linux/arch/x86/kernel/fpu/regset.c
Ingo Molnar 47f01e8cc2 x86/fpu: Fix FPU register read access to the current task
Bobby Powers reported the following FPU warning during ELF coredumping:

   WARNING: CPU: 0 PID: 27452 at arch/x86/kernel/fpu/core.c:324 fpu__activate_stopped+0x8a/0xa0()

This warning unearthed an invalid assumption about fpu__activate_stopped()
that I added in:

  67e97fc2ec ("x86/fpu: Rename init_fpu() to fpu__unlazy_stopped() and add debugging check")

the old init_fpu() function had an (intentional but obscure) side effect:
when FPU registers are accessed for the current task, for reading, then
it synchronized live in-register FPU state with the fpstate by saving it.

So fix this bug by saving the FPU if we are the current task. We'll
still warn in fpu__save() if this is called for not yet stopped
child tasks, so the debugging check is still preserved.

Also rename the function to fpu__activate_fpstate(), because it's not
exclusively used for stopped tasks, but for the current task as well.

( Note that this bug calls for a cleaner separation of access-for-read
  and access-for-modification FPU methods, but we'll do that in separate
  patches. )

Reported-by: Bobby Powers <bobbypowers@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-27 12:40:18 +02:00

357 lines
8.8 KiB
C

/*
* FPU register's regset abstraction, for ptrace, core dumps, etc.
*/
#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
/*
* The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
* as the "regset->n" for the xstate regset will be updated based on the feature
* capabilites supported by the xsave.
*/
int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
{
struct fpu *target_fpu = &target->thread.fpu;
return target_fpu->fpstate_active ? regset->n : 0;
}
int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
{
struct fpu *target_fpu = &target->thread.fpu;
return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
}
int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
struct fpu *fpu = &target->thread.fpu;
if (!cpu_has_fxsr)
return -ENODEV;
fpu__activate_fpstate(fpu);
fpstate_sanitize_xstate(fpu);
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&fpu->state.fxsave, 0, -1);
}
int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
struct fpu *fpu = &target->thread.fpu;
int ret;
if (!cpu_has_fxsr)
return -ENODEV;
fpu__activate_fpstate(fpu);
fpstate_sanitize_xstate(fpu);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&fpu->state.fxsave, 0, -1);
/*
* mxcsr reserved bits must be masked to zero for security reasons.
*/
fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
/*
* update the header bits in the xsave header, indicating the
* presence of FP and SSE state.
*/
if (cpu_has_xsave)
fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE;
return ret;
}
int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
struct fpu *fpu = &target->thread.fpu;
struct xregs_state *xsave;
int ret;
if (!cpu_has_xsave)
return -ENODEV;
fpu__activate_fpstate(fpu);
xsave = &fpu->state.xsave;
/*
* Copy the 48bytes defined by the software first into the xstate
* memory layout in the thread struct, so that we can copy the entire
* xstateregs to the user using one user_regset_copyout().
*/
memcpy(&xsave->i387.sw_reserved,
xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
/*
* Copy the xstate memory layout.
*/
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
return ret;
}
int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
struct fpu *fpu = &target->thread.fpu;
struct xregs_state *xsave;
int ret;
if (!cpu_has_xsave)
return -ENODEV;
fpu__activate_fpstate(fpu);
xsave = &fpu->state.xsave;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
/*
* mxcsr reserved bits must be masked to zero for security reasons.
*/
xsave->i387.mxcsr &= mxcsr_feature_mask;
xsave->header.xfeatures &= xfeatures_mask;
/*
* These bits must be zero.
*/
memset(&xsave->header.reserved, 0, 48);
return ret;
}
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
/*
* FPU tag word conversions.
*/
static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
{
unsigned int tmp; /* to avoid 16 bit prefixes in the code */
/* Transform each pair of bits into 01 (valid) or 00 (empty) */
tmp = ~twd;
tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
