[BOLT] Explicitly check for returns when extending call continuation profile (#143295)

Call continuation logic relies on assumptions about fall-through origin:
- the branch is external to the function,
- fall-through start is at the beginning of the block,
- the block is not an entry point or a landing pad.

Leverage trace information to explicitly check whether the origin is a
return instruction, and defer to checks above only in case of
DSO-external branch source.

This covers both regular and BAT cases, addressing call continuation
fall-through undercounting in the latter mode, which improves BAT
profile quality metrics. For example, for one large binary:
- CFG discontinuity 21.83% -> 0.00%,
- CFG flow imbalance 10.77%/100.00% -> 3.40%/13.82% (weighted/worst)
- CG flow imbalance 8.49% —> 8.49%.

Depends on #143289.

Test Plan: updated callcont-fallthru.s

bolt/test/X86/callcont-fallthru.s

@@ -4,29 +4,43 @@
 # RUN: %clang %cflags -fpic -shared -xc /dev/null -o %t.so
 ## Link against a DSO to ensure PLT entries.
 # RUN: %clangxx %cxxflags %s %t.so -o %t -Wl,-q -nostdlib
-# RUN: link_fdata %s %t %t.pat PREAGGT1
-# RUN: link_fdata %s %t %t.pat2 PREAGGT2
-# RUN-DISABLED: link_fdata %s %t %t.patplt PREAGGPLT
+# Trace to a call continuation, not a landing pad/entry point
+# RUN: link_fdata %s %t %t.pa-base PREAGG-BASE
+# Trace from a return to a landing pad/entry point call continuation
+# RUN: link_fdata %s %t %t.pa-ret PREAGG-RET
+# Trace from an external location to a landing pad/entry point call continuation
+# RUN: link_fdata %s %t %t.pa-ext PREAGG-EXT
+# RUN-DISABLED: link_fdata %s %t %t.pa-plt PREAGG-PLT
 
 # RUN: llvm-strip --strip-unneeded %t -o %t.strip
 # RUN: llvm-objcopy --remove-section=.eh_frame %t.strip %t.noeh
 
 ## Check pre-aggregated traces attach call continuation fallthrough count
-# RUN: llvm-bolt %t.noeh --pa -p %t.pat -o %t.out \
-# RUN:   --print-cfg --print-only=main | FileCheck %s
+## in the basic case (not an entry point, not a landing pad).
+# RUN: llvm-bolt %t.noeh --pa -p %t.pa-base -o %t.out \
+# RUN:   --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK-BASE
 
-## Check pre-aggregated traces don't attach call continuation fallthrough count
-## to secondary entry point (unstripped)
-# RUN: llvm-bolt %t --pa -p %t.pat2 -o %t.out \
-# RUN:   --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK3
-## Check pre-aggregated traces don't attach call continuation fallthrough count
-## to landing pad (stripped, LP)
-# RUN: llvm-bolt %t.strip --pa -p %t.pat2 -o %t.out \
-# RUN:   --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK3
+## Check pre-aggregated traces from a return attach call continuation
+## fallthrough count to secondary entry point (unstripped)
+# RUN: llvm-bolt %t --pa -p %t.pa-ret -o %t.out \
+# RUN:   --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK-ATTACH
+## Check pre-aggregated traces from a return attach call continuation
+## fallthrough count to landing pad (stripped, landing pad)
+# RUN: llvm-bolt %t.strip --pa -p %t.pa-ret -o %t.out \
+# RUN:   --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK-ATTACH
+
+## Check pre-aggregated traces from external location don't attach call
+## continuation fallthrough count to secondary entry point (unstripped)
+# RUN: llvm-bolt %t --pa -p %t.pa-ext -o %t.out \
+# RUN:   --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK-SKIP
+## Check pre-aggregated traces from external location don't attach call
+## continuation fallthrough count to landing pad (stripped, landing pad)
+# RUN: llvm-bolt %t.strip --pa -p %t.pa-ext -o %t.out \
+# RUN:   --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK-SKIP
 
 ## Check pre-aggregated traces don't report zero-sized PLT fall-through as
 ## invalid trace
-# RUN-DISABLED: llvm-bolt %t.strip --pa -p %t.patplt -o %t.out | FileCheck %s \
+# RUN-DISABLED: llvm-bolt %t.strip --pa -p %t.pa-plt -o %t.out | FileCheck %s \
 # RUN-DISABLED:   --check-prefix=CHECK-PLT
 # CHECK-PLT: traces mismatching disassembled function contents: 0
 
@@ -56,11 +70,11 @@ main:
 Ltmp0_br:
 	callq	puts@PLT
 ## Check PLT traces are accepted
-# PREAGGPLT: T #Ltmp0_br# #puts@plt# #puts@plt# 3
+# PREAGG-PLT: T #Ltmp0_br# #puts@plt# #puts@plt# 3
 ## Target is an external-origin call continuation
-# PREAGGT1: T X:0 #Ltmp1# #Ltmp4_br# 2
-# CHECK:      callq puts@PLT
-# CHECK-NEXT: count: 2
+# PREAGG-BASE: T X:0 #Ltmp1# #Ltmp4_br# 2
+# CHECK-BASE:      callq puts@PLT
+# CHECK-BASE-NEXT: count: 2
 
 Ltmp1:
 	movq	-0x10(%rbp), %rax
@@ -71,24 +85,18 @@ Ltmp4:
 	cmpl	$0x0, -0x14(%rbp)
 Ltmp4_br:
 	je	Ltmp0
-# CHECK2:      je .Ltmp0
-# CHECK2-NEXT: count: 3
 
 	movl	$0xa, -0x18(%rbp)
 	callq	foo
 ## Target is a binary-local call continuation
-# PREAGGT1: T #Lfoo_ret# #Ltmp3# #Ltmp3_br# 1
-# CHECK:      callq foo
-# CHECK-NEXT: count: 1
-
-## PLT call continuation fallthrough spanning the call
-# CHECK2:      callq foo
-# CHECK2-NEXT: count: 3
-
+# PREAGG-RET: T #Lfoo_ret# #Ltmp3# #Ltmp3_br# 1
 ## Target is a secondary entry point (unstripped) or a landing pad (stripped)
-# PREAGGT2: T X:0 #Ltmp3# #Ltmp3_br# 2
-# CHECK3:      callq foo
-# CHECK3-NEXT: count: 0
+# PREAGG-EXT: T X:0 #Ltmp3# #Ltmp3_br# 1
+
+# CHECK-ATTACH:      callq foo
+# CHECK-ATTACH-NEXT: count: 1
+# CHECK-SKIP:        callq foo
+# CHECK-SKIP-NEXT:   count: 0
 
 Ltmp3:
 	cmpl	$0x0, -0x18(%rbp)