Merge tag 'core-build-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull orphan section checking from Ingo Molnar:
 "Orphan link sections were a long-standing source of obscure bugs,
  because the heuristics that various linkers & compilers use to handle
  them (include these bits into the output image vs discarding them
  silently) are both highly idiosyncratic and also version dependent.

  Instead of this historically problematic mess, this tree by Kees Cook
  (et al) adds build time asserts and build time warnings if there's any
  orphan section in the kernel or if a section is not sized as expected.

  And because we relied on so many silent assumptions in this area, fix
  a metric ton of dependencies and some outright bugs related to this,
  before we can finally enable the checks on the x86, ARM and ARM64
  platforms"

* tag 'core-build-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  x86/boot/compressed: Warn on orphan section placement
  x86/build: Warn on orphan section placement
  arm/boot: Warn on orphan section placement
  arm/build: Warn on orphan section placement
  arm64/build: Warn on orphan section placement
  x86/boot/compressed: Add missing debugging sections to output
  x86/boot/compressed: Remove, discard, or assert for unwanted sections
  x86/boot/compressed: Reorganize zero-size section asserts
  x86/build: Add asserts for unwanted sections
  x86/build: Enforce an empty .got.plt section
  x86/asm: Avoid generating unused kprobe sections
  arm/boot: Handle all sections explicitly
  arm/build: Assert for unwanted sections
  arm/build: Add missing sections
  arm/build: Explicitly keep .ARM.attributes sections
  arm/build: Refactor linker script headers
  arm64/build: Assert for unwanted sections
  arm64/build: Add missing DWARF sections
  arm64/build: Use common DISCARDS in linker script
  arm64/build: Remove .eh_frame* sections due to unwind tables
  ...

arch/alpha/kernel/vmlinux.lds.S

@@ -72,6 +72,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }

arch/arc/kernel/vmlinux.lds.S

@@ -122,6 +122,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	ELF_DETAILS
 	DISCARDS
 
 	.arcextmap 0 : {

arch/arm/Makefile

@@ -16,6 +16,10 @@ LDFLAGS_vmlinux	+= --be8
 KBUILD_LDFLAGS_MODULE	+= --be8
 endif
 
+# We never want expected sections to be placed heuristically by the
+# linker. All sections should be explicitly named in the linker script.
+LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+
 ifeq ($(CONFIG_ARM_MODULE_PLTS),y)
 KBUILD_LDS_MODULE	+= $(srctree)/arch/arm/kernel/module.lds
 endif

arch/arm/boot/compressed/Makefile

@@ -123,6 +123,8 @@ endif
 LDFLAGS_vmlinux += --no-undefined
 # Delete all temporary local symbols
 LDFLAGS_vmlinux += -X
+# Report orphan sections
+LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
 # Next argument is a linker script
 LDFLAGS_vmlinux += -T
 

arch/arm/boot/compressed/vmlinux.lds.S

@@ -2,6 +2,7 @@
 /*
  *  Copyright (C) 2000 Russell King
  */
+#include <asm/vmlinux.lds.h>
 
 #ifdef CONFIG_CPU_ENDIAN_BE8
 #define ZIMAGE_MAGIC(x) ( (((x) >> 24) & 0x000000ff) | \
@@ -17,8 +18,11 @@ ENTRY(_start)
 SECTIONS
 {
   /DISCARD/ : {
+    COMMON_DISCARDS
     *(.ARM.exidx*)
     *(.ARM.extab*)
+    *(.note.*)
+    *(.rel.*)
     /*
      * Discard any r/w data - this produces a link error if we have any,
      * which is required for PIC decompression.  Local data generates
@@ -36,9 +40,7 @@ SECTIONS
     *(.start)
     *(.text)
     *(.text.*)
-    *(.gnu.warning)
-    *(.glue_7t)
-    *(.glue_7)
+    ARM_STUBS_TEXT
   }
   .table : ALIGN(4) {
     _table_start = .;
@@ -128,12 +130,10 @@ SECTIONS
   PROVIDE(__pecoff_data_size = ALIGN(512) - ADDR(.data));
   PROVIDE(__pecoff_end = ALIGN(512));
 
-  .stab 0		: { *(.stab) }
-  .stabstr 0		: { *(.stabstr) }
-  .stab.excl 0		: { *(.stab.excl) }
-  .stab.exclstr 0	: { *(.stab.exclstr) }
-  .stab.index 0		: { *(.stab.index) }
-  .stab.indexstr 0	: { *(.stab.indexstr) }
-  .comment 0		: { *(.comment) }
+  STABS_DEBUG
+  DWARF_DEBUG
+  ARM_DETAILS
+
+  ARM_ASSERTS
 }
 ASSERT(_edata_real == _edata, "error: zImage file size is incorrect");

arch/arm/kernel/vmlinux.lds.h → arch/arm/include/asm/vmlinux.lds.h

 /* SPDX-License-Identifier: GPL-2.0 */
+#include <asm-generic/vmlinux.lds.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
 #define ARM_CPU_DISCARD(x)
@@ -49,8 +50,29 @@
 		EXIT_CALL						\
 		ARM_MMU_DISCARD(*(.text.fixup))				\
 		ARM_MMU_DISCARD(*(__ex_table))				\
-		*(.discard)						\
-		*(.discard.*)
+		COMMON_DISCARDS
+
+/*
+ * Sections that should stay zero sized, which is safer to explicitly
+ * check instead of blindly discarding.
+ */
+#define ARM_ASSERTS							\
+	.plt : {							\
+		*(.iplt) *(.rel.iplt) *(.iplt) *(.igot.plt)		\
+	}								\
+	ASSERT(SIZEOF(.plt) == 0,					\
+	       "Unexpected run-time procedure linkages detected!")
+
+#define ARM_DETAILS							\
+		ELF_DETAILS						\
+		.ARM.attributes 0 : { *(.ARM.attributes) }
+
+#define ARM_STUBS_TEXT							\
+		*(.gnu.warning)						\
+		*(.glue_7)						\
+		*(.glue_7t)						\
+		*(.vfp11_veneer)                                        \
+		*(.v4_bx)
 
