Merge branch 'topic/objtool' into next

Merge the powerpc objtool support, which we were keeping in a topic
branch in case of any merge conflicts.

Makefile

@@ -933,7 +933,9 @@ ifdef CONFIG_FTRACE_MCOUNT_USE_CC
   endif
 endif
 ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL
-  CC_FLAGS_USING	+= -DCC_USING_NOP_MCOUNT
+  ifdef CONFIG_HAVE_OBJTOOL_NOP_MCOUNT
+    CC_FLAGS_USING	+= -DCC_USING_NOP_MCOUNT
+  endif
 endif
 ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
   ifdef CONFIG_HAVE_C_RECORDMCOUNT

arch/powerpc/Kconfig

@@ -241,6 +241,8 @@ config PPC
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI				if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
 	select HAVE_OPTPROBES
+	select HAVE_OBJTOOL			if PPC32 || MPROFILE_KERNEL
+	select HAVE_OBJTOOL_MCOUNT		if HAVE_OBJTOOL
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS

arch/powerpc/include/asm/asm.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_ASM_H
+#define _ASM_POWERPC_ASM_H
+
+#define _ASM_PTR	" .long "
+
+#endif /* _ASM_POWERPC_ASM_H */

arch/powerpc/include/asm/bug.h

@@ -99,7 +99,8 @@
 	__label__ __label_warn_on;				\
 								\
 	WARN_ENTRY("twi 31, 0, 0", BUGFLAG_WARNING | (flags), __label_warn_on); \
-	unreachable();						\
+	barrier_before_unreachable();				\
+	__builtin_unreachable();				\
 								\
 __label_warn_on:						\
 	break;							\

arch/powerpc/include/asm/linkage.h

@@ -4,6 +4,9 @@
 
 #include <asm/types.h>
 
+#define __ALIGN		.align 2
+#define __ALIGN_STR	".align 2"
+
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 #define cond_syscall(x) \
 	asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n"		\

arch/powerpc/kernel/cpu_setup_6xx.S

@@ -4,6 +4,8 @@
  *    Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
  */
 
+#include <linux/linkage.h>
+
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/cputable.h>
@@ -81,7 +83,7 @@ _GLOBAL(__setup_cpu_745x)
 	blr
 
 /* Enable caches for 603's, 604, 750 & 7400 */
-setup_common_caches:
+SYM_FUNC_START_LOCAL(setup_common_caches)
 	mfspr	r11,SPRN_HID0
 	andi.	r0,r11,HID0_DCE
 	ori	r11,r11,HID0_ICE|HID0_DCE
@@ -95,11 +97,12 @@ setup_common_caches:
 	sync
 	isync
 	blr
+SYM_FUNC_END(setup_common_caches)
 
 /* 604, 604e, 604ev, ...
  * Enable superscalar execution & branch history table
  */
-setup_604_hid0:
+SYM_FUNC_START_LOCAL(setup_604_hid0)
 	mfspr	r11,SPRN_HID0
 	ori	r11,r11,HID0_SIED|HID0_BHTE
 	ori	r8,r11,HID0_BTCD
@@ -110,6 +113,7 @@ setup_604_hid0:
 	sync
 	isync
 	blr
+SYM_FUNC_END(setup_604_hid0)
 
 /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
  * erratas we work around here.
@@ -125,13 +129,14 @@ setup_604_hid0:
  * needed once we have applied workaround #5 (though it's
  * not set by Apple's firmware at least).
  */
-setup_7400_workarounds:
+SYM_FUNC_START_LOCAL(setup_7400_workarounds)
 	mfpvr	r3
 	rlwinm	r3,r3,0,20,31
 	cmpwi	0,r3,0x0207
 	ble	1f
 	blr
-setup_7410_workarounds:
+SYM_FUNC_END(setup_7400_workarounds)
+SYM_FUNC_START_LOCAL(setup_7410_workarounds)
 	mfpvr	r3
 	rlwinm	r3,r3,0,20,31
 	cmpwi	0,r3,0x0100
@@ -151,6 +156,7 @@ setup_7410_workarounds:
 	sync
 	isync
 	blr
+SYM_FUNC_END(setup_7410_workarounds)
 
 /* 740/750/7400/7410
  * Enable Store Gathering (SGE), Address Broadcast (ABE),
@@ -158,7 +164,7 @@ setup_7410_workarounds:
  * Dynamic Power Management (DPM), Speculative (SPD)
  * Clear Instruction cache throttling (ICTC)
  */
-setup_750_7400_hid0:
+SYM_FUNC_START_LOCAL(setup_750_7400_hid0)
 	mfspr	r11,SPRN_HID0
 	ori	r11,r11,HID0_SGE | HID0_ABE | HID0_BHTE | HID0_BTIC
 	oris	r11,r11,HID0_DPM@h
@@ -177,12 +183,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_NO_DPM)
 	sync
 	isync
 	blr
+SYM_FUNC_END(setup_750_7400_hid0)
 
 /* 750cx specific
  * Looks like we have to disable NAP feature for some PLL settings...
  * (waiting for confirmation)
  */
-setup_750cx:
+SYM_FUNC_START_LOCAL(setup_750cx)
 	mfspr	r10, SPRN_HID1
 	rlwinm	r10,r10,4,28,31
 	cmpwi	cr0,r10,7
@@ -196,11 +203,13 @@ setup_750cx:
 	andc	r6,r6,r7
 	stw	r6,CPU_SPEC_FEATURES(r4)
 	blr
+SYM_FUNC_END(setup_750cx)
 
 /* 750fx specific
  */
-setup_750fx:
+SYM_FUNC_START_LOCAL(setup_750fx)
 	blr
+SYM_FUNC_END(setup_750fx)
 
 /* MPC 745x
  * Enable Store Gathering (SGE), Branch Folding (FOLD)
@@ -212,7 +221,7 @@ setup_750fx:
  * Clear Instruction cache throttling (ICTC)
  * Enable L2 HW prefetch
  */
-setup_745x_specifics:
+SYM_FUNC_START_LOCAL(setup_745x_specifics)
 	/* We check for the presence of an L3 cache setup by
 	 * the firmware. If any, we disable NAP capability as
 	 * it's known to be bogus on rev 2.1 and earlier
@@ -270,6 +279,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NO_DPM)
 	sync
 	isync
 	blr
+SYM_FUNC_END(setup_745x_specifics)
 
