Merge tag 'x86_core_for_5.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 CET-IBT (Control-Flow-Integrity) support from Peter Zijlstra:
 "Add support for Intel CET-IBT, available since Tigerlake (11th gen),
  which is a coarse grained, hardware based, forward edge
  Control-Flow-Integrity mechanism where any indirect CALL/JMP must
  target an ENDBR instruction or suffer #CP.

  Additionally, since Alderlake (12th gen)/Sapphire-Rapids, speculation
  is limited to 2 instructions (and typically fewer) on branch targets
  not starting with ENDBR. CET-IBT also limits speculation of the next
  sequential instruction after the indirect CALL/JMP [1].

  CET-IBT is fundamentally incompatible with retpolines, but provides,
  as described above, speculation limits itself"

[1] https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html

* tag 'x86_core_for_5.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  kvm/emulate: Fix SETcc emulation for ENDBR
  x86/Kconfig: Only allow CONFIG_X86_KERNEL_IBT with ld.lld >= 14.0.0
  x86/Kconfig: Only enable CONFIG_CC_HAS_IBT for clang >= 14.0.0
  kbuild: Fixup the IBT kbuild changes
  x86/Kconfig: Do not allow CONFIG_X86_X32_ABI=y with llvm-objcopy
  x86: Remove toolchain check for X32 ABI capability
  x86/alternative: Use .ibt_endbr_seal to seal indirect calls
  objtool: Find unused ENDBR instructions
  objtool: Validate IBT assumptions
  objtool: Add IBT/ENDBR decoding
  objtool: Read the NOENDBR annotation
  x86: Annotate idtentry_df()
  x86,objtool: Move the ASM_REACHABLE annotation to objtool.h
  x86: Annotate call_on_stack()
  objtool: Rework ASM_REACHABLE
  x86: Mark __invalid_creds() __noreturn
  exit: Mark do_group_exit() __noreturn
  x86: Mark stop_this_cpu() __noreturn
  objtool: Ignore extra-symbol code
  objtool: Rename --duplicate to --lto
  ...

Author: torvalds

arch/powerpc/include/asm/livepatch.h

@@ -17,17 +17,6 @@ static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
 	ftrace_instruction_pointer_set(fregs, ip);
 }
 
-#define klp_get_ftrace_location klp_get_ftrace_location
-static inline unsigned long klp_get_ftrace_location(unsigned long faddr)
-{
-	/*
-	 * Live patch works on PPC32 and only with -mprofile-kernel on PPC64. In
-	 * both cases, the ftrace location is always within the first 16 bytes.
-	 */
-	return ftrace_location_range(faddr, faddr + 16);
-}
-#endif /* CONFIG_LIVEPATCH */
-
 #ifdef CONFIG_LIVEPATCH_64
 static inline void klp_init_thread_info(struct task_struct *p)
 {

arch/powerpc/kernel/kprobes.c

@@ -105,6 +105,27 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
 	return addr;
 }
 
+static bool arch_kprobe_on_func_entry(unsigned long offset)
+{
+#ifdef PPC64_ELF_ABI_v2
+#ifdef CONFIG_KPROBES_ON_FTRACE
+	return offset <= 16;
+#else
+	return offset <= 8;
+#endif
+#else
+	return !offset;
+#endif
+}
+
+/* XXX try and fold the magic of kprobe_lookup_name() in this */
+kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
+					 bool *on_func_entry)
+{
+	*on_func_entry = arch_kprobe_on_func_entry(offset);
+	return (kprobe_opcode_t *)(addr + offset);
+}
+
 void *alloc_insn_page(void)
 {
 	void *page;
@@ -218,19 +239,6 @@ static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs
 	kcb->kprobe_saved_msr = regs->msr;
 }
 
