc.gs);
regs->fs = sc.fs;
regs->es = sc.es;
regs->ds = sc.ds;
#endif /* CONFIG_X86_32 */
regs->bx = sc.bx;
regs->cx = sc.cx;
regs->dx = sc.dx;
regs->si = sc.si;
regs->di = sc.di;
regs->bp = sc.bp;
regs->ax = sc.ax;
regs->sp = sc.sp;
regs->ip = sc.ip;
#ifdef CONFIG_X86_64
regs->r8 = sc.r8;
regs->r9 = sc.r9;
regs->r10 = sc.r10;
regs->r11 = sc.r11;
regs->r12 = sc.r12;
regs->r13 = sc.r13;
regs->r14 = sc.r14;
regs->r15 = sc.r15;
#endif /* CONFIG_X86_64 */
/* Get CS/SS and force CPL3 */
regs->cs = sc.cs | 0x03;
regs->ss = sc.ss | 0x03;
regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS);
/* disable syscall checks */
regs->orig_ax = -1;
#ifdef CONFIG_X86_64
/*
* Fix up SS if needed for the benefit of old DOSEMU and
* CRIU.
*/
if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs)))
force_valid_ss(regs);
#endif
return fpu__restore_sig((void __user *)sc.fpstate,
IS_ENABLED(CONFIG_X86_32));
}
static __always_inline int
__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
struct pt_regs *regs, unsigned long mask)
{
#ifdef CONFIG_X86_32
unsafe_put_user(get_user_gs(regs),
(unsigned int __user *)&sc->gs, Efault);
unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault);
unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault);
unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault);
#endif /* CONFIG_X86_32 */
unsafe_put_user(regs->di, &sc->di, Efault);
unsafe_put_user(regs->si, &sc->si, Efault);
unsafe_put_user(regs->bp, &sc->bp, Efault);
unsafe_put_user(regs->sp, &sc->sp, Efault);
unsafe_put_user(regs->bx, &sc->bx, Efault);
unsafe_put_user(regs->dx, &sc->dx, Efault);
unsafe_put_user(regs->cx, &sc->cx, Efault);
unsafe_put_user(regs->ax, &sc->ax, Efault);
#ifdef CONFIG_X86_64
unsafe_put_user(regs->r8, &sc->r8, Efault);
unsafe_put_user(regs->r9, &sc->r9, Efault);
unsafe_put_user(regs->r10, &sc->r10, Efault);
unsafe_put_user(regs->r11, &sc->r11, Efault);
unsafe_put_user(regs->r12, &sc->r12, Efault);
unsafe_put_user(regs->r13, &sc->r13, Efault);
unsafe_put_user(regs->r14, &sc->r14, Efault);
unsafe_put_user(regs->r15, &sc->r15, Efault);
#endif /* CONFIG_X86_64 */
unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault);
unsafe_put_user(current->thread.error_code, &sc->err, Efault);
unsafe_put_user(regs->ip, &sc->ip, Efault);
#ifdef CONFIG_X86_32
unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault);
unsafe_put_user(regs->flags, &sc->flags, Efault);
unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault);
unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault);
#else /* !CONFIG_X86_32 */
unsafe_put_user(regs->flags, &sc->flags, Efault);
unsafe_put_user(regs->cs, &sc->cs, Efault);
unsafe_put_user(0, &sc->gs, Efault);
unsafe_put_user(0, &sc->fs, Efault);
unsafe_put_user(regs->ss, &sc->ss, Efault);
#endif /* CONFIG_X86_32 */
unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault);
/* non-iBCS2 extensions.. */
unsafe_put_user(mask, &sc->oldmask, Efault);
unsafe_put_user(current->thread.cr2, &sc->cr2, Efault);
return 0;
Efault:
return -EFAULT;
}
#define unsafe_put_sigcontext(sc, fp, regs, set, label) \
do { \
if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \
goto label; \
} while(0);
#define unsafe_put_sigmask(set, frame, label) \
unsafe_put_user(*(__u64 *)(set), \
(__u64 __user *)&(frame)->uc.uc_sigmask, \
label)
/*
* Set up a signal frame.
*/
/* x86 ABI requires 16-byte alignment */
#define FRAME_ALIGNMENT 16UL
#define MAX_FRAME_PADDING (FRAME_ALIGNMENT - 1)
/*
* Determine which stack to use..
*/
static unsigned long align_sigframe(unsigned long sp)
{
#ifdef CONFIG_X86_32
/*
* Align the stack pointer according to the i386 ABI,
* i.e. so that on function entry ((sp + 4) & 15) == 0.