 /*
  * Initialize the FPU registers. This is needed to work around an errata

arch/powerpc/kernel/cpu_setup_e500.S

@@ -8,6 +8,8 @@
  * Benjamin Herrenschmidt <benh@kernel.crashing.org>
  */
 
+#include <linux/linkage.h>
+
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
@@ -274,7 +276,7 @@ _GLOBAL(flush_dcache_L1)
 
 	blr
 
-has_L2_cache:
+SYM_FUNC_START_LOCAL(has_L2_cache)
 	/* skip L2 cache on P2040/P2040E as they have no L2 cache */
 	mfspr	r3, SPRN_SVR
 	/* shift right by 8 bits and clear E bit of SVR */
@@ -290,9 +292,10 @@ has_L2_cache:
 1:
 	li	r3, 0
 	blr
+SYM_FUNC_END(has_L2_cache)
 
 /* flush backside L2 cache */
-flush_backside_L2_cache:
+SYM_FUNC_START_LOCAL(flush_backside_L2_cache)
 	mflr	r10
 	bl	has_L2_cache
 	mtlr	r10
@@ -313,6 +316,7 @@ flush_backside_L2_cache:
 	bne	1b
 2:
 	blr
+SYM_FUNC_END(flush_backside_L2_cache)
 
 _GLOBAL(cpu_down_flush_e500v2)
 	mflr r0

arch/powerpc/kernel/entry_32.S

@@ -18,6 +18,8 @@
 #include <linux/err.h>
 #include <linux/sys.h>
 #include <linux/threads.h>
+#include <linux/linkage.h>
+
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -74,17 +76,18 @@ _ASM_NOKPROBE_SYMBOL(prepare_transfer_to_handler)
 #endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_PPC_E500 */
 
 #if defined(CONFIG_PPC_KUEP) && defined(CONFIG_PPC_BOOK3S_32)
-	.globl	__kuep_lock
+SYM_FUNC_START(__kuep_lock)
-__kuep_lock:
 	lwz	r9, THREAD+THSR0(r2)
 	update_user_segments_by_4 r9, r10, r11, r12
 	blr
+SYM_FUNC_END(__kuep_lock)
 
-__kuep_unlock:
+SYM_FUNC_START_LOCAL(__kuep_unlock)
 	lwz	r9, THREAD+THSR0(r2)
 	rlwinm  r9,r9,0,~SR_NX
 	update_user_segments_by_4 r9, r10, r11, r12
 	blr
+SYM_FUNC_END(__kuep_unlock)
 
 .macro	kuep_lock
 	bl	__kuep_lock

arch/powerpc/kernel/entry_64.S

@@ -14,6 +14,7 @@
  *  code, and exception/interrupt return code for PowerPC.
  */
 
+#include <linux/objtool.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <asm/cache.h>
@@ -73,6 +74,7 @@ flush_branch_caches:
 
 	// Flush the link stack
 	.rept 64
+	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 	b	1f

arch/powerpc/kernel/exceptions-64s.S

@@ -13,6 +13,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/hw_irq.h>
 #include <asm/exception-64s.h>
 #include <asm/ptrace.h>
@@ -3140,7 +3141,7 @@ _GLOBAL(enable_machine_check)
 	blr
 
 /* MSR[RI] should be clear because this uses SRR[01] */
-disable_machine_check:
+SYM_FUNC_START_LOCAL(disable_machine_check)
 	mflr	r0
 	bcl	20,31,$+4
 0:	mflr	r3
@@ -3153,3 +3154,4 @@ disable_machine_check:
 	RFI_TO_KERNEL
 1:	mtlr	r0
 	blr
+SYM_FUNC_END(disable_machine_check)

arch/powerpc/kernel/head_40x.S

@@ -28,6 +28,8 @@
 #include <linux/init.h>
 #include <linux/pgtable.h>
 #include <linux/sizes.h>
+#include <linux/linkage.h>
+
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -662,7 +664,7 @@ start_here:
  * kernel initialization.  This maps the first 32 MBytes of memory 1:1
  * virtual to physical and more importantly sets the cache mode.
  */
-initial_mmu:
+SYM_FUNC_START_LOCAL(initial_mmu)
 	tlbia			/* Invalidate all TLB entries */
 	isync
 
@@ -711,6 +713,7 @@ initial_mmu:
 	mtspr	SPRN_EVPR,r0
 
 	blr
+SYM_FUNC_END(initial_mmu)
 
 _GLOBAL(abort)
         mfspr   r13,SPRN_DBCR0

arch/powerpc/kernel/head_64.S

@@ -18,6 +18,7 @@
  *  variants.
  */
 
+#include <linux/linkage.h>
 #include <linux/threads.h>
 #include <linux/init.h>
 #include <asm/reg.h>
@@ -462,7 +463,7 @@ generic_secondary_common_init:
  * Assumes we're mapped EA == RA if the MMU is on.
  */
 #ifdef CONFIG_PPC_BOOK3S
-__mmu_off:
+SYM_FUNC_START_LOCAL(__mmu_off)
 	mfmsr	r3
 	andi.	r0,r3,MSR_IR|MSR_DR
 	beqlr
@@ -473,6 +474,7 @@ __mmu_off:
 	sync
 	rfid
 	b	.	/* prevent speculative execution */
+SYM_FUNC_END(__mmu_off)
 #endif
 
 
@@ -869,7 +871,7 @@ _GLOBAL(start_secondary_resume)
 /*
  * This subroutine clobbers r11 and r12
  */
-enable_64b_mode:
+SYM_FUNC_START_LOCAL(enable_64b_mode)
 	mfmsr	r11			/* grab the current MSR */
 #ifdef CONFIG_PPC_BOOK3E_64
 	oris	r11,r11,0x8000		/* CM bit set, we'll set ICM later */
@@ -881,6 +883,7 @@ enable_64b_mode:
 	isync
 #endif
 	blr
+SYM_FUNC_END(enable_64b_mode)
 
 /*
  * This puts the TOC pointer into r2, offset by 0x8000 (as expected

arch/powerpc/kernel/head_85xx.S

@@ -29,6 +29,8 @@
 #include <linux/init.h>
 #include <linux/threads.h>
 #include <linux/pgtable.h>
+#include <linux/linkage.h>
+
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -885,7 +887,7 @@ KernelSPE:
  * Translate the effec addr in r3 to phys addr. The phys addr will be put
  * into r3(higher 32bit) and r4(lower 32bit)
  */
-get_phys_addr:
+SYM_FUNC_START_LOCAL(get_phys_addr)
 	mfmsr	r8
 	mfspr	r9,SPRN_PID
 	rlwinm	r9,r9,16,0x3fff0000	/* turn PID into MAS6[SPID] */
@@ -907,6 +909,7 @@ get_phys_addr:
 	mfspr	r3,SPRN_MAS7
 #endif
 	blr
+SYM_FUNC_END(get_phys_addr)
 
 /*
  * Global functions

arch/powerpc/kernel/head_8xx.S

@@ -18,6 +18,8 @@
 #include <linux/magic.h>
 #include <linux/pgtable.h>
 #include <linux/sizes.h>
+#include <linux/linkage.h>
+
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -625,7 +627,7 @@ start_here:
  * 24 Mbytes of data, and the 512k IMMR space.  Anything not covered by
  * these mappings is mapped by page tables.
  */
-initial_mmu:
+SYM_FUNC_START_LOCAL(initial_mmu)
 	li	r8, 0
 	mtspr	SPRN_MI_CTR, r8		/* remove PINNED ITLB entries */
 	lis	r10, MD_TWAM@h
@@ -686,6 +688,7 @@ initial_mmu:
 #endif
 	mtspr	SPRN_DER, r8
 	blr
+SYM_FUNC_END(initial_mmu)
 
 _GLOBAL(mmu_pin_tlb)
 	lis	r9, (1f - PAGE_OFFSET)@h

arch/powerpc/kernel/head_book3s_32.S

@@ -18,6 +18,8 @@
 
 #include <linux/init.h>
 #include <linux/pgtable.h>
+#include <linux/linkage.h>
+
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -877,7 +879,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_HPTE_TABLE)
  * Load stuff into the MMU.  Intended to be called with
  * IR=0 and DR=0.
  */
-early_hash_table:
+SYM_FUNC_START_LOCAL(early_hash_table)
 	sync			/* Force all PTE updates to finish */
 	isync
 	tlbia			/* Clear all TLB entries */
@@ -888,8 +890,9 @@ early_hash_table:
 	ori	r6, r6, 3	/* 256kB table */
 	mtspr	SPRN_SDR1, r6
 	blr
+SYM_FUNC_END(early_hash_table)
 
-load_up_mmu:
+SYM_FUNC_START_LOCAL(load_up_mmu)
 	sync			/* Force all PTE updates to finish */
 	isync
 	tlbia			/* Clear all TLB entries */
@@ -918,6 +921,7 @@ BEGIN_MMU_FTR_SECTION
 	LOAD_BAT(7,r3,r4,r5)
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	blr
+SYM_FUNC_END(load_up_mmu)
 
 _GLOBAL(load_segment_registers)
 	li	r0, NUM_USER_SEGMENTS /* load up user segment register values */
@@ -1028,7 +1032,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_HPTE_TABLE)
  * this makes sure it's done.
  *  -- Cort
  */
-clear_bats:
+SYM_FUNC_START_LOCAL(clear_bats)
 	li	r10,0
 
 	mtspr	SPRN_DBAT0U,r10
@@ -1072,6 +1076,7 @@ BEGIN_MMU_FTR_SECTION
 	mtspr	SPRN_IBAT7L,r10
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	blr
+SYM_FUNC_END(clear_bats)
 
 _GLOBAL(update_bats)
 	lis	r4, 1f@h
@@ -1108,15 +1113,16 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	mtspr	SPRN_SRR1, r6
 	rfi
 
-flush_tlbs:
+SYM_FUNC_START_LOCAL(flush_tlbs)
 	lis	r10, 0x40
 1:	addic.	r10, r10, -0x1000
 	tlbie	r10
 	bgt	1b
 	sync
 	blr
+SYM_FUNC_END(flush_tlbs)
 
-mmu_off:
+SYM_FUNC_START_LOCAL(mmu_off)
  	addi	r4, r3, __after_mmu_off - _start
 	mfmsr	r3
 	andi.	r0,r3,MSR_DR|MSR_IR		/* MMU enabled? */
@@ -1128,9 +1134,10 @@ mmu_off:
 	mtspr	SPRN_SRR1,r3
 	sync
 	rfi
+SYM_FUNC_END(mmu_off)
 
 /* We use one BAT to map up to 256M of RAM at _PAGE_OFFSET */
-initial_bats:
+SYM_FUNC_START_LOCAL(initial_bats)
 	lis	r11,PAGE_OFFSET@h
 	tophys(r8,r11)
 #ifdef CONFIG_SMP
@@ -1146,9 +1153,10 @@ initial_bats:
 	mtspr	SPRN_IBAT0U,r11
 	isync
 	blr
+SYM_FUNC_END(initial_bats)
 
 #ifdef CONFIG_BOOTX_TEXT
-setup_disp_bat:
+SYM_FUNC_START_LOCAL(setup_disp_bat)
 	/*
 	 * setup the display bat prepared for us in prom.c
 	 */
@@ -1164,10 +1172,11 @@ setup_disp_bat:
 	mtspr	SPRN_DBAT3L,r8
 	mtspr	SPRN_DBAT3U,r11
 	blr
+SYM_FUNC_END(setup_disp_bat)
 #endif /* CONFIG_BOOTX_TEXT */
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_CPM
-setup_cpm_bat:
+SYM_FUNC_START_LOCAL(setup_cpm_bat)
 	lis	r8, 0xf000
 	ori	r8, r8,	0x002a
 	mtspr	SPRN_DBAT1L, r8
@@ -1177,10 +1186,11 @@ setup_cpm_bat:
 	mtspr	SPRN_DBAT1U, r11
 
 	blr
+SYM_FUNC_END(setup_cpm_bat)
 #endif
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_USBGECKO
-setup_usbgecko_bat:
+SYM_FUNC_START_LOCAL(setup_usbgecko_bat)
 	/* prepare a BAT for early io */
 #if defined(CONFIG_GAMECUBE)
 	lis	r8, 0x0c00
@@ -1199,6 +1209,7 @@ setup_usbgecko_bat:
 	mtspr	SPRN_DBAT1L, r8
 	mtspr	SPRN_DBAT1U, r11
 	blr
+SYM_FUNC_END(setup_usbgecko_bat)
 #endif
 
 	.data

arch/powerpc/kernel/misc_64.S

@@ -9,6 +9,7 @@
  * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
  */
 
+#include <linux/linkage.h>
 #include <linux/sys.h>
 #include <asm/unistd.h>
 #include <asm/errno.h>
@@ -353,7 +354,7 @@ _GLOBAL(kexec_smp_wait)
  *
  * don't overwrite r3 here, it is live for kexec_wait above.
  */
-real_mode:	/* assume normal blr return */
+SYM_FUNC_START_LOCAL(real_mode)	/* assume normal blr return */
 #ifdef CONFIG_PPC_BOOK3E_64
 	/* Create an identity mapping. */
 	b	kexec_create_tlb
@@ -370,6 +371,7 @@ real_mode:	/* assume normal blr return */
 	mtspr	SPRN_SRR0,r11
 	rfid
 #endif
+SYM_FUNC_END(real_mode)
 
