[RFC/RFT PATCH 08/19] x86: Use PIE codegen for the relocatable 64-bit kernel

[Ard Biesheuvel <ardb@kernel.org>]

As an intermediate step towards enabling PIE linking for the x86_64
KASLR kernel, enable PIE codegen for all C and Rust objects that are
linked into the kernel proper. Add a Kconfig option RELOCATABLE_PIE for
this, depending on RELR support in the linker, as the relocation tables
will blow up the kernel image otherwise.

This results in a code size increase of between 0.2% (clang) and 0.5%
(gcc). Performance (hackbench) appears to be unaffected across several
different uarchs.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/Kconfig                  |  4 ++++
 arch/x86/Makefile                 | 19 ++++++++++++++++++-
 arch/x86/boot/Makefile            |  1 +
 arch/x86/boot/compressed/Makefile |  2 +-
 arch/x86/entry/vdso/Makefile      |  1 +
 arch/x86/realmode/rm/Makefile     |  1 +
 include/asm-generic/vmlinux.lds.h |  1 +
 include/linux/hidden.h            |  2 ++
 8 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bf51e17d5813..b3a64cfe04cf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2067,6 +2067,7 @@ config PHYSICAL_START
 config RELOCATABLE
 	bool "Build a relocatable kernel" if X86_32
 	default X86_32
+	select RELOCATABLE_PIE if TOOLS_SUPPORT_RELR
 	help
 	  This builds a kernel image that retains relocation information so it
 	  can be placed someplace besides the default PAGE_OFFSET + 1MB. This
@@ -2087,6 +2088,9 @@ config RELOCATABLE
 	  it has been loaded at and the compile time physical address
 	  (CONFIG_PHYSICAL_START) is used as the minimum location.
 
+config RELOCATABLE_PIE
+	bool
+
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image (KASLR)"
 	select RELOCATABLE
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1d403a3612ea..b211d6c950aa 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -89,6 +89,8 @@ ifdef CONFIG_CC_IS_GCC
 CC_FLAGS_FPU += -mhard-float
 endif
 
+rustflags-nojumptables := $(if $(call rustc-min-version,109300),-Cjump-tables=n,-Zno-jump-tables)
+
 ifeq ($(CONFIG_X86_KERNEL_IBT),y)
 #
 # Kernel IBT has S_CET.NOTRACK_EN=0, as such the compilers must not generate
@@ -100,7 +102,7 @@ ifeq ($(CONFIG_X86_KERNEL_IBT),y)
 #   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104816
 #
 KBUILD_CFLAGS += $(call cc-option,-fcf-protection=branch -fno-jump-tables)
-KBUILD_RUSTFLAGS += -Zcf-protection=branch $(if $(call rustc-min-version,109300),-Cjump-tables=n,-Zno-jump-tables)
+KBUILD_RUSTFLAGS += -Zcf-protection=branch $(rustflags-nojumptables)
 else
 KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
 endif
@@ -178,6 +180,21 @@ endif
         KBUILD_RUSTFLAGS += -Ccode-model=kernel
 
         percpu_seg := gs
+
+        pie-ccflags-$(CONFIG_CC_IS_GCC) += $(call cc-option.-mdirect-extern-access)
+        pie-ccflags-$(CONFIG_CC_IS_CLANG) += -fdirect-access-external-data
+
+        # objtool gets confused by unannotated PIC flavor jump tables
+        pie-ccflags-y += $(call cc-option,-fannotate-jump-tables,-fno-jump-tables)
+
+        pie-cflags-$(CONFIG_RELOCATABLE_PIE) := $(pie-ccflags-y) -fpie -mcmodel=small \
+                                -include $(srctree)/include/linux/hidden.h
+        pie-rustflags-$(CONFIG_RELOCATABLE_PIE) := -Crelocation-model=pie \
+                                -Ccode-model=small -Zdirect-access-external-data=yes \
+                                $(rustflags-nojumptables)
+
+        KBUILD_CFLAGS_KERNEL    += $(pie-cflags-y)
+        KBUILD_RUSTFLAGS_KERNEL += $(pie-rustflags-y)
 endif
 
 ifeq ($(CONFIG_STACKPROTECTOR),y)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 3f9fb3698d66..491b3b2a9a02 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -55,6 +55,7 @@ KBUILD_CFLAGS	:= $(REALMODE_CFLAGS) -D_SETUP
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
+KBUILD_CFLAGS_KERNEL :=
 
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index bc071bdcd11e..96099b5d1064 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -76,7 +76,7 @@ LDFLAGS_vmlinux += -T
 hostprogs	:= mkpiggy
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABbCDGRSTtVW] \(_text\|__data_segment_start\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABbCDdGRSTtVW] \(_text\|__data_segment_start\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
 
 quiet_cmd_voffset = VOFFSET $@
       cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index f247f5f5cb44..bf4221a0fc08 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -143,6 +143,7 @@ endif
 endif
 
 $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+$(obj)/vdso32.so.dbg: KBUILD_CFLAGS_KERNEL :=
 
 $(obj)/vdso32.so.dbg: $(obj)/vdso32/vdso32.lds $(vobjs32) FORCE
 	$(call if_changed,vdso_and_check)
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index a0fb39abc5c8..70bf0a26da91 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -67,3 +67,4 @@ KBUILD_CFLAGS	:= $(REALMODE_CFLAGS) -D_SETUP -D_WAKEUP \
 		   -I$(srctree)/arch/x86/boot
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS_KERNEL :=
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8ca130af301f..1782b6b87b2d 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -373,6 +373,7 @@
 	*(DATA_MAIN)							\
 	*(.data..decrypted)						\
 	*(.ref.data)							\
+	*(.data.rel*)							\
 	*(.data..shared_aligned) /* percpu related */			\
 	*(.data..unlikely)						\
 	__start_once = .;						\
diff --git a/include/linux/hidden.h b/include/linux/hidden.h
index 49a17b6b5962..2ad764c0ca18 100644
--- a/include/linux/hidden.h
+++ b/include/linux/hidden.h
@@ -16,4 +16,6 @@
  * giving them 'hidden' visibility.
  */
 
+#ifndef __BINDGEN__
 #pragma GCC visibility push(hidden)
+#endif
-- 
2.47.3