| 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
| ||
|
Date: Thu, 21 Oct 2021 05:21:12 -0700
From: Nadav Amit <nadav.amit@...il.com>
To: linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org, Nadav Amit <namit@...are.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Andy Lutomirski <luto@...nel.org>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Peter Xu <peterx@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Will Deacon <will@...nel.org>, Yu Zhao <yuzhao@...gle.com>,
Nick Piggin <npiggin@...il.com>, x86@...nel.org
Subject: [PATCH v2 5/5] mm/mprotect: do not flush on permission promotion
From: Nadav Amit <namit@...are.com>
Currently, using mprotect() to unprotect a memory region or uffd to
unprotect a memory region causes a TLB flush. At least on x86, as
protection is promoted, no TLB flush is needed.
Add an arch-specific pte_may_need_flush() which tells whether a TLB
flush is needed based on the old PTE and the new one. Implement an x86
pte_may_need_flush().
For x86, besides the simple logic that PTE protection promotion or
changes of software bits does require a flush, also add logic that
considers the dirty-bit. If the dirty-bit is clear and write-protect is
set, no TLB flush is needed, as x86 updates the dirty-bit atomically
on write, and if the bit is clear, the PTE is reread.
Signed-off-by: Nadav Amit <namit@...are.com>
Cc: Andrea Arcangeli <aarcange@...hat.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Andy Lutomirski <luto@...nel.org>
Cc: Dave Hansen <dave.hansen@...ux.intel.com>
Cc: Peter Xu <peterx@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Will Deacon <will@...nel.org>
Cc: Yu Zhao <yuzhao@...gle.com>
Cc: Nick Piggin <npiggin@...il.com>
Cc: x86@...nel.org
---
arch/x86/include/asm/pgtable_types.h | 2 +
arch/x86/include/asm/tlbflush.h | 80 ++++++++++++++++++++++++++++
include/asm-generic/tlb.h | 14 +++++
mm/huge_memory.c | 9 ++--
mm/mprotect.c | 3 +-
5 files changed, 103 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 40497a9020c6..8668bc661026 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -110,9 +110,11 @@
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
#define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP)
+#define _PAGE_SOFTW4 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW4)
#else
#define _PAGE_NX (_AT(pteval_t, 0))
#define _PAGE_DEVMAP (_AT(pteval_t, 0))
+#define _PAGE_SOFTW4 (_AT(pteval_t, 0))
#endif
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index b587a9ee9cb2..a782adde3d62 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -259,6 +259,86 @@ static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+/*
+ * The enabled_mask tells which bits that were present and gets cleared require
+ * flush.
+ *
+ * The disabled_mask tells which bits that were missing and gets set require
+ * flush.
+ *
+ * All the other bits except the ignored bits will require a flush no matter if
+ * they gets set or cleared.
+ *
+ * Note that we ignore the accessed bit, since anyhow the kernel does not flush
+ * after clearing it in other situations. We also ignore the global bit, as it
+ * is used for protnone.
+ */
+static inline bool pte_flags_may_need_flush(unsigned long oldflags,
+ unsigned long newflags)
+{
+ const pteval_t ignore_mask = _PAGE_SOFTW1 | _PAGE_SOFTW2 |
+ _PAGE_SOFTW3 | _PAGE_SOFTW4 | _PAGE_ACCESSED | _PAGE_GLOBAL;
+ const pteval_t enable_mask = _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT;
+ const pteval_t disable_mask = _PAGE_NX;
+ unsigned long diff = oldflags ^ newflags;
+
+ return diff & ((oldflags & enable_mask) |
+ (newflags & disable_mask) |
+ ~(enable_mask | disable_mask | ignore_mask));
+}
+
+/*
+ * pte_may_need_flush() checks whether permissions were demoted and require a
+ * flush. It should only be used for userspace PTEs.
+ */
+static inline bool pte_may_need_flush(pte_t oldpte, pte_t newpte)
+{
+ /* new is non-present: need only if old is present */
+ if (!pte_present(newpte))
+ return pte_present(oldpte);
+
+ /* old is not present: no need for flush */
+ if (!pte_present(oldpte))
+ return false;
+
+ /*
+ * Avoid open-coding to account for protnone_mask() and perform
+ * comparison of the PTEs.
+ */
+ if (pte_pfn(oldpte) != pte_pfn(newpte))
+ return true;
+
+ return pte_flags_may_need_flush(pte_flags(oldpte),
+ pte_flags(newpte));
+}
+#define pte_may_need_flush pte_may_need_flush
+
+/*
+ * huge_pmd_may_need_flush() checks whether permissions were demoted and
+ * require a flush. It should only be used for userspace huge PMDs.
+ */
+static inline bool huge_pmd_may_need_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+ /* new is non-present: need only if old is present */
+ if (!pmd_present(newpmd))
+ return pmd_present(oldpmd);
+
+ /* old is not present: no need for flush */
+ if (!pmd_present(oldpmd))
+ return false;
+
+ /*
+ * Avoid open-coding to account for protnone_mask() and perform
+ * comparison of the PTEs.
+ */
+ if (pmd_pfn(oldpmd) != pmd_pfn(newpmd))
+ return true;
+
+ return pte_flags_may_need_flush(pmd_flags(oldpmd),
+ pmd_flags(newpmd));
+}
+#define huge_pmd_may_need_flush huge_pmd_may_need_flush
+
#endif /* !MODULE */
#endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 2c68a545ffa7..2d3736c62602 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -654,6 +654,20 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
} while (0)
#endif
+#ifndef pte_may_need_flush
+static inline bool pte_may_need_flush(pte_t oldpte, pte_t newpte)
+{
+ return true;
+}
+#endif
+
+#ifndef huge_pmd_may_need_flush
+static inline bool huge_pmd_may_need_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+ return true;
+}
+#endif
+
#endif /* CONFIG_MMU */
#endif /* _ASM_GENERIC__TLB_H */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f5d0357a25ce..f80936324e6a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1726,7 +1726,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
- pmd_t entry;
+ pmd_t oldpmd, entry;
bool preserve_write;
int ret;
bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
@@ -1802,9 +1802,9 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
* dirty/young flags (which are also known as access/dirty) cannot be
* further modifeid by the hardware.
*/
- entry = pmdp_invalidate_ad(vma, addr, pmd);
+ oldpmd = pmdp_invalidate_ad(vma, addr, pmd);
- entry = pmd_modify(entry, newprot);
+ entry = pmd_modify(oldpmd, newprot);
if (preserve_write)
entry = pmd_mk_savedwrite(entry);
if (uffd_wp) {
@@ -1821,7 +1821,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
ret = HPAGE_PMD_NR;
set_pmd_at(mm, addr, pmd, entry);
- tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
+ if (huge_pmd_may_need_flush(oldpmd, entry))
+ tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
unlock:
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 0f5c87af5c60..6179c82ea72d 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -141,7 +141,8 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
ptent = pte_mkwrite(ptent);
}
ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
- tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
+ if (pte_may_need_flush(oldpte, ptent))
+ tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
pages++;
} else if (is_swap_pte(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
--
2.25.1
Powered by blists - more mailing lists