Merge branch 'x86/fpu' into x86/smap
Reason for merge:
x86/fpu changed the structure of some of the code that x86/smap
changes; mostly fpu-internal.h but also minor changes to the
signal code.
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Resolved Conflicts:
arch/x86/ia32/ia32_signal.c
arch/x86/include/asm/fpu-internal.h
arch/x86/kernel/signal.c
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 0fe1358..409b9cc 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -12,6 +12,7 @@
#include <linux/kernel_stat.h>
#include <linux/regset.h>
+#include <linux/compat.h>
#include <linux/slab.h>
#include <asm/asm.h>
#include <asm/cpufeature.h>
@@ -20,43 +21,76 @@
#include <asm/user.h>
#include <asm/uaccess.h>
#include <asm/xsave.h>
+#include <asm/smap.h>
-extern unsigned int sig_xstate_size;
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+ compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct user_i387_struct
+# define user32_fxsr_struct user_fxsr_struct
+# define ia32_setup_frame __setup_frame
+# define ia32_setup_rt_frame __setup_rt_frame
+#endif
+
+extern unsigned int mxcsr_feature_mask;
extern void fpu_init(void);
+extern void eager_fpu_init(void);
DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+ struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env);
+
extern user_regset_active_fn fpregs_active, xfpregs_active;
extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
xstateregs_get;
extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
xstateregs_set;
-
/*
* xstateregs_active == fpregs_active. Please refer to the comment
* at the definition of fpregs_active.
*/
#define xstateregs_active fpregs_active
-extern struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-extern unsigned int sig_xstate_ia32_size;
-extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
-struct _fpstate_ia32;
-struct _xstate_ia32;
-extern int save_i387_xstate_ia32(void __user *buf);
-extern int restore_i387_xstate_ia32(void __user *buf);
-#endif
-
#ifdef CONFIG_MATH_EMULATION
+# define HAVE_HWFP (boot_cpu_data.hard_math)
extern void finit_soft_fpu(struct i387_soft_struct *soft);
#else
+# define HAVE_HWFP 1
static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
#endif
+static inline int is_ia32_compat_frame(void)
+{
+ return config_enabled(CONFIG_IA32_EMULATION) &&
+ test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+ return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+ return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
#define X87_FSW_ES (1 << 7) /* Exception Summary */
+static __always_inline __pure bool use_eager_fpu(void)
+{
+ return static_cpu_has(X86_FEATURE_EAGER_FPU);
+}
+
static __always_inline __pure bool use_xsaveopt(void)
{
return static_cpu_has(X86_FEATURE_XSAVEOPT);
@@ -72,6 +106,13 @@
return static_cpu_has(X86_FEATURE_FXSR);
}
+static inline void fx_finit(struct i387_fxsave_struct *fx)
+{
+ memset(fx, 0, xstate_size);
+ fx->cwd = 0x37f;
+ fx->mxcsr = MXCSR_DEFAULT;
+}
+
extern void __sanitize_i387_state(struct task_struct *);
static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -81,133 +122,104 @@
__sanitize_i387_state(tsk);
}
-#ifdef CONFIG_X86_64
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
- int err;
+#define user_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile(ASM_STAC "\n" \
+ "1:" #insn "\n\t" \
+ "2: " ASM_CLAC "\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
- /* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
- asm volatile("1: fxrstorq %[fx]\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err)
- : [fx] "m" (*fx), "0" (0));
-#else
- asm volatile("1: rex64/fxrstor (%[fx])\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err)
- : [fx] "R" (fx), "m" (*fx), "0" (0));
-#endif
- return err;
+#define check_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+static inline int fsave_user(struct i387_fsave_struct __user *fx)
+{
+ return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
}
static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
{
- int err;
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
- /*
- * Clear the bytes not touched by the fxsave and reserved
- * for the SW usage.
- */
- err = __clear_user(&fx->sw_reserved,
- sizeof(struct _fpx_sw_bytes));
- if (unlikely(err))
- return -EFAULT;
-
- /* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
- asm volatile(ASM_STAC "\n"
- "1: fxsaveq %[fx]\n\t"
- "2: " ASM_CLAC "\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err), [fx] "=m" (*fx)
- : "0" (0));
-#else
- asm volatile(ASM_STAC "\n"
- "1: rex64/fxsave (%[fx])\n\t"
- "2: " ASM_CLAC "\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err), "=m" (*fx)
- : [fx] "R" (fx), "0" (0));
-#endif
- if (unlikely(err) &&
- __clear_user(fx, sizeof(struct i387_fxsave_struct)))
- err = -EFAULT;
- /* No need to clear here because the caller clears USED_MATH */
- return err;
+ /* See comment in fpu_fxsave() below. */
+ return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
}
-static inline void fpu_fxsave(struct fpu *fpu)
-{
- /* Using "rex64; fxsave %0" is broken because, if the memory operand
- uses any extended registers for addressing, a second REX prefix
- will be generated (to the assembler, rex64 followed by semicolon
- is a separate instruction), and hence the 64-bitness is lost. */
-
-#ifdef CONFIG_AS_FXSAVEQ
- /* Using "fxsaveq %0" would be the ideal choice, but is only supported
- starting with gas 2.16. */
- __asm__ __volatile__("fxsaveq %0"
- : "=m" (fpu->state->fxsave));
-#else
- /* Using, as a workaround, the properly prefixed form below isn't
- accepted by any binutils version so far released, complaining that
- the same type of prefix is used twice if an extended register is
- needed for addressing (fix submitted to mainline 2005-11-21).
- asm volatile("rex64/fxsave %0"
- : "=m" (fpu->state->fxsave));
- This, however, we can work around by forcing the compiler to select
- an addressing mode that doesn't require extended registers. */
- asm volatile("rex64/fxsave (%[fx])"
- : "=m" (fpu->state->fxsave)
- : [fx] "R" (&fpu->state->fxsave));
-#endif
-}
-
-#else /* CONFIG_X86_32 */
-
-/* perform fxrstor iff the processor has extended states, otherwise frstor */
static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
{
- /*
- * The "nop" is needed to make the instructions the same
- * length.
- */
- alternative_input(
- "nop ; frstor %1",
- "fxrstor %1",
- X86_FEATURE_FXSR,
- "m" (*fx));
+ if (config_enabled(CONFIG_X86_32))
+ return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
- return 0;
+ /* See comment in fpu_fxsave() below. */
+ return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+ "m" (*fx));
+}
+
+static inline int frstor_checking(struct i387_fsave_struct *fx)
+{
+ return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
}
static inline void fpu_fxsave(struct fpu *fpu)
{
- asm volatile("fxsave %[fx]"
- : [fx] "=m" (fpu->state->fxsave));
+ if (config_enabled(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave));
+ else {
+ /* Using "rex64; fxsave %0" is broken because, if the memory
+ * operand uses any extended registers for addressing, a second
+ * REX prefix will be generated (to the assembler, rex64
+ * followed by semicolon is a separate instruction), and hence
+ * the 64-bitness is lost.
+ *
+ * Using "fxsaveq %0" would be the ideal choice, but is only
+ * supported starting with gas 2.16.
+ *
+ * Using, as a workaround, the properly prefixed form below
+ * isn't accepted by any binutils version so far released,
+ * complaining that the same type of prefix is used twice if
+ * an extended register is needed for addressing (fix submitted
+ * to mainline 2005-11-21).
+ *
+ * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
+ *
+ * This, however, we can work around by forcing the compiler to
+ * select an addressing mode that doesn't require extended
+ * registers.
+ */
+ asm volatile( "rex64/fxsave (%[fx])"
+ : "=m" (fpu->state->fxsave)
+ : [fx] "R" (&fpu->state->fxsave));
+ }
}
-#endif /* CONFIG_X86_64 */
-
/*
* These must be called with preempt disabled. Returns
* 'true' if the FPU state is still intact.
@@ -250,17 +262,14 @@
return fpu_save_init(&tsk->thread.fpu);
}
-static inline int fpu_fxrstor_checking(struct fpu *fpu)
-{
- return fxrstor_checking(&fpu->state->fxsave);
-}
-
static inline int fpu_restore_checking(struct fpu *fpu)
{
if (use_xsave())
- return fpu_xrstor_checking(fpu);
+ return fpu_xrstor_checking(&fpu->state->xsave);
+ else if (use_fxsr())
+ return fxrstor_checking(&fpu->state->fxsave);
else
- return fpu_fxrstor_checking(fpu);
+ return frstor_checking(&fpu->state->fsave);
}
static inline int restore_fpu_checking(struct task_struct *tsk)
@@ -312,15 +321,52 @@
static inline void __thread_fpu_end(struct task_struct *tsk)
{
__thread_clear_has_fpu(tsk);
- stts();
+ if (!use_eager_fpu())
+ stts();
}
static inline void __thread_fpu_begin(struct task_struct *tsk)
{
- clts();
+ if (!use_eager_fpu())
+ clts();
__thread_set_has_fpu(tsk);
}
+static inline void __drop_fpu(struct task_struct *tsk)
+{
+ if (__thread_has_fpu(tsk)) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ __thread_fpu_end(tsk);
+ }
+}
+
+static inline void drop_fpu(struct task_struct *tsk)
+{
+ /*
+ * Forget coprocessor state..
+ */
+ preempt_disable();
+ tsk->fpu_counter = 0;
+ __drop_fpu(tsk);
+ clear_used_math();
+ preempt_enable();
+}
+
+static inline void drop_init_fpu(struct task_struct *tsk)
+{
+ if (!use_eager_fpu())
+ drop_fpu(tsk);
+ else {
+ if (use_xsave())
+ xrstor_state(init_xstate_buf, -1);
+ else
+ fxrstor_checking(&init_xstate_buf->i387);
+ }
+}
+
/*
* FPU state switching for scheduling.
*
@@ -354,7 +400,12 @@
{
fpu_switch_t fpu;
- fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+ /*
+ * If the task has used the math, pre-load the FPU on xsave processors
+ * or if the past 5 consecutive context-switches used math.
+ */
+ fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
+ new->fpu_counter > 5);
if (__thread_has_fpu(old)) {
if (!__save_init_fpu(old))
cpu = ~0;
@@ -366,14 +417,14 @@
new->fpu_counter++;
__thread_set_has_fpu(new);
prefetch(new->thread.fpu.state);
- } else
+ } else if (!use_eager_fpu())
stts();
} else {
old->fpu_counter = 0;
old->thread.fpu.last_cpu = ~0;
if (fpu.preload) {
new->fpu_counter++;
- if (fpu_lazy_restore(new, cpu))
+ if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
fpu.preload = 0;
else
prefetch(new->thread.fpu.state);
@@ -393,44 +444,40 @@
{
if (fpu.preload) {
if (unlikely(restore_fpu_checking(new)))
- __thread_fpu_end(new);
+ drop_init_fpu(new);
}
}
/*
* Signal frame handlers...
*/
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
+extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
-static inline void __clear_fpu(struct task_struct *tsk)
+static inline int xstate_sigframe_size(void)
{
- if (__thread_has_fpu(tsk)) {
- /* Ignore delayed exceptions from user space */
- asm volatile("1: fwait\n"
- "2:\n"
- _ASM_EXTABLE(1b, 2b));
- __thread_fpu_end(tsk);
+ return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
+{
+ void __user *buf_fx = buf;
+ int size = xstate_sigframe_size();
+
+ if (ia32_frame && use_fxsr()) {
+ buf_fx = buf + sizeof(struct i387_fsave_struct);
+ size += sizeof(struct i387_fsave_struct);
}
+
+ return __restore_xstate_sig(buf, buf_fx, size);
}
/*
- * The actual user_fpu_begin/end() functions
- * need to be preemption-safe.
+ * Need to be preemption-safe.
*
- * NOTE! user_fpu_end() must be used only after you
- * have saved the FP state, and user_fpu_begin() must
- * be used only immediately before restoring it.
- * These functions do not do any save/restore on
- * their own.
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * it. This function does not do any save/restore on their own.
*/
-static inline void user_fpu_end(void)
-{
- preempt_disable();
- __thread_fpu_end(current);
- preempt_enable();
-}
-
static inline void user_fpu_begin(void)
{
preempt_disable();
@@ -439,25 +486,32 @@
preempt_enable();
}
+static inline void __save_fpu(struct task_struct *tsk)
+{
+ if (use_xsave())
+ xsave_state(&tsk->thread.fpu.state->xsave, -1);
+ else
+ fpu_fxsave(&tsk->thread.fpu);
+}
+
/*
* These disable preemption on their own and are safe
*/
static inline void save_init_fpu(struct task_struct *tsk)
{
WARN_ON_ONCE(!__thread_has_fpu(tsk));
+
+ if (use_eager_fpu()) {
+ __save_fpu(tsk);
+ return;
+ }
+
preempt_disable();
__save_init_fpu(tsk);
__thread_fpu_end(tsk);
preempt_enable();
}
-static inline void clear_fpu(struct task_struct *tsk)
-{
- preempt_disable();
- __clear_fpu(tsk);
- preempt_enable();
-}
-
/*
* i387 state interaction
*/
@@ -512,11 +566,34 @@
}
}
-static inline void fpu_copy(struct fpu *dst, struct fpu *src)
+static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
{
- memcpy(dst->state, src->state, xstate_size);
+ if (use_eager_fpu()) {
+ memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
+ __save_fpu(dst);
+ } else {
+ struct fpu *dfpu = &dst->thread.fpu;
+ struct fpu *sfpu = &src->thread.fpu;
+
+ unlazy_fpu(src);
+ memcpy(dfpu->state, sfpu->state, xstate_size);
+ }
}
-extern void fpu_finit(struct fpu *fpu);
+static inline unsigned long
+alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
+ unsigned long *size)
+{
+ unsigned long frame_size = xstate_sigframe_size();
+
+ *buf_fx = sp = round_down(sp - frame_size, 64);
+ if (ia32_frame && use_fxsr()) {
+ frame_size += sizeof(struct i387_fsave_struct);
+ sp -= sizeof(struct i387_fsave_struct);
+ }
+
+ *size = frame_size;
+ return sp;
+}
#endif