-bool arch_kprobe_on_func_entry(unsigned long offset)
-{
-#ifdef PPC64_ELF_ABI_v2
-#ifdef CONFIG_KPROBES_ON_FTRACE
-	return offset <= 16;
-#else
-	return offset <= 8;
-#endif
-#else
-	return !offset;
-#endif
-}
-
 void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->link;

arch/um/kernel/um_arch.c

@@ -424,6 +424,10 @@ void __init check_bugs(void)
 	os_check_bugs();
 }
 
+void apply_ibt_endbr(s32 *start, s32 *end)
+{
+}
+
 void apply_retpolines(s32 *start, s32 *end)
 {
 }

arch/x86/Kconfig

@@ -1842,6 +1842,36 @@ config X86_UMIP
 	  specific cases in protected and virtual-8086 modes. Emulated
 	  results are dummy.
 
+config CC_HAS_IBT
+	# GCC >= 9 and binutils >= 2.29
+	# Retpoline check to work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93654
+	# Clang/LLVM >= 14
+	# https://github.com/llvm/llvm-project/commit/e0b89df2e0f0130881bf6c39bf31d7f6aac00e0f
+	# https://github.com/llvm/llvm-project/commit/dfcf69770bc522b9e411c66454934a37c1f35332
+	def_bool ((CC_IS_GCC && $(cc-option, -fcf-protection=branch -mindirect-branch-register)) || \
+		  (CC_IS_CLANG && CLANG_VERSION >= 140000)) && \
+		  $(as-instr,endbr64)
+
+config X86_KERNEL_IBT
+	prompt "Indirect Branch Tracking"
+	bool
+	depends on X86_64 && CC_HAS_IBT && STACK_VALIDATION
+	# https://github.com/llvm/llvm-project/commit/9d7001eba9c4cb311e03cd8cdc231f9e579f2d0f
+	depends on !LD_IS_LLD || LLD_VERSION >= 140000
+	help
+	  Build the kernel with support for Indirect Branch Tracking, a
+	  hardware support course-grain forward-edge Control Flow Integrity
+	  protection. It enforces that all indirect calls must land on
+	  an ENDBR instruction, as such, the compiler will instrument the
+	  code with them to make this happen.
+
+	  In addition to building the kernel with IBT, seal all functions that
+	  are not indirect call targets, avoiding them ever becomming one.
+
+	  This requires LTO like objtool runs and will slow down the build. It
+	  does significantly reduce the number of ENDBR instructions in the
+	  kernel image.
+
 config X86_INTEL_MEMORY_PROTECTION_KEYS
 	prompt "Memory Protection Keys"
 	def_bool y
@@ -2815,19 +2845,20 @@ config IA32_AOUT
 	help
 	  Support old a.out binaries in the 32bit emulation.
 
-config X86_X32
+config X86_X32_ABI
 	bool "x32 ABI for 64-bit mode"
 	depends on X86_64
+	# llvm-objcopy does not convert x86_64 .note.gnu.property or
+	# compressed debug sections to x86_x32 properly:
+	# https://github.com/ClangBuiltLinux/linux/issues/514
+	# https://github.com/ClangBuiltLinux/linux/issues/1141
+	depends on $(success,$(OBJCOPY) --version | head -n1 | grep -qv llvm)
 	help
 	  Include code to run binaries for the x32 native 32-bit ABI
 	  for 64-bit processors.  An x32 process gets access to the
 	  full 64-bit register file and wide data path while leaving
 	  pointers at 32 bits for smaller memory footprint.
 
-	  You will need a recent binutils (2.22 or later) with
-	  elf32_x86_64 support enabled to compile a kernel with this
-	  option set.
-
 config COMPAT_32
 	def_bool y
 	depends on IA32_EMULATION || X86_32
@@ -2836,7 +2867,7 @@ config COMPAT_32
 
 config COMPAT
 	def_bool y
-	depends on IA32_EMULATION || X86_X32
+	depends on IA32_EMULATION || X86_X32_ABI
 
 if COMPAT
 config COMPAT_FOR_U64_ALIGNMENT

arch/x86/Makefile

@@ -36,7 +36,7 @@ endif
 
 # How to compile the 16-bit code.  Note we always compile for -march=i386;
 # that way we can complain to the user if the CPU is insufficient.
-REALMODE_CFLAGS	:= -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
+REALMODE_CFLAGS	:= -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \
 		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
@@ -62,8 +62,20 @@ export BITS
 #
 KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
 
