From 974f221c84b05b1dc2f5ea50dc16d2a9d1e95eda Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 28 Apr 2016 17:09:04 -0700 Subject: [PATCH] x86/boot: Move compressed kernel to the end of the decompression buffer This change makes later calculations about where the kernel is located easier to reason about. To better understand this change, we must first clarify what 'VO' and 'ZO' are. These values were introduced in commits by hpa: 77d1a4999502 ("x86, boot: make symbols from the main vmlinux available") 37ba7ab5e33c ("x86, boot: make kernel_alignment adjustable; new bzImage fields") Specifically: All names prefixed with 'VO_': - relate to the uncompressed kernel image - the size of the VO image is: VO__end-VO__text ("VO_INIT_SIZE" define) All names prefixed with 'ZO_': - relate to the bootable compressed kernel image (boot/compressed/vmlinux), which is composed of the following memory areas: - head text - compressed kernel (VO image and relocs table) - decompressor code - the size of the ZO image is: ZO__end - ZO_startup_32 ("ZO_INIT_SIZE" define, though see below) The 'INIT_SIZE' value is used to find the larger of the two image sizes: #define ZO_INIT_SIZE (ZO__end - ZO_startup_32 + ZO_z_extract_offset) #define VO_INIT_SIZE (VO__end - VO__text) #if ZO_INIT_SIZE > VO_INIT_SIZE # define INIT_SIZE ZO_INIT_SIZE #else # define INIT_SIZE VO_INIT_SIZE #endif The current code uses extract_offset to decide where to position the copied ZO (i.e. ZO starts at extract_offset). (This is why ZO_INIT_SIZE currently includes the extract_offset.) Why does z_extract_offset exist? It's needed because we are trying to minimize the amount of RAM used for the whole act of creating an uncompressed, executable, properly relocation-linked kernel image in system memory. We do this so that kernels can be booted on even very small systems. To achieve the goal of minimal memory consumption we have implemented an in-place decompression strategy: instead of cleanly separating the VO and ZO images and also allocating some memory for the decompression code's runtime needs, we instead create this elaborate layout of memory buffers where the output (decompressed) stream, as it progresses, overlaps with and destroys the input (compressed) stream. This can only be done safely if the ZO image is placed to the end of the VO range, plus a certain amount of safety distance to make sure that when the last bytes of the VO range are decompressed, the compressed stream pointer is safely beyond the end of the VO range. z_extract_offset is calculated in arch/x86/boot/compressed/mkpiggy.c during the build process, at a point when we know the exact compressed and uncompressed size of the kernel images and can calculate this safe minimum offset value. (Note that the mkpiggy.c calculation is not perfect, because we don't know the decompressor used at that stage, so the z_extract_offset calculation is necessarily imprecise and is mostly based on gzip internals - we'll improve that in the next patch.) When INIT_SIZE is bigger than VO_INIT_SIZE (uncommon but possible), the copied ZO occupies the memory from extract_offset to the end of decompression buffer. It overlaps with the soon-to-be-uncompressed kernel like this: |-----compressed kernel image------| V V 0 extract_offset +INIT_SIZE |-----------|---------------|-------------------------|--------| | | | | VO__text startup_32 of ZO VO__end ZO__end ^ ^ |-------uncompressed kernel image---------| When INIT_SIZE is equal to VO_INIT_SIZE (likely) there's still space left from end of ZO to the end of decompressing buffer, like below. |-compressed kernel image-| V V 0 extract_offset +INIT_SIZE |-----------|---------------|-------------------------|--------| | | | | VO__text startup_32 of ZO ZO__end VO__end ^ ^ |------------uncompressed kernel image-------------| To simplify calculations and avoid special cases, it is cleaner to always place the compressed kernel image in memory so that ZO__end is at the end of the decompression buffer, instead of placing t at the start of extract_offset as is currently done. This patch adds BP_init_size (which is the INIT_SIZE as passed in from the boot_params) into asm-offsets.c to make it visible to the assembly code. Then when moving the ZO, it calculates the starting position of the copied ZO (via BP_init_size and the ZO run size) so that the VO__end will be at the end of the decompression buffer. To make the position calculation safe, the end of ZO is page aligned (and a comment is added to the existing VO alignment for good measure). Signed-off-by: Yinghai Lu [ Rewrote changelog and comments. ] Signed-off-by: Kees Cook Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Baoquan He Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Young Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vivek Goyal Cc: lasse.collin@tukaani.org Link: http://lkml.kernel.org/r/1461888548-32439-3-git-send-email-keescook@chromium.org [ Rewrote the changelog some more. ] Signed-off-by: Ingo Molnar --- arch/x86/boot/compressed/head_32.S | 11 +++++++++-- arch/x86/boot/compressed/head_64.S | 8 ++++++-- arch/x86/boot/compressed/misc.c | 17 +++++++++++++++++ arch/x86/boot/compressed/mkpiggy.c | 3 --- arch/x86/boot/compressed/vmlinux.lds.S | 1 + arch/x86/kernel/asm-offsets.c | 1 + arch/x86/kernel/vmlinux.lds.S | 2 +- 7 files changed, 35 insertions(+), 8 deletions(-) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 26dd9df19a69..8a95e2f845aa 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -176,7 +176,9 @@ preferred_addr: 1: /* Target address to relocate to for decompression */ - addl $z_extract_offset, %ebx + movl BP_init_size(%esi), %eax + subl $_end, %eax + addl %eax, %ebx /* Set up the stack */ leal boot_stack_end(%ebx), %esp @@ -238,8 +240,13 @@ relocated: /* push arguments for extract_kernel: */ pushl $z_run_size /* size of kernel with .bss and .brk */ pushl $z_output_len /* decompressed length, end of relocs */ - leal z_extract_offset_negative(%ebx), %ebp + + movl BP_init_size(%esi), %eax + subl $_end, %eax + movl %ebx, %ebp + subl %eax, %ebp pushl %ebp /* output address */ + pushl $z_input_len /* input_len */ leal input_data(%ebx), %eax pushl %eax /* input_data */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d43c30ed89ed..09cdc0c3ee7e 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -110,7 +110,9 @@ ENTRY(startup_32) 1: /* Target address to relocate to for decompression */ - addl $z_extract_offset, %ebx + movl BP_init_size(%esi), %eax + subl $_end, %eax + addl %eax, %ebx /* * Prepare for entering 64 bit mode @@ -338,7 +340,9 @@ preferred_addr: 1: /* Target address to relocate to for decompression */ - leaq z_extract_offset(%rbp), %rbx + movl BP_init_size(%rsi), %ebx + subl $_end, %ebx + addq %rbp, %rbx /* Set up the stack */ leaq boot_stack_end(%rbx), %rsp diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 45145149c07d..4b4605e94b3c 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -318,6 +318,23 @@ static void parse_elf(void *output) free(phdrs); } +/* + * The compressed kernel image (ZO), has been moved so that its position + * is against the end of the buffer used to hold the uncompressed kernel + * image (VO) and the execution environment (.bss, .brk), which makes sure + * there is room to do the in-place decompression. (See header.S for the + * calculations.) + * + * |-----compressed kernel image------| + * V V + * 0 extract_offset +INIT_SIZE + * |-----------|---------------|-------------------------|--------| + * | | | | + * VO__text startup_32 of ZO VO__end ZO__end + * ^ ^ + * |-------uncompressed kernel image---------| + * + */ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index d8222f213182..b980046c3329 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -85,9 +85,6 @@ int main(int argc, char *argv[]) printf("z_output_len = %lu\n", (unsigned long)olen); printf(".globl z_extract_offset\n"); printf("z_extract_offset = 0x%lx\n", offs); - /* z_extract_offset_negative allows simplification of head_32.S */ - printf(".globl z_extract_offset_negative\n"); - printf("z_extract_offset_negative = -0x%lx\n", offs); printf(".globl z_run_size\n"); printf("z_run_size = %lu\n", run_size); diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 34d047c98284..e24e0a0c90c9 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -70,5 +70,6 @@ SECTIONS _epgtable = . ; } #endif + . = ALIGN(PAGE_SIZE); /* keep ZO size page aligned */ _end = .; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 5c042466f274..674134e9f5e5 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -80,6 +80,7 @@ void common(void) { OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); + OFFSET(BP_init_size, boot_params, hdr.init_size); OFFSET(BP_pref_address, boot_params, hdr.pref_address); OFFSET(BP_code32_start, boot_params, hdr.code32_start); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 4c941f88d405..9297a002d8e5 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -334,7 +334,7 @@ SECTIONS __brk_limit = .; } - . = ALIGN(PAGE_SIZE); + . = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */ _end = .; STABS_DEBUG -- 2.20.1