Re: [PATCH 09/13] purgatory: Core purgatory functionality

From: Borislav Petkov
Date: Thu Jun 05 2014 - 16:08:40 EST

On Tue, Jun 03, 2014 at 09:06:58AM -0400, Vivek Goyal wrote:
> Create a stand alone relocatable object purgatory which runs between two
> kernels. This name, concept and some code has been taken from kexec-tools.
> Idea is that this code runs after a crash and it runs in minimal environment.
> So keep it separate from rest of the kernel and in long term we will have
> to practically do no maintenance of this code.
>
> This code also has the logic to do verify sha256 hashes of various
> segments which have been loaded into memory. So first we verify that
> the kernel we are jumping to is fine and has not been corrupted and
> make progress only if checsums are verified.
>
> This code also takes care of copying some memory contents to backup region.
>
> Signed-off-by: Vivek Goyal <vgoyal@xxxxxxxxxx>
> ---
> arch/x86/Kbuild | 1 +
> arch/x86/Makefile | 6 +++
> arch/x86/purgatory/Makefile | 35 +++++++++++++
> arch/x86/purgatory/entry64.S | 101 ++++++++++++++++++++++++++++++++++++++
> arch/x86/purgatory/purgatory.c | 71 +++++++++++++++++++++++++++
> arch/x86/purgatory/setup-x86_32.S | 17 +++++++
> arch/x86/purgatory/setup-x86_64.S | 58 ++++++++++++++++++++++
> arch/x86/purgatory/stack.S | 19 +++++++
> arch/x86/purgatory/string.c | 13 +++++
> 9 files changed, 321 insertions(+)
> create mode 100644 arch/x86/purgatory/Makefile
> create mode 100644 arch/x86/purgatory/entry64.S
> create mode 100644 arch/x86/purgatory/purgatory.c
> create mode 100644 arch/x86/purgatory/setup-x86_32.S
> create mode 100644 arch/x86/purgatory/setup-x86_64.S
> create mode 100644 arch/x86/purgatory/stack.S
> create mode 100644 arch/x86/purgatory/string.c
>
> diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
> index e5287d8..faaeee7 100644
> --- a/arch/x86/Kbuild
> +++ b/arch/x86/Kbuild
> @@ -16,3 +16,4 @@ obj-$(CONFIG_IA32_EMULATION) += ia32/
>
> obj-y += platform/
> obj-y += net/
> +obj-$(CONFIG_KEXEC) += purgatory/
> diff --git a/arch/x86/Makefile b/arch/x86/Makefile
> index 33f71b0..0b25c6c 100644
> --- a/arch/x86/Makefile
> +++ b/arch/x86/Makefile
> @@ -186,6 +186,11 @@ archscripts: scripts_basic
> archheaders:
> $(Q)$(MAKE) $(build)=arch/x86/syscalls all
>
> +archprepare:
> +ifeq ($(CONFIG_KEXEC),y)
> + $(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c
> +endif
> +
> ###
> # Kernel objects
>
> @@ -249,6 +254,7 @@ archclean:
> $(Q)rm -rf $(objtree)/arch/x86_64
> $(Q)$(MAKE) $(clean)=$(boot)
> $(Q)$(MAKE) $(clean)=arch/x86/tools

ifeq ($(CONFIG_KEXEC),y)
$(Q)$(MAKE) $(clean)=arch/x86/purgatory
endif

>
> PHONY += kvmconfig
> kvmconfig:
> diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
> new file mode 100644
> index 0000000..8dbf8f5
> --- /dev/null
> +++ b/arch/x86/purgatory/Makefile
> @@ -0,0 +1,35 @@
> +ifeq ($(CONFIG_X86_64),y)
> + purgatory-y := purgatory.o entry64.o stack.o setup-x86_64.o sha256.o string.o
> +else
> + purgatory-y := purgatory.o stack.o sha256.o setup-x86_32.o
> +endif
> +
> +targets += $(purgatory-y)
> +PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
> +
> +LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
> +targets += purgatory.ro
> +
> +# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
> +# in turn leaves some undefined symbols like __fentry__ in purgatory and not
> +# sure how to relocate those. Like kexec-tools, custom flags.
> +
> +ifeq ($(CONFIG_X86_64),y)
> +KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -mcmodel=large -Os -fno-builtin -ffreestanding -c -MD
> +else
> +KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -Os -fno-builtin -ffreestanding -c -MD -m32
> +endif

