summaryrefslogtreecommitdiff
path: root/arch/arm64/mm
diff options
context:
space:
mode:
authorRyan Roberts <ryan.roberts@arm.com>2024-02-15 13:32:05 +0300
committerAndrew Morton <akpm@linux-foundation.org>2024-02-23 02:27:19 +0300
commitf0c2264958e18bc7bc35b567d51b99461e4de34f (patch)
treebdcaf1234ea5a65dbd1c45ad00268a3b61b26806 /arch/arm64/mm
parentb972fc6afba002319fe23bc698ce6431ee43868c (diff)
downloadlinux-f0c2264958e18bc7bc35b567d51b99461e4de34f.tar.xz
arm64/mm: automatically fold contpte mappings
There are situations where a change to a single PTE could cause the contpte block in which it resides to become foldable (i.e. could be repainted with the contiguous bit). Such situations arise, for example, when user space temporarily changes protections, via mprotect, for individual pages, such can be the case for certain garbage collectors. We would like to detect when such a PTE change occurs. However this can be expensive due to the amount of checking required. Therefore only perform the checks when an indiviual PTE is modified via mprotect (ptep_modify_prot_commit() -> set_pte_at() -> set_ptes(nr=1)) and only when we are setting the final PTE in a contpte-aligned block. Link: https://lkml.kernel.org/r/20240215103205.2607016-19-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Barry Song <21cnbao@gmail.com> Cc: Borislav Petkov (AMD) <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morse <james.morse@arm.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'arch/arm64/mm')
-rw-r--r--arch/arm64/mm/contpte.c64
1 files changed, 64 insertions, 0 deletions
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index 50e0173dc5ee..16788f07716d 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -73,6 +73,70 @@ static void contpte_convert(struct mm_struct *mm, unsigned long addr,
__set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES);
}
+void __contpte_try_fold(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ /*
+ * We have already checked that the virtual and pysical addresses are
+ * correctly aligned for a contpte mapping in contpte_try_fold() so the
+ * remaining checks are to ensure that the contpte range is fully
+ * covered by a single folio, and ensure that all the ptes are valid
+ * with contiguous PFNs and matching prots. We ignore the state of the
+ * access and dirty bits for the purpose of deciding if its a contiguous
+ * range; the folding process will generate a single contpte entry which
+ * has a single access and dirty bit. Those 2 bits are the logical OR of
+ * their respective bits in the constituent pte entries. In order to
+ * ensure the contpte range is covered by a single folio, we must
+ * recover the folio from the pfn, but special mappings don't have a
+ * folio backing them. Fortunately contpte_try_fold() already checked
+ * that the pte is not special - we never try to fold special mappings.
+ * Note we can't use vm_normal_page() for this since we don't have the
+ * vma.
+ */
+
+ unsigned long folio_start, folio_end;
+ unsigned long cont_start, cont_end;
+ pte_t expected_pte, subpte;
+ struct folio *folio;
+ struct page *page;
+ unsigned long pfn;
+ pte_t *orig_ptep;
+ pgprot_t prot;
+
+ int i;
+
+ if (!mm_is_user(mm))
+ return;
+
+ page = pte_page(pte);
+ folio = page_folio(page);
+ folio_start = addr - (page - &folio->page) * PAGE_SIZE;
+ folio_end = folio_start + folio_nr_pages(folio) * PAGE_SIZE;
+ cont_start = ALIGN_DOWN(addr, CONT_PTE_SIZE);
+ cont_end = cont_start + CONT_PTE_SIZE;
+
+ if (folio_start > cont_start || folio_end < cont_end)
+ return;
+
+ pfn = ALIGN_DOWN(pte_pfn(pte), CONT_PTES);
+ prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
+ expected_pte = pfn_pte(pfn, prot);
+ orig_ptep = ptep;
+ ptep = contpte_align_down(ptep);
+
+ for (i = 0; i < CONT_PTES; i++) {
+ subpte = pte_mkold(pte_mkclean(__ptep_get(ptep)));
+ if (!pte_same(subpte, expected_pte))
+ return;
+ expected_pte = pte_advance_pfn(expected_pte, 1);
+ ptep++;
+ }
+
+ pte = pte_mkcont(pte);
+ contpte_convert(mm, addr, orig_ptep, pte);
+}
+EXPORT_SYMBOL(__contpte_try_fold);
+
void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{