*/
sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4;
#else /* !CONFIG_X86_32 */
sp = round_down(sp, FRAME_ALIGNMENT) - 8;
#endif
return sp;
}
static void __user *
get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
void __user **fpstate)
{
/* Default to using normal stack */
bool nested_altstack = on_sig_stack(regs->sp);
bool entering_altstack = false;
unsigned long math_size = 0;
unsigned long sp = regs->sp;
unsigned long buf_fx = 0;
int ret;
/* redzone */
if (IS_ENABLED(CONFIG_X86_64))
sp -= 128;
/* This is the X/Open sanctioned signal stack switching. */
if (ka->sa.sa_flags & SA_ONSTACK) {
/*
* This checks nested_altstack via sas_ss_flags(). Sensible
* programs use SS_AUTODISARM, which disables that check, and
* programs that don't use SS_AUTODISARM get compatible.
*/
if (sas_ss_flags(sp) == 0) {
sp = current->sas_ss_sp + current->sas_ss_size;
entering_altstack = true;
}
} else if (IS_ENABLED(CONFIG_X86_32) &&
!nested_altstack &&
regs->ss != __USER_DS &&
!(ka->sa.sa_flags & SA_RESTORER) &&
ka->sa.sa_restorer) {
/* This is the legacy signal stack switching. */
sp = (unsigned long) ka->sa.sa_restorer;
entering_altstack = true;
}
sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
&buf_fx, &math_size);
*fpstate = (void __user *)sp;
sp = align_sigframe(sp - frame_size);
/*
* If we are on the alternate signal stack and would overflow it, don't.
* Return an always-bogus address instead so we will die with SIGSEGV.
*/
if (unlikely((nested_altstack || entering_altstack) &&
!__on_sig_stack(sp))) {
if (show_unhandled_signals && printk_ratelimit())
pr_info("%s[%d] overflowed sigaltstack\n",
current->comm, task_pid_nr(current));
return (void __user *)-1L;
}
/* save i387 and extended state */
ret = copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size);
if (ret < 0)
return (void __user *)-1L;
return (void __user *)sp;
}
#ifdef CONFIG_X86_32
static const struct {
u16 poplmovl;
u32 val;
u16 int80;
} __attribute__((packed)) retcode = {
0xb858, /* popl %eax; movl $..., %eax */
__NR_sigreturn,
0x80cd, /* int $0x80 */
};
static const struct {
u8 movl;
u32 val;
u16 int80;
u8 pad;
} __attribute__((packed)) rt_retcode = {
0xb8, /* movl $..., %eax */
__NR_rt_sigreturn,
0x80cd, /* int $0x80 */
0
};
static int
__setup_frame(int sig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs)
{
struct sigframe __user *frame;
void __user *restorer;
void __user *fp = NULL;
frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);
if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
unsafe_put_user(sig, &frame->sig, Efault);
unsafe_put_sigcontext(&frame->sc, fp, regs, set, Efault);
unsafe_put_user(set->sig[1], &frame->extramask[0], Efault);
if (current->mm->context.vdso)
restorer = current->mm->context.vdso +
vdso_image_32.sym___kernel_sigreturn;
else
restorer = &frame->retcode;
if (ksig->ka.sa.sa_flags & SA_RESTORER)
restorer = ksig->ka.sa.sa_restorer;
/* Set up to return from userspace. */
unsafe_put_user(restorer, &frame->pretcode, Efault);
/*
* This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80
*
* WE DO NOT USE IT ANY MORE! It's only left here for historical
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
unsafe_put_user(*((u64 *)&retcode), (u64 *)frame->retcode, Efault);
user_access_end();
/* Set up registers for signal handler */
regs->sp = (unsigned long)frame;
regs->ip = (unsigned long)ksig->ka.sa.sa_handler;
regs->ax = (unsigned long)sig;
regs->dx = 0;
regs->cx = 0;
regs->ds = __USER_DS;
regs->es = __USER_DS;
regs->ss = __USER_DS;
regs->cs = __USER_CS;
return 0;
Efault:
user_access_end();
return -EFAULT;
}
static int __setup_rt_frame(int sig, struct ksignal *ksig,
sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
void __user *restorer;
void __user *fp = NULL;
frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);
if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
