Re: KASAN debug kernel fails to boot at early stage when CONFIG_SMP=y is set (kernel 6.5-rc5, PowerMac G4 3,6)

[Christophe Leroy <christophe.leroy@csgroup.eu>]

Le 12/09/2023 à 17:59, Erhard Furtner a écrit :
> 
> printk: bootconsole [udbg0] enabled
> Total memory = 2048MB; using 4096kB for hash table
> mapin_ram:125
> mmu_mapin_ram:169 0 30000000 1400000 2000000
> __mmu_mapin_ram:146 0 1400000
> __mmu_mapin_ram:155 1400000
> __mmu_mapin_ram:146 1400000 30000000
> __mmu_mapin_ram:155 20000000
> __mapin_ram_chunk:107 20000000 30000000
> __mapin_ram_chunk:117
> mapin_ram:134
> kasan_mmu_init:129
> kasan_mmu_init:132 0
> kasan_mmu_init:137
> ioremap() called early from btext_map+0x64/0xdc. Use early_ioremap() instead
> Linux version 6.6.0-rc1-PMacG4-dirty (root@T1000) (gcc (Gentoo 12.3.1_p20230526 p2) 12.3.1 20230526, GNU ld (Gentoo 2.40 p7) 2.40.0) #5 SMP Tue Sep 12 16:50:47 CEST 2023
> kasan_init_region: c0000000 30000000 f8000000 fe000000
> kasan_init_region: loop f8000000 fe000000
> 
> 
> So I get no "kasan_init_region: setbat" line and don't reach "KASAN init done".

Ah ok, maybe your CPU only has 4 BATs and they are all used, following 
change would tell us.

diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 850783cfa9c7..bd26767edce7 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -86,6 +86,7 @@ int __init find_free_bat(void)
  		if (!(bat[1].batu & 3))
  			return b;
  	}
+	pr_err("NO FREE BAT (%d)\n", n);
  	return -1;
  }


Or you have 8 BATs in which case it's an alignment problem, you need to 
increase CONFIG_DATA_SHIFT to 23, for that you need CONFIG_ADVANCED and 
CONFIG_DATA_SHIFT_BOOL

But regardless of that there is a problem we need to find out, because 
it should work without BATs.

As the BATs allocation fails, it falls back to :

	phys = memblock_phys_alloc_range(k_end - k_start, PAGE_SIZE, 0,
						 MEMBLOCK_ALLOC_ANYWHERE);
		if (!phys)
			return -ENOMEM;
	}

	ret = kasan_init_shadow_page_tables(k_start, k_end);
	if (ret)
		return ret;

	for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE) {
		pmd_t *pmd = pmd_off_k(k_cur);
		pte_t pte = pfn_pte(PHYS_PFN(phys + k_cur - k_start), PAGE_KERNEL);

		__set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0);
	}
	flush_tlb_kernel_range(k_start, k_end);
	memset(kasan_mem_to_shadow(start), 0, k_end - k_start);


While the __weak function that you confirmed working is:

	ret = kasan_init_shadow_page_tables(k_start, k_end);
	if (ret)
		return ret;

	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
	if (!block)
		return -ENOMEM;

	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
		pmd_t *pmd = pmd_off_k(k_cur);
		void *va = block + k_cur - k_start;
		pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);

		__set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0);
	}
	flush_tlb_kernel_range(k_start, k_end);


I'm having hard time to understand what's could be wrong at the first place.

Could you try following change:

diff --git a/arch/powerpc/mm/kasan/book3s_32.c 
b/arch/powerpc/mm/kasan/book3s_32.c
index 9954b7a3b7ae..e04f21908c6a 100644
--- a/arch/powerpc/mm/kasan/book3s_32.c
+++ b/arch/powerpc/mm/kasan/book3s_32.c
@@ -38,7 +38,7 @@ int __init kasan_init_region(void *start, size_t size)

  	if (k_nobat < k_end) {
  		phys = memblock_phys_alloc_range(k_end - k_nobat, PAGE_SIZE, 0,
-						 MEMBLOCK_ALLOC_ANYWHERE);
+						 MEMBLOCK_ALLOC_ACCESSIBLE);
  		if (!phys)
  			return -ENOMEM;
  	}

And also that one:


diff --git a/arch/powerpc/mm/kasan/init_32.c 
b/arch/powerpc/mm/kasan/init_32.c
index a70828a6d935..bc1c075489f4 100644
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -84,6 +84,9 @@ kasan_update_early_region(unsigned long k_start, 
unsigned long k_end, pte_t pte)
  {
  	unsigned long k_cur;

+	if (k_start == k_end)
+		return;
+
  	for (k_cur = k_start; k_cur != k_end; k_cur += PAGE_SIZE) {
  		pmd_t *pmd = pmd_off_k(k_cur);
  		pte_t *ptep = pte_offset_kernel(pmd, k_cur);



Thanks
Christophe