From: Barry Song <[email protected]>

In many cases, the pages passed to vmap() may include high-order
pages allocated with __GFP_COMP flags. For example, the systemheap
often allocates pages in descending order: order 8, then 4, then 0.
Currently, vmap() iterates over every page individually—even pages
inside a high-order block are handled one by one.

This patch detects high-order pages and maps them as a single
contiguous block whenever possible.

An alternative would be to implement a new API, vmap_sg(), but that
change seems to be large in scope.

When vmapping a 128MB dma-buf using the systemheap, this patch
makes system_heap_do_vmap() roughly 17× faster.

W/ patch:
[   10.404769] system_heap_do_vmap took 2494000 ns
[   12.525921] system_heap_do_vmap took 2467008 ns
[   14.517348] system_heap_do_vmap took 2471008 ns
[   16.593406] system_heap_do_vmap took 2444000 ns
[   19.501341] system_heap_do_vmap took 2489008 ns

W/o patch:
[    7.413756] system_heap_do_vmap took 42626000 ns
[    9.425610] system_heap_do_vmap took 42500992 ns
[   11.810898] system_heap_do_vmap took 42215008 ns
[   14.336790] system_heap_do_vmap took 42134992 ns
[   16.373890] system_heap_do_vmap took 42750000 ns

Cc: David Hildenbrand <[email protected]>
Cc: Uladzislau Rezki <[email protected]>
Cc: Sumit Semwal <[email protected]>
Cc: John Stultz <[email protected]>
Cc: Maxime Ripard <[email protected]>
Tested-by: Tangquan Zheng <[email protected]>
Signed-off-by: Barry Song <[email protected]>
---
 * diff with rfc:
 Many code refinements based on David's suggestions, thanks!
 Refine comment and changelog according to Uladzislau, thanks!
 rfc link:
 https://lore.kernel.org/linux-mm/[email protected]/

 mm/vmalloc.c | 45 +++++++++++++++++++++++++++++++++++++++------
 1 file changed, 39 insertions(+), 6 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 41dd01e8430c..8d577767a9e5 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -642,6 +642,29 @@ static int vmap_small_pages_range_noflush(unsigned long 
addr, unsigned long end,
        return err;
 }
 
+static inline int get_vmap_batch_order(struct page **pages,
+               unsigned int stride, unsigned int max_steps, unsigned int idx)
+{
+       int nr_pages = 1;
+
+       /*
+        * Currently, batching is only supported in vmap_pages_range
+        * when page_shift == PAGE_SHIFT.
+        */
+       if (stride != 1)
+               return 0;
+
+       nr_pages = compound_nr(pages[idx]);
+       if (nr_pages == 1)
+               return 0;
+       if (max_steps < nr_pages)
+               return 0;
+
+       if (num_pages_contiguous(&pages[idx], nr_pages) == nr_pages)
+               return compound_order(pages[idx]);
+       return 0;
+}
+
 /*
  * vmap_pages_range_noflush is similar to vmap_pages_range, but does not
  * flush caches.
@@ -655,23 +678,33 @@ int __vmap_pages_range_noflush(unsigned long addr, 
unsigned long end,
                pgprot_t prot, struct page **pages, unsigned int page_shift)
 {
        unsigned int i, nr = (end - addr) >> PAGE_SHIFT;
+       unsigned int stride;
 
        WARN_ON(page_shift < PAGE_SHIFT);
 
+       /*
+        * For vmap(), users may allocate pages from high orders down to
+        * order 0, while always using PAGE_SHIFT as the page_shift.
+        * We first check whether the initial page is a compound page. If so,
+        * there may be an opportunity to batch multiple pages together.
+        */
        if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
-                       page_shift == PAGE_SHIFT)
+                       (page_shift == PAGE_SHIFT && !PageCompound(pages[0])))
                return vmap_small_pages_range_noflush(addr, end, prot, pages);
 
-       for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
-               int err;
+       stride = 1U << (page_shift - PAGE_SHIFT);
+       for (i = 0; i < nr; ) {
+               int err, order;
 
-               err = vmap_range_noflush(addr, addr + (1UL << page_shift),
+               order = get_vmap_batch_order(pages, stride, nr - i, i);
+               err = vmap_range_noflush(addr, addr + (1UL << (page_shift + 
order)),
                                        page_to_phys(pages[i]), prot,
-                                       page_shift);
+                                       page_shift + order);
                if (err)
                        return err;
 
-               addr += 1UL << page_shift;
+               addr += 1UL  << (page_shift + order);
+               i += 1U << (order + page_shift - PAGE_SHIFT);
        }
 
        return 0;
-- 
2.39.3 (Apple Git-146)

Reply via email to