 #define ARM_TEXT							\
 		IDMAP_TEXT						\
@@ -64,9 +86,7 @@
 		CPUIDLE_TEXT						\
 		LOCK_TEXT						\
 		KPROBES_TEXT						\
-		*(.gnu.warning)						\
-		*(.glue_7)						\
-		*(.glue_7t)						\
+		ARM_STUBS_TEXT						\
 		. = ALIGN(4);						\
 		*(.got)			/* Global offset table */	\
 		ARM_CPU_KEEP(PROC_INFO)

arch/arm/kernel/vmlinux-xip.lds.S

@@ -9,15 +9,13 @@
 
 #include <linux/sizes.h>
 
-#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/mpu.h>
 #include <asm/page.h>
 
-#include "vmlinux.lds.h"
-
 OUTPUT_ARCH(arm)
 ENTRY(stext)
 
@@ -152,6 +150,10 @@ SECTIONS
 	_end = .;
 
 	STABS_DEBUG
+	DWARF_DEBUG
+	ARM_DETAILS
+
+	ARM_ASSERTS
 }
 
 /*

arch/arm/kernel/vmlinux.lds.S

@@ -9,15 +9,13 @@
 #else
 
 #include <linux/pgtable.h>
-#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/mpu.h>
 #include <asm/page.h>
 
-#include "vmlinux.lds.h"
-
 OUTPUT_ARCH(arm)
 ENTRY(stext)
 
@@ -151,6 +149,10 @@ SECTIONS
 	_end = .;
 
 	STABS_DEBUG
+	DWARF_DEBUG
+	ARM_DETAILS
+
+	ARM_ASSERTS
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX

arch/arm64/Makefile

@@ -28,6 +28,10 @@ LDFLAGS_vmlinux	+= --fix-cortex-a53-843419
   endif
 endif
 
+# We never want expected sections to be placed heuristically by the
+# linker. All sections should be explicitly named in the linker script.
+LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+
 ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y)
   ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y)
 $(warning LSE atomics not supported by binutils)
@@ -46,13 +50,16 @@ endif
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only	\
 		   $(compat_vdso) $(cc_has_k_constraint)
-KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
 KBUILD_AFLAGS	+= $(compat_vdso)
 
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)
 
+# Avoid generating .eh_frame* sections.
+KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables -fno-unwind-tables
+KBUILD_AFLAGS	+= -fno-asynchronous-unwind-tables -fno-unwind-tables
+
 ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
 prepare: stack_protector_prepare
 stack_protector_prepare: prepare0

arch/arm64/kernel/smccc-call.S

@@ -9,7 +9,6 @@
 #include <asm/assembler.h>
 
 	.macro SMCCC instr
-	.cfi_startproc
 	\instr	#0
 	ldr	x4, [sp]
 	stp	x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
@@ -21,7 +20,6 @@
 	b.ne	1f
 	str	x6, [x4, ARM_SMCCC_QUIRK_STATE_OFFS]
 1:	ret
-	.cfi_endproc
 	.endm
 
 /*

arch/arm64/kernel/vmlinux.lds.S

@@ -6,6 +6,7 @@
  */
 
 #define RO_EXCEPTION_TABLE_ALIGN	8
+#define RUNTIME_DISCARD_EXIT
 
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
@@ -96,13 +97,10 @@ SECTIONS
 	 * matching the same input section name.  There is no documented
 	 * order of matching.
 	 */
+	DISCARDS
 	/DISCARD/ : {
-		EXIT_CALL
-		*(.discard)
-		*(.discard.*)
 		*(.interp .dynamic)
 		*(.dynsym .dynstr .hash .gnu.hash)
-		*(.eh_frame)
 	}
 
 	. = KIMAGE_VADDR;
@@ -131,6 +129,14 @@ SECTIONS
 		*(.got)			/* Global offset table		*/
 	}
 
+	/*
+	 * Make sure that the .got.plt is either completely empty or it
+	 * contains only the lazy dispatch entries.
+	 */
+	.got.plt : { *(.got.plt) }
+	ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18,
+	       "Unexpected GOT/PLT entries detected!")
+
 	. = ALIGN(SEGMENT_ALIGN);
 	_etext = .;			/* End of text section */
 
@@ -249,8 +255,22 @@ SECTIONS
 	_end = .;
 
 	STABS_DEBUG
+	DWARF_DEBUG
+	ELF_DETAILS
 
 	HEAD_SYMBOLS
+
+	/*
+	 * Sections that should stay zero sized, which is safer to
+	 * explicitly check instead of blindly discarding.
+	 */
+	.plt : {
+		*(.plt) *(.plt.*) *(.iplt) *(.igot)
+	}
+	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+
+	.data.rel.ro : { *(.data.rel.ro) }
+	ASSERT(SIZEOF(.data.rel.ro) == 0, "Unexpected RELRO detected!")
 }
 
 #include "image-vars.h"

arch/arm64/mm/mmu.c

@@ -43,7 +43,7 @@
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
-u64 __section(".mmuoff.data.write") vabits_actual;
+u64 __section(.mmuoff.data.write) vabits_actual;
 EXPORT_SYMBOL(vabits_actual);
 
 u64 kimage_voffset __ro_after_init;

arch/csky/kernel/vmlinux.lds.S

@@ -109,6 +109,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }

arch/hexagon/kernel/vmlinux.lds.S

@@ -67,5 +67,6 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 }

arch/ia64/kernel/vmlinux.lds.S

@@ -218,6 +218,7 @@ SECTIONS {
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	/* Default discards */
 	DISCARDS

arch/mips/kernel/vmlinux.lds.S

@@ -202,6 +202,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	/* These must appear regardless of  .  */
 	.gptab.sdata : {

arch/nds32/kernel/vmlinux.lds.S

@@ -64,6 +64,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }

arch/nios2/kernel/vmlinux.lds.S

@@ -58,6 +58,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }

arch/openrisc/kernel/vmlinux.lds.S

@@ -103,6 +103,7 @@ SECTIONS
 	/* Throw in the debugging sections */
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
         /* Sections to be discarded -- must be last */
 	DISCARDS

arch/parisc/boot/compressed/vmlinux.lds.S

@@ -84,6 +84,7 @@ SECTIONS
 	}
 
 	STABS_DEBUG
+	ELF_DETAILS
 	.note 0 : { *(.note) }
 
 	/* Sections to be discarded */

arch/parisc/kernel/vmlinux.lds.S

@@ -164,6 +164,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	ELF_DETAILS
 	.note 0 : { *(.note) }
 