 /*
  * kexec_sequence(newstack, start, image, control, clear_all(),

arch/powerpc/kernel/swsusp_32.S

@@ -1,5 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/threads.h>
+#include <linux/linkage.h>
+
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/cputable.h>
@@ -400,7 +402,7 @@ _ASM_NOKPROBE_SYMBOL(swsusp_arch_resume)
 /* FIXME:This construct is actually not useful since we don't shut
  * down the instruction MMU, we could just flip back MSR-DR on.
  */
-turn_on_mmu:
+SYM_FUNC_START_LOCAL(turn_on_mmu)
 	mflr	r4
 	mtsrr0	r4
 	mtsrr1	r3
@@ -408,4 +410,5 @@ turn_on_mmu:
 	isync
 	rfi
 _ASM_NOKPROBE_SYMBOL(turn_on_mmu)
+SYM_FUNC_END(turn_on_mmu)
 

arch/powerpc/kernel/vdso/Makefile

@@ -102,3 +102,5 @@ quiet_cmd_vdso64ld_and_check = VDSO64L $@
       cmd_vdso64ld_and_check = $(VDSOCC) $(c_flags) $(CC64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) -z noexecstack ; $(cmd_vdso_check)
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(VDSOCC) $(a_flags) $(CC64FLAGS) $(AS64FLAGS) -c -o $@ $<
+
+OBJECT_FILES_NON_STANDARD := y

arch/powerpc/kernel/vector.S

@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/reg.h>
@@ -185,7 +186,7 @@ fphalf:
  * Internal routine to enable floating point and set FPSCR to 0.
  * Don't call it from C; it doesn't use the normal calling convention.
  */
-fpenable:
+SYM_FUNC_START_LOCAL(fpenable)
 #ifdef CONFIG_PPC32
 	stwu	r1,-64(r1)
 #else
@@ -202,6 +203,7 @@ fpenable:
 	mffs	fr31
 	MTFSF_L(fr1)
 	blr
+SYM_FUNC_END(fpenable)
 
 fpdisable:
 	mtlr	r12

arch/powerpc/kvm/book3s_hv_interrupts.S

@@ -9,6 +9,7 @@
  * Authors: Alexander Graf <agraf@suse.de>
  */
 
+#include <linux/linkage.h>
 #include <asm/ppc_asm.h>
 #include <asm/kvm_asm.h>
 #include <asm/reg.h>
@@ -107,7 +108,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 /*
  * void kvmhv_save_host_pmu(void)
  */
-kvmhv_save_host_pmu:
+SYM_FUNC_START_LOCAL(kvmhv_save_host_pmu)
 BEGIN_FTR_SECTION
 	/* Work around P8 PMAE bug */
 	li	r3, -1
@@ -154,3 +155,4 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	stw	r8, HSTATE_PMC5(r13)
 	stw	r9, HSTATE_PMC6(r13)
 31:	blr
+SYM_FUNC_END(kvmhv_save_host_pmu)

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -10,6 +10,8 @@
  * Authors: Alexander Graf <agraf@suse.de>
  */
 
+#include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/ppc_asm.h>
 #include <asm/code-patching-asm.h>
 #include <asm/kvm_asm.h>
@@ -1522,12 +1524,14 @@ kvm_flush_link_stack:
 
 	/* Flush the link stack. On Power8 it's up to 32 entries in size. */
 	.rept 32
+	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 
 	/* And on Power9 it's up to 64. */
 BEGIN_FTR_SECTION
 	.rept 32
+	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
@@ -2358,7 +2362,7 @@ hmi_realmode:
  * This routine calls kvmppc_read_intr, a C function, if an external
  * interrupt is pending.
  */
-kvmppc_check_wake_reason:
+SYM_FUNC_START_LOCAL(kvmppc_check_wake_reason)
 	mfspr	r6, SPRN_SRR1
 BEGIN_FTR_SECTION
 	rlwinm	r6, r6, 45-31, 0xf	/* extract wake reason field (P8) */
@@ -2427,6 +2431,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	addi	r1, r1, PPC_MIN_STKFRM
 	mtlr	r0
 	blr
+SYM_FUNC_END(kvmppc_check_wake_reason)
 
 /*
  * Save away FP, VMX and VSX registers.
@@ -2434,7 +2439,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
  * N.B. r30 and r31 are volatile across this function,
  * thus it is not callable from C.
  */
-kvmppc_save_fp:
+SYM_FUNC_START_LOCAL(kvmppc_save_fp)
 	mflr	r30
 	mr	r31,r3
 	mfmsr	r5
@@ -2462,6 +2467,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	stw	r6,VCPU_VRSAVE(r31)
 	mtlr	r30
 	blr
+SYM_FUNC_END(kvmppc_save_fp)
 
 /*
  * Load up FP, VMX and VSX registers
@@ -2469,7 +2475,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
  * N.B. r30 and r31 are volatile across this function,
  * thus it is not callable from C.
  */
-kvmppc_load_fp:
+SYM_FUNC_START_LOCAL(kvmppc_load_fp)
 	mflr	r30
 	mr	r31,r4
 	mfmsr	r9
@@ -2498,6 +2504,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mtlr	r30
 	mr	r4,r31
 	blr
+SYM_FUNC_END(kvmppc_load_fp)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 /*
@@ -2746,7 +2753,7 @@ kvmppc_bad_host_intr:
  *   r9 has a vcpu pointer (in)
  *   r0 is used as a scratch register
  */
-kvmppc_msr_interrupt:
+SYM_FUNC_START_LOCAL(kvmppc_msr_interrupt)
 	rldicl	r0, r11, 64 - MSR_TS_S_LG, 62
 	cmpwi	r0, 2 /* Check if we are in transactional state..  */
 	ld	r11, VCPU_INTR_MSR(r9)
@@ -2755,13 +2762,14 @@ kvmppc_msr_interrupt:
 	li	r0, 1
 1:	rldimi	r11, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG
 	blr
+SYM_FUNC_END(kvmppc_msr_interrupt)
 
 /*
  * void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu)
  *
  * Load up guest PMU state.  R3 points to the vcpu struct.
  */
-kvmhv_load_guest_pmu:
+SYM_FUNC_START_LOCAL(kvmhv_load_guest_pmu)
 	mr	r4, r3
 	mflr	r0
 	li	r3, 1
@@ -2811,13 +2819,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	isync
 	mtlr	r0
 	blr
+SYM_FUNC_END(kvmhv_load_guest_pmu)
 
 /*
  * void kvmhv_load_host_pmu(void)
  *
  * Reload host PMU state saved in the PACA by kvmhv_save_host_pmu.
  */
-kvmhv_load_host_pmu:
+SYM_FUNC_START_LOCAL(kvmhv_load_host_pmu)
 	mflr	r0
 	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
 	cmpwi	r4, 0
@@ -2859,6 +2868,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	isync
 	mtlr	r0
 23:	blr
+SYM_FUNC_END(kvmhv_load_host_pmu)
 