unsafe_put_user(sig, &frame->sig, Efault);
unsafe_put_user(&frame->info, &frame->pinfo, Efault);
unsafe_put_user(&frame->uc, &frame->puc, Efault);
/* Create the ucontext. */
if (static_cpu_has(X86_FEATURE_XSAVE))
unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault);
else
unsafe_put_user(0, &frame->uc.uc_flags, Efault);
unsafe_put_user(0, &frame->uc.uc_link, Efault);
unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);
/* Set up to return from userspace. */
restorer = current->mm->context.vdso +
vdso_image_32.sym___kernel_rt_sigreturn;
if (ksig->ka.sa.sa_flags & SA_RESTORER)
restorer = ksig->ka.sa.sa_restorer;
unsafe_put_user(restorer, &frame->pretcode, Efault);
/*
* This is movl $__NR_rt_sigreturn, %ax ; int $0x80
*
* WE DO NOT USE IT ANY MORE! It's only left here for historical
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
unsafe_put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode, Efault);
unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
unsafe_put_sigmask(set, frame, Efault);
user_access_end();
if (copy_siginfo_to_user(&frame->info, &ksig->info))
return -EFAULT;
/* Set up registers for signal handler */
regs->sp = (unsigned long)frame;
regs->ip = (unsigned long)ksig->ka.sa.sa_handler;
regs->ax = (unsigned long)sig;
regs->dx = (unsigned long)&frame->info;
regs->cx = (unsigned long)&frame->uc;
regs->ds = __USER_DS;
regs->es = __USER_DS;
regs->ss = __USER_DS;
regs->cs = __USER_CS;
return 0;
Efault:
user_access_end();
return -EFAULT;
}
#else /* !CONFIG_X86_32 */
static unsigned long frame_uc_flags(struct pt_regs *regs)
{
unsigned long flags;
if (boot_cpu_has(X86_FEATURE_XSAVE))
flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS;
else
flags = UC_SIGCONTEXT_SS;
if (likely(user_64bit_mode(regs)))
flags |= UC_STRICT_RESTORE_SS;
return flags;
}
static int __setup_rt_frame(int sig, struct ksignal *ksig,
sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
void __user *fp = NULL;
unsigned long uc_flags;
/* x86-64 should always use SA_RESTORER. */
if (!(ksig->ka.sa.sa_flags & SA_RESTORER))
return -EFAULT;
frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
uc_flags = frame_uc_flags(regs);
if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
/* Create the ucontext. */
unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault);
unsafe_put_user(0, &frame->uc.uc_link, Efault);
unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault);
unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
unsafe_put_sigmask(set, frame, Efault);
user_access_end();
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
if (copy_siginfo_to_user(&frame->info, &ksig->info))
return -EFAULT;
}
/* Set up registers for signal handler */
regs->di = sig;
/* In case the signal handler was declared without prototypes */
regs->ax = 0;
/* This also works for non SA_SIGINFO handlers because they expect the
next argument after the signal number on the stack. */
regs->si = (unsigned long)&frame->info;
regs->dx = (unsigned long)&frame->uc;
regs->ip = (unsigned long) ksig->ka.sa.sa_handler;
regs->sp = (unsigned long)frame;
/*
* Set up the CS and SS registers to run signal handlers in
* 64-bit mode, even if the handler happens to be interrupting
* 32-bit or 16-bit code.
*
* SS is subtle. In 64-bit mode, we don't need any particular
* SS descriptor, but we do need SS to be valid. It's possible
* that the old SS is entirely bogus -- this can happen if the
* signal we're trying to deliver is #GP or #SS caused by a bad
* SS value. We also have a compatibility issue here: DOSEMU
* relies on the contents of the SS register indicating the
* SS value at the time of the signal, even though that code in
* DOSEMU predates sigreturn's ability to restore SS. (DOSEMU
* avoids relying on sigreturn to restore SS; instead it uses
* a trampoline.) So we do our best: if the old SS was valid,
* we keep it. Otherwise we replace it.