 	/* Sections to be discarded */

arch/powerpc/kernel/vmlinux.lds.S

@@ -360,8 +360,8 @@ SECTIONS
 	PROVIDE32 (end = .);
 
 	STABS_DEBUG
-
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 	/DISCARD/ : {

arch/riscv/kernel/vmlinux.lds.S

@@ -98,6 +98,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }

arch/s390/kernel/vmlinux.lds.S

@@ -181,6 +181,7 @@ SECTIONS
 	/* Debugging sections.	*/
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	/* Sections to be discarded */
 	DISCARDS

arch/sh/kernel/vmlinux.lds.S

@@ -76,6 +76,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }

arch/sparc/kernel/vmlinux.lds.S

@@ -187,6 +187,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }

arch/um/kernel/dyn.lds.S

@@ -164,8 +164,8 @@ SECTIONS
   PROVIDE (end = .);
 
   STABS_DEBUG
-
   DWARF_DEBUG
+  ELF_DETAILS
 
   DISCARDS
 }

arch/um/kernel/uml.lds.S

@@ -108,8 +108,8 @@ SECTIONS
   PROVIDE (end = .);
 
   STABS_DEBUG
-
   DWARF_DEBUG
+  ELF_DETAILS
 
   DISCARDS
 }

arch/x86/Makefile

@@ -209,6 +209,10 @@ ifdef CONFIG_X86_64
 LDFLAGS_vmlinux += -z max-page-size=0x200000
 endif
 
+# We never want expected sections to be placed heuristically by the
+# linker. All sections should be explicitly named in the linker script.
+LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+
 archscripts: scripts_basic
 	$(Q)$(MAKE) $(build)=arch/x86/tools relocs
 

arch/x86/boot/compressed/Makefile

@@ -29,7 +29,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst
 
 KBUILD_CFLAGS := -m$(BITS) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
+KBUILD_CFLAGS += -fno-strict-aliasing -fPIE
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
@@ -45,24 +45,19 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 # Disable relocation relaxation in case the link is not PIE.
 KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no)
+KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
 UBSAN_SANITIZE :=n
 
 KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE)
+KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info)
 # Compressed kernel should be built as PIE since it may be loaded at any
 # address by the bootloader.
-ifeq ($(CONFIG_X86_32),y)
-KBUILD_LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
-else
-# To build 64-bit compressed kernel as PIE, we disable relocation
-# overflow check to avoid relocation overflow error with a new linker
-# command-line option, -z noreloc-overflow.
-KBUILD_LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
-	&& echo "-z noreloc-overflow -pie --no-dynamic-linker")
-endif
-LDFLAGS_vmlinux := -T
+LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker)
+LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+LDFLAGS_vmlinux += -T
 
 hostprogs	:= mkpiggy
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
@@ -96,30 +91,8 @@ vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
 
-# The compressed kernel is built with -fPIC/-fPIE so that a boot loader
-# can place it anywhere in memory and it will still run. However, since
-# it is executed as-is without any ELF relocation processing performed
-# (and has already had all relocation sections stripped from the binary),
-# none of the code can use data relocations (e.g. static assignments of
-# pointer values), since they will be meaningless at runtime. This check
-# will refuse to link the vmlinux if any of these relocations are found.
-quiet_cmd_check_data_rel = DATAREL $@
-define cmd_check_data_rel
-	for obj in $(filter %.o,$^); do \
-		$(READELF) -S $$obj | grep -qF .rel.local && { \
-			echo "error: $$obj has data relocations!" >&2; \
-			exit 1; \
-		} || true; \
-	done
-endef
-
-# We need to run two commands under "if_changed", so merge them into a
-# single invocation.
-quiet_cmd_check-and-link-vmlinux = LD      $@
-      cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
-
 $(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
-	$(call if_changed,check-and-link-vmlinux)
+	$(call if_changed,ld)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE

arch/x86/boot/compressed/head_32.S

@@ -33,32 +33,13 @@
 #include <asm/bootparam.h>
 
 /*
- * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X
- * relocation to get the symbol address in PIC.  When the compressed x86
- * kernel isn't built as PIC, the linker optimizes R_386_GOT32X
- * relocations to their fixed symbol addresses.  However, when the
- * compressed x86 kernel is loaded at a different address, it leads
- * to the following load failure:
- *
- *   Failed to allocate space for phdrs
- *
- * during the decompression stage.
- *
- * If the compressed x86 kernel is relocatable at run-time, it should be
- * compiled with -fPIE, instead of -fPIC, if possible and should be built as
- * Position Independent Executable (PIE) so that linker won't optimize
- * R_386_GOT32X relocation to its fixed symbol address.  Older
- * linkers generate R_386_32 relocations against locally defined symbols,
- * _bss, _ebss, _got, _egot and _end, in PIE.  It isn't wrong, just less
- * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
- * R_386_32 relocations when relocating the kernel.  To generate
- * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as
- * hidden:
+ * These symbols needed to be marked as .hidden to prevent the BFD linker from
+ * generating R_386_32 (rather than R_386_RELATIVE) relocations for them when
+ * the 32-bit compressed kernel is linked as PIE. This is no longer necessary,
+ * but it doesn't hurt to keep them .hidden.
  */
 	.hidden _bss
 	.hidden _ebss
-	.hidden _got
-	.hidden _egot
 	.hidden _end
 
 	__HEAD
@@ -77,10 +58,10 @@ SYM_FUNC_START(startup_32)
 	leal	(BP_scratch+4)(%esi), %esp
 	call	1f
 1:	popl	%edx
-	subl	$1b, %edx
+	addl	$_GLOBAL_OFFSET_TABLE_+(.-1b), %edx
 
 	/* Load new GDT */
-	leal	gdt(%edx), %eax
+	leal	gdt@GOTOFF(%edx), %eax
 	movl	%eax, 2(%eax)
 	lgdt	(%eax)
 
@@ -93,14 +74,16 @@ SYM_FUNC_START(startup_32)
 	movl	%eax, %ss
 
 /*
- * %edx contains the address we are loaded at by the boot loader and %ebx
- * contains the address where we should move the kernel image temporarily
- * for safe in-place decompression. %ebp contains the address that the kernel
- * will be decompressed to.
+ * %edx contains the address we are loaded at by the boot loader (plus the
+ * offset to the GOT).  The below code calculates %ebx to be the address where
+ * we should move the kernel image temporarily for safe in-place decompression
+ * (again, plus the offset to the GOT).
+ *
+ * %ebp is calculated to be the address that the kernel will be decompressed to.
  */
 
 #ifdef CONFIG_RELOCATABLE
-	movl	%edx, %ebx
+	leal	startup_32@GOTOFF(%edx), %ebx
 
 #ifdef CONFIG_EFI_STUB
 /*
@@ -111,7 +94,7 @@ SYM_FUNC_START(startup_32)
  *	image_offset = startup_32 - image_base
  * Otherwise image_offset will be zero and has no effect on the calculations.
  */
-	subl    image_offset(%edx), %ebx
+	subl    image_offset@GOTOFF(%edx), %ebx
 #endif
 
 	movl	BP_kernel_alignment(%esi), %eax
@@ -128,10 +111,10 @@ SYM_FUNC_START(startup_32)
 	movl	%ebx, %ebp	// Save the output address for later
 	/* Target address to relocate to for decompression */
 	addl    BP_init_size(%esi), %ebx
-	subl    $_end, %ebx
+	subl    $_end@GOTOFF, %ebx
 
 	/* Set up the stack */
-	leal	boot_stack_end(%ebx), %esp
+	leal	boot_stack_end@GOTOFF(%ebx), %esp
 
 	/* Zero EFLAGS */
 	pushl	$0
@@ -142,8 +125,8 @@ SYM_FUNC_START(startup_32)
  * where decompression in place becomes safe.
  */
 	pushl	%esi
-	leal	(_bss-4)(%edx), %esi
-	leal	(_bss-4)(%ebx), %edi
+	leal	(_bss@GOTOFF-4)(%edx), %esi
+	leal	(_bss@GOTOFF-4)(%ebx), %edi
 	movl	$(_bss - startup_32), %ecx
 	shrl	$2, %ecx
 	std
@@ -156,14 +139,14 @@ SYM_FUNC_START(startup_32)
 	 * during extract_kernel below. To avoid any issues, repoint the GDTR
 	 * to the new copy of the GDT.
 	 */
-	leal	gdt(%ebx), %eax
+	leal	gdt@GOTOFF(%ebx), %eax
 	movl	%eax, 2(%eax)
 	lgdt	(%eax)
 
 /*
  * Jump to the relocated address.
  */
-	leal	.Lrelocated(%ebx), %eax
+	leal	.Lrelocated@GOTOFF(%ebx), %eax
 	jmp	*%eax
 SYM_FUNC_END(startup_32)
 
@@ -173,7 +156,7 @@ SYM_FUNC_START_ALIAS(efi_stub_entry)
 	add	$0x4, %esp
 	movl	8(%esp), %esi	/* save boot_params pointer */
 	call	efi_main
-	leal	startup_32(%eax), %eax
+	/* efi_main returns the possibly relocated address of startup_32 */
 	jmp	*%eax
 SYM_FUNC_END(efi32_stub_entry)
 SYM_FUNC_END_ALIAS(efi_stub_entry)
@@ -186,37 +169,23 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
  * Clear BSS (stack is currently empty)
  */
 	xorl	%eax, %eax
-	leal	_bss(%ebx), %edi
-	leal	_ebss(%ebx), %ecx
+	leal	_bss@GOTOFF(%ebx), %edi
+	leal	_ebss@GOTOFF(%ebx), %ecx
 	subl	%edi, %ecx
 	shrl	$2, %ecx
 	rep	stosl
 
-/*
- * Adjust our own GOT
- */
-	leal	_got(%ebx), %edx
-	leal	_egot(%ebx), %ecx
-1:
-	cmpl	%ecx, %edx
-	jae	2f
-	addl	%ebx, (%edx)
-	addl	$4, %edx
-	jmp	1b
-2:
-
 /*
  * Do the extraction, and jump to the new kernel..
  */
 	/* push arguments for extract_kernel: */
-	pushl	$z_output_len	/* decompressed length, end of relocs */
 
+	pushl	output_len@GOTOFF(%ebx)	/* decompressed length, end of relocs */
 	pushl	%ebp			/* output address */
-
-	pushl	$z_input_len	/* input_len */
-	leal	input_data(%ebx), %eax
+	pushl	input_len@GOTOFF(%ebx)	/* input_len */
+	leal	input_data@GOTOFF(%ebx), %eax
 	pushl	%eax			/* input_data */
-	leal	boot_heap(%ebx), %eax
+	leal	boot_heap@GOTOFF(%ebx), %eax
 	pushl	%eax			/* heap area */
 	pushl	%esi			/* real mode pointer */
 	call	extract_kernel		/* returns kernel location in %eax */

arch/x86/boot/compressed/head_64.S

@@ -40,11 +40,35 @@
  */
 	.hidden _bss
 	.hidden _ebss
-	.hidden _got
-	.hidden _egot
 	.hidden _end
 
 	__HEAD
+
+/*
+ * This macro gives the relative virtual address of X, i.e. the offset of X
+ * from startup_32. This is the same as the link-time virtual address of X,
+ * since startup_32 is at 0, but defining it this way tells the
+ * assembler/linker that we do not want the actual run-time address of X. This
+ * prevents the linker from trying to create unwanted run-time relocation
+ * entries for the reference when the compressed kernel is linked as PIE.
+ *
+ * A reference X(%reg) will result in the link-time VA of X being stored with
+ * the instruction, and a run-time R_X86_64_RELATIVE relocation entry that
+ * adds the 64-bit base address where the kernel is loaded.
+ *
+ * Replacing it with (X-startup_32)(%reg) results in the offset being stored,
+ * and no run-time relocation.
+ *
+ * The macro should be used as a displacement with a base register containing
+ * the run-time address of startup_32 [i.e. rva(X)(%reg)], or as an immediate
+ * [$ rva(X)].
+ *
+ * This macro can only be used from within the .head.text section, since the
+ * expression requires startup_32 to be in the same section as the code being
+ * assembled.
+ */
+#define rva(X) ((X) - startup_32)
+
 	.code32
 SYM_FUNC_START(startup_32)
 	/*
@@ -67,10 +91,10 @@ SYM_FUNC_START(startup_32)
 	leal	(BP_scratch+4)(%esi), %esp
 	call	1f
 1:	popl	%ebp
-	subl	$1b, %ebp
+	subl	$ rva(1b), %ebp
 
 	/* Load new GDT with the 64bit segments using 32bit descriptor */
-	leal	gdt(%ebp), %eax
+	leal	rva(gdt)(%ebp), %eax
 	movl	%eax, 2(%eax)
 	lgdt	(%eax)
 
@@ -83,7 +107,7 @@ SYM_FUNC_START(startup_32)
 	movl	%eax, %ss
 
 /* setup a stack and make sure cpu supports long mode. */
-	leal	boot_stack_end(%ebp), %esp
+	leal	rva(boot_stack_end)(%ebp), %esp
 
 	call	verify_cpu
 	testl	%eax, %eax
@@ -110,7 +134,7 @@ SYM_FUNC_START(startup_32)
  *	image_offset = startup_32 - image_base
  * Otherwise image_offset will be zero and has no effect on the calculations.
  */
-	subl    image_offset(%ebp), %ebx
+	subl    rva(image_offset)(%ebp), %ebx
 #endif
 
 	movl	BP_kernel_alignment(%esi), %eax
@@ -126,7 +150,7 @@ SYM_FUNC_START(startup_32)
 
 	/* Target address to relocate to for decompression */
 	addl	BP_init_size(%esi), %ebx
-	subl	$_end, %ebx
+	subl	$ rva(_end), %ebx
 
 /*
  * Prepare for entering 64 bit mode
@@ -154,19 +178,19 @@ SYM_FUNC_START(startup_32)
 1:
 
 	/* Initialize Page tables to 0 */
-	leal	pgtable(%ebx), %edi
+	leal	rva(pgtable)(%ebx), %edi
 	xorl	%eax, %eax
 	movl	$(BOOT_INIT_PGT_SIZE/4), %ecx
 	rep	stosl
 
 	/* Build Level 4 */
-	leal	pgtable + 0(%ebx), %edi
+	leal	rva(pgtable + 0)(%ebx), %edi
 	leal	0x1007 (%edi), %eax
 	movl	%eax, 0(%edi)
 	addl	%edx, 4(%edi)
 
 	/* Build Level 3 */
-	leal	pgtable + 0x1000(%ebx), %edi
+	leal	rva(pgtable + 0x1000)(%ebx), %edi
 	leal	0x1007(%edi), %eax
 	movl	$4, %ecx
 1:	movl	%eax, 0x00(%edi)
@@ -177,7 +201,7 @@ SYM_FUNC_START(startup_32)
 	jnz	1b
 
 	/* Build Level 2 */
-	leal	pgtable + 0x2000(%ebx), %edi
+	leal	rva(pgtable + 0x2000)(%ebx), %edi
 	movl	$0x00000183, %eax
 	movl	$2048, %ecx
 1:	movl	%eax, 0(%edi)
@@ -188,7 +212,7 @@ SYM_FUNC_START(startup_32)
 	jnz	1b
 
 	/* Enable the boot page tables */
-	leal	pgtable(%ebx), %eax
+	leal	rva(pgtable)(%ebx), %eax
 	movl	%eax, %cr3
 
 	/* Enable Long mode in EFER (Extended Feature Enable Register) */
@@ -213,14 +237,14 @@ SYM_FUNC_START(startup_32)
 	 * We place all of the values on our mini stack so lret can
 	 * used to perform that far jump.
 	 */
-	leal	startup_64(%ebp), %eax
+	leal	rva(startup_64)(%ebp), %eax
 #ifdef CONFIG_EFI_MIXED
-	movl	efi32_boot_args(%ebp), %edi
+	movl	rva(efi32_boot_args)(%ebp), %edi
 	cmp	$0, %edi
 	jz	1f
-	leal	efi64_stub_entry(%ebp), %eax
-	movl	efi32_boot_args+4(%ebp), %esi
-	movl	efi32_boot_args+8(%ebp), %edx	// saved bootparams pointer
+	leal	rva(efi64_stub_entry)(%ebp), %eax
+	movl	rva(efi32_boot_args+4)(%ebp), %esi
+	movl	rva(efi32_boot_args+8)(%ebp), %edx	// saved bootparams pointer
 	cmpl	$0, %edx
 	jnz	1f
 	/*
@@ -231,7 +255,7 @@ SYM_FUNC_START(startup_32)
 	 * the correct stack alignment for entry.
 	 */
 	subl	$40, %esp
-	leal	efi_pe_entry(%ebp), %eax
+	leal	rva(efi_pe_entry)(%ebp), %eax
 	movl	%edi, %ecx			// MS calling convention
 	movl	%esi, %edx
 1:
@@ -257,18 +281,18 @@ SYM_FUNC_START(efi32_stub_entry)
 
 	call	1f
 1:	pop	%ebp
-	subl	$1b, %ebp
+	subl	$ rva(1b), %ebp
 
-	movl	%esi, efi32_boot_args+8(%ebp)
+	movl	%esi, rva(efi32_boot_args+8)(%ebp)
 SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL)
-	movl	%ecx, efi32_boot_args(%ebp)
-	movl	%edx, efi32_boot_args+4(%ebp)
-	movb	$0, efi_is64(%ebp)
+	movl	%ecx, rva(efi32_boot_args)(%ebp)
+	movl	%edx, rva(efi32_boot_args+4)(%ebp)
+	movb	$0, rva(efi_is64)(%ebp)
 
