| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <a6223864-7263-5450-0890-0f05a137d8c2@ghiti.fr>
Date: Sat, 9 Oct 2021 19:20:20 +0200
From: Alexandre ghiti <alex@...ti.fr>
To: Alexandre Ghiti <alexandre.ghiti@...onical.com>,
Michael Ellerman <mpe@...erman.id.au>,
Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Paul Mackerras <paulus@...ba.org>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
linuxppc-dev@...ts.ozlabs.org, linux-kernel@...r.kernel.org,
linux-riscv@...ts.infradead.org
Subject: Re: [PATCH v7 1/3] riscv: Introduce CONFIG_RELOCATABLE
Arf, I have sent this patchset with the wrong email address. @Palmer
tell me if you want me to resend it correctly.
Thanks,
Alex
On 10/9/21 7:12 PM, Alexandre Ghiti wrote:
> From: Alexandre Ghiti <alex@...ti.fr>
>
> This config allows to compile 64b kernel as PIE and to relocate it at
> any virtual address at runtime: this paves the way to KASLR.
> Runtime relocation is possible since relocation metadata are embedded into
> the kernel.
>
> Note that relocating at runtime introduces an overhead even if the
> kernel is loaded at the same address it was linked at and that the compiler
> options are those used in arm64 which uses the same RELA relocation
> format.
>
> Signed-off-by: Alexandre Ghiti <alex@...ti.fr>
> ---
> arch/riscv/Kconfig | 12 ++++++++
> arch/riscv/Makefile | 7 +++--
> arch/riscv/kernel/vmlinux.lds.S | 6 ++++
> arch/riscv/mm/Makefile | 4 +++
> arch/riscv/mm/init.c | 54 ++++++++++++++++++++++++++++++++-
> 5 files changed, 80 insertions(+), 3 deletions(-)
>
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index ea16fa2dd768..043ba92559fa 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -213,6 +213,18 @@ config PGTABLE_LEVELS
> config LOCKDEP_SUPPORT
> def_bool y
>
> +config RELOCATABLE
> + bool
> + depends on MMU && 64BIT && !XIP_KERNEL
> + help
> + This builds a kernel as a Position Independent Executable (PIE),
> + which retains all relocation metadata required to relocate the
> + kernel binary at runtime to a different virtual address than the
> + address it was linked at.
> + Since RISCV uses the RELA relocation format, this requires a
> + relocation pass at runtime even if the kernel is loaded at the
> + same address it was linked at.
> +
> source "arch/riscv/Kconfig.socs"
> source "arch/riscv/Kconfig.erratas"
>
> diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
> index 0eb4568fbd29..2f509915f246 100644
> --- a/arch/riscv/Makefile
> +++ b/arch/riscv/Makefile
> @@ -9,9 +9,12 @@
> #
>
> OBJCOPYFLAGS := -O binary
> -LDFLAGS_vmlinux :=
> +ifeq ($(CONFIG_RELOCATABLE),y)
> + LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro
> + KBUILD_CFLAGS += -fPIE
> +endif
> ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
> - LDFLAGS_vmlinux := --no-relax
> + LDFLAGS_vmlinux += --no-relax
> KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
> CC_FLAGS_FTRACE := -fpatchable-function-entry=8
> endif
> diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
> index 5104f3a871e3..862a8c09723c 100644
> --- a/arch/riscv/kernel/vmlinux.lds.S
> +++ b/arch/riscv/kernel/vmlinux.lds.S
> @@ -133,6 +133,12 @@ SECTIONS
>
> BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
>
> + .rela.dyn : ALIGN(8) {
> + __rela_dyn_start = .;
> + *(.rela .rela*)
> + __rela_dyn_end = .;
> + }
> +
> #ifdef CONFIG_EFI
> . = ALIGN(PECOFF_SECTION_ALIGNMENT);
> __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end);
> diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
> index 7ebaef10ea1b..2d33ec574bbb 100644
> --- a/arch/riscv/mm/Makefile
> +++ b/arch/riscv/mm/Makefile
> @@ -1,6 +1,10 @@
> # SPDX-License-Identifier: GPL-2.0-only
>
> CFLAGS_init.o := -mcmodel=medany
> +ifdef CONFIG_RELOCATABLE
> +CFLAGS_init.o += -fno-pie
> +endif
> +
> ifdef CONFIG_FTRACE
> CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE)
> CFLAGS_REMOVE_cacheflush.o = $(CC_FLAGS_FTRACE)
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index c0cddf0fc22d..42041c12d496 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -20,6 +20,9 @@
> #include <linux/dma-map-ops.h>
> #include <linux/crash_dump.h>
> #include <linux/hugetlb.h>
> +#ifdef CONFIG_RELOCATABLE
> +#include <linux/elf.h>
> +#endif
>
> #include <asm/fixmap.h>
> #include <asm/tlbflush.h>
> @@ -103,7 +106,7 @@ static void __init print_vm_layout(void)
> print_mlm("lowmem", (unsigned long)PAGE_OFFSET,
> (unsigned long)high_memory);
> #ifdef CONFIG_64BIT
> - print_mlm("kernel", (unsigned long)KERNEL_LINK_ADDR,
> + print_mlm("kernel", (unsigned long)kernel_map.virt_addr,
> (unsigned long)ADDRESS_SPACE_END);
> #endif
> }
> @@ -518,6 +521,44 @@ static __init pgprot_t pgprot_from_va(uintptr_t va)
> #error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
> #endif
>
> +#ifdef CONFIG_RELOCATABLE
> +extern unsigned long __rela_dyn_start, __rela_dyn_end;
> +
> +static void __init relocate_kernel(void)
> +{
> + Elf64_Rela *rela = (Elf64_Rela *)&__rela_dyn_start;
> + /*
> + * This holds the offset between the linked virtual address and the
> + * relocated virtual address.
> + */
> + uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR;
> + /*
> + * This holds the offset between kernel linked virtual address and
> + * physical address.
> + */
> + uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr;
> +
> + for ( ; rela < (Elf64_Rela *)&__rela_dyn_end; rela++) {
> + Elf64_Addr addr = (rela->r_offset - va_kernel_link_pa_offset);
> + Elf64_Addr relocated_addr = rela->r_addend;
> +
> + if (rela->r_info != R_RISCV_RELATIVE)
> + continue;
> +
> + /*
> + * Make sure to not relocate vdso symbols like rt_sigreturn
> + * which are linked from the address 0 in vmlinux since
> + * vdso symbol addresses are actually used as an offset from
> + * mm->context.vdso in VDSO_OFFSET macro.
> + */
> + if (relocated_addr >= KERNEL_LINK_ADDR)
> + relocated_addr += reloc_offset;
> +
> + *(Elf64_Addr *)addr = relocated_addr;
> + }
> +}
> +#endif /* CONFIG_RELOCATABLE */
> +
> #ifdef CONFIG_XIP_KERNEL
> static void __init create_kernel_page_table(pgd_t *pgdir,
> __always_unused bool early)
> @@ -625,6 +666,17 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
> BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
> #endif
>
> +#ifdef CONFIG_RELOCATABLE
> + /*
> + * Early page table uses only one PGDIR, which makes it possible
> + * to map PGDIR_SIZE aligned on PGDIR_SIZE: if the relocation offset
> + * makes the kernel cross over a PGDIR_SIZE boundary, raise a bug
> + * since a part of the kernel would not get mapped.
> + */
> + BUG_ON(PGDIR_SIZE - (kernel_map.virt_addr & (PGDIR_SIZE - 1)) < kernel_map.size);
> + relocate_kernel();
> +#endif
> +
> pt_ops.alloc_pte = alloc_pte_early;
> pt_ops.get_pte_virt = get_pte_virt_early;
> #ifndef __PAGETABLE_PMD_FOLDED
Powered by blists - more mailing lists