Re: [PATCH v2 1/2] zsmalloc: add function to query object size

[Minchan Kim <minchan@kernel.org>]

On Fri, Dec 07, 2012 at 04:45:53PM -0800, Nitin Gupta wrote:
> On Sun, Dec 2, 2012 at 11:52 PM, Minchan Kim <minchan@kernel.org> wrote:
> > On Sun, Dec 02, 2012 at 11:20:42PM -0800, Nitin Gupta wrote:
> >>
> >>
> >> On Nov 30, 2012, at 5:54 AM, Minchan Kim <minchan.kernel.2@gmail.com> wrote:
> >>
> >> > On Thu, Nov 29, 2012 at 10:54:48PM -0800, Nitin Gupta wrote:
> >> >> Changelog v2 vs v1:
> >> >> - None
> >> >>
> >> >> Adds zs_get_object_size(handle) which provides the size of
> >> >> the given object. This is useful since the user (zram etc.)
> >> >> now do not have to maintain object sizes separately, saving
> >> >> on some metadata size (4b per page).
> >> >>
> >> >> The object handle encodes <page, offset> pair which currently points
> >> >> to the start of the object. Now, the handle implicitly stores the size
> >> >> information by pointing to the object's end instead. Since zsmalloc is
> >> >> a slab based allocator, the start of the object can be easily determined
> >> >> and the difference between the end offset encoded in the handle and the
> >> >> start gives us the object size.
> >> >>
> >> >> Signed-off-by: Nitin Gupta <ngupta@vflare.org>
> >> > Acked-by: Minchan Kim <minchan@kernel.org>
> >> >
> >> > I already had a few comment in your previous versoin.
> >> > I'm OK although you ignore them because I can make follow up patch about
> >> > my nitpick but could you answer below my question?
> >> >
> >> >> ---
> >> >> drivers/staging/zsmalloc/zsmalloc-main.c |  177 +++++++++++++++++++++---------
> >> >> drivers/staging/zsmalloc/zsmalloc.h      |    1 +
> >> >> 2 files changed, 127 insertions(+), 51 deletions(-)
> >> >>
> >> >> diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
> >> >> index 09a9d35..65c9d3b 100644
> >> >> --- a/drivers/staging/zsmalloc/zsmalloc-main.c
> >> >> +++ b/drivers/staging/zsmalloc/zsmalloc-main.c
> >> >> @@ -112,20 +112,20 @@
> >> >> #define MAX_PHYSMEM_BITS 36
> >> >> #else /* !CONFIG_HIGHMEM64G */
> >> >> /*
> >> >> - * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
> >> >> + * If this definition of MAX_PHYSMEM_BITS is used, OFFSET_BITS will just
> >> >>  * be PAGE_SHIFT
> >> >>  */
> >> >> #define MAX_PHYSMEM_BITS BITS_PER_LONG
> >> >> #endif
> >> >> #endif
> >> >> #define _PFN_BITS        (MAX_PHYSMEM_BITS - PAGE_SHIFT)
> >> >> -#define OBJ_INDEX_BITS    (BITS_PER_LONG - _PFN_BITS)
> >> >> -#define OBJ_INDEX_MASK    ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
> >> >> +#define OFFSET_BITS    (BITS_PER_LONG - _PFN_BITS)
> >> >> +#define OFFSET_MASK    ((_AC(1, UL) << OFFSET_BITS) - 1)
> >> >>
> >> >> #define MAX(a, b) ((a) >= (b) ? (a) : (b))
> >> >> /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
> >> >> #define ZS_MIN_ALLOC_SIZE \
> >> >> -    MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
> >> >> +    MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OFFSET_BITS))
> >> >> #define ZS_MAX_ALLOC_SIZE    PAGE_SIZE
> >> >>
> >> >> /*
> >> >> @@ -256,6 +256,11 @@ static int is_last_page(struct page *page)
> >> >>    return PagePrivate2(page);
> >> >> }
> >> >>
> >> >> +static unsigned long get_page_index(struct page *page)
> >> >> +{
> >> >> +    return is_first_page(page) ? 0 : page->index;
> >> >> +}
> >> >> +
> >> >> static void get_zspage_mapping(struct page *page, unsigned int *class_idx,
> >> >>                enum fullness_group *fullness)
> >> >> {
> >> >> @@ -433,39 +438,86 @@ static struct page *get_next_page(struct page *page)
> >> >>    return next;
> >> >> }
> >> >>
> >> >> -/* Encode <page, obj_idx> as a single handle value */
> >> >> -static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
> >> >> +static struct page *get_prev_page(struct page *page)
> >> >> {
> >> >> -    unsigned long handle;
> >> >> +    struct page *prev, *first_page;
> >> >>
> >> >> -    if (!page) {
> >> >> -        BUG_ON(obj_idx);
> >> >> -        return NULL;
> >> >> -    }
