x86, xsave: dynamically allocate sigframes fpstate instead of static allocation

dynamically allocate fpstate on the stack, instead of static allocation
in the current sigframe layout on the user stack. This will allow the
fpstate structure to grow in the future, which includes extended state
information supporting xsave/xrstor.

signal handlers will be able to access the fpstate pointer from the
sigcontext structure asusual, with no change. For the non RT sigframe's
(which are supported only for 32bit apps), current static fpstate layout
in the sigframe will be unused(so that we don't change the extramask[]
offset in the sigframe and thus prevent breaking app's which modify
extramask[]).

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/ia32/ia32_signal.c

@@ -179,9 +179,10 @@ struct sigframe
 	u32 pretcode;
 	int sig;
 	struct sigcontext_ia32 sc;
-	struct _fpstate_ia32 fpstate;
+	struct _fpstate_ia32 fpstate_unused; /* look at kernel/sigframe.h */
 	unsigned int extramask[_COMPAT_NSIG_WORDS-1];
 	char retcode[8];
+	/* fp state follows here */
 };
 
 struct rt_sigframe
@@ -192,8 +193,8 @@ struct rt_sigframe
 	u32 puc;
 	compat_siginfo_t info;
 	struct ucontext_ia32 uc;
-	struct _fpstate_ia32 fpstate;
 	char retcode[8];
+	/* fp state follows here */
 };
 
 #define COPY(x)		{ 		\
@@ -402,7 +403,8 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
  * Determine which stack to use..
  */
 static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
-				 size_t frame_size)
+				 size_t frame_size,
+				 struct _fpstate_ia32 **fpstate)
 {
 	unsigned long sp;
 
@@ -421,6 +423,11 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 		 ka->sa.sa_restorer)
 		sp = (unsigned long) ka->sa.sa_restorer;
 
+	if (used_math()) {
+		sp = sp - sig_xstate_ia32_size;
+		*fpstate = (struct _fpstate_ia32 *) sp;
+	}
+
 	sp -= frame_size;
 	/* Align the stack pointer according to the i386 ABI,
 	 * i.e. so that on function entry ((sp + 4) & 15) == 0. */
@@ -434,6 +441,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 	struct sigframe __user *frame;
 	void __user *restorer;
 	int err = 0;
+	struct _fpstate_ia32 __user *fpstate = NULL;
 
 	/* copy_to_user optimizes that into a single 8 byte store */
 	static const struct {
@@ -448,7 +456,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 		0,
 	};
 
-	frame = get_sigframe(ka, regs, sizeof(*frame));
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
@@ -457,8 +465,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 	if (err)
 		goto give_sigsegv;
 
-	err |= ia32_setup_sigcontext(&frame->sc, &frame->fpstate, regs,
-					set->sig[0]);
+	err |= ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]);
 	if (err)
 		goto give_sigsegv;
 
@@ -522,6 +529,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	struct rt_sigframe __user *frame;
 	void __user *restorer;
 	int err = 0;
+	struct _fpstate_ia32 __user *fpstate = NULL;
 
 	/* __copy_to_user optimizes that into a single 8 byte store */
 	static const struct {
@@ -537,7 +545,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		0,
 	};
 
-	frame = get_sigframe(ka, regs, sizeof(*frame));
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
@@ -556,7 +564,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	err |= __put_user(sas_ss_flags(regs->sp),
 			  &frame->uc.uc_stack.ss_flags);
 	err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
-	err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+	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)

arch/x86/kernel/i387.c

@@ -24,6 +24,7 @@
 # define save_i387_ia32		save_i387
 # define restore_i387_ia32	restore_i387
 # define _fpstate_ia32		_fpstate
+# define sig_xstate_ia32_size   sig_xstate_size
 # define user_i387_ia32_struct	user_i387_struct
 # define user32_fxsr_struct	user_fxsr_struct
 #endif
@@ -36,6 +37,7 @@
 
 static unsigned int		mxcsr_feature_mask __read_mostly = 0xffffffffu;
 unsigned int xstate_size;
+unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
 static struct i387_fxsave_struct fx_scratch __cpuinitdata;
 
 void __cpuinit mxcsr_feature_mask_init(void)

