Re: [PATCH v10 20/22] x86: mm: Convert dump_pagetables to use walk_page_range

[Steven Price]

On 07/08/2019 00:58, Andrew Morton wrote:
> On Wed, 31 Jul 2019 16:46:01 +0100 Steven Price <steven.price@xxxxxxx> wrote:
> 
>> Make use of the new functionality in walk_page_range to remove the
>> arch page walking code and use the generic code to walk the page tables.
>>
>> The effective permissions are passed down the chain using new fields
>> in struct pg_state.
>>
>> The KASAN optimisation is implemented by including test_p?d callbacks
>> which can decide to skip an entire tree of entries
>>
>> ...
>>
>> +static const struct ptdump_range ptdump_ranges[] = {
>> +#ifdef CONFIG_X86_64
>>  
>> -#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
>> -#define pgd_none(a)  (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
>> +#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1))
>> +#define normalize_addr(u) ((signed long)(u << normalize_addr_shift) \
>> +				>> normalize_addr_shift)
>>  
>> -static inline bool is_hypervisor_range(int idx)
>> -{
>> -#ifdef CONFIG_X86_64
>> -	/*
>> -	 * A hole in the beginning of kernel address space reserved
>> -	 * for a hypervisor.
>> -	 */
>> -	return	(idx >= pgd_index(GUARD_HOLE_BASE_ADDR)) &&
>> -		(idx <  pgd_index(GUARD_HOLE_END_ADDR));
>> +	{0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
>> +	{normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL},
> 
> This blows up because PGD_LEVEL_MULT is sometimes not a constant.
> 
> x86_64 allmodconfig:
> 
> In file included from ./arch/x86/include/asm/pgtable_types.h:249:0,
>                  from ./arch/x86/include/asm/paravirt_types.h:45,
>                  from ./arch/x86/include/asm/ptrace.h:94,
>                  from ./arch/x86/include/asm/math_emu.h:5,
>                  from ./arch/x86/include/asm/processor.h:12,
>                  from ./arch/x86/include/asm/cpufeature.h:5,
>                  from ./arch/x86/include/asm/thread_info.h:53,
>                  from ./include/linux/thread_info.h:38,
>                  from ./arch/x86/include/asm/preempt.h:7,
>                  from ./include/linux/preempt.h:78,
>                  from ./include/linux/spinlock.h:51,
>                  from ./include/linux/wait.h:9,
>                  from ./include/linux/wait_bit.h:8,
>                  from ./include/linux/fs.h:6,
>                  from ./include/linux/debugfs.h:15,
>                  from arch/x86/mm/dump_pagetables.c:11:
> ./arch/x86/include/asm/pgtable_64_types.h:56:22: error: initializer element is not constant
>  #define PTRS_PER_PGD 512
>                       ^

This is very unhelpful of GCC - it's actually PTRS_PER_P4D which isn't
constant!

> arch/x86/mm/dump_pagetables.c:363:6: note: in expansion of macro âPTRS_PER_PGDâ
>   {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
>       ^~~~~~~~~~~~
> ./arch/x86/include/asm/pgtable_64_types.h:56:22: note: (near initialization for âptdump_ranges[0].endâ)
>  #define PTRS_PER_PGD 512
>                       ^
> arch/x86/mm/dump_pagetables.c:363:6: note: in expansion of macro âPTRS_PER_PGDâ
>   {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
>       ^~~~~~~~~~~~
> arch/x86/mm/dump_pagetables.c:360:27: error: initializer element is not constant
>  #define normalize_addr(u) ((signed long)(u << normalize_addr_shift) \
>                            ^
> arch/x86/mm/dump_pagetables.c:364:3: note: in expansion of macro ânormalize_addrâ
>   {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL},
>    ^~~~~~~~~~~~~~
> arch/x86/mm/dump_pagetables.c:360:27: note: (near initialization for âptdump_ranges[1].startâ)
>  #define normalize_addr(u) ((signed long)(u << normalize_addr_shift) \
>                            ^
> arch/x86/mm/dump_pagetables.c:364:3: note: in expansion of macro ânormalize_addrâ
>   {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL},
> 
> I don't know what to do about this so I'll drop the series.

My best solution to this is to simply make ptdump_ranges dynamic (see
below). But there are other problems with this series (thanks for
spotting them), so I'll send out another version later.

Thanks,

Steve

----8<-----
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 998c7f46763c..8fc129ff985e 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -353,7 +353,10 @@ static void note_page(struct ptdump_state *pt_st,
unsigned long addr, int level,
        }
 }

-static const struct ptdump_range ptdump_ranges[] = {
+static void ptdump_walk_pgd_level_core(struct seq_file *m, struct
mm_struct *mm,
+                                      bool checkwx, bool dmesg)
+{
+       const struct ptdump_range ptdump_ranges[] = {
 #ifdef CONFIG_X86_64

 #define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1))
@@ -368,9 +371,6 @@ static const struct ptdump_range ptdump_ranges[] = {
        {0, 0}
 };

-static void ptdump_walk_pgd_level_core(struct seq_file *m, struct
mm_struct *mm,
-                                      bool checkwx, bool dmesg)
-{
        struct pg_state st = {
                .ptdump = {
                        .note_page      = note_page,