sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads.

The Montgomery Multiply, Montgomery Square, and Multiple-Precision
Multiply instructions work by loading a combination of the floating
point and multiple register windows worth of integer registers
with the inputs.

These values are 64-bit.  But for 32-bit userland processes we only
save the low 32-bits of each integer register during a register spill.
This is because the register window save area is in the user stack and
has a fixed layout.

Therefore, the only way to use these instruction in 32-bit mode is to
perform the following sequence:

1) Load the top-32bits of a choosen integer register with a sentinel,
   say "-1".  This will be in the outer-most register window.

   The idea is that we're trying to see if the outer-most register
   window gets spilled, and thus the 64-bit values were truncated.

2) Load all the inputs for the montmul/montsqr/mpmul instruction,
   down to the inner-most register window.

3) Execute the opcode.

4) Traverse back up to the outer-most register window.

5) Check the sentinel, if it's still "-1" store the results.
   Otherwise retry the entire sequence.

This retry is extremely troublesome.  If you're just unlucky and an
interrupt or other trap happens, it'll push that outer-most window to
the stack and clear the sentinel when we restore it.

We could retry forever and never make forward progress if interrupts
arrive at a fast enough rate (consider perf events as one example).
So we have do limited retries and fallback to software which is
extremely non-deterministic.

Luckily it's very straightforward to provide a mechanism to let
32-bit applications use a 64-bit stack.  Stacks in 64-bit mode are
biased by 2047 bytes, which means that the lowest bit is set in the
actual %sp register value.

So if we see bit zero set in a 32-bit application's stack we treat
it like a 64-bit stack.

Runtime detection of such a facility is tricky, and cumbersome at
best.  For example, just trying to use a biased stack and seeing if it
works is hard to recover from (the signal handler will need to use an
alt stack, plus something along the lines of longjmp).  Therefore, we
add a system call to report a bitmask of arch specific features like
this in a cheap and less hairy way.

With help from Andy Polyakov.

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 24 insertions, 10 deletions

diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index cef99fbc0a21..830502fe62b4 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -232,9 +232,10 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 	struct pt_regs *regs = current_thread_info()->kregs;
 	unsigned long usp = regs->u_regs[UREG_I6];
 
-	if (!(test_thread_flag(TIF_32BIT)))
+	if (test_thread_64bit_stack(usp))
 		usp += STACK_BIAS;
-	else
+
+	if (test_thread_flag(TIF_32BIT))
 		usp &= 0xffffffffUL;
 
 	usp -= len;
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 4e2276631081..a3fe4dcc0aa6 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -259,6 +259,11 @@ static inline bool test_and_clear_restore_sigmask(void)
 
 #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
 
+#define thread32_stack_is_64bit(__SP) (((__SP) & 0x1) != 0)
+#define test_thread_64bit_stack(__SP) \
+	((test_thread_flag(TIF_32BIT) && !thread32_stack_is_64bit(__SP)) ? \
+	 false : true)
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 48f2807d3265..71b5a67522ab 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -372,7 +372,9 @@ etrap_spill_fixup_64bit:				\
 
 /* Normal 32bit spill */
 #define SPILL_2_GENERIC(ASI)				\
-	srl	%sp, 0, %sp;				\
+	and	%sp, 1, %g3;				\
+	brnz,pn	%g3, (. - (128 + 4));			\
+	 srl	%sp, 0, %sp;				\
 	stwa	%l0, [%sp + %g0] ASI;			\
 	mov	0x04, %g3;				\
 	stwa	%l1, [%sp + %g3] ASI;			\
@@ -398,14 +400,16 @@ etrap_spill_fixup_64bit:				\
 	stwa	%i6, [%g1 + %g0] ASI;			\
 	stwa	%i7, [%g1 + %g3] ASI;			\
 	saved;						\
-        retry; nop; nop;				\
+        retry;						\
 	b,a,pt	%xcc, spill_fixup_dax;			\
 	b,a,pt	%xcc, spill_fixup_mna;			\
 	b,a,pt	%xcc, spill_fixup;
 
 #define SPILL_2_GENERIC_ETRAP		\
 etrap_user_spill_32bit:			\
-	srl	%sp, 0, %sp;		\
+	and	%sp, 1, %g3;		\
+	brnz,pn	%g3, etrap_user_spill_64bit;	\
+	 srl	%sp, 0, %sp;		\
 	stwa	%l0, [%sp + 0x00] %asi;	\
 	stwa	%l1, [%sp + 0x04] %asi;	\
 	stwa	%l2, [%sp + 0x08] %asi;	\
@@ -427,7 +431,7 @@ etrap_user_spill_32bit:			\
 	ba,pt	%xcc, etrap_save;	\
 	 wrpr	%g1, %cwp;		\
 	nop; nop; nop; nop;		\
-	nop; nop; nop; nop;		\
+	nop; nop;			\
 	ba,a,pt	%xcc, etrap_spill_fixup_32bit; \
 	ba,a,pt	%xcc, etrap_spill_fixup_32bit; \
 	ba,a,pt	%xcc, etrap_spill_fixup_32bit;
@@ -592,7 +596,9 @@ user_rtt_fill_64bit:					\
 
 /* Normal 32bit fill */
 #define FILL_2_GENERIC(ASI)				\
-	srl	%sp, 0, %sp;				\
+	and	%sp, 1, %g3;				\
+	brnz,pn	%g3, (. - (128 + 4));			\
+	 srl	%sp, 0, %sp;				\
 	lduwa	[%sp + %g0] ASI, %l0;			\
 	mov	0x04, %g2;				\
 	mov	0x08, %g3;				\
@@ -616,14 +622,16 @@ user_rtt_fill_64bit:					\
 	lduwa	[%g1 + %g3] ASI, %i6;			\
 	lduwa	[%g1 + %g5] ASI, %i7;			\
 	restored;					\
-	retry; nop; nop; nop; nop;			\
+	retry; nop; nop;				\
 	b,a,pt	%xcc, fill_fixup_dax;			\
 	b,a,pt	%xcc, fill_fixup_mna;			\
 	b,a,pt	%xcc, fill_fixup;
 
 #define FILL_2_GENERIC_RTRAP				\
 user_rtt_fill_32bit:					\
-	srl	%sp, 0, %sp;				\
+	and	%sp, 1, %g3;				\
+	brnz,pn	%g3, user_rtt_fill_64bit;		\
+	 srl	%sp, 0, %sp;				\
 	lduwa	[%sp + 0x00] %asi, %l0;			\
 	lduwa	[%sp + 0x04] %asi, %l1;			\
 	lduwa	[%sp + 0x08] %asi, %l2;			\
@@ -643,7 +651,7 @@ user_rtt_fill_32bit:					\
 	ba,pt	%xcc, user_rtt_pre_restore;		\
 	 restored;					\
 	nop; nop; nop; nop; nop;			\
-	nop; nop; nop; nop; nop;			\
+	nop; nop; nop;					\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;