ARC: dw2 unwind: enable cfi pseudo ops in string lib

This uses a new set of annoations viz. ENTRY_CFI/END_CFI to enabel cfi
ops generation.

Note that we didn't change the normal ENTRY/EXIT as we don't actually
want unwind info in the trap/exception/interrutp handlers which use
these, as unwinder then gets confused (it keeps recursing vs. stopping).
Semantically these are leaf routines and unwinding should stop when it
hits those routines.

Before
------

    28.52%     1.19%          9929  hackbench  libuClibc-1.0.17.so   [.] __write_nocancel
            |
            ---__write_nocancel
               |--8.95%--EV_Trap
               |           --8.25%--sys_write
               |                     |--3.93%--sock_write_iter
     ...
               |--2.62%--memset   <==== [LEAF entry as no unwind info]
                         ^^^^^^

After
-----

    29.46%     1.24%         13622  hackbench  libuClibc-1.0.17.so   [.] __write_nocancel
            |
            ---__write_nocancel
               |--9.31%--EV_Trap
               |           --8.62%--sys_write
               |                     |--4.17%--sock_write_iter
     ...
               |--6.19%--sys_write
               |           --6.19%--sock_write_iter
               |                     unix_stream_sendmsg
               |                     |--1.62%--sock_alloc_send_pskb
               |                     |--0.89%--sock_def_readable
               |                     |--0.88%--_raw_spin_unlock_irqrestore
               |                     |--0.69%--memset
               |                     |         ^^^^^^     <==== [now in proper callframe]
               |                     |
               |                      --0.52%--skb_copy_datagram_from_iter

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

arch/arc/kernel/ctx_sw_asm.S

@@ -23,6 +23,7 @@
 	.global __switch_to
 	.type   __switch_to, @function
 __switch_to:
+	CFI_STARTPROC
 
 	/* Save regs on kernel mode stack of task */
 	st.a    blink, [sp, -4]
@@ -59,4 +60,4 @@ __switch_to:
 	ld.ab   blink, [sp, 4]
 	j       [blink]
 
-END(__switch_to)
+END_CFI(__switch_to)

arch/arc/lib/memcmp.S

@@ -16,7 +16,7 @@
 #define SHIFT r2
 #endif
 
-ENTRY(memcmp)
+ENTRY_CFI(memcmp)
 	or	r12,r0,r1
 	asl_s	r12,r12,30
 	sub	r3,r2,1
@@ -149,4 +149,4 @@ ENTRY(memcmp)
 .Lnil:
 	j_s.d	[blink]
 	mov	r0,0
-END(memcmp)
+END_CFI(memcmp)

arch/arc/lib/memcpy-700.S

@@ -8,7 +8,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(memcpy)
+ENTRY_CFI(memcpy)
 	or	r3,r0,r1
 	asl_s	r3,r3,30
 	mov_s	r5,r0
@@ -63,4 +63,4 @@ ENTRY(memcpy)
 .Lendbloop:
 	j_s.d	[blink]
 	stb	r12,[r5,0]
-END(memcpy)
+END_CFI(memcpy)

arch/arc/lib/memcpy-archs.S

@@ -40,7 +40,7 @@
 # define ZOLAND			0xF
 #endif
 
-ENTRY(memcpy)
+ENTRY_CFI(memcpy)
 	prefetch [r1]		; Prefetch the read location
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
@@ -233,4 +233,4 @@ ENTRY(memcpy)
 .Lcopybytewise_3:
 	j	[blink]
 
-END(memcpy)
+END_CFI(memcpy)

arch/arc/lib/memset-archs.S

@@ -10,7 +10,7 @@
 
 #undef PREALLOC_NOT_AVAIL
 
-ENTRY(memset)
+ENTRY_CFI(memset)
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
 ;;; if size is zero
@@ -112,11 +112,11 @@ ENTRY(memset)
 
 	j	[blink]
 
-END(memset)
+END_CFI(memset)
 
-ENTRY(memzero)
+ENTRY_CFI(memzero)
     ; adjust bzero args to memset args
     mov r2, r1
     b.d  memset    ;tail call so need to tinker with blink
     mov r1, 0
-END(memzero)
+END_CFI(memzero)

arch/arc/lib/memset.S

@@ -10,7 +10,7 @@
 
 #define SMALL	7 /* Must be at least 6 to deal with alignment/loop issues.  */
 
-ENTRY(memset)
+ENTRY_CFI(memset)
 	mov_s	r4,r0
 	or	r12,r0,r2
 	bmsk.f	r12,r12,1
@@ -46,14 +46,14 @@ ENTRY(memset)
 	stb.ab	r1,[r4,1]
 .Ltiny_end:
 	j_s	[blink]
-END(memset)
+END_CFI(memset)
 
 ; memzero: @r0 = mem, @r1 = size_t
 ; memset:  @r0 = mem, @r1 = char, @r2 = size_t
 
-ENTRY(memzero)
+ENTRY_CFI(memzero)
     ; adjust bzero args to memset args
     mov r2, r1
     mov r1, 0
     b  memset    ;tail call so need to tinker with blink
-END(memzero)
+END_CFI(memzero)

arch/arc/lib/strchr-700.S

@@ -13,7 +13,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strchr)
+ENTRY_CFI(strchr)
 	extb_s	r1,r1
 	asl	r5,r1,8
 	bmsk	r2,r0,1
@@ -130,4 +130,4 @@ ENTRY(strchr)
 	j_s.d	[blink]
 	mov.mi	r0,0
 #endif /* ENDIAN */
-END(strchr)
+END_CFI(strchr)

arch/arc/lib/strcmp-archs.S

@@ -8,7 +8,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strcmp)
+ENTRY_CFI(strcmp)
 	or	r2, r0, r1
 	bmsk_s	r2, r2, 1
 	brne	r2, 0, @.Lcharloop
@@ -75,4 +75,4 @@ ENTRY(strcmp)
 .Lcmpend:
 	j_s.d	[blink]
 	sub	r0, r2, r3
-END(strcmp)
+END_CFI(strcmp)

arch/arc/lib/strcmp.S

@@ -15,7 +15,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strcmp)
+ENTRY_CFI(strcmp)
 	or	r2,r0,r1
 	bmsk_s	r2,r2,1
 	brne	r2,0,.Lcharloop
@@ -93,4 +93,4 @@ ENTRY(strcmp)
 .Lcmpend:
 	j_s.d	[blink]
 	sub	r0,r2,r3
-END(strcmp)
+END_CFI(strcmp)

arch/arc/lib/strcpy-700.S

@@ -18,7 +18,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strcpy)
+ENTRY_CFI(strcpy)
 	or	r2,r0,r1
 	bmsk_s	r2,r2,1
 	brne.d	r2,0,charloop
@@ -67,4 +67,4 @@ charloop:
 	brne.d	r3,0,charloop
 	stb.ab	r3,[r10,1]
 	j	[blink]
-END(strcpy)
+END_CFI(strcpy)

arch/arc/lib/strlen.S

@@ -8,7 +8,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strlen)
+ENTRY_CFI(strlen)
 	or	r3,r0,7
 	ld	r2,[r3,-7]
 	ld.a	r6,[r3,-3]
@@ -80,4 +80,4 @@ ENTRY(strlen)
 .Learly_end:
 	b.d	.Lend
 	sub_s.ne r1,r1,r1
-END(strlen)
+END_CFI(strlen)