On Thu, May 12, 2016 at 07:06:03PM +0300, Yury Norov wrote:
> diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
> index 24ed037..fda75ce 100644
> --- a/arch/arm64/include/asm/elf.h
> +++ b/arch/arm64/include/asm/elf.h
> @@ -138,7 +138,10 @@ typedef struct user_fpsimd_state elf_fpregset_t;
> */
> #define ELF_PLAT_INIT(_r, load_addr) (_r)->regs[0] = 0
>
> -#define SET_PERSONALITY(ex) clear_thread_flag(TIF_32BIT);
> +#define SET_PERSONALITY(ex) do { \
> + clear_thread_flag(TIF_32BIT); \
> + set_fs(TASK_SIZE_64); \
> +} while (0)
>
> #define ARCH_DLINFO \
> do { \
> @@ -181,7 +184,11 @@ typedef compat_elf_greg_t
> compat_elf_gregset_t[COMPAT_ELF_NGREG];
> ((x)->e_flags & EF_ARM_EABI_MASK))
>
> #define compat_start_thread compat_start_thread
> -#define COMPAT_SET_PERSONALITY(ex) set_thread_flag(TIF_32BIT);
> +#define COMPAT_SET_PERSONALITY(ex) do {
> \
> + set_thread_flag(TIF_32BIT); \
> + set_fs(TASK_SIZE_32); \
> +} while (0)
> +
> #define COMPAT_ARCH_DLINFO
> extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
> int uses_interp);
> diff --git a/arch/arm64/include/asm/uaccess.h
> b/arch/arm64/include/asm/uaccess.h
> index 0685d74..5b269e6 100644
> --- a/arch/arm64/include/asm/uaccess.h
> +++ b/arch/arm64/include/asm/uaccess.h
> @@ -60,7 +60,7 @@ extern int fixup_exception(struct pt_regs *regs);
> #define KERNEL_DS (-1UL)
> #define get_ds() (KERNEL_DS)
>
> -#define USER_DS TASK_SIZE_64
> +#define USER_DS TASK_SIZE
We can avoid the USER_DS change as long as SET_PERSONALITY updates the
thread's addr_limit. There are very few explicit set_fs(USER_DS) calls
and they are on the thread exit path (or exec).
That's unless we try to make a generic set_fs(USER_DS) addition to
something like setup_new_exec() and we wouldn't need the SET_PERSONALITY
changes:
diff --git a/fs/exec.c b/fs/exec.c
index c4010b8207a1..54cc537f5986 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1226,6 +1226,9 @@ EXPORT_SYMBOL(would_dump);
void setup_new_exec(struct linux_binprm * bprm)
{
+ /* set the address limit for the new executable */
+ set_fs(USER_DS);
+
arch_pick_mmap_layout(current->mm);
/* This is the point of no return */
> #define get_fs() (current_thread_info()->addr_limit)
>
> static inline void set_fs(mm_segment_t fs)
> diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> index 8062482..2b25930 100644
> --- a/arch/arm64/kernel/process.c
> +++ b/arch/arm64/kernel/process.c
> @@ -211,17 +211,13 @@ static void tls_thread_flush(void)
> {
> asm ("msr tpidr_el0, xzr");
>
> - if (is_compat_task()) {
> - current->thread.tp_value = 0;
> -
> - /*
> - * We need to ensure ordering between the shadow state and the
> - * hardware state, so that we don't corrupt the hardware state
> - * with a stale shadow state during context switch.
> - */
> - barrier();
> - asm ("msr tpidrro_el0, xzr");
> - }
> + /*
> + * We need to ensure ordering between the shadow state and the
> + * hardware state, so that we don't corrupt the hardware state
> + * with a stale shadow state during context switch.
> + */
> + barrier();
> + asm ("msr tpidrro_el0, xzr");
> }
Why did you dropped tp_value initialisation? Context switching on native
64-bit tasks rely on copying the tpidr_el0 in and out of tp_value.
However, compat tasks use the read-only tpidrro_el0 register set
explicitly via a system call. Until this call happens, the TLS register
would contain some garbage after the thread has been switched back in.
--
Catalin
