Merge branch 'tip/x86/urgent'

Merge the x86/urgent objtool/IBT changes as a base
Signed-off-by: Peter Zijlstra <peterz@infradead.org>

MAINTAINERS

@@ -21434,6 +21434,15 @@ F:	arch/x86/include/asm/uv/
 F:	arch/x86/kernel/apic/x2apic_uv_x.c
 F:	arch/x86/platform/uv/
 
+X86 STACK UNWINDING
+M:	Josh Poimboeuf <jpoimboe@redhat.com>
+M:	Peter Zijlstra <peterz@infradead.org>
+S:	Supported
+F:	arch/x86/include/asm/unwind*.h
+F:	arch/x86/kernel/dumpstack.c
+F:	arch/x86/kernel/stacktrace.c
+F:	arch/x86/kernel/unwind_*.c
+
 X86 VDSO
 M:	Andy Lutomirski <luto@kernel.org>
 L:	linux-kernel@vger.kernel.org

arch/x86/Kconfig

@@ -1866,7 +1866,7 @@ config X86_KERNEL_IBT
 	  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.
+	  are not indirect call targets, avoiding them ever becoming one.
 
 	  This requires LTO like objtool runs and will slow down the build. It
 	  does significantly reduce the number of ENDBR instructions in the

arch/x86/entry/entry_64.S

@@ -337,6 +337,9 @@ SYM_CODE_END(ret_from_fork)
 
 	call	\cfunc
 
+	/* For some configurations \cfunc ends up being a noreturn. */
+	REACHABLE
+
 	jmp	error_return
 .endm
 

arch/x86/include/asm/intel-family.h

@@ -26,6 +26,7 @@
  *		_G	- parts with extra graphics on
  *		_X	- regular server parts
  *		_D	- micro server parts
+ *		_N,_P	- other mobile parts
  *
  *		Historical OPTDIFFs:
  *
@@ -107,8 +108,10 @@
 
 #define INTEL_FAM6_ALDERLAKE		0x97	/* Golden Cove / Gracemont */
 #define INTEL_FAM6_ALDERLAKE_L		0x9A	/* Golden Cove / Gracemont */
+#define INTEL_FAM6_ALDERLAKE_N		0xBE
 
 #define INTEL_FAM6_RAPTORLAKE		0xB7
+#define INTEL_FAM6_RAPTORLAKE_P		0xBA
 
 /* "Small Core" Processors (Atom) */
 

arch/x86/include/asm/microcode.h

@@ -131,10 +131,12 @@ extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 void reload_early_microcode(void);
 extern bool initrd_gone;
+void microcode_bsp_resume(void);
 #else
 static inline void __init load_ucode_bsp(void)			{ }
 static inline void load_ucode_ap(void)				{ }
 static inline void reload_early_microcode(void)			{ }
+static inline void microcode_bsp_resume(void)			{ }
 #endif
 
 #endif /* _ASM_X86_MICROCODE_H */

arch/x86/include/asm/static_call.h

@@ -26,6 +26,7 @@
 	    ".align 4						\n"	\
 	    ".globl " STATIC_CALL_TRAMP_STR(name) "		\n"	\
 	    STATIC_CALL_TRAMP_STR(name) ":			\n"	\
+	    ANNOTATE_NOENDBR						\
 	    insns "						\n"	\
 	    ".byte 0x53, 0x43, 0x54				\n"	\
 	    ".type " STATIC_CALL_TRAMP_STR(name) ", @function	\n"	\

arch/x86/kernel/cpu/microcode/core.c

@@ -758,9 +758,9 @@ static struct subsys_interface mc_cpu_interface = {
 };
 
 /**
- * mc_bp_resume - Update boot CPU microcode during resume.
+ * microcode_bsp_resume - Update boot CPU microcode during resume.
  */
-static void mc_bp_resume(void)
+void microcode_bsp_resume(void)
 {
 	int cpu = smp_processor_id();
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
@@ -772,7 +772,7 @@ static void mc_bp_resume(void)
 }
 
 static struct syscore_ops mc_syscore_ops = {
-	.resume			= mc_bp_resume,
+	.resume			= microcode_bsp_resume,
 };
 
 static int mc_cpu_starting(unsigned int cpu)

arch/x86/kernel/unwind_orc.c

@@ -339,11 +339,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
 	struct stack_info *info = &state->stack_info;
 	void *addr = (void *)_addr;
 
-	if (!on_stack(info, addr, len) &&
-	    (get_stack_info(addr, state->task, info, &state->stack_mask)))
-		return false;
+	if (on_stack(info, addr, len))
+		return true;
 
-	return true;
+	return !get_stack_info(addr, state->task, info, &state->stack_mask) &&
+		on_stack(info, addr, len);
 }
 
 static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,

arch/x86/lib/putuser.S

@@ -48,6 +48,7 @@ SYM_FUNC_START(__put_user_1)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL)
+	ENDBR
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -62,6 +63,7 @@ SYM_FUNC_START(__put_user_2)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL)
+	ENDBR
 	ASM_STAC
 2:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -76,6 +78,7 @@ SYM_FUNC_START(__put_user_4)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL)
+	ENDBR
 	ASM_STAC
 3:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -90,6 +93,7 @@ SYM_FUNC_START(__put_user_8)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL)
+	ENDBR
 	ASM_STAC
 4:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32

arch/x86/lib/retpoline.S

@@ -31,6 +31,7 @@
 	.align RETPOLINE_THUNK_SIZE
 SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
 	UNWIND_HINT_EMPTY
+	ANNOTATE_NOENDBR
 
