mirror of
https://github.com/torvalds/linux.git
synced 2024-12-22 02:52:56 +00:00
974f221c84
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:77d1a49995("x86, boot: make symbols from the main vmlinux available")37ba7ab5e3("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 <yinghai@kernel.org> [ Rewrote changelog and comments. ] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Young <dyoung@redhat.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> 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 <mingo@kernel.org>
90 lines
2.6 KiB
C
90 lines
2.6 KiB
C
/*
|
|
* Generate definitions needed by assembly language modules.
|
|
* This code generates raw asm output which is post-processed to extract
|
|
* and format the required data.
|
|
*/
|
|
#define COMPILE_OFFSETS
|
|
|
|
#include <linux/crypto.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/suspend.h>
|
|
#include <linux/kbuild.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/thread_info.h>
|
|
#include <asm/sigframe.h>
|
|
#include <asm/bootparam.h>
|
|
#include <asm/suspend.h>
|
|
|
|
#ifdef CONFIG_XEN
|
|
#include <xen/interface/xen.h>
|
|
#endif
|
|
|
|
#ifdef CONFIG_X86_32
|
|
# include "asm-offsets_32.c"
|
|
#else
|
|
# include "asm-offsets_64.c"
|
|
#endif
|
|
|
|
void common(void) {
|
|
BLANK();
|
|
OFFSET(TI_flags, thread_info, flags);
|
|
OFFSET(TI_status, thread_info, status);
|
|
OFFSET(TI_addr_limit, thread_info, addr_limit);
|
|
|
|
BLANK();
|
|
OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
|
|
|
|
BLANK();
|
|
OFFSET(pbe_address, pbe, address);
|
|
OFFSET(pbe_orig_address, pbe, orig_address);
|
|
OFFSET(pbe_next, pbe, next);
|
|
|
|
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
|
|
BLANK();
|
|
OFFSET(IA32_SIGCONTEXT_ax, sigcontext_32, ax);
|
|
OFFSET(IA32_SIGCONTEXT_bx, sigcontext_32, bx);
|
|
OFFSET(IA32_SIGCONTEXT_cx, sigcontext_32, cx);
|
|
OFFSET(IA32_SIGCONTEXT_dx, sigcontext_32, dx);
|
|
OFFSET(IA32_SIGCONTEXT_si, sigcontext_32, si);
|
|
OFFSET(IA32_SIGCONTEXT_di, sigcontext_32, di);
|
|
OFFSET(IA32_SIGCONTEXT_bp, sigcontext_32, bp);
|
|
OFFSET(IA32_SIGCONTEXT_sp, sigcontext_32, sp);
|
|
OFFSET(IA32_SIGCONTEXT_ip, sigcontext_32, ip);
|
|
|
|
BLANK();
|
|
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
|
|
#endif
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
BLANK();
|
|
OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
|
|
OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
|
|
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
|
|
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
|
|
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
|
|
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
|
|
OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
|
|
#endif
|
|
|
|
#ifdef CONFIG_XEN
|
|
BLANK();
|
|
OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
|
|
OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
|
|
#endif
|
|
|
|
BLANK();
|
|
OFFSET(BP_scratch, boot_params, scratch);
|
|
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
|
|
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);
|
|
|
|
BLANK();
|
|
DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
|
|
}
|