[kvm-unit-tests,v4,13/17] powerpc/ppc64: relocate linker VMAs

QEMU loads the unit test, but due to the way it translates the
unit test's linker VMA to the LMA, we can't just link such that
VMA == LMA. Thus, we link with VMA == 0x0, and then deal with
relocation.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
---
 configure               |  2 ++
 powerpc/Makefile.common | 11 ++++++++--
 powerpc/Makefile.ppc64  |  1 +
 powerpc/cstart64.S      | 34 ++++++++++++++++++++++++++----
 powerpc/flat.lds        | 13 +++++++++++-
 powerpc/reloc64.c       | 55 +++++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 109 insertions(+), 7 deletions(-)
 create mode 100644 powerpc/reloc64.c

On Mon, Feb 15, 2016 at 02:49:22PM +0100, Andrew Jones wrote:
> QEMU loads the unit test, but due to the way it translates the
> unit test's linker VMA to the LMA, we can't just link such that
> VMA == LMA. Thus, we link with VMA == 0x0, and then deal with
> relocation.
> 
> Signed-off-by: Andrew Jones <drjones@redhat.com>
> Tested-by: Laurent Vivier <lvivier@redhat.com>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  configure               |  2 ++
>  powerpc/Makefile.common | 11 ++++++++--
>  powerpc/Makefile.ppc64  |  1 +
>  powerpc/cstart64.S      | 34 ++++++++++++++++++++++++++----
>  powerpc/flat.lds        | 13 +++++++++++-
>  powerpc/reloc64.c       | 55 +++++++++++++++++++++++++++++++++++++++++++++++++
>  6 files changed, 109 insertions(+), 7 deletions(-)
>  create mode 100644 powerpc/reloc64.c
> 
> diff --git a/configure b/configure
> index b367224093369..b2ad199da7873 100755
> --- a/configure
> +++ b/configure
> @@ -5,6 +5,7 @@ kerneldir=/lib/modules/$(uname -r)/build
>  cc=gcc
>  ld=ld
>  objcopy=objcopy
> +objdump=objdump
>  ar=ar
>  arch=`uname -m | sed -e s/i.86/i386/ | sed -e 's/arm.*/arm/'`
>  host=$arch
> @@ -132,6 +133,7 @@ PROCESSOR=$processor
>  CC=$cross_prefix$cc
>  LD=$cross_prefix$ld
>  OBJCOPY=$cross_prefix$objcopy
> +OBJDUMP=$cross_prefix$objdump
>  AR=$cross_prefix$ar
>  API=$api
>  TEST_DIR=$testdir
> diff --git a/powerpc/Makefile.common b/powerpc/Makefile.common
> index de4d1ef3ac816..9654bce1752eb 100644
> --- a/powerpc/Makefile.common
> +++ b/powerpc/Makefile.common
> @@ -22,6 +22,7 @@ CFLAGS += -Wextra
>  CFLAGS += -O2
>  CFLAGS += -I lib -I lib/libfdt
>  CFLAGS += -Wa,-mregnames
> +CFLAGS += -fpie
>  
>  asm-offsets = lib/$(ARCH)/asm-offsets.h
>  include scripts/asm-offsets.mak
> @@ -37,11 +38,17 @@ libgcc := $(shell $(CC) $(machine) --print-libgcc-file-name)
>  start_addr := $(shell printf "%x\n" $$(( $(phys_base) + $(kernel_offset) )))
>  
>  FLATLIBS = $(libcflat) $(LIBFDT_archive) $(libgcc)
> -%.elf: LDFLAGS = $(CFLAGS) -nostdlib
> +%.elf: LDFLAGS = $(CFLAGS) -nostdlib -pie
>  %.elf: %.o $(FLATLIBS) powerpc/flat.lds
>  	$(CC) $(LDFLAGS) -o $@ \
>  		-Wl,-T,powerpc/flat.lds,--build-id=none,-Ttext=$(start_addr) \
>  		$(filter %.o, $^) $(FLATLIBS)
> +	@echo -n Checking $@ for unsupported reloc types...
> +	@if $(OBJDUMP) -R $@ | grep R_ | grep -v R_PPC64_RELATIVE; then	\
> +		false;							\
> +	else								\
> +		echo " looks good.";					\
> +	fi
>  
>  $(TEST_DIR)/boot_rom.bin: $(TEST_DIR)/boot_rom.elf
>  	dd if=/dev/zero of=$@ bs=256 count=1
> @@ -60,4 +67,4 @@ generated_files = $(asm-offsets)
>  
>  test_cases: $(generated_files) $(tests-common) $(tests)
>  
> -$(TEST_DIR)/selftest.elf: $(cstart.o) $(TEST_DIR)/selftest.o
> +$(TEST_DIR)/selftest.elf: $(cstart.o) $(reloc.o) $(TEST_DIR)/selftest.o
> diff --git a/powerpc/Makefile.ppc64 b/powerpc/Makefile.ppc64
> index 95bf6772d65ed..e965627991916 100644
> --- a/powerpc/Makefile.ppc64
> +++ b/powerpc/Makefile.ppc64
> @@ -8,6 +8,7 @@ ldarch = elf64-powerpc
>  kernel_offset = 0x0
>  
>  cstart.o = $(TEST_DIR)/cstart64.o
> +reloc.o  = $(TEST_DIR)/reloc64.o
>  cflatobjs += lib/ppc64/spinlock.o
>  
>  # ppc64 specific tests
> diff --git a/powerpc/cstart64.S b/powerpc/cstart64.S
> index 6d47eb59bb53e..d1a5531eb1c44 100644
> --- a/powerpc/cstart64.S
> +++ b/powerpc/cstart64.S
> @@ -24,12 +24,33 @@
>   */
>  .globl start
>  start:
> -	LOAD_REG_IMMEDIATE(r1, stackptr)
> -	LOAD_REG_IMMEDIATE(r2, tocptr)
> +	/*
> +	 * We were loaded at QEMU's kernel load address, but we're not
> +	 * allowed to link there due to how QEMU deals with linker VMAs,
> +	 * so we just linked at zero. This means the first thing to do is
> +	 * to find our stack and toc, and then do a relocate.
