sparc64: NG4 memset 32 bits overflow

Early in boot Linux patches memset and memcpy to branch to platform
optimized versions of these routines.  The NG4 (Niagra 4) versions are
currently used on all platforms starting from T4.  Recently, there were M7
optimized routines added into UEK4 but not into mainline yet.  So, even
with M7 optimized routines NG4 are still going to be used on T4, T5, M5,
and M6 processors.

While investigating how to improve initialization time of dentry_hashtable
which is 8G long on M6 ldom with 7T of main memory, I noticed that
memset() does not reset all the memory in this array, after studying the
code, I realized that NG4memset() branches use %icc register instead of
%xcc to check compare, so if value of length is over 32-bit long, which is
true for 8G array, these routines fail to work properly.

The fix is to replace all %icc with %xcc in these routines.  (Alternative
is to use %ncc, but this is misleading, as the code already has sparcv9
only instructions, and cannot be compiled on 32-bit).

This is important to fix this bug, because even older T4-4 can have 2T of
memory, and there are large memory proportional data structures in kernel
which can be larger than 4G in size.  The failing of memset() is silent
and corruption is hard to detect.

Link: http://lkml.kernel.org/r/1488432825-92126-2-git-send-email-pasha.tatashin@oracle.com
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Reviewed-by: Babu Moger <babu.moger@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 13 insertions, 13 deletions

diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S
index 7c0c81f18837..c07834f3a6fc 100644
--- a/arch/sparc/lib/NG4memset.S
+++ b/arch/sparc/lib/NG4memset.S
@@ -13,14 +13,14 @@
 	.globl		NG4memset
 NG4memset:
 	andcc		%o1, 0xff, %o4
-	be,pt		%icc, 1f
+	be,pt		%xcc, 1f
 	 mov		%o2, %o1
 	sllx		%o4, 8, %g1
 	or		%g1, %o4, %o2
 	sllx		%o2, 16, %g1
 	or		%g1, %o2, %o2
 	sllx		%o2, 32, %g1
-	ba,pt		%icc, 1f
+	ba,pt		%xcc, 1f
 	 or		%g1, %o2, %o4
 	.size		NG4memset,.-NG4memset
 
@@ -29,7 +29,7 @@ NG4memset:
 NG4bzero:
 	clr		%o4
 1:	cmp		%o1, 16
-	ble		%icc, .Ltiny
+	ble		%xcc, .Ltiny
 	 mov		%o0, %o3
 	sub		%g0, %o0, %g1
 	and		%g1, 0x7, %g1
@@ -37,7 +37,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stb		%o4, [%o0 + 0x00]
 	subcc		%g1, 1, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Laligned8:
 	cmp		%o1, 64 + (64 - 8)
@@ -48,7 +48,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x8, %o0
 .Laligned64:
 	andn		%o1, 64 - 1, %g1
@@ -58,30 +58,30 @@ NG4bzero:
 1:	stxa		%o4, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
 	subcc		%g1, 0x40, %g1
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x40, %o0
 .Lpostloop:
 	cmp		%o1, 8
-	bl,pn		%icc, .Ltiny
+	bl,pn		%xcc, .Ltiny
 	 membar		#StoreStore|#StoreLoad
 .Lmedium:
 	andn		%o1, 0x7, %g1
 	sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 0x8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x08, %o0
 	andcc		%o1, 0x4, %g1
-	be,pt		%icc, .Ltiny
+	be,pt		%xcc, .Ltiny
 	 sub		%o1, %g1, %o1
 	stw		%o4, [%o0 + 0x00]
 	add		%o0, 0x4, %o0
 .Ltiny:
 	cmp		%o1, 0
-	be,pn		%icc, .Lexit
+	be,pn		%xcc, .Lexit
 1:	 subcc		%o1, 1, %o1
 	stb		%o4, [%o0 + 0x00]
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Lexit:
 	retl
@@ -99,8 +99,8 @@ NG4bzero:
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %o5] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x30, %o0
-	ba,a,pt		%icc, .Lpostloop
+	ba,a,pt		%xcc, .Lpostloop
 	 nop
 	.size		NG4bzero,.-NG4bzero