 /*
  * void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use)
@@ -2866,7 +2876,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
  * Save guest PMU state into the vcpu struct.
  * r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA)
  */
-kvmhv_save_guest_pmu:
+SYM_FUNC_START_LOCAL(kvmhv_save_guest_pmu)
 	mr	r9, r3
 	mr	r8, r4
 BEGIN_FTR_SECTION
@@ -2942,6 +2952,7 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_MMCRS, r4
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 22:	blr
+SYM_FUNC_END(kvmhv_save_guest_pmu)
 
 /*
  * This works around a hardware bug on POWER8E processors, where

arch/powerpc/kvm/fpu.S

@@ -6,6 +6,8 @@
  */
 
 #include <linux/pgtable.h>
+#include <linux/linkage.h>
+
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -110,18 +112,22 @@ FPS_THREE_IN(fsel)
  * R8 = (double*)&param3 [load_three]
  * LR = instruction call function
  */
-fpd_load_three:
+SYM_FUNC_START_LOCAL(fpd_load_three)
 	lfd	2,0(r8)			/* load param3 */
-fpd_load_two:
+SYM_FUNC_START_LOCAL(fpd_load_two)
 	lfd	1,0(r7)			/* load param2 */
-fpd_load_one:
+SYM_FUNC_START_LOCAL(fpd_load_one)
 	lfd	0,0(r6)			/* load param1 */
-fpd_load_none:
+SYM_FUNC_START_LOCAL(fpd_load_none)
 	lfd	3,0(r3)			/* load up fpscr value */
 	MTFSF_L(3)
 	lwz	r6, 0(r4)		/* load cr */
 	mtcr	r6
 	blr
+SYM_FUNC_END(fpd_load_none)
+SYM_FUNC_END(fpd_load_one)
+SYM_FUNC_END(fpd_load_two)
+SYM_FUNC_END(fpd_load_three)
 
 /*
  * End of double instruction processing
@@ -131,13 +137,14 @@ fpd_load_none:
  * R5 = (double*)&result
  * LR = caller of instruction call function
  */
-fpd_return:
+SYM_FUNC_START_LOCAL(fpd_return)
 	mfcr	r6
 	stfd	0,0(r5)			/* save result */
 	mffs	0
 	stfd	0,0(r3)			/* save new fpscr value */
 	stw	r6,0(r4)		/* save new cr value */
 	blr
+SYM_FUNC_END(fpd_return)
 
 /*
  * Double operation with no input operand

arch/powerpc/platforms/52xx/lite5200_sleep.S

@@ -1,4 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+
 #include <asm/reg.h>
 #include <asm/ppc_asm.h>
 #include <asm/processor.h>
@@ -178,7 +180,8 @@ sram_code:
 
 
 	/* local udelay in sram is needed */
-  udelay: /* r11 - tb_ticks_per_usec, r12 - usecs, overwrites r13 */
+SYM_FUNC_START_LOCAL(udelay)
+	/* r11 - tb_ticks_per_usec, r12 - usecs, overwrites r13 */
 	mullw	r12, r12, r11
 	mftb	r13	/* start */
 	add	r12, r13, r12 /* end */
@@ -187,6 +190,7 @@ sram_code:
 	cmp	cr0, r13, r12
 	blt	1b
 	blr
+SYM_FUNC_END(udelay)
 
 sram_code_end:
 
@@ -271,7 +275,7 @@ _ASM_NOKPROBE_SYMBOL(lite5200_wakeup)
 	SAVE_SR(n+2, addr+2);	\
 	SAVE_SR(n+3, addr+3);
 
-save_regs:
+SYM_FUNC_START_LOCAL(save_regs)
 	stw	r0, 0(r4)
 	stw	r1, 0x4(r4)
 	stw	r2, 0x8(r4)
@@ -317,6 +321,7 @@ save_regs:
 	SAVE_SPRN(TBRU,  0x5b)
 
 	blr
+SYM_FUNC_END(save_regs)
 
 
 /* restore registers */
@@ -336,7 +341,7 @@ save_regs:
 	LOAD_SR(n+2, addr+2);	\
 	LOAD_SR(n+3, addr+3);
 
-restore_regs:
+SYM_FUNC_START_LOCAL(restore_regs)
 	lis	r4, registers@h
 	ori	r4, r4, registers@l
 
@@ -393,6 +398,7 @@ restore_regs:
 
 	blr
 _ASM_NOKPROBE_SYMBOL(restore_regs)
+SYM_FUNC_END(restore_regs)
 
 
 
@@ -403,7 +409,7 @@ _ASM_NOKPROBE_SYMBOL(restore_regs)
  * Flush data cache
  * Do this by just reading lots of stuff into the cache.
  */
-flush_data_cache:
+SYM_FUNC_START_LOCAL(flush_data_cache)
 	lis	r3,CONFIG_KERNEL_START@h
 	ori	r3,r3,CONFIG_KERNEL_START@l
 	li	r4,NUM_CACHE_LINES
@@ -413,3 +419,4 @@ flush_data_cache:
 	addi	r3,r3,L1_CACHE_BYTES	/* Next line, please */
 	bdnz	1b
 	blr
+SYM_FUNC_END(flush_data_cache)

arch/x86/Kconfig

@@ -195,6 +195,7 @@ config X86
 	select HAVE_CONTEXT_TRACKING_USER_OFFSTACK	if HAVE_CONTEXT_TRACKING_USER
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_OBJTOOL_MCOUNT		if HAVE_OBJTOOL
+	select HAVE_OBJTOOL_NOP_MCOUNT		if HAVE_OBJTOOL_MCOUNT
 	select HAVE_BUILDTIME_MCOUNT_SORT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS

drivers/crypto/vmx/Makefile

@@ -19,3 +19,5 @@ targets += aesp8-ppc.S ghashp8-ppc.S
 
 $(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
 	$(call if_changed,perl)
+
+OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y

kernel/trace/Kconfig

@@ -82,6 +82,13 @@ config HAVE_OBJTOOL_MCOUNT
 	help
 	  Arch supports objtool --mcount
 
