| 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
| ||
|
Message-Id: <20230727141837.3386072-4-ryan.roberts@arm.com>
Date: Thu, 27 Jul 2023 15:18:37 +0100
From: Ryan Roberts <ryan.roberts@....com>
To: Andrew Morton <akpm@...ux-foundation.org>,
Matthew Wilcox <willy@...radead.org>,
Yin Fengwei <fengwei.yin@...el.com>,
David Hildenbrand <david@...hat.com>,
Yu Zhao <yuzhao@...gle.com>, Yang Shi <shy828301@...il.com>,
"Huang, Ying" <ying.huang@...el.com>, Zi Yan <ziy@...dia.com>,
Nathan Chancellor <nathan@...nel.org>,
Alexander Gordeev <agordeev@...ux.ibm.com>,
Gerald Schaefer <gerald.schaefer@...ux.ibm.com>
Cc: Ryan Roberts <ryan.roberts@....com>, linux-kernel@...r.kernel.org,
linux-mm@...ck.org
Subject: [PATCH v4 3/3] mm: Batch-zap large anonymous folio PTE mappings
This allows batching the rmap removal with folio_remove_rmap_range(),
which means we avoid spuriously adding a partially unmapped folio to the
deferred 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.
A complicating factor is that for platforms where MMU_GATHER_NO_GATHER
is enabled (e.g. s390), __tlb_remove_page() drops a reference to the
page. This means that the folio reference count could drop to zero while
still in use (i.e. before folio_remove_rmap_range() is called). This
does not happen on other platforms because the actual page freeing is
deferred.
Solve this by appropriately getting/putting the folio to guarrantee it
does not get freed early. Given the need to get/put the folio in the
batch path, we stick to the non-batched path if the folio is not large.
While the batched path is functionally correct for a folio with 1 page,
it is unlikely to be as efficient as the existing non-batched path in
this case.
Signed-off-by: Ryan Roberts <ryan.roberts@....com>
---
mm/memory.c | 132 ++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 132 insertions(+)
diff --git a/mm/memory.c b/mm/memory.c
index 01f39e8144ef..d35bd8d2b855 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1391,6 +1391,99 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
}
+static inline unsigned long page_cont_mapped_vaddr(struct page *page,
+ struct page *anchor, unsigned long anchor_vaddr)
+{
+ unsigned long offset;
+ unsigned long vaddr;
+
+ offset = (page_to_pfn(page) - page_to_pfn(anchor)) << PAGE_SHIFT;
+ vaddr = anchor_vaddr + offset;
+
+ if (anchor > page) {
+ if (vaddr > anchor_vaddr)
+ return 0;
+ } else {
+ if (vaddr < anchor_vaddr)
+ return ULONG_MAX;
+ }
+
+ return vaddr;
+}
+
+static int folio_nr_pages_cont_mapped(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;
+ struct page *folio_end;
+
+ if (!folio_test_large(folio))
+ return 1;
+
+ folio_end = &folio->page + folio_nr_pages(folio);
+ end = min(page_cont_mapped_vaddr(folio_end, 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)
+ break;
+
+ pfn++;
+ pte++;
+ }
+
+ return i;
+}
+
+static unsigned long try_zap_anon_pte_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ struct folio *folio,
+ struct page *page, pte_t *pte,
+ unsigned long addr, int nr_pages,
+ struct zap_details *details)
+{
+ struct mm_struct *mm = tlb->mm;
+ pte_t ptent;
+ bool full;
+ int i;
+
+ /* __tlb_remove_page may drop a ref; prevent going to 0 while in use. */
+ folio_get(folio);
+
+ for (i = 0; i < nr_pages;) {
+ ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm);
+ tlb_remove_tlb_entry(tlb, pte, addr);
+ zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent);
+ 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);
+
+ folio_put(folio);
+
+ 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,
@@ -1428,6 +1521,45 @@ 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.
+ */
+ if (page && PageAnon(page)) {
+ struct folio *folio = page_folio(page);
+
+ if (folio_test_large(folio)) {
+ int nr_pages_req, nr_pages;
+ int counter = mm_counter(page);
+
+ nr_pages_req = folio_nr_pages_cont_mapped(
+ folio, page, pte, addr,
+ end);
+
+ /* folio may be freed on return. */
+ nr_pages = try_zap_anon_pte_range(
+ tlb, vma, folio, page,
+ pte, addr, nr_pages_req,
+ details);
+
+ rss[counter] -= nr_pages;
+ nr_pages--;
+ pte += nr_pages;
+ addr += nr_pages << PAGE_SHIFT;
+
+ if (unlikely(nr_pages < nr_pages_req)) {
+ 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
Powered by blists - more mailing lists