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
 		      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
@@ -55,7 +56,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
 
 	.align RETPOLINE_THUNK_SIZE
 SYM_CODE_START(__x86_indirect_thunk_array)
-	ANNOTATE_NOENDBR // apply_retpolines
 
 #define GEN(reg) THUNK reg
 #include <asm/GEN-for-each-reg.h>

arch/x86/platform/pvh/head.S

@@ -50,6 +50,7 @@
 #define PVH_DS_SEL		(PVH_GDT_ENTRY_DS * 8)
 
 SYM_CODE_START_LOCAL(pvh_start_xen)
+	UNWIND_HINT_EMPTY
 	cld
 
 	lgdt (_pa(gdt))

arch/x86/power/cpu.c

@@ -25,6 +25,7 @@
 #include <asm/cpu.h>
 #include <asm/mmu_context.h>
 #include <asm/cpu_device_id.h>
+#include <asm/microcode.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -262,11 +263,18 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
 	perf_restore_debug_store();
-	msr_restore_context(ctxt);
 
 	c = &cpu_data(smp_processor_id());
 	if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL))
 		init_ia32_feat_ctl(c);
+
+	microcode_bsp_resume();
+
+	/*
+	 * This needs to happen after the microcode has been updated upon resume
+	 * because some of the MSRs are "emulated" in microcode.
+	 */
+	msr_restore_context(ctxt);
 }
 
 /* Needed by apm.c */

arch/x86/xen/xen-head.S

@@ -45,6 +45,7 @@ SYM_CODE_END(hypercall_page)
 	__INIT
 SYM_CODE_START(startup_xen)
 	UNWIND_HINT_EMPTY
+	ANNOTATE_NOENDBR
 	cld
 
 	/* Clear .bss */

include/linux/cpu.h

@@ -167,7 +167,7 @@ static inline int suspend_disable_secondary_cpus(void) { return 0; }
 static inline void suspend_enable_secondary_cpus(void) { }
 #endif /* !CONFIG_PM_SLEEP_SMP */
 
-void cpu_startup_entry(enum cpuhp_state state);
+void __noreturn cpu_startup_entry(enum cpuhp_state state);
 
 void cpu_idle_poll_ctrl(bool enable);
 

lib/strncpy_from_user.c

@@ -25,7 +25,7 @@
  * hit it), 'max' is the address space maximum (and we return
  * -EFAULT if we hit it).
  */
-static inline long do_strncpy_from_user(char *dst, const char __user *src,
+static __always_inline long do_strncpy_from_user(char *dst, const char __user *src,
 					unsigned long count, unsigned long max)
 {
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;

lib/strnlen_user.c

@@ -20,7 +20,7 @@
  * if it fits in a aligned 'long'. The caller needs to check
  * the return value against "> max".
  */
-static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
+static __always_inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
 {
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
 	unsigned long align, res = 0;

scripts/Makefile.build

@@ -231,7 +231,7 @@ objtool_args =								\
 	$(if $(part-of-module), --module)				\
 	$(if $(CONFIG_X86_KERNEL_IBT), --lto --ibt)			\
 	$(if $(CONFIG_FRAME_POINTER),, --no-fp)				\
-	$(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\
+	$(if $(CONFIG_GCOV_KERNEL), --no-unreachable)			\
 	$(if $(CONFIG_RETPOLINE), --retpoline)				\
 	$(if $(CONFIG_X86_SMAP), --uaccess)				\
 	$(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount)		\

scripts/link-vmlinux.sh

@@ -140,7 +140,7 @@ objtool_link()
 		if ! is_enabled CONFIG_FRAME_POINTER; then
 			objtoolopt="${objtoolopt} --no-fp"
 		fi
-		if is_enabled CONFIG_GCOV_KERNEL || is_enabled CONFIG_LTO_CLANG; then
+		if is_enabled CONFIG_GCOV_KERNEL; then
 			objtoolopt="${objtoolopt} --no-unreachable"
 		fi
 		if is_enabled CONFIG_RETPOLINE; then

tools/objtool/check.c

@@ -184,6 +184,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"do_group_exit",
 		"stop_this_cpu",
 		"__invalid_creds",
+               "cpu_startup_entry",
 	};
 
 	if (!func)
@@ -3217,9 +3218,8 @@ validate_ibt_reloc(struct objtool_file *file, struct reloc *reloc)
 static void warn_noendbr(const char *msg, struct section *sec, unsigned long offset,
 			 struct instruction *dest)
 {
-	WARN_FUNC("%srelocation to !ENDBR: %s+0x%lx", sec, offset, msg,
-		  dest->func ? dest->func->name : dest->sec->name,
-		  dest->func ? dest->offset - dest->func->offset : dest->offset);
+	WARN_FUNC("%srelocation to !ENDBR: %s", sec, offset, msg,
+		  offstr(dest->sec, dest->offset));
 }
 
 static void validate_ibt_dest(struct objtool_file *file, struct instruction *insn,
@@ -3823,11 +3823,8 @@ static int validate_ibt(struct objtool_file *file)
 			struct instruction *dest;
 
 			dest = validate_ibt_reloc(file, reloc);
-			if (is_data && dest && !dest->noendbr) {
-				warn_noendbr("data ", reloc->sym->sec,
-					     reloc->sym->offset + reloc->addend,
-					     dest);
-			}
+			if (is_data && dest && !dest->noendbr)
+				warn_noendbr("data ", sec, reloc->offset, dest);
 		}
 	}