+config HAVE_OBJTOOL_NOP_MCOUNT
+	bool
+	help
+	  Arch supports the objtool options --mcount with --mnop.
+	  An architecture can select this if it wants to enable nop'ing
+	  of ftrace locations.
+
 config HAVE_C_RECORDMCOUNT
 	bool
 	help

scripts/Makefile.lib

@@ -256,6 +256,9 @@ objtool-args-$(CONFIG_HAVE_JUMP_LABEL_HACK)		+= --hacks=jump_label
 objtool-args-$(CONFIG_HAVE_NOINSTR_HACK)		+= --hacks=noinstr
 objtool-args-$(CONFIG_X86_KERNEL_IBT)			+= --ibt
 objtool-args-$(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL)	+= --mcount
+ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL
+objtool-args-$(CONFIG_HAVE_OBJTOOL_NOP_MCOUNT)		+= --mnop
+endif
 objtool-args-$(CONFIG_UNWINDER_ORC)			+= --orc
 objtool-args-$(CONFIG_RETPOLINE)			+= --retpoline
 objtool-args-$(CONFIG_RETHUNK)				+= --rethunk

tools/objtool/arch/powerpc/Build

@@ -0,0 +1,2 @@
+objtool-y += decode.o
+objtool-y += special.o

tools/objtool/arch/powerpc/decode.c

@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <objtool/check.h>
+#include <objtool/elf.h>
+#include <objtool/arch.h>
+#include <objtool/warn.h>
+#include <objtool/builtin.h>
+#include <objtool/endianness.h>
+
+int arch_ftrace_match(char *name)
+{
+	return !strcmp(name, "_mcount");
+}
+
+unsigned long arch_dest_reloc_offset(int addend)
+{
+	return addend;
+}
+
+bool arch_callee_saved_reg(unsigned char reg)
+{
+	return false;
+}
+
+int arch_decode_hint_reg(u8 sp_reg, int *base)
+{
+	exit(-1);
+}
+
+const char *arch_nop_insn(int len)
+{
+	exit(-1);
+}
+
+const char *arch_ret_insn(int len)
+{
+	exit(-1);
+}
+
+int arch_decode_instruction(struct objtool_file *file, const struct section *sec,
+			    unsigned long offset, unsigned int maxlen,
+			    unsigned int *len, enum insn_type *type,
+			    unsigned long *immediate,
+			    struct list_head *ops_list)
+{
+	unsigned int opcode;
+	enum insn_type typ;
+	unsigned long imm;
+	u32 insn;
+
+	insn = bswap_if_needed(file->elf, *(u32 *)(sec->data->d_buf + offset));
+	opcode = insn >> 26;
+	typ = INSN_OTHER;
+	imm = 0;
+
+	switch (opcode) {
+	case 18: /* b[l][a] */
+		if ((insn & 3) == 1) /* bl */
+			typ = INSN_CALL;
+
+		imm = insn & 0x3fffffc;
+		if (imm & 0x2000000)
+			imm -= 0x4000000;
+		break;
+	}
+
+	if (opcode == 1)
+		*len = 8;
+	else
+		*len = 4;
+
+	*type = typ;
+	*immediate = imm;
+
+	return 0;
+}
+
+unsigned long arch_jump_destination(struct instruction *insn)
+{
+	return insn->offset + insn->immediate;
+}
+
+bool arch_pc_relative_reloc(struct reloc *reloc)
+{
+	/*
+	 * The powerpc build only allows certain relocation types, see
+	 * relocs_check.sh, and none of those accepted are PC relative.
+	 */
+	return false;
+}
+
+void arch_initial_func_cfi_state(struct cfi_init_state *state)
+{
+	int i;
+
+	for (i = 0; i < CFI_NUM_REGS; i++) {
+		state->regs[i].base = CFI_UNDEFINED;
+		state->regs[i].offset = 0;
+	}
+
+	/* initial CFA (call frame address) */
+	state->cfa.base = CFI_SP;
+	state->cfa.offset = 0;
+
+	/* initial LR (return address) */
+	state->regs[CFI_RA].base = CFI_CFA;
+	state->regs[CFI_RA].offset = 0;
+}

tools/objtool/arch/powerpc/include/arch/cfi_regs.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _OBJTOOL_CFI_REGS_H
+#define _OBJTOOL_CFI_REGS_H
+
+#define CFI_BP 1
+#define CFI_SP CFI_BP
+#define CFI_RA 32
+#define CFI_NUM_REGS 33
+
+#endif

tools/objtool/arch/powerpc/include/arch/elf.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _OBJTOOL_ARCH_ELF
+#define _OBJTOOL_ARCH_ELF
+
+#define R_NONE R_PPC_NONE
+#define R_ABS64 R_PPC64_ADDR64
+#define R_ABS32 R_PPC_ADDR32
+
+#endif /* _OBJTOOL_ARCH_ELF */

tools/objtool/arch/powerpc/include/arch/special.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _PPC_ARCH_SPECIAL_H
+#define _PPC_ARCH_SPECIAL_H
+
+#define EX_ENTRY_SIZE 8
+#define EX_ORIG_OFFSET 0
+#define EX_NEW_OFFSET 4
+
+#define JUMP_ENTRY_SIZE 16
+#define JUMP_ORIG_OFFSET 0
+#define JUMP_NEW_OFFSET 4
+#define JUMP_KEY_OFFSET 8
+
+#define ALT_ENTRY_SIZE 12
+#define ALT_ORIG_OFFSET 0
+#define ALT_NEW_OFFSET 4
+#define ALT_FEATURE_OFFSET 8
+#define ALT_ORIG_LEN_OFFSET 10
+#define ALT_NEW_LEN_OFFSET 11
+
+#endif /* _PPC_ARCH_SPECIAL_H */

tools/objtool/arch/powerpc/special.c

@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <string.h>
+#include <stdlib.h>
+#include <objtool/special.h>
+#include <objtool/builtin.h>
+
+
+bool arch_support_alt_relocation(struct special_alt *special_alt,
+				 struct instruction *insn,
+				 struct reloc *reloc)
+{
+	exit(-1);
+}
+
+struct reloc *arch_find_switch_table(struct objtool_file *file,
+				    struct instruction *insn)
+{
+	exit(-1);
+}

tools/objtool/arch/x86/decode.c

@@ -23,6 +23,11 @@
 #include <objtool/builtin.h>
 #include <arch/elf.h>
 
+int arch_ftrace_match(char *name)
+{
+	return !strcmp(name, "__fentry__");
+}
+
 static int is_x86_64(const struct elf *elf)
 {
 	switch (elf->ehdr.e_machine) {

tools/objtool/arch/x86/include/arch/elf.h

@@ -2,5 +2,7 @@
 #define _OBJTOOL_ARCH_ELF
 
 #define R_NONE R_X86_64_NONE
+#define R_ABS64 R_X86_64_64
+#define R_ABS32 R_X86_64_32
 
