Le 05/09/2025 à 05:55, Ritesh Harjani a écrit :
Christophe Leroy <christophe.le...@csgroup.eu> writes:

PAGE_KERNEL_TEXT is an old macro that is used to tell kernel whether
kernel text has to be mapped read-only or read-write based on build
time options.

But nowadays, with functionnalities like jump_labels, static links,
etc ... more only less all kernels need to be read-write at some
point, and some combinations of configs failed to work due to
innacurate setting of PAGE_KERNEL_TEXT. On the other hand, today
we have CONFIG_STRICT_KERNEL_RWX which implements a more controlled
access to kernel modifications.

Instead of trying to keep PAGE_KERNEL_TEXT accurate with all
possible options that may imply kernel text modification, always
set kernel text read-write at startup and rely on
CONFIG_STRICT_KERNEL_RWX to provide accurate protection.

Reported-by: Erhard Furtner <erhar...@mailbox.org>
Closes: 
https://lore.kernel.org/all/342b4120-911c-4723-82ec-d8c9b03a8...@mailbox.org/
Signed-off-by: Christophe Leroy <christophe.le...@csgroup.eu>
---
  arch/powerpc/include/asm/pgtable.h | 12 ------------
  arch/powerpc/mm/book3s32/mmu.c     |  4 ++--
  arch/powerpc/mm/pgtable_32.c       |  2 +-
  3 files changed, 3 insertions(+), 15 deletions(-)


AFAIU - mmu_mark_initmem_nx gets called during kernel_init() which is
way after static call initialization correct? i.e.

start_kernel
   ...
   jump_label_init()
   static_call_init()
   ...
   ...
   rest_init()      /* Do the rest non-__init'ed, we're now alive */
     kernel_init()
       free_initmem() -> mark_initmem_nx() -> __mark_initmem_nx -> 
mmu_mark_initmem_nx()
       mark_readonly()
         if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && rodata_enabled) {
            jump_label_init_ro()
            mark_rodata_ro() -> ....
            ...
         ...

Then I guess we mainly only need __mapin_ram_chunk() to be PAGE_KERNEL_X (RWX)
instead of PAGE_KERNEL_TEXT (ROX), isn't it?

Let me quickly validate it...
...Ok, so I was able to get just this diff to be working.

Thoughts?

setibat() doesn't take into account whether it is RO or RW. Only X or NX is taken into account, so it doesn't matter whether it is X or ROX.

Then allthough you are right in principle, once the PAGE_KERNEL_TEXT is removed from __mapin_ram_chunk() it becomes completely useless, so better get rid of PAGE_KERNEL_TEXT completely.


diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 15276068f657..0c9ef705803e 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -104,7 +104,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, 
unsigned long top)
         p = memstart_addr + s;
         for (; s < top; s += PAGE_SIZE) {
                 ktext = core_kernel_text(v);
-               map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL);
+               map_kernel_page(v, p, ktext ? PAGE_KERNEL_X : PAGE_KERNEL);
                 v += PAGE_SIZE;
                 p += PAGE_SIZE;
         }

-ritesh



diff --git a/arch/powerpc/include/asm/pgtable.h 
b/arch/powerpc/include/asm/pgtable.h
index 93d77ad5a92f..d8f944a5a037 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -20,18 +20,6 @@ struct mm_struct;
  #include <asm/nohash/pgtable.h>
  #endif /* !CONFIG_PPC_BOOK3S */
-/*
- * Protection used for kernel text. We want the debuggers to be able to
- * set breakpoints anywhere, so don't write protect the kernel text
- * on platforms where such control is possible.
- */
-#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) 
|| \
-       defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE)
-#define PAGE_KERNEL_TEXT       PAGE_KERNEL_X
-#else
-#define PAGE_KERNEL_TEXT       PAGE_KERNEL_ROX
-#endif
-
  /* Make modules code happy. We don't set RO yet */
  #define PAGE_KERNEL_EXEC      PAGE_KERNEL_X
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index be9c4106e22f..c42ecdf94e48 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -204,7 +204,7 @@ int mmu_mark_initmem_nx(void)
for (i = 0; i < nb - 1 && base < top;) {
                size = bat_block_size(base, top);
-               setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+               setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
                base += size;
        }
        if (base < top) {
@@ -215,7 +215,7 @@ int mmu_mark_initmem_nx(void)
                                pr_warn("Some RW data is getting mapped X. "
                                        "Adjust CONFIG_DATA_SHIFT to avoid 
that.\n");
                }
-               setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+               setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
                base += size;
        }
        for (; i < nb; i++)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 15276068f657..0c9ef705803e 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -104,7 +104,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, 
unsigned long top)
        p = memstart_addr + s;
        for (; s < top; s += PAGE_SIZE) {
                ktext = core_kernel_text(v);
-               map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL);
+               map_kernel_page(v, p, ktext ? PAGE_KERNEL_X : PAGE_KERNEL);
                v += PAGE_SIZE;
                p += PAGE_SIZE;
        }
--
2.49.0


Reply via email to