Commit b445e26c authored by David S. Miller's avatar David S. Miller
Browse files

[SPARC64]: Avoid membar instructions in delay slots. 



In particular, avoid membar instructions in the delay
slot of a jmpl instruction.

UltraSPARC-I, II, IIi, and IIe have a bug, documented in
the UltraSPARC-IIi User's Manual, Appendix K, Erratum 51

The long and short of it is that if the IMU unit misses
on a branch or jmpl, and there is a store buffer synchronizing
membar in the delay slot, the chip can stop fetching instructions.

If interrupts are enabled or some other trap is enabled, the
chip will unwedge itself, but performance will suffer.

We already had a workaround for this bug in a few spots, but
it's better to have the entire tree sanitized for this rule.

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 020f46a3

arch/sparc64/kernel/entry.S

+4 −2
Original line number Original line Diff line number Diff line
@@ -271,8 +271,9 @@ cplus_fptrap_insn_1: 
	fmuld		%f0, %f2, %f26

	fmuld		%f0, %f2, %f26

	faddd		%f0, %f2, %f28

	faddd		%f0, %f2, %f28

	fmuld		%f0, %f2, %f30

	fmuld		%f0, %f2, %f30

	b,pt		%xcc, fpdis_exit

	membar		#Sync

	membar		#Sync

	b,pt		%xcc, fpdis_exit

	 nop

2:	andcc		%g5, FPRS_DU, %g0

2:	andcc		%g5, FPRS_DU, %g0

	bne,pt		%icc, 3f

	bne,pt		%icc, 3f

	 fzero		%f32

	 fzero		%f32
@@ -301,8 +302,9 @@ cplus_fptrap_insn_2: 
	fmuld		%f32, %f34, %f58

	fmuld		%f32, %f34, %f58

	faddd		%f32, %f34, %f60

	faddd		%f32, %f34, %f60

	fmuld		%f32, %f34, %f62

	fmuld		%f32, %f34, %f62

	ba,pt		%xcc, fpdis_exit

	membar		#Sync

	membar		#Sync

	ba,pt		%xcc, fpdis_exit

	 nop

3:	mov		SECONDARY_CONTEXT, %g3

3:	mov		SECONDARY_CONTEXT, %g3

	add		%g6, TI_FPREGS, %g1

	add		%g6, TI_FPREGS, %g1

	ldxa		[%g3] ASI_DMMU, %g5

	ldxa		[%g3] ASI_DMMU, %g5

arch/sparc64/kernel/semaphore.c

+8 −4
Original line number Original line Diff line number Diff line
@@ -32,8 +32,9 @@ static __inline__ int __sem_update_count(struct semaphore *sem, int incr) 
"	add	%1, %4, %1\n"

"	add	%1, %4, %1\n"

"	cas	[%3], %0, %1\n"

"	cas	[%3], %0, %1\n"

"	cmp	%0, %1\n"

"	cmp	%0, %1\n"

"	bne,pn	%%icc, 1b\n"

"	membar	#StoreLoad | #StoreStore\n"

"	membar	#StoreLoad | #StoreStore\n"

"	bne,pn	%%icc, 1b\n"

"	 nop\n"

	: "=&r" (old_count), "=&r" (tmp), "=m" (sem->count)

	: "=&r" (old_count), "=&r" (tmp), "=m" (sem->count)

	: "r" (&sem->count), "r" (incr), "m" (sem->count)

	: "r" (&sem->count), "r" (incr), "m" (sem->count)

	: "cc");

	: "cc");
@@ -71,8 +72,9 @@ void up(struct semaphore *sem) 
"	cmp	%%g1, %%g7\n"

"	cmp	%%g1, %%g7\n"

"	bne,pn	%%icc, 1b\n"

"	bne,pn	%%icc, 1b\n"

"	 addcc	%%g7, 1, %%g0\n"

"	 addcc	%%g7, 1, %%g0\n"