 #endif /* _OBJTOOL_ARCH_ELF */

tools/objtool/arch/x86/include/arch/endianness.h

@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ARCH_ENDIANNESS_H
-#define _ARCH_ENDIANNESS_H
-
-#include <endian.h>
-
-#define __TARGET_BYTE_ORDER __LITTLE_ENDIAN
-
-#endif /* _ARCH_ENDIANNESS_H */

tools/objtool/builtin-check.c

@@ -82,6 +82,7 @@ const struct option check_options[] = {
 	OPT_BOOLEAN(0, "dry-run", &opts.dryrun, "don't write modifications"),
 	OPT_BOOLEAN(0, "link", &opts.link, "object is a linked object"),
 	OPT_BOOLEAN(0, "module", &opts.module, "object is part of a kernel module"),
+	OPT_BOOLEAN(0, "mnop", &opts.mnop, "nop out mcount call sites"),
 	OPT_BOOLEAN(0, "no-unreachable", &opts.no_unreachable, "skip 'unreachable instruction' warnings"),
 	OPT_BOOLEAN(0, "sec-address", &opts.sec_address, "print section addresses in warnings"),
 	OPT_BOOLEAN(0, "stats", &opts.stats, "print statistics"),
@@ -150,6 +151,16 @@ static bool opts_valid(void)
 	return false;
 }
 
+static bool mnop_opts_valid(void)
+{
+	if (opts.mnop && !opts.mcount) {
+		ERROR("--mnop requires --mcount");
+		return false;
+	}
+
+	return true;
+}
+
 static bool link_opts_valid(struct objtool_file *file)
 {
 	if (opts.link)
@@ -198,6 +209,9 @@ int objtool_run(int argc, const char **argv)
 	if (!file)
 		return 1;
 
+	if (!mnop_opts_valid())
+		return 1;
+
 	if (!link_opts_valid(file))
 		return 1;
 

tools/objtool/check.c

@@ -207,7 +207,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 		return false;
 
 	insn = find_insn(file, func->sec, func->offset);
-	if (!insn->func)
+	if (!insn || !insn->func)
 		return false;
 
 	func_for_each_insn(file, func, insn) {
@@ -852,9 +852,9 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file)
 
 static int create_mcount_loc_sections(struct objtool_file *file)
 {
-	struct section *sec;
+	int addrsize = elf_class_addrsize(file->elf);
-	unsigned long *loc;
 	struct instruction *insn;
+	struct section *sec;
 	int idx;
 
 	sec = find_section_by_name(file->elf, "__mcount_loc");
@@ -871,23 +871,25 @@ static int create_mcount_loc_sections(struct objtool_file *file)
 	list_for_each_entry(insn, &file->mcount_loc_list, call_node)
 		idx++;
 
-	sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx);
+	sec = elf_create_section(file->elf, "__mcount_loc", 0, addrsize, idx);
 	if (!sec)
 		return -1;
 
+	sec->sh.sh_addralign = addrsize;
+
 	idx = 0;
 	list_for_each_entry(insn, &file->mcount_loc_list, call_node) {
+		void *loc;
 
-		loc = (unsigned long *)sec->data->d_buf + idx;
+		loc = sec->data->d_buf + idx;
-		memset(loc, 0, sizeof(unsigned long));
+		memset(loc, 0, addrsize);
 
-		if (elf_add_reloc_to_insn(file->elf, sec,
+		if (elf_add_reloc_to_insn(file->elf, sec, idx,
-					  idx * sizeof(unsigned long),
+					  addrsize == sizeof(u64) ? R_ABS64 : R_ABS32,
-					  R_X86_64_64,
 					  insn->sec, insn->offset))
 			return -1;
 
-		idx++;
+		idx += addrsize;
 	}
 
 	return 0;
@@ -1254,18 +1256,19 @@ static void annotate_call_site(struct objtool_file *file,
 	if (opts.mcount && sym->fentry) {
 		if (sibling)
 			WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset);
+		if (opts.mnop) {
+			if (reloc) {
+				reloc->type = R_NONE;
+				elf_write_reloc(file->elf, reloc);
+			}
 
-		if (reloc) {
+			elf_write_insn(file->elf, insn->sec,
-			reloc->type = R_NONE;
+				       insn->offset, insn->len,
-			elf_write_reloc(file->elf, reloc);
+				       arch_nop_insn(insn->len));
+
+			insn->type = INSN_NOP;
 		}
 
-		elf_write_insn(file->elf, insn->sec,
-			       insn->offset, insn->len,
-			       arch_nop_insn(insn->len));
-
-		insn->type = INSN_NOP;
-
 		list_add_tail(&insn->call_node, &file->mcount_loc_list);
 		return;
 	}
@@ -2100,7 +2103,7 @@ static int read_unwind_hints(struct objtool_file *file)
 			return -1;
 		}
 
-		cfi.cfa.offset = bswap_if_needed(hint->sp_offset);
+		cfi.cfa.offset = bswap_if_needed(file->elf, hint->sp_offset);
 		cfi.type = hint->type;
 		cfi.end = hint->end;
 
@@ -2313,7 +2316,7 @@ static int classify_symbols(struct objtool_file *file)
 			if (arch_is_rethunk(func))
 				func->return_thunk = true;
 
-			if (!strcmp(func->name, "__fentry__"))
+			if (arch_ftrace_match(func->name))
 				func->fentry = true;
 
 			if (is_profiling_func(func->name))
@@ -2389,9 +2392,11 @@ static int decode_sections(struct objtool_file *file)
 	 * Must be before add_jump_destinations(), which depends on 'func'
 	 * being set for alternatives, to enable proper sibling call detection.
 	 */
-	ret = add_special_section_alts(file);
+	if (opts.stackval || opts.orc || opts.uaccess || opts.noinstr) {
-	if (ret)
+		ret = add_special_section_alts(file);
-		return ret;
+		if (ret)
+			return ret;
+	}
 
 	ret = add_jump_destinations(file);
 	if (ret)

tools/objtool/elf.c

@@ -1129,6 +1129,7 @@ static struct section *elf_create_rela_reloc_section(struct elf *elf, struct sec
 {
 	char *relocname;
 	struct section *sec;
+	int addrsize = elf_class_addrsize(elf);
 
 	relocname = malloc(strlen(base->name) + strlen(".rela") + 1);
 	if (!relocname) {
@@ -1138,7 +1139,10 @@ static struct section *elf_create_rela_reloc_section(struct elf *elf, struct sec
 	strcpy(relocname, ".rela");
 	strcat(relocname, base->name);
 