Those variable assignments have a lot of duplication, let's simplify
(diff ontop):


Index: b/arch/x86/purgatory/Makefile
===================================================================
--- a/arch/x86/purgatory/Makefile 2014-06-05 21:43:31.957252700 +0200
+++ b/arch/x86/purgatory/Makefile 2014-06-05 21:42:12.743256165 +0200
@@ -1,7 +1,7 @@
+purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o
+
ifeq ($(CONFIG_X86_64),y)
- purgatory-y := purgatory.o entry64.o stack.o setup-x86_64.o sha256.o string.o
-else
- purgatory-y := purgatory.o stack.o sha256.o setup-x86_32.o
+ purgatory-y += entry64.o string.o
endif

targets += $(purgatory-y)
@@ -14,10 +14,12 @@ targets += purgatory.ro
# in turn leaves some undefined symbols like __fentry__ in purgatory and not
# sure how to relocate those. Like kexec-tools, custom flags.

+KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os
+
ifeq ($(CONFIG_X86_64),y)
-KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -mcmodel=large -Os -fno-builtin -ffreestanding -c -MD
+KBUILD_CFLAGS += -mcmodel=large
else
-KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -Os -fno-builtin -ffreestanding -c -MD -m32
+KBUILD_CFLAGS += -m32
endif

$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE

> +
> +$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
> + $(call if_changed,ld)
> +
> +targets += kexec-purgatory.c
> +
> +quiet_cmd_bin2c = BIN2C $@
> + cmd_bin2c = cat $(obj)/purgatory.ro | $(srctree)/scripts/basic/bin2c kexec_purgatory > $(obj)/kexec-purgatory.c
> +
> +$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
> + $(call if_changed,bin2c)
> +
> +
> +obj-$(CONFIG_KEXEC) += kexec-purgatory.o
> diff --git a/arch/x86/purgatory/entry64.S b/arch/x86/purgatory/entry64.S
> new file mode 100644
> index 0000000..219b50b
> --- /dev/null
> +++ b/arch/x86/purgatory/entry64.S
> @@ -0,0 +1,101 @@
> +/*
> + * Copyright (C) 2003,2004 Eric Biederman (ebiederm@xxxxxxxxxxxx)
> + * Copyright (C) 2014 Red Hat Inc.
> +
> + * Author(s): Vivek Goyal <vgoyal@xxxxxxxxxx>
> + *
> + * This code has been taken from kexec-tools.
> + *
> + * This source code is licensed under the GNU General Public License,
> + * Version 2. See the file COPYING for more details.
> + */
> +
> + .text
> + .balign 16
> + .code64
> + .globl entry64, entry64_regs
> +
> +
> +entry64:
> + /* Setup a gdt that should be preserved */
> + lgdt gdt(%rip)
> +
> + /* load the data segments */
> + movl $0x18, %eax /* data segment */
> + movl %eax, %ds
> + movl %eax, %es
> + movl %eax, %ss
> + movl %eax, %fs
> + movl %eax, %gs
> +
> + /* Setup new stack */
> + leaq stack_init(%rip), %rsp
> + pushq $0x10 /* CS */
> + leaq new_cs_exit(%rip), %rax
> + pushq %rax
> + lretq
> +new_cs_exit:
> +
> + /* Load the registers */
> + movq rax(%rip), %rax
> + movq rbx(%rip), %rbx
> + movq rcx(%rip), %rcx
> + movq rdx(%rip), %rdx
> + movq rsi(%rip), %rsi
> + movq rdi(%rip), %rdi
> + movq rsp(%rip), %rsp
> + movq rbp(%rip), %rbp
> + movq r8(%rip), %r8
> + movq r9(%rip), %r9
> + movq r10(%rip), %r10
> + movq r11(%rip), %r11
> + movq r12(%rip), %r12
> + movq r13(%rip), %r13
> + movq r14(%rip), %r14
> + movq r15(%rip), %r15
> +
> + /* Jump to the new code... */
> + jmpq *rip(%rip)
> +
> + .section ".rodata"
> + .balign 4
> +entry64_regs:
> +rax: .quad 0x00000000

Simply 0x0? Or am I missing something?