*/
regs->cs = __USER_CS;
if (unlikely(regs->ss != __USER_DS))
force_valid_ss(regs);
return 0;
Efault:
user_access_end();
return -EFAULT;
}
#endif /* CONFIG_X86_32 */
#ifdef CONFIG_X86_X32_ABI
static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to,
const struct kernel_siginfo *from)
{
struct compat_siginfo new;
copy_siginfo_to_external32(&new, from);
if (from->si_signo == SIGCHLD) {
new._sifields._sigchld_x32._utime = from->si_utime;
new._sifields._sigchld_x32._stime = from->si_stime;
}
if (copy_to_user(to, &new, sizeof(struct compat_siginfo)))
return -EFAULT;
return 0;
}
int copy_siginfo_to_user32(struct compat_siginfo __user *to,
const struct kernel_siginfo *from)
{
if (in_x32_syscall())
return x32_copy_siginfo_to_user(to, from);
return __copy_siginfo_to_user32(to, from);
}
#endif /* CONFIG_X86_X32_ABI */
static int x32_setup_rt_frame(struct ksignal *ksig,
compat_sigset_t *set,
struct pt_regs *regs)
{
#ifdef CONFIG_X86_X32_ABI
struct rt_sigframe_x32 __user *frame;
unsigned long uc_flags;
void __user *restorer;
void __user *fp = NULL;
if (!(ksig->ka.sa.sa_flags & SA_RESTORER))
return -EFAULT;
frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);
uc_flags = frame_uc_flags(regs);
if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
/* Create the ucontext. */
unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault);
unsafe_put_user(0, &frame->uc.uc_link, Efault);
unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);
unsafe_put_user(0, &frame->uc.uc__pad0, Efault);
restorer = ksig->ka.sa.sa_restorer;
unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault);
unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
unsafe_put_sigmask(set, frame, Efault);
user_access_end();
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
if (x32_copy_siginfo_to_user(&frame->info, &ksig->info))
return -EFAULT;
}
/* Set up registers for signal handler */
regs->sp = (unsigned long) frame;
regs->ip = (unsigned long) ksig->ka.sa.sa_handler;
/* We use the x32 calling convention here... */
regs->di = ksig->sig;
regs->si = (unsigned long) &frame->info;
regs->dx = (unsigned long) &frame->uc;
loadsegment(ds, __USER_DS);
loadsegment(es, __USER_DS);
regs->cs = __USER_CS;
regs->ss = __USER_DS;
#endif /* CONFIG_X86_X32_ABI */
return 0;
#ifdef CONFIG_X86_X32_ABI
Efault:
user_access_end();
return -EFAULT;
#endif
}
/*
* Do a signal return; undo the signal stack.
*/
#ifdef CONFIG_X86_32
SYSCALL_DEFINE0(sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct sigframe __user *frame;
sigset_t set;
frame = (struct sigframe __user *)(regs->sp - 8);
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
if (__get_user(set.sig[0], &frame->sc.oldmask) ||
__get_user(set.sig[1], &frame->extramask[0]))
goto badframe;
set_current_blocked(&set);
/*
* x86_32 has no uc_flags bits relevant to restore_sigcontext.
* Save a few cycles by skipping the __get_user.
*/
if (restore_sigcontext(regs, &frame->sc, 0))
goto badframe;
return regs->ax;
badframe:
signal_fault(regs, frame, "sigreturn");
return 0;
}
#endif /* CONFIG_X86_32 */
SYSCALL_DEFINE0(rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
sigset_t set;
unsigned long uc_flags;
frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask))
goto badframe;
if (__get_user(uc_flags, &frame->uc.uc_flags))
goto badframe;
set_current_blocked(&set);
if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
goto badframe;
return regs->ax;
badframe:
signal_fault(regs, frame, "rt_sigreturn");
return 0;
}
/*
* There are four different struct types for signal frame: sigframe_ia32,
* rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case
* -- the largest size. It means the size for 64-bit apps is a bit more
* than needed, but this keeps the code simple.
*/
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
# define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct sigframe_ia32)
#else
# define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct rt_sigframe)
#endif
/*
* The FP state frame contains an XSAVE buffer which must be 64-byte aligned.
* If a signal frame starts at an unaligned address, extra space is required.
* This is the max alignment padding, conservatively.