-# Intel CET isn't enabled in the kernel
+ifeq ($(CONFIG_X86_KERNEL_IBT),y)
+#
+# Kernel IBT has S_CET.NOTRACK_EN=0, as such the compilers must not generate
+# NOTRACK prefixes. Current generation compilers unconditionally employ NOTRACK
+# for jump-tables, as such, disable jump-tables for now.
+#
+# (jump-tables are implicitly disabled by RETPOLINE)
+#
+#   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104816
+#
+KBUILD_CFLAGS += $(call cc-option,-fcf-protection=branch -fno-jump-tables)
+else
 KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
+endif
 
 ifeq ($(CONFIG_X86_32),y)
         BITS := 32
@@ -140,22 +152,6 @@ else
         KBUILD_CFLAGS += -mcmodel=kernel
 endif
 
-ifdef CONFIG_X86_X32
-	x32_ld_ok := $(call try-run,\
-			/bin/echo -e '1: .quad 1b' | \
-			$(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" - && \
-			$(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMP.o" && \
-			$(LD) -m elf32_x86_64 "$$TMP.o" -o "$$TMP",y,n)
-        ifeq ($(x32_ld_ok),y)
-                CONFIG_X86_X32_ABI := y
-                KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI
-                KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI
-        else
-                $(warning CONFIG_X86_X32 enabled but no binutils support)
-        endif
-endif
-export CONFIG_X86_X32_ABI
-
 #
 # If the function graph tracer is used with mcount instead of fentry,
 # '-maccumulate-outgoing-args' is needed to prevent a GCC bug

arch/x86/crypto/crc32c-pcl-intel-asm_64.S

@@ -195,6 +195,7 @@ crc_array:
 .altmacro
 LABEL crc_ %i
 .noaltmacro
+	ENDBR
 	crc32q   -i*8(block_0), crc_init
 	crc32q   -i*8(block_1), crc1
 	crc32q   -i*8(block_2), crc2
@@ -204,6 +205,7 @@ LABEL crc_ %i
 .altmacro
 LABEL crc_ %i
 .noaltmacro
+	ENDBR
 	crc32q   -i*8(block_0), crc_init
 	crc32q   -i*8(block_1), crc1
 # SKIP  crc32  -i*8(block_2), crc2 ; Don't do this one yet
@@ -237,6 +239,7 @@ LABEL crc_ %i
 	################################################################
 
 LABEL crc_ 0
+	ENDBR
 	mov     tmp, len
 	cmp     $128*24, tmp
 	jae     full_block

arch/x86/entry/entry_64.S

@@ -86,6 +86,7 @@
 
 SYM_CODE_START(entry_SYSCALL_64)
 	UNWIND_HINT_EMPTY
+	ENDBR
 
 	swapgs
 	/* tss.sp2 is scratch space. */
@@ -94,6 +95,7 @@ SYM_CODE_START(entry_SYSCALL_64)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
 
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS				/* pt_regs->ss */
@@ -276,6 +278,7 @@ SYM_FUNC_END(__switch_to_asm)
 .pushsection .text, "ax"
 SYM_CODE_START(ret_from_fork)
 	UNWIND_HINT_EMPTY
+	ANNOTATE_NOENDBR // copy_thread
 	movq	%rax, %rdi
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
@@ -350,6 +353,7 @@ SYM_CODE_END(ret_from_fork)
 .macro idtentry vector asmsym cfunc has_error_code:req
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
+	ENDBR
 	ASM_CLAC
 