arch/x86/kernel/sigframe.h

@@ -3,9 +3,18 @@ struct sigframe {
 	char __user *pretcode;
 	int sig;
 	struct sigcontext sc;
-	struct _fpstate fpstate;
+	/*
+	 * fpstate is unused. fpstate is moved/allocated after
+	 * retcode[] below. This movement allows to have the FP state and the
+	 * future state extensions (xsave) stay together.
+	 * And at the same time retaining the unused fpstate, prevents changing
+	 * the offset of extramask[] in the sigframe and thus prevent any
+	 * legacy application accessing/modifying it.
+	 */
+	struct _fpstate fpstate_unused;
 	unsigned long extramask[_NSIG_WORDS-1];
 	char retcode[8];
+	/* fp state follows here */
 };
 
 struct rt_sigframe {
@@ -15,13 +24,14 @@ struct rt_sigframe {
 	void __user *puc;
 	struct siginfo info;
 	struct ucontext uc;
-	struct _fpstate fpstate;
 	char retcode[8];
+	/* fp state follows here */
 };
 #else
 struct rt_sigframe {
 	char __user *pretcode;
 	struct ucontext uc;
 	struct siginfo info;
+	/* fp state follows here */
 };
 #endif

arch/x86/kernel/signal_32.c

@@ -306,7 +306,8 @@ setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
  * Determine which stack to use..
  */
 static inline void __user *
-get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size)
+get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
+	     struct _fpstate **fpstate)
 {
 	unsigned long sp;
 
@@ -332,6 +333,11 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size)
 			sp = (unsigned long) ka->sa.sa_restorer;
 	}
 
+	if (used_math()) {
+		sp = sp - sig_xstate_size;
+		*fpstate = (struct _fpstate *) sp;
+	}
+
 	sp -= frame_size;
 	/*
 	 * Align the stack pointer according to the i386 ABI,
@@ -350,8 +356,9 @@ setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
 	void __user *restorer;
 	int err = 0;
 	int usig;
+	struct _fpstate __user *fpstate = NULL;
 
-	frame = get_sigframe(ka, regs, sizeof(*frame));
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
@@ -366,7 +373,7 @@ setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
 	if (err)
 		goto give_sigsegv;
 
-	err = setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+	err = setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]);
 	if (err)
 		goto give_sigsegv;
 
@@ -427,8 +434,9 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	void __user *restorer;
 	int err = 0;
 	int usig;
+	struct _fpstate __user *fpstate = NULL;
 
-	frame = get_sigframe(ka, regs, sizeof(*frame));
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
@@ -453,7 +461,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	err |= __put_user(sas_ss_flags(regs->sp),
 			  &frame->uc.uc_stack.ss_flags);
 	err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
-	err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+	err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
 				regs, set->sig[0]);
 	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
 	if (err)

arch/x86/kernel/signal_64.c

@@ -281,7 +281,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	struct task_struct *me = current;
 
 	if (used_math()) {
-		fp = get_stack(ka, regs, sizeof(struct _fpstate)); 
+		fp = get_stack(ka, regs, sig_xstate_size);
 		frame = (void __user *)round_down(
 			(unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
 

arch/x86/kernel/xsave.c

@@ -17,6 +17,10 @@ unsigned int pcntxt_hmask, pcntxt_lmask;
  */
 struct xsave_struct *init_xstate_buf;
 
+#ifdef CONFIG_X86_64
+unsigned int sig_xstate_size = sizeof(struct _fpstate);
+#endif
+
 /*
  * Enable the extended processor state save/restore feature
  */

include/asm-x86/i387.h

@@ -20,6 +20,7 @@
 #include <asm/uaccess.h>
 #include <asm/xsave.h>
 
+extern unsigned int sig_xstate_size;
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
@@ -31,6 +32,7 @@ extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
 extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set;
 
 #ifdef CONFIG_IA32_EMULATION
+extern unsigned int sig_xstate_ia32_size;
 struct _fpstate_ia32;
 extern int save_i387_ia32(struct _fpstate_ia32 __user *buf);
 extern int restore_i387_ia32(struct _fpstate_ia32 __user *buf);