"	ble,pn	%%icc, 3f\n"

"	membar	#StoreLoad | #StoreStore\n"

"	membar	#StoreLoad | #StoreStore\n"

"	ble,pn	%%icc, 3f\n"

"	 nop\n"

"2:\n"

"2:\n"

"	.subsection 2\n"

"	.subsection 2\n"

"3:	mov	%0, %%g1\n"

"3:	mov	%0, %%g1\n"
@@ -128,8 +130,9 @@ void __sched down(struct semaphore *sem) 
"	cmp	%%g1, %%g7\n"

"	cmp	%%g1, %%g7\n"

"	bne,pn	%%icc, 1b\n"

"	bne,pn	%%icc, 1b\n"

"	 cmp	%%g7, 1\n"

"	 cmp	%%g7, 1\n"

"	bl,pn	%%icc, 3f\n"

"	membar	#StoreLoad | #StoreStore\n"

"	membar	#StoreLoad | #StoreStore\n"

"	bl,pn	%%icc, 3f\n"

"	 nop\n"

"2:\n"

"2:\n"

"	.subsection 2\n"

"	.subsection 2\n"

"3:	mov	%0, %%g1\n"

"3:	mov	%0, %%g1\n"
@@ -233,8 +236,9 @@ int __sched down_interruptible(struct semaphore *sem) 
"	cmp	%%g1, %%g7\n"

"	cmp	%%g1, %%g7\n"

"	bne,pn	%%icc, 1b\n"

"	bne,pn	%%icc, 1b\n"

"	 cmp	%%g7, 1\n"

"	 cmp	%%g7, 1\n"

"	bl,pn	%%icc, 3f\n"

"	membar	#StoreLoad | #StoreStore\n"

"	membar	#StoreLoad | #StoreStore\n"

"	bl,pn	%%icc, 3f\n"

"	 nop\n"

"2:\n"

"2:\n"

"	.subsection 2\n"

"	.subsection 2\n"

"3:	mov	%2, %%g1\n"

"3:	mov	%2, %%g1\n"

arch/sparc64/kernel/trampoline.S

+2 −1
Original line number Original line Diff line number Diff line
@@ -98,8 +98,9 @@ startup_continue: 




	sethi		%hi(prom_entry_lock), %g2

	sethi		%hi(prom_entry_lock), %g2

1:	ldstub		[%g2 + %lo(prom_entry_lock)], %g1

1:	ldstub		[%g2 + %lo(prom_entry_lock)], %g1

	brnz,pn		%g1, 1b

	membar		#StoreLoad | #StoreStore

	membar		#StoreLoad | #StoreStore

	brnz,pn		%g1, 1b

	 nop





	sethi		%hi(p1275buf), %g2

	sethi		%hi(p1275buf), %g2

	or		%g2, %lo(p1275buf), %g2

	or		%g2, %lo(p1275buf), %g2

arch/sparc64/lib/U1memcpy.S

+53 −50
Original line number Original line Diff line number Diff line
@@ -87,14 +87,17 @@ 
#define LOOP_CHUNK3(src, dest, len, branch_dest)		\

#define LOOP_CHUNK3(src, dest, len, branch_dest)		\

	MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)

	MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)





#define DO_SYNC			membar	#Sync;

#define STORE_SYNC(dest, fsrc)				\

#define STORE_SYNC(dest, fsrc)				\

	EX_ST(STORE_BLK(%fsrc, %dest));			\

	EX_ST(STORE_BLK(%fsrc, %dest));			\

	add			%dest, 0x40, %dest;

	add			%dest, 0x40, %dest;	\

	DO_SYNC





#define STORE_JUMP(dest, fsrc, target)			\

#define STORE_JUMP(dest, fsrc, target)			\

	EX_ST(STORE_BLK(%fsrc, %dest));			\

	EX_ST(STORE_BLK(%fsrc, %dest));			\

	add			%dest, 0x40, %dest;	\

	add			%dest, 0x40, %dest;	\

	ba,pt			%xcc, target;

	ba,pt			%xcc, target;		\

	 nop;





#define FINISH_VISCHUNK(dest, f0, f1, left)	\

#define FINISH_VISCHUNK(dest, f0, f1, left)	\

	subcc			%left, 8, %left;\

	subcc			%left, 8, %left;\
@@ -239,17 +242,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f0, %f2, %f48

	 faligndata	%f0, %f2, %f48

1:	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)

1:	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)

	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)

	STORE_JUMP(o0, f48, 40f) membar #Sync

	STORE_JUMP(o0, f48, 40f)

2:	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)

2:	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)

	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)

	STORE_JUMP(o0, f48, 48f) membar #Sync

	STORE_JUMP(o0, f48, 48f)

3:	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)

3:	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)

	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)

	STORE_JUMP(o0, f48, 56f) membar #Sync

	STORE_JUMP(o0, f48, 56f)





1:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)

1:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -260,17 +263,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f2, %f4, %f48

	 faligndata	%f2, %f4, %f48

1:	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)

1:	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)

	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)

	STORE_JUMP(o0, f48, 41f) membar #Sync

	STORE_JUMP(o0, f48, 41f)

2:	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)

2:	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)

	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)

	STORE_JUMP(o0, f48, 49f) membar #Sync

	STORE_JUMP(o0, f48, 49f)

3:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)

3:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)

	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)

	STORE_JUMP(o0, f48, 57f) membar #Sync

	STORE_JUMP(o0, f48, 57f)





1:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)

1:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -281,17 +284,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f4, %f6, %f48

	 faligndata	%f4, %f6, %f48

1:	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)

1:	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)

	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)

	STORE_JUMP(o0, f48, 42f) membar #Sync

	STORE_JUMP(o0, f48, 42f)

2:	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)

2:	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)

	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)

	STORE_JUMP(o0, f48, 50f) membar #Sync

	STORE_JUMP(o0, f48, 50f)

3:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)

3:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)

	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)

	STORE_JUMP(o0, f48, 58f) membar #Sync

	STORE_JUMP(o0, f48, 58f)





1:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)

1:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -302,17 +305,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f6, %f8, %f48

	 faligndata	%f6, %f8, %f48

1:	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)

1:	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)

	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)

	STORE_JUMP(o0, f48, 43f) membar #Sync

	STORE_JUMP(o0, f48, 43f)

2:	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)

2:	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)

	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)

	STORE_JUMP(o0, f48, 51f) membar #Sync

	STORE_JUMP(o0, f48, 51f)

3:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)

3:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)

	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)

	STORE_JUMP(o0, f48, 59f) membar #Sync

	STORE_JUMP(o0, f48, 59f)





1:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)

1:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -323,17 +326,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f8, %f10, %f48

	 faligndata	%f8, %f10, %f48

1:	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)

1:	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)

	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)

	STORE_JUMP(o0, f48, 44f) membar #Sync

	STORE_JUMP(o0, f48, 44f)

2:	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)

2:	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)

	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)

	STORE_JUMP(o0, f48, 52f) membar #Sync

	STORE_JUMP(o0, f48, 52f)

3:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)

3:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)

	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)

	STORE_JUMP(o0, f48, 60f) membar #Sync

	STORE_JUMP(o0, f48, 60f)





1:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)

1:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -344,17 +347,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f10, %f12, %f48

	 faligndata	%f10, %f12, %f48

1:	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)

1:	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)

	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)

	STORE_JUMP(o0, f48, 45f) membar #Sync

	STORE_JUMP(o0, f48, 45f)

2:	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)

2:	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)

	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)

	STORE_JUMP(o0, f48, 53f) membar #Sync

	STORE_JUMP(o0, f48, 53f)

3:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)

3:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)

	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)

	STORE_JUMP(o0, f48, 61f) membar #Sync

	STORE_JUMP(o0, f48, 61f)





1:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)

1:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -365,17 +368,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f12, %f14, %f48

	 faligndata	%f12, %f14, %f48

1:	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)

1:	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)

	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)

	STORE_JUMP(o0, f48, 46f) membar #Sync

	STORE_JUMP(o0, f48, 46f)

2:	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)

2:	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)

	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)

	STORE_JUMP(o0, f48, 54f) membar #Sync

	STORE_JUMP(o0, f48, 54f)

3:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)

3:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)

	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)

	STORE_JUMP(o0, f48, 62f) membar #Sync

	STORE_JUMP(o0, f48, 62f)





1:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)

1:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)

	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -386,17 +389,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 
	ba,pt		%xcc, 1b+4

	ba,pt		%xcc, 1b+4

	 faligndata	%f14, %f16, %f48

	 faligndata	%f14, %f16, %f48

1:	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)

1:	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)

	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)

	STORE_JUMP(o0, f48, 47f) membar #Sync

	STORE_JUMP(o0, f48, 47f)

2:	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)

2:	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)

	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)

	STORE_JUMP(o0, f48, 55f) membar #Sync

	STORE_JUMP(o0, f48, 55f)

3:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)

3:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)

	STORE_SYNC(o0, f48) membar #Sync

	STORE_SYNC(o0, f48)

	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)

	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)

	STORE_JUMP(o0, f48, 63f) membar #Sync

	STORE_JUMP(o0, f48, 63f)





40:	FINISH_VISCHUNK(o0, f0,  f2,  g3)

40:	FINISH_VISCHUNK(o0, f0,  f2,  g3)

41:	FINISH_VISCHUNK(o0, f2,  f4,  g3)

41:	FINISH_VISCHUNK(o0, f2,  f4,  g3)

arch/sparc64/lib/VISsave.S

+13 −2
Original line number Original line Diff line number Diff line
@@ -72,7 +72,11 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 




	stda		%f48, [%g3 + %g1] ASI_BLK_P

	stda		%f48, [%g3 + %g1] ASI_BLK_P

5:	membar		#Sync

5:	membar		#Sync

	jmpl		%g7 + %g0, %g0

	ba,pt		%xcc, 80f

	 nop



	.align		32

80:	jmpl		%g7 + %g0, %g0

	 nop

	 nop





6:	ldub		[%g3 + TI_FPSAVED], %o5

6:	ldub		[%g3 + TI_FPSAVED], %o5
@@ -87,8 +91,11 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 
	stda		%f32, [%g2 + %g1] ASI_BLK_P

	stda		%f32, [%g2 + %g1] ASI_BLK_P

	stda		%f48, [%g3 + %g1] ASI_BLK_P

	stda		%f48, [%g3 + %g1] ASI_BLK_P

	membar		#Sync

	membar		#Sync

	jmpl		%g7 + %g0, %g0

	ba,pt		%xcc, 80f

	 nop





	.align		32

80:	jmpl		%g7 + %g0, %g0

	 nop

	 nop





	.align		32

	.align		32
@@ -126,6 +133,10 @@ VISenterhalf: 
	stda		%f0, [%g2 + %g1] ASI_BLK_P

	stda		%f0, [%g2 + %g1] ASI_BLK_P

	stda		%f16, [%g3 + %g1] ASI_BLK_P

	stda		%f16, [%g3 + %g1] ASI_BLK_P

	membar		#Sync

	membar		#Sync

	ba,pt		%xcc, 4f

	 nop



	.align		32

4:	and		%o5, FPRS_DU, %o5

4:	and		%o5, FPRS_DU, %o5

	jmpl		%g7 + %g0, %g0

	jmpl		%g7 + %g0, %g0

	 wr		%o5, FPRS_FEF, %fprs
 
	 wr		%o5, FPRS_FEF, %fprs

CRA Git | Maintained and supported by SUSTech CRA and CCSE