sparc64: Fix userspace FPU register corruptions.

commit 44922150d87cef616fd183220d43d8fde4d41390 upstream.

If we have a series of events from userpsace, with %fprs=FPRS_FEF,
like follows:

ETRAP
	ETRAP
		VIS_ENTRY(fprs=0x4)
		VIS_EXIT
		RTRAP (kernel FPU restore with fpu_saved=0x4)
	RTRAP

We will not restore the user registers that were clobbered by the FPU
using kernel code in the inner-most trap.

Traps allocate FPU save slots in the thread struct, and FPU using
sequences save the "dirty" FPU registers only.

This works at the initial trap level because all of the registers
get recorded into the top-level FPU save area, and we'll return
to userspace with the FPU disabled so that any FPU use by the user
will take an FPU disabled trap wherein we'll load the registers
back up properly.

But this is not how trap returns from kernel to kernel operate.

The simplest fix for this bug is to always save all FPU register state
for anything other than the top-most FPU save area.

Getting rid of the optimized inner-slot FPU saving code ends up
making VISEntryHalf degenerate into plain VISEntry.

Longer term we need to do something smarter to reinstate the partial
save optimizations.  Perhaps the fundament error is having trap entry
and exit allocate FPU save slots and restore register state.  Instead,
the VISEntry et al. calls should be doing that work.

This bug is about two decades old.

Reported-by: James Y Knight <jyknight@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[bwh: Backported to 3.2:
 - Adjust context
 - Drop changes to NG4memcpy.S and ksyms.c]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

2 files changed, 6 insertions, 75 deletions

diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 39ca301..3a8c2af 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -28,18 +28,12 @@
  * Must preserve %o5 between VISEntryHalf and VISExitHalf */
 
 #define VISEntryHalf					\
-	rd		%fprs, %o5;			\
-	andcc		%o5, FPRS_FEF, %g0;		\
-	be,pt		%icc, 297f;			\
-	 sethi		%hi(298f), %g7;			\
-	sethi		%hi(VISenterhalf), %g1;		\
-	jmpl		%g1 + %lo(VISenterhalf), %g0;	\
-	 or		%g7, %lo(298f), %g7;		\
-	clr		%o5;				\
-297:	wr		%o5, FPRS_FEF, %fprs;		\
-298:
+	VISEntry
 
 #define VISExitHalf					\
+	VISExit
+
+#define VISExitHalfFast					\
 	wr		%o5, 0, %fprs;
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9..a063d84 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -44,9 +44,8 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 
 	 stx		%g3, [%g6 + TI_GSR]
 2:	add		%g6, %g1, %g3
-	cmp		%o5, FPRS_DU
-	be,pn		%icc, 6f
-	 sll		%g1, 3, %g1
+	mov		FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+	sll		%g1, 3, %g1
 	stb		%o5, [%g3 + TI_FPSAVED]
 	rd		%gsr, %g2
 	add		%g6, %g1, %g3
@@ -80,65 +79,3 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 	.align		32
 80:	jmpl		%g7 + %g0, %g0
 	 nop
-
-6:	ldub		[%g3 + TI_FPSAVED], %o5
-	or		%o5, FPRS_DU, %o5
-	add		%g6, TI_FPREGS+0x80, %g2
-	stb		%o5, [%g3 + TI_FPSAVED]
-
-	sll		%g1, 5, %g1
-	add		%g6, TI_FPREGS+0xc0, %g3
-	wr		%g0, FPRS_FEF, %fprs
-	membar		#Sync
-	stda		%f32, [%g2 + %g1] ASI_BLK_P
-	stda		%f48, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 80f
-	 nop
-
-	.align		32
-80:	jmpl		%g7 + %g0, %g0
-	 nop
-
-	.align		32
-VISenterhalf:
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	brnz,a,pn	%g1, 1f
-	 cmp		%g1, 1
-	stb		%g0, [%g6 + TI_FPSAVED]
-	stx		%fsr, [%g6 + TI_XFSR]
-	clr		%o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%g0, FPRS_FEF, %fprs
-
-1:	bne,pn		%icc, 2f
-	 srl		%g1, 1, %g1
-	ba,pt		%xcc, vis1
-	 sub		%g7, 8, %g7
-2:	addcc		%g6, %g1, %g3
-	sll		%g1, 3, %g1
-	andn		%o5, FPRS_DU, %g2
-	stb		%g2, [%g3 + TI_FPSAVED]
-
-	rd		%gsr, %g2
-	add		%g6, %g1, %g3
-	stx		%g2, [%g3 + TI_GSR]
-	add		%g6, %g1, %g2
-	stx		%fsr, [%g2 + TI_XFSR]
-	sll		%g1, 5, %g1
-3:	andcc		%o5, FPRS_DL, %g0
-	be,pn		%icc, 4f
-	 add		%g6, TI_FPREGS, %g2
-
-	add		%g6, TI_FPREGS+0x40, %g3
-	membar		#Sync
-	stda		%f0, [%g2 + %g1] ASI_BLK_P
-	stda		%f16, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 4f
-	 nop
-
-	.align		32
-4:	and		%o5, FPRS_DU, %o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%o5, FPRS_FEF, %fprs