 	.if \has_error_code == 0
@@ -417,6 +421,7 @@ SYM_CODE_END(\asmsym)
 .macro idtentry_mce_db vector asmsym cfunc
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
+	ENDBR
 	ASM_CLAC
 
 	pushq	$-1			/* ORIG_RAX: no syscall to restart */
@@ -472,6 +477,7 @@ SYM_CODE_END(\asmsym)
 .macro idtentry_vc vector asmsym cfunc
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
+	ENDBR
 	ASM_CLAC
 
 	/*
@@ -533,6 +539,7 @@ SYM_CODE_END(\asmsym)
 .macro idtentry_df vector asmsym cfunc
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=8
+	ENDBR
 	ASM_CLAC
 
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
@@ -544,6 +551,9 @@ SYM_CODE_START(\asmsym)
 	movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
 	call	\cfunc
 
+	/* For some configurations \cfunc ends up being a noreturn. */
+	REACHABLE
+
 	jmp	paranoid_exit
 
 _ASM_NOKPROBE(\asmsym)
@@ -564,6 +574,7 @@ __irqentry_text_start:
 	.align 16
 	.globl __irqentry_text_end
 __irqentry_text_end:
+	ANNOTATE_NOENDBR
 
 SYM_CODE_START_LOCAL(common_interrupt_return)
 SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
@@ -608,8 +619,8 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 
 	/* Restore RDI. */
 	popq	%rdi
-	SWAPGS
-	INTERRUPT_RETURN
+	swapgs
+	jmp	.Lnative_iret
 
 
 SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
@@ -626,9 +637,14 @@ SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
 	 * when returning from IPI handler.
 	 */
-	INTERRUPT_RETURN
+#ifdef CONFIG_XEN_PV
+SYM_INNER_LABEL(early_xen_iret_patch, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
+	.byte 0xe9
+	.long .Lnative_iret - (. + 4)
+#endif
 
-SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL)
+.Lnative_iret:
 	UNWIND_HINT_IRET_REGS
 	/*
 	 * Are we returning to a stack segment from the LDT?  Note: in
@@ -640,6 +656,7 @@ SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL)
 #endif
 
 SYM_INNER_LABEL(native_irq_return_iret, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR // exc_double_fault
 	/*
 	 * This may fault.  Non-paranoid faults on return to userspace are
 	 * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
@@ -734,6 +751,7 @@ SYM_FUNC_START(asm_load_gs_index)
 	FRAME_BEGIN
 	swapgs
 .Lgs_change:
+	ANNOTATE_NOENDBR // error_entry
 	movl	%edi, %gs
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
 	swapgs
@@ -804,6 +822,7 @@ SYM_CODE_END(exc_xen_hypervisor_callback)
  */
 SYM_CODE_START(xen_failsafe_callback)
 	UNWIND_HINT_EMPTY
+	ENDBR
 	movl	%ds, %ecx
 	cmpw	%cx, 0x10(%rsp)
 	jne	1f
@@ -1063,6 +1082,7 @@ SYM_CODE_END(error_return)
  */
 SYM_CODE_START(asm_exc_nmi)
 	UNWIND_HINT_IRET_REGS
+	ENDBR
 
 	/*
 	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
@@ -1310,6 +1330,7 @@ first_nmi:
 #endif
 
 repeat_nmi:
+	ANNOTATE_NOENDBR // this code
 	/*
 	 * If there was a nested NMI, the first NMI's iret will return
 	 * here. But NMIs are still enabled and we can take another
@@ -1338,6 +1359,7 @@ repeat_nmi:
 	.endr
 	subq	$(5*8), %rsp
 end_repeat_nmi:
+	ANNOTATE_NOENDBR // this code
 
 	/*
 	 * Everything below this point can be preempted by a nested NMI.
@@ -1421,6 +1443,7 @@ SYM_CODE_END(asm_exc_nmi)
  */
 SYM_CODE_START(ignore_sysret)
 	UNWIND_HINT_EMPTY
+	ENDBR
 	mov	$-ENOSYS, %eax
 	sysretl
 SYM_CODE_END(ignore_sysret)