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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAFULd4bGtZJorhUn7C-G9nMh4OsFtwcyo6eoHuN62nn0p4anrQ@mail.gmail.com>
Date:   Tue, 24 Oct 2023 14:39:51 +0200
From:   Uros Bizjak <ubizjak@...il.com>
To:     Brian Gerst <brgerst@...il.com>
Cc:     linux-kernel@...r.kernel.org, x86@...nel.org,
        Ingo Molnar <mingo@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Borislav Petkov <bp@...en8.de>,
        "H . Peter Anvin" <hpa@...or.com>,
        Peter Zijlstra <peterz@...radead.org>
Subject: Re: [PATCH 3/9] x86/stackprotector/64: Convert stack protector to
 normal percpu variable

On Mon, Oct 23, 2023 at 11:17 PM Brian Gerst <brgerst@...il.com> wrote:
>
> Older versions of GCC fixed the location of the stack protector canary
> at %gs:40.  This constraint forced the percpu section to be linked at
> virtual address 0 so that the canary could be the first data object in
> the percpu section.  Supporting the zero-based percpu section requires
> additional code to handle relocations for RIP-relative references to
> percpu data, extra complexity to kallsyms, and workarounds for linker
> bugs due to the use of absolute symbols.
>
> Since version 8.1, GCC has options to configure the location of the
> canary value.  This allows the canary to be turned into a normal
> percpu variable and removes the constraint that the percpu section
> be zero-based.
>
> Signed-off-by: Brian Gerst <brgerst@...il.com>
> ---
>  arch/x86/Kconfig                          |  5 ++-
>  arch/x86/Makefile                         | 19 +++++++-----
>  arch/x86/entry/entry_64.S                 |  2 +-
>  arch/x86/include/asm/processor.h          | 15 +--------
>  arch/x86/include/asm/stackprotector.h     | 37 +++++------------------
>  arch/x86/kernel/asm-offsets_64.c          |  6 ----
>  arch/x86/kernel/cpu/common.c              |  4 +--
>  scripts/gcc-x86_64-has-stack-protector.sh |  4 ---
>  8 files changed, 24 insertions(+), 68 deletions(-)
>  delete mode 100755 scripts/gcc-x86_64-has-stack-protector.sh
>
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 039872be1630..c95e0ce557da 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -410,12 +410,11 @@ config PGTABLE_LEVELS
>
>  config CC_HAS_SANE_STACKPROTECTOR
>         bool
> -       default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) $(CLANG_FLAGS)) if 64BIT
> +       default $(cc-option,-mstack-protector-guard-reg=gs -mstack-protector-guard-symbol=__stack_chk_guard) if 64BIT
>         default $(cc-option,-mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard)
>         help
>           We have to make sure stack protector is unconditionally disabled if
> -         the compiler produces broken code or if it does not let us control
> -         the segment on 32-bit kernels.
> +         the compiler does not allow control of the segment and symbol.

All compilers that support -mstack-protector-guard-reg=gs
-mstack-protector-guard-symbol=__stack_chk_guard correctly emit
segment prefix register, so checking for broken code here is indeed
overkill. gcc-x86_64-has-stack-protector.sh can rightfully be removed.

>
>  menu "Processor type and features"
>
> diff --git a/arch/x86/Makefile b/arch/x86/Makefile
> index 22e41d9dbc23..169f086997ec 100644
> --- a/arch/x86/Makefile
> +++ b/arch/x86/Makefile
> @@ -111,13 +111,7 @@ ifeq ($(CONFIG_X86_32),y)
>          # temporary until string.h is fixed
>          KBUILD_CFLAGS += -ffreestanding
>
> -       ifeq ($(CONFIG_STACKPROTECTOR),y)
> -               ifeq ($(CONFIG_SMP),y)
> -                       KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
> -               else
> -                       KBUILD_CFLAGS += -mstack-protector-guard=global
> -               endif
> -       endif
> +       percpu_seg := fs
>  else
>          BITS := 64
>          UTS_MACHINE := x86_64
> @@ -167,6 +161,17 @@ else
>          KBUILD_CFLAGS += -mcmodel=kernel
>          KBUILD_RUSTFLAGS += -Cno-redzone=y
>          KBUILD_RUSTFLAGS += -Ccode-model=kernel
> +
> +       percpu_seg := gs
> +endif
> +
> +ifeq ($(CONFIG_STACKPROTECTOR),y)
> +       ifeq ($(CONFIG_SMP),y)
> +               KBUILD_CFLAGS += -mstack-protector-guard-reg=$(percpu_seg) \
> +                                -mstack-protector-guard-symbol=__stack_chk_guard

Maybe use here:

KBUILD_CFLAGS += -mstack-protector-guard-reg=$(percpu_seg)
KBUILD_CFLAGS += -mstack-protector-guard-symbol=__stack_chk_guard

Looks nicer...

Uros.

