On Thu, Aug 01, 2024 at 01:06:47PM +0100, Mark Brown wrote:
> diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> index 5f00cb0da9c3..d6d3a96cf2e4 100644
> --- a/arch/arm64/kernel/process.c
> +++ b/arch/arm64/kernel/process.c
> @@ -285,9 +285,32 @@ static void flush_gcs(void)
> write_sysreg_s(0, SYS_GCSPR_EL0);
> }
>
> +static int copy_thread_gcs(struct task_struct *p,
> + const struct kernel_clone_args *args)
> +{
> + unsigned long gcs;
> +
> + gcs = gcs_alloc_thread_stack(p, args);
> + if (IS_ERR_VALUE(gcs))
> + return PTR_ERR((void *)gcs);
Is 0 an ok value here? I can see further down that
gcs_alloc_thread_stack() may return 0.
> +
> + p->thread.gcs_el0_mode = current->thread.gcs_el0_mode;
> + p->thread.gcs_el0_locked = current->thread.gcs_el0_locked;
> +
> + /* Ensure the current state of the GCS is seen by CoW */
> + gcsb_dsync();
I don't get this barrier. What does it have to do with CoW, which memory
effects is it trying to order?
> diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c
> index b0a67efc522b..b71f6b408513 100644
> --- a/arch/arm64/mm/gcs.c
> +++ b/arch/arm64/mm/gcs.c
> @@ -8,6 +8,138 @@
> #include <asm/cpufeature.h>
> #include <asm/page.h>
>
> +static unsigned long alloc_gcs(unsigned long addr, unsigned long size)
> +{
> + int flags = MAP_ANONYMOUS | MAP_PRIVATE;
> + struct mm_struct *mm = current->mm;
> + unsigned long mapped_addr, unused;
> +
> + if (addr)
> + flags |= MAP_FIXED_NOREPLACE;
> +
> + mmap_write_lock(mm);
> + mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags,
> + VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL);
> + mmap_write_unlock(mm);
> +
> + return mapped_addr;
> +}
> +
> +static unsigned long gcs_size(unsigned long size)
> +{
> + if (size)
> + return PAGE_ALIGN(size);
> +
> + /* Allocate RLIMIT_STACK/2 with limits of PAGE_SIZE..2G */
> + size = PAGE_ALIGN(min_t(unsigned long long,
> + rlimit(RLIMIT_STACK) / 2, SZ_2G));
> + return max(PAGE_SIZE, size);
> +}
So we still have RLIMIT_STACK/2. I thought we got rid of that and just
went with RLIMIT_STACK (or I misremember).
> +
> +static bool gcs_consume_token(struct mm_struct *mm, unsigned long user_addr)
> +{
> + u64 expected = GCS_CAP(user_addr);
> + u64 val;
> + int ret;
> +
> + /* This should really be an atomic cmpxchg. It is not. */
> + ret = access_remote_vm(mm, user_addr, &val, sizeof(val),
> + FOLL_FORCE);
> + if (ret != sizeof(val))
> + return false;
> +
> + if (val != expected)
> + return false;
> +
> + val = 0;
> + ret = access_remote_vm(mm, user_addr, &val, sizeof(val),
> + FOLL_FORCE | FOLL_WRITE);
> + if (ret != sizeof(val))
> + return false;
> +
> + return true;
> +}
As per the clone3() thread, I think we should try to use
get_user_page_vma_remote() and do a cmpxchg() directly.
How does the user write the initial token? Do we need any barriers
before/after consuming the token?
--
Catalin