-	sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rela), 0);
+	if (addrsize == sizeof(u32))
+		sec = elf_create_section(elf, relocname, 0, sizeof(Elf32_Rela), 0);
+	else
+		sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rela), 0);
 	free(relocname);
 	if (!sec)
 		return NULL;
@@ -1147,7 +1151,7 @@ static struct section *elf_create_rela_reloc_section(struct elf *elf, struct sec
 	sec->base = base;
 
 	sec->sh.sh_type = SHT_RELA;
-	sec->sh.sh_addralign = 8;
+	sec->sh.sh_addralign = addrsize;
 	sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx;
 	sec->sh.sh_info = base->idx;
 	sec->sh.sh_flags = SHF_INFO_LINK;

tools/objtool/include/objtool/arch.h

@@ -69,6 +69,8 @@ struct stack_op {
 
 struct instruction;
 
+int arch_ftrace_match(char *name);
+
 void arch_initial_func_cfi_state(struct cfi_init_state *state);
 
 int arch_decode_instruction(struct objtool_file *file, const struct section *sec,
@@ -93,4 +95,6 @@ bool arch_is_rethunk(struct symbol *sym);
 
 int arch_rewrite_retpolines(struct objtool_file *file);
 
+bool arch_pc_relative_reloc(struct reloc *reloc);
+
 #endif /* _ARCH_H */

tools/objtool/include/objtool/builtin.h

@@ -31,6 +31,7 @@ struct opts {
 	bool backup;
 	bool dryrun;
 	bool link;
+	bool mnop;
 	bool module;
 	bool no_unreachable;
 	bool sec_address;

tools/objtool/include/objtool/elf.h

@@ -142,6 +142,14 @@ static inline bool has_multiple_files(struct elf *elf)
 	return elf->num_files > 1;
 }
 
+static inline int elf_class_addrsize(struct elf *elf)
+{
+	if (elf->ehdr.e_ident[EI_CLASS] == ELFCLASS32)
+		return sizeof(u32);
+	else
+		return sizeof(u64);
+}
+
 struct elf *elf_open_read(const char *name, int flags);
 struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr);
 

tools/objtool/include/objtool/endianness.h

@@ -2,33 +2,33 @@
 #ifndef _OBJTOOL_ENDIANNESS_H
 #define _OBJTOOL_ENDIANNESS_H
 
-#include <arch/endianness.h>
 #include <linux/kernel.h>
 #include <endian.h>
-
+#include <objtool/elf.h>
-#ifndef __TARGET_BYTE_ORDER
-#error undefined arch __TARGET_BYTE_ORDER
-#endif
-
-#if __BYTE_ORDER != __TARGET_BYTE_ORDER
-#define __NEED_BSWAP 1
-#else
-#define __NEED_BSWAP 0
-#endif
 
 /*
- * Does a byte swap if target endianness doesn't match the host, i.e. cross
+ * Does a byte swap if target file endianness doesn't match the host, i.e. cross
  * compilation for little endian on big endian and vice versa.
  * To be used for multi-byte values conversion, which are read from / about
  * to be written to a target native endianness ELF file.
  */
-#define bswap_if_needed(val)						\
+static inline bool need_bswap(struct elf *elf)
+{
+	return (__BYTE_ORDER == __LITTLE_ENDIAN) ^
+	       (elf->ehdr.e_ident[EI_DATA] == ELFDATA2LSB);
+}
+
+#define bswap_if_needed(elf, val)					\
 ({									\
 	__typeof__(val) __ret;						\
+	bool __need_bswap = need_bswap(elf);				\
 	switch (sizeof(val)) {						\
-	case 8: __ret = __NEED_BSWAP ? bswap_64(val) : (val); break;	\
+	case 8:								\
-	case 4: __ret = __NEED_BSWAP ? bswap_32(val) : (val); break;	\
+		__ret = __need_bswap ? bswap_64(val) : (val); break;	\
-	case 2: __ret = __NEED_BSWAP ? bswap_16(val) : (val); break;	\
+	case 4:								\
+		__ret = __need_bswap ? bswap_32(val) : (val); break;	\
+	case 2:								\
+		__ret = __need_bswap ? bswap_16(val) : (val); break;	\
 	default:							\
 		BUILD_BUG(); break;					\
 	}								\

tools/objtool/orc_dump.c

@@ -76,6 +76,7 @@ int orc_dump(const char *_objname)
 	GElf_Rela rela;
 	GElf_Sym sym;
 	Elf_Data *data, *symtab = NULL, *rela_orc_ip = NULL;
+	struct elf dummy_elf = {};
 
 
 	objname = _objname;
@@ -94,6 +95,12 @@ int orc_dump(const char *_objname)
 		return -1;
 	}
 
+	if (!elf64_getehdr(elf)) {
+		WARN_ELF("elf64_getehdr");
+		return -1;
+	}
+	memcpy(&dummy_elf.ehdr, elf64_getehdr(elf), sizeof(dummy_elf.ehdr));
+
 	if (elf_getshdrnum(elf, &nr_sections)) {
 		WARN_ELF("elf_getshdrnum");
 		return -1;
@@ -198,11 +205,11 @@ int orc_dump(const char *_objname)
 
 		printf(" sp:");
 
-		print_reg(orc[i].sp_reg, bswap_if_needed(orc[i].sp_offset));
+		print_reg(orc[i].sp_reg, bswap_if_needed(&dummy_elf, orc[i].sp_offset));
 
 		printf(" bp:");
 
-		print_reg(orc[i].bp_reg, bswap_if_needed(orc[i].bp_offset));
+		print_reg(orc[i].bp_reg, bswap_if_needed(&dummy_elf, orc[i].bp_offset));
 
 		printf(" type:%s end:%d\n",
 		       orc_type_name(orc[i].type), orc[i].end);

tools/objtool/orc_gen.c

@@ -97,8 +97,8 @@ static int write_orc_entry(struct elf *elf, struct section *orc_sec,
 	/* populate ORC data */
 	orc = (struct orc_entry *)orc_sec->data->d_buf + idx;
 	memcpy(orc, o, sizeof(*orc));
-	orc->sp_offset = bswap_if_needed(orc->sp_offset);
+	orc->sp_offset = bswap_if_needed(elf, orc->sp_offset);
-	orc->bp_offset = bswap_if_needed(orc->bp_offset);
+	orc->bp_offset = bswap_if_needed(elf, orc->bp_offset);
 
 	/* populate reloc for ip */
 	if (elf_add_reloc_to_insn(elf, ip_sec, idx * sizeof(int), R_X86_64_PC32,

tools/objtool/special.c

@@ -87,7 +87,8 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 	if (entry->feature) {
 		unsigned short feature;
 
-		feature = bswap_if_needed(*(unsigned short *)(sec->data->d_buf +
+		feature = bswap_if_needed(elf,
+					  *(unsigned short *)(sec->data->d_buf +
 							      offset +
 							      entry->feature));
 		arch_handle_alternative(feature, alt);