 	/* Save firmware GDTR and code/data selectors */
-	sgdtl	efi32_boot_gdt(%ebp)
-	movw	%cs, efi32_boot_cs(%ebp)
-	movw	%ds, efi32_boot_ds(%ebp)
+	sgdtl	rva(efi32_boot_gdt)(%ebp)
+	movw	%cs, rva(efi32_boot_cs)(%ebp)
+	movw	%ds, rva(efi32_boot_ds)(%ebp)
 
 	/* Disable paging */
 	movl	%cr0, %eax
@@ -347,30 +371,11 @@ SYM_CODE_START(startup_64)
 
 	/* Target address to relocate to for decompression */
 	movl	BP_init_size(%rsi), %ebx
-	subl	$_end, %ebx
+	subl	$ rva(_end), %ebx
 	addq	%rbp, %rbx
 
 	/* Set up the stack */
-	leaq	boot_stack_end(%rbx), %rsp
-
-	/*
-	 * paging_prepare() and cleanup_trampoline() below can have GOT
-	 * references. Adjust the table with address we are running at.
-	 *
-	 * Zero RAX for adjust_got: the GOT was not adjusted before;
-	 * there's no adjustment to undo.
-	 */
-	xorq	%rax, %rax
-
-	/*
-	 * Calculate the address the binary is loaded at and use it as
-	 * a GOT adjustment.
-	 */
-	call	1f
-1:	popq	%rdi
-	subq	$1b, %rdi
-
-	call	.Ladjust_got
+	leaq	rva(boot_stack_end)(%rbx), %rsp
 
 	/*
 	 * At this point we are in long mode with 4-level paging enabled,
@@ -444,7 +449,7 @@ SYM_CODE_START(startup_64)
 	lretq
 trampoline_return:
 	/* Restore the stack, the 32-bit trampoline uses its own stack */
-	leaq	boot_stack_end(%rbx), %rsp
+	leaq	rva(boot_stack_end)(%rbx), %rsp
 
 	/*
 	 * cleanup_trampoline() would restore trampoline memory.
@@ -456,7 +461,7 @@ trampoline_return:
 	 * this function call.
 	 */
 	pushq	%rsi
-	leaq	top_pgtable(%rbx), %rdi
+	leaq	rva(top_pgtable)(%rbx), %rdi
 	call	cleanup_trampoline
 	popq	%rsi
 
@@ -464,30 +469,15 @@ trampoline_return:
 	pushq	$0
 	popfq
 
-	/*
-	 * Previously we've adjusted the GOT with address the binary was
-	 * loaded at. Now we need to re-adjust for relocation address.
-	 *
-	 * Calculate the address the binary is loaded at, so that we can
-	 * undo the previous GOT adjustment.
-	 */
-	call	1f
-1:	popq	%rax
-	subq	$1b, %rax
-
-	/* The new adjustment is the relocation address */
-	movq	%rbx, %rdi
-	call	.Ladjust_got
-
 /*
  * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
 	pushq	%rsi
 	leaq	(_bss-8)(%rip), %rsi
-	leaq	(_bss-8)(%rbx), %rdi
-	movq	$_bss /* - $startup_32 */, %rcx
-	shrq	$3, %rcx
+	leaq	rva(_bss-8)(%rbx), %rdi
+	movl	$(_bss - startup_32), %ecx
+	shrl	$3, %ecx
 	std
 	rep	movsq
 	cld
@@ -498,15 +488,15 @@ trampoline_return:
 	 * during extract_kernel below. To avoid any issues, repoint the GDTR
 	 * to the new copy of the GDT.
 	 */
-	leaq	gdt64(%rbx), %rax
-	leaq	gdt(%rbx), %rdx
+	leaq	rva(gdt64)(%rbx), %rax
+	leaq	rva(gdt)(%rbx), %rdx
 	movq	%rdx, 2(%rax)
 	lgdt	(%rax)
 
 /*
  * Jump to the relocated address.
  */
-	leaq	.Lrelocated(%rbx), %rax
+	leaq	rva(.Lrelocated)(%rbx), %rax
 	jmp	*%rax
 SYM_CODE_END(startup_64)
 
@@ -518,7 +508,7 @@ SYM_FUNC_START_ALIAS(efi_stub_entry)
 	movq	%rdx, %rbx			/* save boot_params pointer */
 	call	efi_main
 	movq	%rbx,%rsi
-	leaq	startup_64(%rax), %rax
+	leaq	rva(startup_64)(%rax), %rax
 	jmp	*%rax
 SYM_FUNC_END(efi64_stub_entry)
 SYM_FUNC_END_ALIAS(efi_stub_entry)
@@ -544,9 +534,9 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 	movq	%rsi, %rdi		/* real mode address */
 	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
 	leaq	input_data(%rip), %rdx  /* input_data */
-	movl	$z_input_len, %ecx	/* input_len */
+	movl	input_len(%rip), %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
-	movl	$z_output_len, %r9d	/* decompressed length, end of relocs */
+	movl	output_len(%rip), %r9d	/* decompressed length, end of relocs */
 	call	extract_kernel		/* returns kernel location in %rax */
 	popq	%rsi
 
@@ -556,27 +546,6 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 	jmp	*%rax
 SYM_FUNC_END(.Lrelocated)
 
-/*
- * Adjust the global offset table
- *
- * RAX is the previous adjustment of the table to undo (use 0 if it's the
- * first time we touch GOT).
- * RDI is the new adjustment to apply.
- */
-.Ladjust_got:
-	/* Walk through the GOT adding the address to the entries */
-	leaq	_got(%rip), %rdx
-	leaq	_egot(%rip), %rcx
-1:
-	cmpq	%rcx, %rdx
-	jae	2f
-	subq	%rax, (%rdx)	/* Undo previous adjustment */
-	addq	%rdi, (%rdx)	/* Apply the new adjustment */
-	addq	$8, %rdx
-	jmp	1b
-2:
-	ret
-
 	.code32
 /*
  * This is the 32-bit trampoline that will be copied over to low memory.
@@ -702,7 +671,7 @@ SYM_DATA(efi_is64, .byte 1)
 #define BS32_handle_protocol	88 // offsetof(efi_boot_services_32_t, handle_protocol)
 #define LI32_image_base		32 // offsetof(efi_loaded_image_32_t, image_base)
 
