Re: [PATCH 1/2] x86/boot: robustify calling startup_{32,64}() from the decompressor code
From: H. Peter Anvin
Date: Mon Oct 31 2022 - 16:31:30 EST
On October 31, 2022 8:10:46 AM PDT, Alexander Lobakin <alexandr.lobakin@xxxxxxxxx> wrote:
>After commit ce697ccee1a8 ("kbuild: remove head-y syntax"), I
>started digging whether x86 is ready from removing this old cruft.
>Removing its objects from the list makes the kernel unbootable.
>This applies only to bzImage, vmlinux still works correctly.
>The reason is that with no strict object order determined by the
>linker arguments, not the linker script, startup_64 can be placed
>not right at the beginning of the kernel.
>Here's vmlinux.map's beginning before removing:
>
>ffffffff81000000 vmlinux.o:(.head.text)
>ffffffff81000000 startup_64
>ffffffff81000070 secondary_startup_64
>ffffffff81000075 secondary_startup_64_no_verify
>ffffffff81000160 verify_cpu
>
>and after:
>
>ffffffff81000000 vmlinux.o:(.head.text)
>ffffffff81000000 pvh_start_xen
>ffffffff81000080 startup_64
>ffffffff810000f0 secondary_startup_64
>ffffffff810000f5 secondary_startup_64_no_verify
>
>Not a problem itself, but the self-extractor code has the address of
>that function hardcoded the beginning, not looking onto the ELF
>header, which always contains the address of startup_{32,64}().
>
>So, instead of doing an "act of blind faith", just take the address
>from the ELF header and extract a relative offset to the entry
>point. The decompressor function already returns a pointer to the
>beginning of the kernel to the Asm code, which then jumps to it,
>so add that offset to the return value.
>This doesn't change anything for now, but allows to resign from the
>"head object list" for x86 and makes sure valid Kbuild or any other
>improvements won't break anything here in general.
>
>Signed-off-by: Alexander Lobakin <alexandr.lobakin@xxxxxxxxx>
>---
> arch/x86/boot/compressed/head_32.S | 2 +-
> arch/x86/boot/compressed/head_64.S | 2 +-
> arch/x86/boot/compressed/misc.c | 16 +++++++++++-----
> 3 files changed, 13 insertions(+), 7 deletions(-)
>
>diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
>index 3b354eb9516d..56f9847e208b 100644
>--- a/arch/x86/boot/compressed/head_32.S
>+++ b/arch/x86/boot/compressed/head_32.S
>@@ -187,7 +187,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
> leal boot_heap@GOTOFF(%ebx), %eax
> pushl %eax /* heap area */
> pushl %esi /* real mode pointer */
>- call extract_kernel /* returns kernel location in %eax */
>+ call extract_kernel /* returns kernel entry point in %eax */
> addl $24, %esp
>
> /*
>diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
>index d33f060900d2..aeba5aa3d26c 100644
>--- a/arch/x86/boot/compressed/head_64.S
>+++ b/arch/x86/boot/compressed/head_64.S
>@@ -593,7 +593,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
> movl input_len(%rip), %ecx /* input_len */
> movq %rbp, %r8 /* output target address */
> movl output_len(%rip), %r9d /* decompressed length, end of relocs */
>- call extract_kernel /* returns kernel location in %rax */
>+ call extract_kernel /* returns kernel entry point in %rax */
> popq %rsi
>
> /*
>diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
>index cf690d8712f4..96ae5af29f49 100644
>--- a/arch/x86/boot/compressed/misc.c
>+++ b/arch/x86/boot/compressed/misc.c
>@@ -277,7 +277,7 @@ static inline void handle_relocations(void *output, unsigned long output_len,
> { }
> #endif
>
>-static void parse_elf(void *output)
>+static size_t parse_elf(void *output)
> {
> #ifdef CONFIG_X86_64
> Elf64_Ehdr ehdr;
>@@ -287,6 +287,7 @@ static void parse_elf(void *output)
> Elf32_Phdr *phdrs, *phdr;
> #endif
> void *dest;
>+ size_t off;
> int i;
>
> memcpy(&ehdr, output, sizeof(ehdr));
>@@ -295,16 +296,19 @@ static void parse_elf(void *output)
> ehdr.e_ident[EI_MAG2] != ELFMAG2 ||
> ehdr.e_ident[EI_MAG3] != ELFMAG3) {
> error("Kernel is not a valid ELF file");
>- return;
>+ return 0;
> }
>
> debug_putstr("Parsing ELF... ");
>
> phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum);
>- if (!phdrs)
>+ if (!phdrs) {
> error("Failed to allocate space for phdrs");
>+ return 0;
>+ }
>
> memcpy(phdrs, output + ehdr.e_phoff, sizeof(*phdrs) * ehdr.e_phnum);
>+ off = ehdr.e_entry - phdrs->p_paddr;
>
> for (i = 0; i < ehdr.e_phnum; i++) {
> phdr = &phdrs[i];
>@@ -328,6 +332,7 @@ static void parse_elf(void *output)
> }
>
> free(phdrs);
>+ return off;
> }
>
> /*
>@@ -356,6 +361,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
> const unsigned long kernel_total_size = VO__end - VO__text;
> unsigned long virt_addr = LOAD_PHYSICAL_ADDR;
> unsigned long needed_size;
>+ size_t off;
>
> /* Retain x86 boot parameters pointer passed from startup_32/64. */
> boot_params = rmode;
>@@ -456,14 +462,14 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
> debug_putstr("\nDecompressing Linux... ");
> __decompress(input_data, input_len, NULL, NULL, output, output_len,
> NULL, error);
>- parse_elf(output);
>+ off = parse_elf(output);
> handle_relocations(output, output_len, virt_addr);
> debug_putstr("done.\nBooting the kernel.\n");
>
> /* Disable exception handling before booting the kernel */
> cleanup_exception_handling();
>
>- return output;
>+ return output + off;
> }
>
> void fortify_panic(const char *name)
Put the entry points in dedicated sections and declare them explicitly in the linker script (the standard name for this section would be .init, but we presumably want .init.32 and .init.64 to keep 32- and 64-bit code in separate sections.)