> +	 */
> +	bl	0f
> +0:	mflr	r31
> +	subi	r31, r31, 0b - start    /* QEMU's kernel load address */
> +	ld	r1, (p_stack - start)(r31)
> +	ld	r2, (p_toc - start)(r31)
> +	add	r1, r1, r31
> +	add	r2, r2, r31
>  
>  	/* save DTB pointer */
>  	std	r3, 56(r1)
>  
> +	/*
> +	 * Call relocate. relocate is C code, but careful to not use
> +	 * any global references, as they may use absolute addresses,
> +	 * which are, obviously, not yet relocated.
> +	 */
> +	mr	r3, r31
> +	ld	r4, (p_dyn - start)(r31)
> +	add	r4, r4, r31
> +	bl	relocate
> +
>  	bl	hcall_patch_broken_sc1
>  
>  	/* complete setup */
> @@ -37,13 +58,18 @@ start:
>  	bl	setup
>  
>  	/* run the test */
> -	LOAD_REG_IMMEDIATE(r5, __argc)
> -	LOAD_REG_IMMEDIATE(r4, __argv)
> +	LOAD_REG_ADDR(r5, __argc)
> +	LOAD_REG_ADDR(r4, __argv)
>  	lwz	r3, 0(r5)
>  	bl	main
>  	bl	exit
>  	b	halt
>  
> +.align 3
> +p_stack:	.llong  stackptr
> +p_toc:		.llong  tocptr
> +p_dyn:		.llong  dynamic_start
> +
>  .text
>  .align 3
>  
> diff --git a/powerpc/flat.lds b/powerpc/flat.lds
> index 84087057c0ce2..53221e8b4211c 100644
> --- a/powerpc/flat.lds
> +++ b/powerpc/flat.lds
> @@ -6,11 +6,22 @@ SECTIONS
>      etext = .;
>      .opd : { *(.opd) }
>      . = ALIGN(16);
> +    .dynamic : {
> +        dynamic_start = .;
> +        *(.dynamic)
> +    }
> +    .dynsym : {
> +        dynsym_start = .;
> +        *(.dynsym)
> +    }
> +    .rela.dyn : { *(.rela*) }
> +    . = ALIGN(16);
>      .data : {
>          *(.data)
> +        *(.data.rel*)
>      }
>      . = ALIGN(16);
> -    .rodata : { *(.rodata) }
> +    .rodata : { *(.rodata) *(.rodata.*) }
>      . = ALIGN(16);
>      .bss : { *(.bss) }
>      . = ALIGN(256);
> diff --git a/powerpc/reloc64.c b/powerpc/reloc64.c
> new file mode 100644
> index 0000000000000..d919372bf9288
> --- /dev/null
> +++ b/powerpc/reloc64.c
> @@ -0,0 +1,55 @@
> +/*
> + * relocate R_PPC_RELATIVE RELA entries. Normally this is done in
> + * assembly code to avoid the risk of using absolute addresses before
> + * they're relocated. We use C, but cautiously (no global references).
> + *
> + * Copyright (C) 2016, Red Hat Inc, Andrew Jones <drjones@redhat.com>
> + *
> + * This work is licensed under the terms of the GNU LGPL, version 2.
> + */
> +#define DT_NULL		0
> +#define DT_RELA 	7
> +#define DT_RELACOUNT	0x6ffffff9
> +#define R_PPC_RELATIVE	22
> +
> +struct elf64_dyn {
> +	signed long long tag;
> +	unsigned long long val;
> +};
> +
> +#define RELA_GET_TYPE(rela_ptr) ((rela_ptr)->info & 0xffffffff)
> +struct elf64_rela {
> +	unsigned long long offset;
> +	unsigned long long info;
> +	signed long long addend;
> +};
> +
> +void relocate(unsigned long load_addr, struct elf64_dyn *dyn_table)
> +{
> +	unsigned long long rela_addr = 0, rela_count = 0, *addr;
> +	struct elf64_dyn *d = dyn_table;
> +	struct elf64_rela *r;
> +
> +	while (d && d->tag != DT_NULL) {
> +		if (d->tag == DT_RELA)
> +			rela_addr = d->val;
> +		else if (d->tag == DT_RELACOUNT)
> +			rela_count = d->val;
> +		if (rela_addr && rela_count)
> +			break;
> +		++d;
> +	}
> +
> +	if (!rela_addr || !rela_count)
> +		return;
> +
> +	r = (void *)(rela_addr + load_addr);
> +
> +	while (rela_count--) {
> +		if (RELA_GET_TYPE(r) == R_PPC_RELATIVE) {
> +			addr = (void *)(r->offset + load_addr);
> +			*addr = r->addend + load_addr;
> +		}
> +		++r;
> +	}
> +}