-	.text
+	__HEAD
 	.code32
 SYM_FUNC_START(efi32_pe_entry)
 /*
@@ -724,12 +693,12 @@ SYM_FUNC_START(efi32_pe_entry)
 
 	call	1f
 1:	pop	%ebx
-	subl	$1b, %ebx
+	subl	$ rva(1b), %ebx
 
 	/* Get the loaded image protocol pointer from the image handle */
 	leal	-4(%ebp), %eax
 	pushl	%eax				// &loaded_image
-	leal	loaded_image_proto(%ebx), %eax
+	leal	rva(loaded_image_proto)(%ebx), %eax
 	pushl	%eax				// pass the GUID address
 	pushl	8(%ebp)				// pass the image handle
 
@@ -764,7 +733,7 @@ SYM_FUNC_START(efi32_pe_entry)
 	 * use it before we get to the 64-bit efi_pe_entry() in C code.
 	 */
 	subl	%esi, %ebx
-	movl	%ebx, image_offset(%ebp)	// save image_offset
+	movl	%ebx, rva(image_offset)(%ebp)	// save image_offset
 	jmp	efi32_pe_stub_entry
 
 2:	popl	%edi				// restore callee-save registers

arch/x86/boot/compressed/mkpiggy.c

@@ -60,6 +60,12 @@ int main(int argc, char *argv[])
 	printf(".incbin \"%s\"\n", argv[1]);
 	printf("input_data_end:\n");
 
+	printf(".section \".rodata\",\"a\",@progbits\n");
+	printf(".globl input_len\n");
+	printf("input_len:\n\t.long %lu\n", ilen);
+	printf(".globl output_len\n");
+	printf("output_len:\n\t.long %lu\n", (unsigned long)olen);
+
 	retval = 0;
 bail:
 	if (f)

arch/x86/boot/compressed/vmlinux.lds.S

@@ -42,12 +42,6 @@ SECTIONS
 		*(.rodata.*)
 		_erodata = . ;
 	}
-	.got : {
-		_got = .;
-		KEEP(*(.got.plt))
-		KEEP(*(.got))
-		_egot = .;
-	}
 	.data :	{
 		_data = . ;
 		*(.data)
@@ -75,5 +69,49 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);	/* keep ZO size page aligned */
 	_end = .;
 
+	STABS_DEBUG
+	DWARF_DEBUG
+	ELF_DETAILS
+
 	DISCARDS
+	/DISCARD/ : {
+		*(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss)
+		*(.hash) *(.gnu.hash)
+		*(.note.*)
+	}
+
+	.got.plt (INFO) : {
+		*(.got.plt)
+	}
+	ASSERT(SIZEOF(.got.plt) == 0 ||
+#ifdef CONFIG_X86_64
+	       SIZEOF(.got.plt) == 0x18,
+#else
+	       SIZEOF(.got.plt) == 0xc,
+#endif
+	       "Unexpected GOT/PLT entries detected!")
+
+	/*
+	 * Sections that should stay zero sized, which is safer to
+	 * explicitly check instead of blindly discarding.
+	 */
+	.got : {
+		*(.got)
+	}
+	ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!")
+
+	.plt : {
+		*(.plt) *(.plt.*)
+	}
+	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+
+	.rel.dyn : {
+		*(.rel.*) *(.rel_*)
+	}
+	ASSERT(SIZEOF(.rel.dyn) == 0, "Unexpected run-time relocations (.rel) detected!")
+
+	.rela.dyn : {
+		*(.rela.*) *(.rela_*)
+	}
+	ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
 }

arch/x86/boot/setup.ld

@@ -20,7 +20,7 @@ SECTIONS
 	.initdata	: { *(.initdata) }
 	__end_init = .;
 
-	.text		: { *(.text) }
+	.text		: { *(.text .text.*) }
 	.text32		: { *(.text32) }
 
 	. = ALIGN(16);

arch/x86/include/asm/asm.h

@@ -141,11 +141,15 @@
 # define _ASM_EXTABLE_FAULT(from, to)				\
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
 
+# ifdef CONFIG_KPROBES
 #  define _ASM_NOKPROBE(entry)					\
 	.pushsection "_kprobe_blacklist","aw" ;			\
 	_ASM_ALIGN ;						\
 	_ASM_PTR (entry);					\
 	.popsection
+# else
+#  define _ASM_NOKPROBE(entry)
+# endif
 
 #else /* ! __ASSEMBLY__ */
 # define _EXPAND_EXTABLE_HANDLE(x) #x

arch/x86/kernel/vmlinux.lds.S

@@ -411,10 +411,47 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
-}
 
+	/*
+	 * Make sure that the .got.plt is either completely empty or it
+	 * contains only the lazy dispatch entries.
+	 */
+	.got.plt (INFO) : { *(.got.plt) }
+	ASSERT(SIZEOF(.got.plt) == 0 ||
+#ifdef CONFIG_X86_64
+	       SIZEOF(.got.plt) == 0x18,
+#else
+	       SIZEOF(.got.plt) == 0xc,
+#endif
+	       "Unexpected GOT/PLT entries detected!")
+
+	/*
+	 * Sections that should stay zero sized, which is safer to
+	 * explicitly check instead of blindly discarding.
+	 */
+	.got : {
+		*(.got) *(.igot.*)
+	}
+	ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!")
+
+	.plt : {
+		*(.plt) *(.plt.*) *(.iplt)
+	}
+	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+
+	.rel.dyn : {
+		*(.rel.*) *(.rel_*)
+	}
+	ASSERT(SIZEOF(.rel.dyn) == 0, "Unexpected run-time relocations (.rel) detected!")
+
+	.rela.dyn : {
+		*(.rela.*) *(.rela_*)
+	}
+	ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
+}
 