> +rbx: .quad 0x00000000
> +rcx: .quad 0x00000000
> +rdx: .quad 0x00000000
> +rsi: .quad 0x00000000
> +rdi: .quad 0x00000000
> +rsp: .quad 0x00000000
> +rbp: .quad 0x00000000
> +r8: .quad 0x00000000
> +r9: .quad 0x00000000
> +r10: .quad 0x00000000
> +r11: .quad 0x00000000
> +r12: .quad 0x00000000
> +r13: .quad 0x00000000
> +r14: .quad 0x00000000
> +r15: .quad 0x00000000
> +rip: .quad 0x00000000
> + .size entry64_regs, . - entry64_regs
> +
> + /* GDT */
> + .section ".rodata"
> + .balign 16
> +gdt:
> + /* 0x00 unusable segment
> + * 0x08 unused
> + * so use them as gdt ptr
> + */
> + .word gdt_end - gdt - 1
> + .quad gdt
> + .word 0, 0, 0
> +
> + /* 0x10 4GB flat code segment */
> + .word 0xFFFF, 0x0000, 0x9A00, 0x00AF
> +
> + /* 0x18 4GB flat data segment */
> + .word 0xFFFF, 0x0000, 0x9200, 0x00CF
> +gdt_end:
> +stack: .quad 0, 0
> +stack_init:
> diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
> new file mode 100644
> index 0000000..3a808db
> --- /dev/null
> +++ b/arch/x86/purgatory/purgatory.c
> @@ -0,0 +1,71 @@
> +/*
> + * purgatory: Runs between two kernels
> + *
> + * Copyright (C) 2014 Red Hat Inc.
> + *
> + * Author:
> + * Vivek Goyal <vgoyal@xxxxxxxxxx>
> + *
> + * This source code is licensed under the GNU General Public License,
> + * Version 2. See the file COPYING for more details.
> + */
> +
> +#include "sha256.h"
> +#include "../boot/string.h"
> +
> +struct sha_region {
> + unsigned long start;
> + unsigned long len;
> +};
> +
> +unsigned long backup_dest = 0;
> +unsigned long backup_src = 0;
> +unsigned long backup_sz = 0;
> +
> +u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
> +
> +struct sha_region sha_regions[16] = {};
> +
> +/*
> + * On x86, second kernel requries first 640K of memory to boot. Copy
> + * first 640K to a backup region in reserved memory range so that second
> + * kernel can use first 640K.
> + */
> +static int copy_backup_region(void)
> +{
> + if (backup_dest)
> + memcpy((void *)backup_dest, (void *)backup_src, backup_sz);
> +
> + return 0;
> +}
> +
> +int verify_sha256_digest(void)
> +{
> + struct sha_region *ptr, *end;
> + u8 digest[SHA256_DIGEST_SIZE];
> + struct sha256_state sctx;
> +
> + sha256_init(&sctx);
> + end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])];
> + for (ptr = sha_regions; ptr < end; ptr++)
> + sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
> +
> + sha256_final(&sctx, digest);
> +
> + if (memcmp(digest, sha256_digest, sizeof(digest)) != 0)

if (memcmp(...))
return 1;

should be a bit cleaner.

> + return 1;
> +
> + return 0;
> +}
> +
> +void purgatory(void)
> +{
> + int ret;
> +
> + ret = verify_sha256_digest();
> + if (ret) {
> + /* loop forever */
> + for (;;);

checkpatch bitches about this:

ERROR: trailing statements should be on next line
#303: FILE: arch/x86/purgatory/purgatory.c:68:
+ for (;;);

> + }
> + copy_backup_region();
> +}
--
Regards/Gruss,
Boris.

Sent from a fat crate under my desk. Formatting is fine.
--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/