Index: llvm/lib/Analysis/InlineCost.cpp
===================================================================
--- llvm/lib/Analysis/InlineCost.cpp
+++ llvm/lib/Analysis/InlineCost.cpp
@@ -377,6 +377,10 @@
   /// Attempt to evaluate indirect calls to boost its inline cost.
   const bool BoostIndirectCalls;
 
+  /// If true, inlining may be more conservative to take the caller's
+  /// inlineability into account.
+  const bool CallerMayBeInlined;
+
   /// Inlining cost measured in abstract units, accounts for all the
   /// instructions expected to be executed for a given function invocation.
   /// Instructions that are statically proven to be dead based on call-site
@@ -626,12 +630,14 @@
       std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
       Optional<function_ref<BlockFrequencyInfo &(Function &)>> &GetBFI,
       ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE, Function &Callee,
-      CallBase &Call, const InlineParams &Params, bool BoostIndirect = true)
+      CallBase &Call, const InlineParams &Params, bool BoostIndirect = true,
+      bool CallerMayBeInlined = true)
       : CallAnalyzer(TTI, GetAssumptionCache, GetBFI, PSI, ORE, Callee, Call),
         ComputeFullInlineCost(OptComputeFullInlineCost ||
                               Params.ComputeFullInlineCost || ORE),
         Params(Params), Threshold(Params.DefaultThreshold),
-        BoostIndirectCalls(BoostIndirect) {}
+        BoostIndirectCalls(BoostIndirect),
+        CallerMayBeInlined(CallerMayBeInlined) {}
   void dump();
 
   virtual ~InlineCostCallAnalyzer() {}
@@ -1164,11 +1170,14 @@
   int VectorBonusPercent = TTI.getInlinerVectorBonusPercent();
   int LastCallToStaticBonus = InlineConstants::LastCallToStaticBonus;
 
-  // Lambda to set all the above bonus and bonus percentages to 0.
-  auto DisallowAllBonuses = [&]() {
-    SingleBBBonusPercent = 0;
-    VectorBonusPercent = 0;
-    LastCallToStaticBonus = 0;
+  // Lambda to set all the above bonus and bonus percentages to 0, if doing so
+  // might help us inline the caller elsewhere.
+  auto DisallowAllBonusesForCallerInlinability = [&]() {
+    if (CallerMayBeInlined) {
+      SingleBBBonusPercent = 0;
+      VectorBonusPercent = 0;
+      LastCallToStaticBonus = 0;
+    }
   };
 
   // Use the OptMinSizeThreshold or OptSizeThreshold knob if they are available
@@ -1212,7 +1221,7 @@
       // LastCallToStatic bonus. While this bonus might result in code size
       // reduction, it can cause the size of a non-cold caller to increase
       // preventing it from being inlined.
-      DisallowAllBonuses();
+      DisallowAllBonusesForCallerInlinability();
       Threshold = MinIfValid(Threshold, Params.ColdCallSiteThreshold);
     } else if (PSI) {
       // Use callee's global profile information only if we have no way of
@@ -1229,7 +1238,7 @@
         // LastCallToStatic bonus. While this bonus might result in code size
         // reduction, it can cause the size of a non-cold caller to increase
         // preventing it from being inlined.
-        DisallowAllBonuses();
+        DisallowAllBonusesForCallerInlinability();
         Threshold = MinIfValid(Threshold, Params.ColdThreshold);
       }
     }
@@ -2173,11 +2182,17 @@
   if (Call.isNoInline())
     return llvm::InlineCost::getNever("noinline call site attribute");
 
+  // FIXME: use_begin() == use_end() only implies inlining isn't possible if
+  // we're not doing some form of LTO later.
+  bool CallerMayBeInlined = !(Caller->hasFnAttribute(Attribute::NoInline) ||
+                              Caller->use_begin() == Caller->use_end());
+
   LLVM_DEBUG(llvm::dbgs() << "      Analyzing call of " << Callee->getName()
                           << "... (caller:" << Caller->getName() << ")\n");
 
   InlineCostCallAnalyzer CA(CalleeTTI, GetAssumptionCache, GetBFI, PSI, ORE,
-                            *Callee, Call, Params);
+                            *Callee, Call, Params, /*BoostIndirect=*/true,
+                            CallerMayBeInlined);
   InlineResult ShouldInline = CA.analyze();
 
   LLVM_DEBUG(CA.dump());
Index: llvm/test/Transforms/Inline/bpi-cold-inlining.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Inline/bpi-cold-inlining.ll
@@ -0,0 +1,76 @@
+; RUN: opt < %s -passes=inline -inline-cold-callsite-threshold=0 -S | FileCheck %s
+
+declare void @foo(i32)
+
+@a = external global i1
+
+define internal void @callee1() {
+  call void @foo(i32 1)
+  ret void
+}
+
+; CHECK-LABEL: define void @not_inlined_if_cold
+define void @not_inlined_if_cold() {
+entry:
+  %a = load i1, i1* @a
+  br i1 %a, label %if.then, label %if.end, !prof !0
+
+if.then:
+  ; CHECK: call void @callee1()
+  call void @callee1()
+  br label %if.end
+
+if.end:
+  ; CHECK: ret void
+  ret void
+}
+
+@not_inlined_if_cold_addr = global void ()* @not_inlined_if_cold
+
+define internal void @callee2() {
+  call void @foo(i32 2)
+  ret void
+}
+
+; CHECK-LABEL: define void @gets_inlined_noinline_and_cold
+define void @gets_inlined_noinline_and_cold() #0 {
+entry:
+  %a = load i1, i1* @a
+  br i1 %a, label %if.then, label %if.end, !prof !0
+
+if.then:
+  ; CHECK: call void @foo(i32 2)
+  call void @callee2()
+  br label %if.end
+
+if.end:
+  ; CHECK: ret void
+  ret void
+}
+
+@gets_inlined_noinline_and_cold_addr = global void ()* @gets_inlined_noinline_and_cold
+
+define internal void @callee3() {
+  call void @foo(i32 3)
+  ret void
+}
+
+; CHECK-LABEL: define void @gets_inlined_no_uses_and_cold
+define void @gets_inlined_no_uses_and_cold() {
+entry:
+  %a = load i1, i1* @a
+  br i1 %a, label %if.then, label %if.end, !prof !0
+
+if.then:
+  ; CHECK: call void @foo(i32 3)
+  call void @callee3()
+  br label %if.end
+
+if.end:
+  ; CHECK: ret void
+  ret void
+}
+
+attributes #0 = { noinline }
+
+!0 = !{!"branch_weights", i32 1, i32 2000}