/* and move the valid bits to the lower byte. */
tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
return tmp;
}
#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16)
#define FP_EXP_TAG_VALID 0
#define FP_EXP_TAG_ZERO 1
#define FP_EXP_TAG_SPECIAL 2
#define FP_EXP_TAG_EMPTY 3
static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave)
{
struct _fpxreg *st;
u32 tos = (fxsave->swd >> 11) & 7;
u32 twd = (unsigned long) fxsave->twd;
u32 tag;
u32 ret = 0xffff0000u;
int i;
for (i = 0; i < 8; i++, twd >>= 1) {
if (twd & 0x1) {
st = FPREG_ADDR(fxsave, (i - tos) & 7);
switch (st->exponent & 0x7fff) {
case 0x7fff:
tag = FP_EXP_TAG_SPECIAL;
break;
case 0x0000:
if (!st->significand[0] &&
!st->significand[1] &&
!st->significand[2] &&
!st->significand[3])
tag = FP_EXP_TAG_ZERO;
else
tag = FP_EXP_TAG_SPECIAL;
break;
default:
if (st->significand[3] & 0x8000)
tag = FP_EXP_TAG_VALID;
else
tag = FP_EXP_TAG_SPECIAL;
break;
}
} else {
tag = FP_EXP_TAG_EMPTY;
}
ret |= tag << (2 * i);
}
return ret;
}
/*
* FXSR floating point environment conversions.
*/
void
convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
{
struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
int i;
env->cwd = fxsave->cwd | 0xffff0000u;
env->swd = fxsave->swd | 0xffff0000u;
env->twd = twd_fxsr_to_i387(fxsave);
#ifdef CONFIG_X86_64
env->fip = fxsave->rip;
env->foo = fxsave->rdp;
/*
* should be actually ds/cs at fpu exception time, but
* that information is not available in 64bit mode.
*/
env->fcs = task_pt_regs(tsk)->cs;
if (tsk == current) {
savesegment(ds, env->fos);
} else {
env->fos = tsk->thread.ds;
}
env->fos |= 0xffff0000;
#else
env->fip = fxsave->fip;
env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
env->foo = fxsave->foo;
env->fos = fxsave->fos;
#endif
for (i = 0; i < 8; ++i)
memcpy(&to[i], &from[i], sizeof(to[0]));
}
void convert_to_fxsr(struct task_struct *tsk,
const struct user_i387_ia32_struct *env)
{
struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
int i;
fxsave->cwd = env->cwd;
fxsave->swd = env->swd;
fxsave->twd = twd_i387_to_fxsr(env->twd);
fxsave->fop = (u16) ((u32) env->fcs >> 16);
#ifdef CONFIG_X86_64
fxsave->rip = env->fip;
fxsave->rdp = env->foo;
/* cs and ds ignored */
#else
fxsave->fip = env->fip;
fxsave->fcs = (env->fcs & 0xffff);
fxsave->foo = env->foo;
fxsave->fos = env->fos;
#endif
for (i = 0; i < 8; ++i)
memcpy(&to[i], &from[i], sizeof(from[0]));
}
int fpregs_get(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
struct fpu *fpu = &target->thread.fpu;
struct user_i387_ia32_struct env;
fpu__activate_fpstate(fpu);
if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
if (!cpu_has_fxsr)
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&fpu->state.fsave, 0,
-1);
fpstate_sanitize_xstate(fpu);
if (kbuf && pos == 0 && count == sizeof(env)) {
convert_from_fxsr(kbuf, target);
return 0;
}
convert_from_fxsr(&env, target);
return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
}
int fpregs_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
struct fpu *fpu = &target->thread.fpu;
struct user_i387_ia32_struct env;
int ret;
fpu__activate_fpstate(fpu);
fpstate_sanitize_xstate(fpu);
if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
if (!cpu_has_fxsr)
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&fpu->state.fsave, 0,
-1);
if (pos > 0 || count < sizeof(env))
convert_from_fxsr(&env, target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
if (!ret)
convert_to_fxsr(target, &env);
/*
* update the header bit in the xsave header, indicating the
* presence of FP.
*/
if (cpu_has_xsave)
fpu->state.xsave.header.xfeatures |= XSTATE_FP;
return ret;
}
/*
* FPU state for core dumps.
* This is only used for a.out dumps now.
* It is declared generically using elf_fpregset_t (which is
* struct user_i387_struct) but is in fact only used for 32-bit
* dumps, so on 64-bit it is really struct user_i387_ia32_struct.
*/
int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
{
struct task_struct *tsk = current;
struct fpu *fpu = &tsk->thread.fpu;
int fpvalid;
fpvalid = fpu->fpstate_active;
if (fpvalid)
fpvalid = !fpregs_get(tsk, NULL,
0, sizeof(struct user_i387_ia32_struct),
ufpu, NULL);
return fpvalid;
}
EXPORT_SYMBOL(dump_fpu);
#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */