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>

2 files changed, 72 insertions, 45 deletions

diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 016acb30fa4a..4fbb4195bc63 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -22,11 +22,30 @@
 #include <asm/uaccess.h>
 #include <asm/xsave.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);
 
 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;
@@ -39,19 +58,11 @@ extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
  */
 #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
 
@@ -119,17 +130,6 @@ static inline int fsave_user(struct i387_fsave_struct __user *fx)
 
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
-	int err;
-
-	/*
-	 * 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;
-
 	if (config_enabled(CONFIG_X86_32))
 		return check_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
 	else if (config_enabled(CONFIG_AS_FXSAVEQ))
@@ -189,19 +189,6 @@ static inline void fpu_fxsave(struct fpu *fpu)
 			     : [fx] "R" (&fpu->state->fxsave));
 	}
 }
-#ifdef CONFIG_X86_64
-
-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  /* CONFIG_X86_32 */
-
-#define ia32_setup_frame	__setup_frame
-#define ia32_setup_rt_frame	__setup_rt_frame
-
-#endif	/* CONFIG_X86_64 */
 
 /*
  * These must be called with preempt disabled. Returns
@@ -392,10 +379,28 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
 /*
  * 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 int xstate_sigframe_size(void)
+{
+	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);
+}
 
-static inline void __clear_fpu(struct task_struct *tsk)
+static inline void __drop_fpu(struct task_struct *tsk)
 {
 	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
@@ -443,11 +448,21 @@ static inline void save_init_fpu(struct task_struct *tsk)
 	preempt_enable();
 }
 
-static inline void clear_fpu(struct task_struct *tsk)
+static inline void stop_fpu_preload(struct task_struct *tsk)
 {
+	tsk->fpu_counter = 0;
+}
+
+static inline void drop_fpu(struct task_struct *tsk)
+{
+	/*
+	 * Forget coprocessor state..
+	 */
+	stop_fpu_preload(tsk);
 	preempt_disable();
-	__clear_fpu(tsk);
+	__drop_fpu(tsk);
 	preempt_enable();
+	clear_used_math();
 }
 
 /*
@@ -511,4 +526,20 @@ static inline void fpu_copy(struct fpu *dst, struct fpu *src)
 
 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
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index aaac810e8613..c1d989a15193 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -38,9 +38,6 @@ extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 extern void xsave_init(void);
 extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 extern int init_fpu(struct task_struct *child);
-extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
-			    void __user *fpstate,
-			    struct _fpx_sw_bytes *sw);
 
 static inline int fpu_xrstor_checking(struct xsave_struct *fx)
 {
@@ -68,8 +65,7 @@ static inline int xsave_user(struct xsave_struct __user *buf)
 	 * Clear the xsave header first, so that reserved fields are
 	 * initialized to zero.
 	 */
-	err = __clear_user(&buf->xsave_hdr,
-			   sizeof(struct xsave_hdr_struct));
+	err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
 	if (unlikely(err))
 		return -EFAULT;