> >> >> +    first_page = get_first_page(page);
> >> >> +    if (page == first_page)
> >> >> +        prev = NULL;
> >> >> +    else if (page == (struct page *)first_page->private)
> >> >> +        prev = first_page;
> >> >> +    else
> >> >> +        prev = list_entry(page->lru.prev, struct page, lru);
> >> >>
> >> >> -    handle = page_to_pfn(page) << OBJ_INDEX_BITS;
> >> >> -    handle |= (obj_idx & OBJ_INDEX_MASK);
> >> >> +    return prev;
> >> >>
> >> >> -    return (void *)handle;
> >> >> }
> >> >>
> >> >> -/* Decode <page, obj_idx> pair from the given object handle */
> >> >> -static void obj_handle_to_location(unsigned long handle, struct page **page,
> >> >> -                unsigned long *obj_idx)
> >> >> +static void *encode_ptr(struct page *page, unsigned long offset)
> >> >> {
> >> >> -    *page = pfn_to_page(handle >> OBJ_INDEX_BITS);
> >> >> -    *obj_idx = handle & OBJ_INDEX_MASK;
> >> >> +    unsigned long ptr;
> >> >> +    ptr = page_to_pfn(page) << OFFSET_BITS;
> >> >> +    ptr |= offset & OFFSET_MASK;
> >> >> +    return (void *)ptr;
> >> >> +}
> >> >> +
> >> >> +static void decode_ptr(unsigned long ptr, struct page **page,
> >> >> +                    unsigned int *offset)
> >> >> +{
> >> >> +    *page = pfn_to_page(ptr >> OFFSET_BITS);
> >> >> +    *offset = ptr & OFFSET_MASK;
> >> >> +}
> >> >> +
> >> >> +static struct page *obj_handle_to_page(unsigned long handle)
> >> >> +{
> >> >> +    struct page *page;
> >> >> +    unsigned int offset;
> >> >> +
> >> >> +    decode_ptr(handle, &page, &offset);
> >> >> +    if (offset < get_page_index(page))
> >> >> +        page = get_prev_page(page);
> >> >> +
> >> >> +    return page;
> >> >> +}
> >> >> +
> >> >> +static unsigned int obj_handle_to_offset(unsigned long handle,
> >> >> +                    unsigned int class_size)
> >> >> +{
> >> >> +    struct page *page;
> >> >> +    unsigned int offset;
> >> >> +
> >> >> +    decode_ptr(handle, &page, &offset);
> >> >> +    if (offset < get_page_index(page))
> >> >> +        offset = PAGE_SIZE - class_size + get_page_index(page);
> >> >> +    else
> >> >> +        offset = roundup(offset, class_size) - class_size;
> >> >> +
> >> >> +    return offset;
> >> >> }
> >> >>
> >> >> -static unsigned long obj_idx_to_offset(struct page *page,
> >> >> -                unsigned long obj_idx, int class_size)
> >> >> +/* Encode <page, offset, size> as a single handle value */
> >> >> +static void *obj_location_to_handle(struct page *page, unsigned int offset,
> >> >> +                unsigned int size, unsigned int class_size)
> >> >> {
> >> >> -    unsigned long off = 0;
> >> >> +    struct page *endpage;
> >> >> +    unsigned int endoffset;
> >> >>
> >> >> -    if (!is_first_page(page))
> >> >> -        off = page->index;
> >> >> +    if (!page) {
> >> >> +        BUG_ON(offset);
> >> >> +        return NULL;
> >> >> +    }
> >> >
> >> > What do you expect to catch with above check?
> >> >
> >> >
> >>
> >> This would catch cases where, say, user passes handle to a zero page to this function. In general, just a sanity check since pfn 0 and any non-zero offset is invalid.
> >
> > You mean zero_page is always pfn 0?
> > No, we can't assume it.
> >
> 
> Sorry, missed this point.    Though it's not correct to embed the
> assumption that the zero-page handle will have pfn of 0, but in
> general, PFN 0 is always invalid. However, for 0 size requests

Not true. PFN 0 is valid. Why do you think pfn 0 is invalid?

> zsmalloc returns NULL, so user should be also to pass <PFN=0,offset=0>
> pair to this function. However, <PFN=0, offset!=0> is invalid and this

I don't get it. If zs_malloc return 0, it means FAILED. 
How can user pass it in obj_location_to_handle?

> is what this assert checks.

Although you are worry that someone might use the function in future,
Just enough with below.

        BUG_ON(!page);

The assertion isn't effecitve so we don't need that.

> 
> Thanks,
> Nitin
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

-- 
Kind regards,
Minchan Kim