Merge tag 'x86_urgent_for_v5.18_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Fix the MSI message data struct definition

 - Use local labels in the exception table macros to avoid symbol
   conflicts with clang LTO builds

 - A couple of fixes to objtool checking of the relatively newly added
   SLS and IBT code

 - Rename a local var in the WARN* macro machinery to prevent shadowing

* tag 'x86_urgent_for_v5.18_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/msi: Fix msi message data shadow struct
  x86/extable: Prefer local labels in .set directives
  x86,bpf: Avoid IBT objtool warning
  objtool: Fix SLS validation for kcov tail-call replacement
  objtool: Fix IBT tail-call detection
  x86/bug: Prevent shadowing in __WARN_FLAGS
  x86/mm/tlb: Revert retpoline avoidance approach

6 files changed, 54 insertions, 57 deletions

diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index c878fed3056f..fbcfec4dc4cc 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -154,24 +154,24 @@
 
 # define DEFINE_EXTABLE_TYPE_REG \
 	".macro extable_type_reg type:req reg:req\n"						\
-	".set found, 0\n"									\
-	".set regnr, 0\n"									\
+	".set .Lfound, 0\n"									\
+	".set .Lregnr, 0\n"									\
 	".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n"		\
 	".ifc \\reg, %%\\rs\n"									\
-	".set found, found+1\n"									\
-	".long \\type + (regnr << 8)\n"								\
+	".set .Lfound, .Lfound+1\n"								\
+	".long \\type + (.Lregnr << 8)\n"							\
 	".endif\n"										\
-	".set regnr, regnr+1\n"									\
+	".set .Lregnr, .Lregnr+1\n"								\
 	".endr\n"										\
-	".set regnr, 0\n"									\
+	".set .Lregnr, 0\n"									\
 	".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n"	\
 	".ifc \\reg, %%\\rs\n"									\
-	".set found, found+1\n"									\
-	".long \\type + (regnr << 8)\n"								\
+	".set .Lfound, .Lfound+1\n"								\
+	".long \\type + (.Lregnr << 8)\n"							\
 	".endif\n"										\
-	".set regnr, regnr+1\n"									\
+	".set .Lregnr, .Lregnr+1\n"								\
 	".endr\n"										\
-	".if (found != 1)\n"									\
+	".if (.Lfound != 1)\n"									\
 	".error \"extable_type_reg: bad register argument\"\n"					\
 	".endif\n"										\
 	".endm\n"
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 4d20a293c6fd..aaf0cb0db4ae 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -78,9 +78,9 @@ do {								\
  */
 #define __WARN_FLAGS(flags)					\
 do {								\
-	__auto_type f = BUGFLAG_WARNING|(flags);		\
+	__auto_type __flags = BUGFLAG_WARNING|(flags);		\
 	instrumentation_begin();				\
-	_BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE);			\
+	_BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE);		\
 	instrumentation_end();					\
 } while (0)
 
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
index b85147d75626..d71c7e8b738d 100644
--- a/arch/x86/include/asm/msi.h
+++ b/arch/x86/include/asm/msi.h
@@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 /* Structs and defines for the X86 specific MSI message format */
 
 typedef struct x86_msi_data {
-	u32	vector			:  8,
-		delivery_mode		:  3,
-		dest_mode_logical	:  1,
-		reserved		:  2,
-		active_low		:  1,
-		is_level		:  1;
-
-	u32	dmar_subhandle;
+	union {
+		struct {
+			u32	vector			:  8,
+				delivery_mode		:  3,
+				dest_mode_logical	:  1,
+				reserved		:  2,
+				active_low		:  1,
+				is_level		:  1;
+		};
+		u32	dmar_subhandle;
+	};
 } __attribute__ ((packed)) arch_msi_msg_data_t;
 #define arch_msi_msg_data	x86_msi_data
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6eb4d91d5365..d400b6d9d246 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -855,13 +855,11 @@ done:
 			nr_invalidate);
 }
 
-static bool tlb_is_not_lazy(int cpu)
+static bool tlb_is_not_lazy(int cpu, void *data)
 {
 	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
 }
 
-static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
-
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
 EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);
 
@@ -890,36 +888,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables) {
+	if (info->freed_tables)
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
-	} else {
-		/*
-		 * Although we could have used on_each_cpu_cond_mask(),
-		 * open-coding it has performance advantages, as it eliminates
-		 * the need for indirect calls or retpolines. In addition, it
-		 * allows to use a designated cpumask for evaluating the
-		 * condition, instead of allocating one.
-		 *
-		 * This code works under the assumption that there are no nested
-		 * TLB flushes, an assumption that is already made in
-		 * flush_tlb_mm_range().
-		 *
-		 * cond_cpumask is logically a stack-local variable, but it is
-		 * more efficient to have it off the stack and not to allocate
-		 * it on demand. Preemption is disabled and this code is
-		 * non-reentrant.
-		 */
-		struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask);
-		int cpu;
-
-		cpumask_clear(cond_cpumask);
-
-		for_each_cpu(cpu, cpumask) {
-			if (tlb_is_not_lazy(cpu))
-				__cpumask_set_cpu(cpu, cond_cpumask);
-		}
-		on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true);
-	}
+	else
+		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
+				(void *)info, 1, cpumask);
 }
 
 void flush_tlb_multi(const struct cpumask *cpumask,
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8fe35ed11fd6..16b6efacf7c6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -412,6 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 		EMIT_LFENCE();
 		EMIT2(0xFF, 0xE0 + reg);
 	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
+		OPTIMIZER_HIDE_VAR(reg);
 		emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
 	} else
 #endif
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 6de5085e3e5a..bd0c2c828940 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1155,6 +1155,17 @@ static void annotate_call_site(struct objtool_file *file,
 			               : arch_nop_insn(insn->len));
 
 		insn->type = sibling ? INSN_RETURN : INSN_NOP;
+
+		if (sibling) {
+			/*
+			 * We've replaced the tail-call JMP insn by two new
+			 * insn: RET; INT3, except we only have a single struct
+			 * insn here. Mark it retpoline_safe to avoid the SLS
+			 * warning, instead of adding another insn.
+			 */
+			insn->retpoline_safe = true;
+		}
+
 		return;
 	}
 
@@ -1239,11 +1250,20 @@ static bool same_function(struct instruction *insn1, struct instruction *insn2)
 	return insn1->func->pfunc == insn2->func->pfunc;
 }
 
-static bool is_first_func_insn(struct instruction *insn)
+static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn)
 {
-	return insn->offset == insn->func->offset ||
-	       (insn->type == INSN_ENDBR &&
-		insn->offset == insn->func->offset + insn->len);
+	if (insn->offset == insn->func->offset)
+		return true;
+
+	if (ibt) {
+		struct instruction *prev = prev_insn_same_sym(file, insn);
+
+		if (prev && prev->type == INSN_ENDBR &&
+		    insn->offset == insn->func->offset + prev->len)
+			return true;
+	}
+
+	return false;
 }
 
 /*
@@ -1327,7 +1347,7 @@ static int add_jump_destinations(struct objtool_file *file)
 				insn->jump_dest->func->pfunc = insn->func;
 
 			} else if (!same_function(insn, insn->jump_dest) &&
-				   is_first_func_insn(insn->jump_dest)) {
+				   is_first_func_insn(file, insn->jump_dest)) {
 				/* internal sibling call (without reloc) */
 				add_call_dest(file, insn, insn->jump_dest->func, true);
 			}