This allows batching the rmap removal with folio_remove_rmap_range(),
which means we avoid spuriously adding a partially unmapped folio to the
deferrred split queue in the common case, which reduces split queue lock
contention.
Previously each page was removed from the rmap individually with
page_remove_rmap(). If the first page belonged to a large folio, this
would cause page_remove_rmap() to conclude that the folio was now
partially mapped and add the folio to the deferred split queue. But
subsequent calls would cause the folio to become fully unmapped, meaning
there is no value to adding it to the split queue.
Signed-off-by: Ryan Roberts <[email protected]>
---
mm/memory.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 119 insertions(+)
diff --git a/mm/memory.c b/mm/memory.c
index 53896d46e686..9165ed1b9fc2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -914,6 +914,57 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
return 0;
}
+static inline unsigned long page_addr(struct page *page,
+ struct page *anchor, unsigned long anchor_addr)
+{
+ unsigned long offset;
+ unsigned long addr;
+
+ offset = (page_to_pfn(page) - page_to_pfn(anchor)) << PAGE_SHIFT;
+ addr = anchor_addr + offset;
+
+ if (anchor > page) {
+ if (addr > anchor_addr)
+ return 0;
+ } else {
+ if (addr < anchor_addr)
+ return ULONG_MAX;
+ }
+
+ return addr;
+}
+
+static int calc_anon_folio_map_pgcount(struct folio *folio,
+ struct page *page, pte_t *pte,
+ unsigned long addr, unsigned long end)
+{
+ pte_t ptent;
+ int floops;
+ int i;
+ unsigned long pfn;
+
+ end = min(page_addr(&folio->page + folio_nr_pages(folio), page, addr),
+ end);
+ floops = (end - addr) >> PAGE_SHIFT;
+ pfn = page_to_pfn(page);
+ pfn++;
+ pte++;
+
+ for (i = 1; i < floops; i++) {
+ ptent = ptep_get(pte);
+
+ if (!pte_present(ptent) ||
+ pte_pfn(ptent) != pfn) {
+ return i;
+ }
+
+ pfn++;
+ pte++;
+ }
+
+ return floops;
+}
+
/*
* Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page
* is required to copy this pte.
@@ -1379,6 +1430,44 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
}
+static unsigned long zap_anon_pte_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ struct page *page, pte_t *pte,
+ unsigned long addr, unsigned long end,
+ bool *full_out)
+{
+ struct folio *folio = page_folio(page);
+ struct mm_struct *mm = tlb->mm;
+ pte_t ptent;
+ int pgcount;
+ int i;
+ bool full;
+
+ pgcount = calc_anon_folio_map_pgcount(folio, page, pte, addr, end);
+
+ for (i = 0; i < pgcount;) {
+ ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm);
+ tlb_remove_tlb_entry(tlb, pte, addr);
+ full = __tlb_remove_page(tlb, page, 0);
+
+ if (unlikely(page_mapcount(page) < 1))
+ print_bad_pte(vma, addr, ptent, page);
+
+ i++;
+ page++;
+ pte++;
+ addr += PAGE_SIZE;
+
+ if (unlikely(full))
+ break;
+ }
+
+ folio_remove_rmap_range(folio, page - i, i, vma);
+
+ *full_out = full;
+ return i;
+}
+
static unsigned long zap_pte_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
@@ -1415,6 +1504,36 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
page = vm_normal_page(vma, addr, ptent);
if (unlikely(!should_zap_page(details, page)))
continue;
+
+ /*
+ * Batch zap large anonymous folio mappings. This allows
+ * batching the rmap removal, which means we avoid
+ * spuriously adding a partially unmapped folio to the
+ * deferrred split queue in the common case, which
+ * reduces split queue lock contention. Require the VMA
+ * to be anonymous to ensure that none of the PTEs in
+ * the range require zap_install_uffd_wp_if_needed().
+ */
+ if (page && PageAnon(page) && vma_is_anonymous(vma)) {
+ bool full;
+ int pgcount;
+
+ pgcount = zap_anon_pte_range(tlb, vma,
+ page, pte, addr, end, &full);
+
+ rss[mm_counter(page)] -= pgcount;
+ pgcount--;
+ pte += pgcount;
+ addr += pgcount << PAGE_SHIFT;
+
+ if (unlikely(full)) {
+ force_flush = 1;
+ addr += PAGE_SIZE;
+ break;
+ }
+ continue;
+ }
+
ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
tlb_remove_tlb_entry(tlb, pte, addr);
--
2.25.1
On Mon, Jun 26, 2023 at 11:15 AM Ryan Roberts <[email protected]> wrote:
>
> This allows batching the rmap removal with folio_remove_rmap_range(),
> which means we avoid spuriously adding a partially unmapped folio to the
> deferrred split queue in the common case, which reduces split queue lock
> contention.
>
> Previously each page was removed from the rmap individually with
> page_remove_rmap(). If the first page belonged to a large folio, this
> would cause page_remove_rmap() to conclude that the folio was now
> partially mapped and add the folio to the deferred split queue. But
> subsequent calls would cause the folio to become fully unmapped, meaning
> there is no value to adding it to the split queue.
>
> Signed-off-by: Ryan Roberts <[email protected]>
> ---
> mm/memory.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 119 insertions(+)
We don't really need this patch for the series to work. So again, I'd
split it out.
On 27/06/2023 04:04, Yu Zhao wrote:
> On Mon, Jun 26, 2023 at 11:15 AM Ryan Roberts <[email protected]> wrote:
>>
>> This allows batching the rmap removal with folio_remove_rmap_range(),
>> which means we avoid spuriously adding a partially unmapped folio to the
>> deferrred split queue in the common case, which reduces split queue lock
>> contention.
>>
>> Previously each page was removed from the rmap individually with
>> page_remove_rmap(). If the first page belonged to a large folio, this
>> would cause page_remove_rmap() to conclude that the folio was now
>> partially mapped and add the folio to the deferred split queue. But
>> subsequent calls would cause the folio to become fully unmapped, meaning
>> there is no value to adding it to the split queue.
>>
>> Signed-off-by: Ryan Roberts <[email protected]>
>> ---
>> mm/memory.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++++
>> 1 file changed, 119 insertions(+)
>
> We don't really need this patch for the series to work. So again, I'd
> split it out.
The reason I included it in the MVP was that without it I was seeing high lock
contention for the split queue lock, which was significantly eating the
performance gains. But since then Yin Fengwei's patch to make this more
efficient has been accepted so perhaps that solves the problem and in that case
we can drop this as you suggest. If I still see a reasonable perf improvement
without it, I'll drop for v2.