 #ifdef CONFIG_X86_32
 /*

drivers/firmware/efi/libstub/Makefile

@@ -18,7 +18,8 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ \
 # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
 # disable the stackleak plugin
 cflags-$(CONFIG_ARM64)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
-				   -fpie $(DISABLE_STACKLEAK_PLUGIN)
+				   -fpie $(DISABLE_STACKLEAK_PLUGIN) \
+				   $(call cc-option,-mbranch-protection=none)
 cflags-$(CONFIG_ARM)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
@@ -26,7 +27,7 @@ cflags-$(CONFIG_ARM)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
 cflags-$(CONFIG_EFI_GENERIC_STUB) += -I$(srctree)/scripts/dtc/libfdt
 
 KBUILD_CFLAGS			:= $(cflags-y) -Os -DDISABLE_BRANCH_PROFILING \
-				   -include $(srctree)/drivers/firmware/efi/libstub/hidden.h \
+				   -include $(srctree)/include/linux/hidden.h \
 				   -D__NO_FORTIFY \
 				   -ffreestanding \
 				   -fno-stack-protector \
@@ -65,6 +66,12 @@ lib-$(CONFIG_ARM64)		+= arm64-stub.o
 lib-$(CONFIG_X86)		+= x86-stub.o
 CFLAGS_arm32-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 
+# Even when -mbranch-protection=none is set, Clang will generate a
+# .note.gnu.property for code-less object files (like lib/ctype.c),
+# so work around this by explicitly removing the unwanted section.
+# https://bugs.llvm.org/show_bug.cgi?id=46480
+STUBCOPY_FLAGS-y		+= --remove-section=.note.gnu.property
+
 #
 # For x86, bootloaders like systemd-boot or grub-efi do not zero-initialize the
 # .bss section, so the .bss section of the EFI stub needs to be included in the

drivers/firmware/efi/libstub/hidden.h

-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * To prevent the compiler from emitting GOT-indirected (and thus absolute)
- * references to any global symbols, override their visibility as 'hidden'
- */
-#pragma GCC visibility push(hidden)

include/asm-generic/vmlinux.lds.h

@@ -34,6 +34,7 @@
  *
  *	STABS_DEBUG
  *	DWARF_DEBUG
+ *	ELF_DETAILS
  *
  *	DISCARDS		// must be the last
  * }
@@ -581,7 +582,10 @@
  */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
+		*(.text.hot .text.hot.*)				\
+		*(TEXT_MAIN .text.fixup)				\
+		*(.text.unlikely .text.unlikely.*)			\
+		*(.text.unknown .text.unknown.*)			\
 		NOINSTR_TEXT						\
 		*(.text..refcount)					\
 		*(.ref.text)						\
@@ -812,15 +816,21 @@
 		.debug_macro	0 : { *(.debug_macro) }			\
 		.debug_addr	0 : { *(.debug_addr) }
 
-		/* Stabs debugging sections.  */
+/* Stabs debugging sections. */
 #define STABS_DEBUG							\
 		.stab 0 : { *(.stab) }					\
 		.stabstr 0 : { *(.stabstr) }				\
 		.stab.excl 0 : { *(.stab.excl) }			\
 		.stab.exclstr 0 : { *(.stab.exclstr) }			\
 		.stab.index 0 : { *(.stab.index) }			\
-		.stab.indexstr 0 : { *(.stab.indexstr) }		\
-		.comment 0 : { *(.comment) }
+		.stab.indexstr 0 : { *(.stab.indexstr) }
+
+/* Required sections not related to debugging. */
+#define ELF_DETAILS							\
+		.comment 0 : { *(.comment) }				\
+		.symtab 0 : { *(.symtab) }				\
+		.strtab 0 : { *(.strtab) }				\
+		.shstrtab 0 : { *(.shstrtab) }
 
 #ifdef CONFIG_GENERIC_BUG
 #define BUG_TABLE							\
@@ -955,13 +965,38 @@
 	EXIT_DATA
 #endif
 
+/*
+ * Clang's -fsanitize=kernel-address and -fsanitize=thread produce
+ * unwanted sections (.eh_frame and .init_array.*), but
+ * CONFIG_CONSTRUCTORS wants to keep any .init_array.* sections.
+ * https://bugs.llvm.org/show_bug.cgi?id=46478
+ */
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN)
+# ifdef CONFIG_CONSTRUCTORS
+#  define SANITIZER_DISCARDS						\
+	*(.eh_frame)
+# else
+#  define SANITIZER_DISCARDS						\
+	*(.init_array) *(.init_array.*)					\
+	*(.eh_frame)
+# endif
+#else
+# define SANITIZER_DISCARDS
+#endif
+
+#define COMMON_DISCARDS							\
+	SANITIZER_DISCARDS						\
+	*(.discard)							\
+	*(.discard.*)							\
+	*(.modinfo)							\
+	/* ld.bfd warns about .gnu.version* even when not emitted */	\
+	*(.gnu.version*)						\
+
 #define DISCARDS							\
 	/DISCARD/ : {							\
 	EXIT_DISCARDS							\
 	EXIT_CALL							\
-	*(.discard)							\
-	*(.discard.*)							\
-	*(.modinfo)							\
+	COMMON_DISCARDS							\
 	}
 
 /**

include/linux/hidden.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * When building position independent code with GCC using the -fPIC option,
+ * (or even the -fPIE one on older versions), it will assume that we are
+ * building a dynamic object (either a shared library or an executable) that
+ * may have symbol references that can only be resolved at load time. For a
+ * variety of reasons (ELF symbol preemption, the CoW footprint of the section
+ * that is modified by the loader), this results in all references to symbols
+ * with external linkage to go via entries in the Global Offset Table (GOT),
+ * which carries absolute addresses which need to be fixed up when the
+ * executable image is loaded at an offset which is different from its link
+ * time offset.
+ *
+ * Fortunately, there is a way to inform the compiler that such symbol
+ * references will be satisfied at link time rather than at load time, by
+ * giving them 'hidden' visibility.
+ */
+
+#pragma GCC visibility push(hidden)