> +       else
> +               KBUILD_CFLAGS += -mstack-protector-guard=global
> +       endif
>  endif
>
>  #
> diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
> index 1a88ad8a7b48..cddcc236aaae 100644
> --- a/arch/x86/entry/entry_64.S
> +++ b/arch/x86/entry/entry_64.S
> @@ -190,7 +190,7 @@ SYM_FUNC_START(__switch_to_asm)
>
>  #ifdef CONFIG_STACKPROTECTOR
>         movq    TASK_stack_canary(%rsi), %rbx
> -       movq    %rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
> +       movq    %rbx, PER_CPU_VAR(__stack_chk_guard)
>  #endif
>
>         /*
> diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
> index ae81a7191c1c..04371f60e3c6 100644
> --- a/arch/x86/include/asm/processor.h
> +++ b/arch/x86/include/asm/processor.h
> @@ -394,16 +394,7 @@ struct irq_stack {
>
>  #ifdef CONFIG_X86_64
>  struct fixed_percpu_data {
> -       /*
> -        * GCC hardcodes the stack canary as %gs:40.  Since the
> -        * irq_stack is the object at %gs:0, we reserve the bottom
> -        * 48 bytes of the irq stack for the canary.
> -        *
> -        * Once we are willing to require -mstack-protector-guard-symbol=
> -        * support for x86_64 stackprotector, we can get rid of this.
> -        */
>         char            gs_base[40];
> -       unsigned long   stack_canary;
>  };
>
>  DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
> @@ -418,11 +409,7 @@ extern asmlinkage void entry_SYSCALL32_ignore(void);
>
>  /* Save actual FS/GS selectors and bases to current->thread */
>  void current_save_fsgs(void);
> -#else  /* X86_64 */
> -#ifdef CONFIG_STACKPROTECTOR
> -DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
> -#endif
> -#endif /* !X86_64 */
> +#endif /* X86_64 */
>
>  struct perf_event;
>
> diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
> index 00473a650f51..33abbd29ea26 100644
> --- a/arch/x86/include/asm/stackprotector.h
> +++ b/arch/x86/include/asm/stackprotector.h
> @@ -2,26 +2,13 @@
>  /*
>   * GCC stack protector support.
>   *
> - * Stack protector works by putting predefined pattern at the start of
> + * Stack protector works by putting a predefined pattern at the start of
>   * the stack frame and verifying that it hasn't been overwritten when
> - * returning from the function.  The pattern is called stack canary
> - * and unfortunately gcc historically required it to be at a fixed offset
> - * from the percpu segment base.  On x86_64, the offset is 40 bytes.
> + * returning from the function.  The pattern is called the stack canary
> + * and is a unique value for each task.
>   *
> - * The same segment is shared by percpu area and stack canary.  On
> - * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
> - * base of percpu area.  The first occupant of the percpu area is always
> - * fixed_percpu_data which contains stack_canary at the appropriate
> - * offset.  On x86_32, the stack canary is just a regular percpu
> - * variable.
> - *
> - * Putting percpu data in %fs on 32-bit is a minor optimization compared to
> - * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
> - * to load 0 into %fs on exit to usermode, whereas with percpu data in
> - * %gs, we are likely to load a non-null %gs on return to user mode.
> - *
> - * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
> - * support, we can remove some of this complexity.
> + * GCC is configured to read the stack canary value from the __stack_chk_guard
> + * per-cpu variable, which is changed on task switch.
>   */
>
>  #ifndef _ASM_STACKPROTECTOR_H
> @@ -36,6 +23,8 @@
>
>  #include <linux/sched.h>
>
> +DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
> +
>  /*
>   * Initialize the stackprotector canary value.
>   *
> @@ -51,25 +40,13 @@ static __always_inline void boot_init_stack_canary(void)
>  {
>         unsigned long canary = get_random_canary();
>
> -#ifdef CONFIG_X86_64
> -       BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
> -#endif
> -
>         current->stack_canary = canary;
> -#ifdef CONFIG_X86_64
> -       this_cpu_write(fixed_percpu_data.stack_canary, canary);
> -#else
>         this_cpu_write(__stack_chk_guard, canary);
> -#endif
>  }
>
>  static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
>  {
> -#ifdef CONFIG_X86_64
> -       per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
> -#else
>         per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
> -#endif
>  }
>
>  #else  /* STACKPROTECTOR */
> diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
> index bb65371ea9df..590b6cd0eac0 100644
> --- a/arch/x86/kernel/asm-offsets_64.c
> +++ b/arch/x86/kernel/asm-offsets_64.c
> @@ -54,11 +54,5 @@ int main(void)
>         BLANK();
>  #undef ENTRY
>
> -       BLANK();
> -
> -#ifdef CONFIG_STACKPROTECTOR
> -       OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
> -       BLANK();
> -#endif
>         return 0;
>  }
> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
> index b14fc8c1c953..f9c8bd27b642 100644
> --- a/arch/x86/kernel/cpu/common.c
> +++ b/arch/x86/kernel/cpu/common.c
> @@ -2103,15 +2103,13 @@ void syscall_init(void)
>                X86_EFLAGS_AC|X86_EFLAGS_ID);
>  }
>
> -#else  /* CONFIG_X86_64 */
> +#endif /* CONFIG_X86_64 */
>
>  #ifdef CONFIG_STACKPROTECTOR
>  DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
>  EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
>  #endif
>
> -#endif /* CONFIG_X86_64 */
> -
>  /*
>   * Clear all 6 debug registers:
>   */
> diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
> deleted file mode 100755
> index 75e4e22b986a..000000000000
> --- a/scripts/gcc-x86_64-has-stack-protector.sh
> +++ /dev/null
> @@ -1,4 +0,0 @@
> -#!/bin/sh
> -# SPDX-License-Identifier: GPL-2.0
> -
> -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
> --
> 2.41.0
>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