linux-kernel - Re: [PATCH v2 2/4] mm, page_owner: record page owner for each subpage

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <ee93f01a-9f34-d237-9a34-33314f4298bc@suse.cz>
Date:   Tue, 24 Sep 2019 17:10:59 +0200
From:   Vlastimil Babka <vbabka@...e.cz>
To:     "Kirill A. Shutemov" <kirill@...temov.name>
Cc:     linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
        linux-kernel@...r.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Michal Hocko <mhocko@...nel.org>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Matthew Wilcox <willy@...radead.org>
Subject: Re: [PATCH v2 2/4] mm, page_owner: record page owner for each subpage

On 9/24/19 1:31 PM, Kirill A. Shutemov wrote:
> On Tue, Aug 20, 2019 at 03:18:26PM +0200, Vlastimil Babka wrote:
>> Currently, page owner info is only recorded for the first page of a high-order
>> allocation, and copied to tail pages in the event of a split page. With the
>> plan to keep previous owner info after freeing the page, it would be benefical
>> to record page owner for each subpage upon allocation. This increases the
>> overhead for high orders, but that should be acceptable for a debugging option.
>>
>> The order stored for each subpage is the order of the whole allocation. This
>> makes it possible to calculate the "head" pfn and to recognize "tail" pages
>> (quoted because not all high-order allocations are compound pages with true
>> head and tail pages). When reading the page_owner debugfs file, keep skipping
>> the "tail" pages so that stats gathered by existing scripts don't get inflated.
>>
>> Signed-off-by: Vlastimil Babka <vbabka@...e.cz>
>> ---
>>  mm/page_owner.c | 40 ++++++++++++++++++++++++++++------------
>>  1 file changed, 28 insertions(+), 12 deletions(-)
>>
>> diff --git a/mm/page_owner.c b/mm/page_owner.c
>> index addcbb2ae4e4..813fcb70547b 100644
>> --- a/mm/page_owner.c
>> +++ b/mm/page_owner.c
>> @@ -154,18 +154,23 @@ static noinline depot_stack_handle_t save_stack(gfp_t flags)
>>  	return handle;
>>  }
>>  
>> -static inline void __set_page_owner_handle(struct page_ext *page_ext,
>> -	depot_stack_handle_t handle, unsigned int order, gfp_t gfp_mask)
>> +static inline void __set_page_owner_handle(struct page *page,
>> +	struct page_ext *page_ext, depot_stack_handle_t handle,
>> +	unsigned int order, gfp_t gfp_mask)
>>  {
>>  	struct page_owner *page_owner;
>> +	int i;
>>  
>> -	page_owner = get_page_owner(page_ext);
>> -	page_owner->handle = handle;
>> -	page_owner->order = order;
>> -	page_owner->gfp_mask = gfp_mask;
>> -	page_owner->last_migrate_reason = -1;
>> +	for (i = 0; i < (1 << order); i++) {
>> +		page_owner = get_page_owner(page_ext);
>> +		page_owner->handle = handle;
>> +		page_owner->order = order;
>> +		page_owner->gfp_mask = gfp_mask;
>> +		page_owner->last_migrate_reason = -1;
>> +		__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
>>  
>> -	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
>> +		page_ext = lookup_page_ext(page + i);
> 
> Isn't it off-by-one? You are calculating page_ext for the next page,
> right?

You're right, thanks!

> And cant we just do page_ext++ here instead?

Unfortunately no, as that implies sizeof(page_ext), which only declares
unsigned long flags; and the rest is runtime-determined.
Perhaps I could add a wrapper named e.g. page_ext_next() that would use
get_entry_size() internally and hide the necessary casts to void * and back?