*/
#define MAX_XSAVE_PADDING 63UL
/*
* The frame data is composed of the following areas and laid out as:
*
* -------------------------
* | alignment padding |
* -------------------------
* | (f)xsave frame |
* -------------------------
* | fsave header |
* -------------------------
* | alignment padding |
* -------------------------
* | siginfo + ucontext |
* -------------------------
*/
/* max_frame_size tells userspace the worst case signal stack size. */
static unsigned long __ro_after_init max_frame_size;
void __init init_sigframe_size(void)
{
max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING;
max_frame_size += fpu__get_fpstate_size() + MAX_XSAVE_PADDING;
/* Userspace expects an aligned size. */
max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT);
pr_info("max sigframe size: %lu\n", max_frame_size);
}
unsigned long get_sigframe_size(void)
{
return max_frame_size;
}
static inline int is_ia32_compat_frame(struct ksignal *ksig)
{
return IS_ENABLED(CONFIG_IA32_EMULATION) &&
ksig->ka.sa.sa_flags & SA_IA32_ABI;
}
static inline int is_ia32_frame(struct ksignal *ksig)
{
return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig);
}
static inline int is_x32_frame(struct ksignal *ksig)
{
return IS_ENABLED(CONFIG_X86_X32_ABI) &&
ksig->ka.sa.sa_flags & SA_X32_ABI;
}
static int
setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
{
int usig = ksig->sig;
sigset_t *set = sigmask_to_save();
compat_sigset_t *cset = (compat_sigset_t *) set;
/* Perform fixup for the pre-signal frame. */
rseq_signal_deliver(ksig, regs);
/* Set up the stack frame */
if (is_ia32_frame(ksig)) {
if (ksig->ka.sa.sa_flags & SA_SIGINFO)
return ia32_setup_rt_frame(usig, ksig, cset, regs);
else
return ia32_setup_frame(usig, ksig, cset, regs);
} else if (is_x32_frame(ksig)) {
return x32_setup_rt_frame(ksig, cset, regs);
} else {
return __setup_rt_frame(ksig->sig, ksig, set, regs);
}
}
static void
handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
bool stepping, failed;
struct fpu *fpu = &current->thread.fpu;
if (v8086_mode(regs))
save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);
/* Are we from a system call? */
if (syscall_get_nr(current, regs) != -1) {
/* If so, check system call restarting.. */
switch (syscall_get_error(current, regs)) {
case -ERESTART_RESTARTBLOCK:
case -ERESTARTNOHAND:
regs->ax = -EINTR;
break;
case -ERESTARTSYS:
if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
regs->ax = -EINTR;
break;
}
fallthrough;
case -ERESTARTNOINTR:
regs->ax = regs->orig_ax;
regs->ip -= 2;
break;
}
}
/*
* If TF is set due to a debugger (TIF_FORCED_TF), clear TF now
* so that register information in the sigcontext is correct and
* then notify the tracer before entering the signal handler.
*/
stepping = test_thread_flag(TIF_SINGLESTEP);
if (stepping)
user_disable_single_step(current);
failed = (setup_rt_frame(ksig, regs) < 0);
if (!failed) {
/*
* Clear the direction flag as per the ABI for function entry.
*
* Clear RF when entering the signal handler, because
* it might disable possible debug exception from the
* signal handler.
*
* Clear TF for the case when it wasn't set by debugger to
* avoid the recursive send_sigtrap() in SIGTRAP handler.
*/
regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
/*
* Ensure the signal handler starts with the new fpu state.
*/
fpu__clear_user_states(fpu);
}
signal_setup_done(failed, ksig, stepping);
}
static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
{
#ifdef CONFIG_IA32_EMULATION
if (current->restart_block.arch_data & TS_COMPAT)
return __NR_ia32_restart_syscall;
#endif
#ifdef CONFIG_X86_X32_ABI
return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
#else
return __NR_restart_syscall;
#endif
}
/*
* Note that 'init' is a special process: it doesn't get signals it doesn't
* want to handle. Thus you cannot kill init even with a SIGKILL even by
* mistake.
*/
void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal)
{
struct ksignal ksig;
if (has_signal && get_signal(&ksig)) {
/* Whee! Actually deliver the signal. */
handle_signal(&ksig, regs);
return;
}
/* Did we come from a system call? */
if (syscall_get_nr(current, regs) != -1) {
/* Restart the system call - no handlers present */
switch (syscall_get_error(current, regs)) {
case -ERESTARTNOHAND:
case -ERESTARTSYS:
case -ERESTARTNOINTR:
regs->ax = regs->orig_ax;
regs->ip -= 2;
break;
case -ERESTART_RESTARTBLOCK:
regs->ax = get_nr_restart_syscall(regs);
regs->ip -= 2;
break;
}
}
/*
* If there's no signal to deliver, we just put the saved sigmask
* back.
*/
restore_saved_sigmask();
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
{
struct task_struct *me = current;
if (show_unhandled_signals && printk_ratelimit()) {
printk("%s"
"%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
me->comm, me->pid, where, frame,
regs->ip, regs->sp, regs->orig_ax);
print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
force_sig(SIGSEGV);
}
#ifdef CONFIG_X86_X32_ABI
COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe_x32 __user *frame;
sigset_t set;
unsigned long uc_flags;
frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask))
goto badframe;
if (__get_user(uc_flags, &frame->uc.uc_flags))
goto badframe;
set_current_blocked(&set);
if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
goto badframe;
if (compat_restore_altstack(&frame->uc.uc_stack))
goto badframe;
return regs->ax;
badframe:
signal_fault(regs, frame, "x32 rt_sigreturn");
return 0;
}
#endif