[PATCH 6/6] libdl/rtl-obj.c: synchronize cache after code relocation.

[Gedare Bloom]

On Sun, Jul 17, 2016 at 6:48 PM,  <pisa at cmp.felk.cvut.cz> wrote:
> From: Pavel Pisa <pisa at cmp.felk.cvut.cz>
>
> Memory content changes caused by relocation has to be
> propagated to memory/cache level which is used/snooped
> during instruction cache fill.
> ---
>  cpukit/libdl/rtl-elf.c |  3 +++
>  cpukit/libdl/rtl-obj.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++--
>  cpukit/libdl/rtl-obj.h |  9 +++++++
>  cpukit/libdl/rtl-rap.c |  3 +++
>  4 files changed, 80 insertions(+), 2 deletions(-)
>
> diff --git a/cpukit/libdl/rtl-elf.c b/cpukit/libdl/rtl-elf.c
> index 0eee540..85853be 100644
> --- a/cpukit/libdl/rtl-elf.c
> +++ b/cpukit/libdl/rtl-elf.c
> @@ -941,6 +941,9 @@ rtems_rtl_elf_file_load (rtems_rtl_obj_t* obj, int fd)
>    if (!rtems_rtl_obj_relocate (obj, fd, rtems_rtl_elf_relocator, &ehdr))
>      return false;
>
> +  if (!rtems_rtl_obj_synchronize_cache (obj))
> +    return false;
> +
>    rtems_rtl_symbol_obj_erase_local (obj);
>
>    if (!rtems_rtl_elf_load_details (obj))
> diff --git a/cpukit/libdl/rtl-obj.c b/cpukit/libdl/rtl-obj.c
> index 00a1c6e..dba661d 100644
> --- a/cpukit/libdl/rtl-obj.c
> +++ b/cpukit/libdl/rtl-obj.c
> @@ -558,6 +558,71 @@ rtems_rtl_obj_relocate (rtems_rtl_obj_t*             obj,
>    return rtems_rtl_obj_section_handler (mask, obj, fd, handler, data);
>  }
>
> +/**
> + * Cache synchronization after runtime object load (dlopen)
> + */
> +typedef struct
> +{
> +  uint32_t mask;
> +  void     *start_va;
> +  void     *end_va;
> +} rtems_rtl_obj_sect_sync_ctx_t;
> +
> +static bool
> +rtems_rtl_obj_sect_sync_handler (rtems_chain_node* node, void* data)
> +{
> +  rtems_rtl_obj_sect_t*   sect = (rtems_rtl_obj_sect_t*) node;
> +  rtems_rtl_obj_sect_sync_ctx_t* sync_ctx = data;
> +  uintptr_t old_end;
> +  uintptr_t new_start;
> +
> +  if ( !(sect->flags & sync_ctx->mask) || !sect->size)
> +    return true;
> +
> +  if (sync_ctx->end_va == sync_ctx->start_va) {
> +    sync_ctx->start_va = sect->base;
> +  } else {
> +    old_end = (uintptr_t)sync_ctx->end_va & ~(CPU_CACHE_LINE_BYTES - 1);
> +    new_start = (uintptr_t)sect->base & ~(CPU_CACHE_LINE_BYTES - 1);
> +    if ( (sect->base <  sync_ctx->start_va) ||
> +         (new_start - old_end > CPU_CACHE_LINE_BYTES) ) {
> +      rtems_cache_instruction_sync_after_code_change(sync_ctx->start_va,
> +                             sync_ctx->end_va - sync_ctx->start_va + 1);
> +      sync_ctx->start_va = sect->base;
> +    }
> +  }
> +
> +  sync_ctx->end_va = sect->base + sect->size;
> +
> +  return true;
> +}
> +
> +bool
> +rtems_rtl_obj_synchronize_cache (rtems_rtl_obj_t*    obj)
> +{
> +  rtems_rtl_obj_sect_sync_ctx_t sync_ctx;
> +
> +  if (CPU_CACHE_LINE_BYTES == 0)
> +    return true;
> +
> +  sync_ctx.mask = RTEMS_RTL_OBJ_SECT_TEXT | RTEMS_RTL_OBJ_SECT_CONST |
> +                  RTEMS_RTL_OBJ_SECT_DATA | RTEMS_RTL_OBJ_SECT_BSS |
> +                  RTEMS_RTL_OBJ_SECT_EXEC;
> +
> +  sync_ctx.start_va = 0;
> +  sync_ctx.end_va = sync_ctx.start_va;
> +  rtems_rtl_chain_iterate (&obj->sections,
> +                           rtems_rtl_obj_sect_sync_handler,
> +                           &sync_ctx);
> +
> +  if (sync_ctx.end_va != sync_ctx.start_va) {
> +    rtems_cache_instruction_sync_after_code_change(sync_ctx.start_va,
> +                              sync_ctx.end_va - sync_ctx.start_va);
> +  }
> +
> +  return true;
> +}
> +
>  bool
>  rtems_rtl_obj_load_symbols (rtems_rtl_obj_t*             obj,
>                              int                          fd,
> @@ -618,8 +683,6 @@ rtems_rtl_obj_sections_loader (uint32_t                     mask,
>        first = false;
>      }
>
> -    rtems_cache_instruction_sync_after_code_change(base, base_offset);
> -
>      node = rtems_chain_next (node);
>    }
>
> diff --git a/cpukit/libdl/rtl-obj.h b/cpukit/libdl/rtl-obj.h
> index 1202fd5..b1cb1d5 100644
> --- a/cpukit/libdl/rtl-obj.h
> +++ b/cpukit/libdl/rtl-obj.h
> @@ -494,6 +494,15 @@ bool rtems_rtl_obj_relocate (rtems_rtl_obj_t*             obj,
>                               void*                        data);
>
>  /**
> + * Synchronize caches to make code visible to CPU(s)
> + *
> + * @param obj The object file's descriptor.
> + * @retval true Cache synchronization succeed.
> + * @retval false Cache synchronization failed.
> + */
There does not actually appear to be any failure path?

> +bool rtems_rtl_obj_synchronize_cache (rtems_rtl_obj_t*    obj);
> +
> +/**
>   * Relocate an object file's unresolved reference.
>   *
>   * @param rec The unresolved relocation record.
> diff --git a/cpukit/libdl/rtl-rap.c b/cpukit/libdl/rtl-rap.c
> index 439eb20..0cb169e 100644
> --- a/cpukit/libdl/rtl-rap.c
> +++ b/cpukit/libdl/rtl-rap.c
> @@ -970,6 +970,9 @@ rtems_rtl_rap_file_load (rtems_rtl_obj_t* obj, int fd)
>    if (!rtems_rtl_rap_relocate (&rap, obj))
>      return false;
>
> +  if (!rtems_rtl_obj_synchronize_cache (obj))
> +    return false;
> +
>    return true;
>  }
>
> --
> 1.9.1
>
> _______________________________________________
> devel mailing list
> devel at rtems.org
> http://lists.rtems.org/mailman/listinfo/devel