On 2/4/19 10:19 AM, Matthew Wilcox wrote:
> On Sun, Feb 03, 2019 at 09:21:33PM -0800, john.hubbard@xxxxxxxxx wrote:
>> +/*
>> + * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload
>> + * the page's refcount so that two separate items are tracked: the original page
>> + * reference count, and also a new count of how many get_user_pages() calls were
>> + * made against the page. ("gup-pinned" is another term for the latter).
>> + *
>> + * With this scheme, get_user_pages() becomes special: such pages are marked
>> + * as distinct from normal pages. As such, the new put_user_page() call (and
>> + * its variants) must be used in order to release gup-pinned pages.
>> + *
>> + * Choice of value:
>> + *
>> + * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference
>> + * counts with respect to get_user_pages() and put_user_page() becomes simpler,
>> + * due to the fact that adding an even power of two to the page refcount has
>> + * the effect of using only the upper N bits, for the code that counts up using
>> + * the bias value. This means that the lower bits are left for the exclusive
>> + * use of the original code that increments and decrements by one (or at least,
>> + * by much smaller values than the bias value).
>> + *
>> + * Of course, once the lower bits overflow into the upper bits (and this is
>> + * OK, because subtraction recovers the original values), then visual inspection
>> + * no longer suffices to directly view the separate counts. However, for normal
>> + * applications that don't have huge page reference counts, this won't be an
>> + * issue.
>> + *
>> + * This has to work on 32-bit as well as 64-bit systems. In the more constrained
>> + * 32-bit systems, the 10 bit value of the bias value leaves 22 bits for the
>> + * upper bits. Therefore, only about 4M calls to get_user_page() may occur for
>> + * a page.
>
> The refcount is 32-bit on both 64 and 32 bit systems. This limit
> exists on both sizes of system.
>
Oh right, I'll just delete that last paragraph, then. Thanks for catching that.
thanks,
--
John Hubbard
NVIDIA
