| 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: <20220929222936.14584-17-rick.p.edgecombe@intel.com>
Date: Thu, 29 Sep 2022 15:29:13 -0700
From: Rick Edgecombe <rick.p.edgecombe@...el.com>
To: x86@...nel.org, "H . Peter Anvin" <hpa@...or.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org, linux-mm@...ck.org,
linux-arch@...r.kernel.org, linux-api@...r.kernel.org,
Arnd Bergmann <arnd@...db.de>,
Andy Lutomirski <luto@...nel.org>,
Balbir Singh <bsingharora@...il.com>,
Borislav Petkov <bp@...en8.de>,
Cyrill Gorcunov <gorcunov@...il.com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Eugene Syromiatnikov <esyr@...hat.com>,
Florian Weimer <fweimer@...hat.com>,
"H . J . Lu" <hjl.tools@...il.com>, Jann Horn <jannh@...gle.com>,
Jonathan Corbet <corbet@....net>,
Kees Cook <keescook@...omium.org>,
Mike Kravetz <mike.kravetz@...cle.com>,
Nadav Amit <nadav.amit@...il.com>,
Oleg Nesterov <oleg@...hat.com>, Pavel Machek <pavel@....cz>,
Peter Zijlstra <peterz@...radead.org>,
Randy Dunlap <rdunlap@...radead.org>,
"Ravi V . Shankar" <ravi.v.shankar@...el.com>,
Weijiang Yang <weijiang.yang@...el.com>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
joao.moreira@...el.com, John Allen <john.allen@....com>,
kcc@...gle.com, eranian@...gle.com, rppt@...nel.org,
jamorris@...ux.microsoft.com, dethoma@...rosoft.com
Cc: rick.p.edgecombe@...el.com, Yu-cheng Yu <yu-cheng.yu@...el.com>
Subject: [PATCH v2 16/39] x86/mm: Update maybe_mkwrite() for shadow stack
From: Yu-cheng Yu <yu-cheng.yu@...el.com>
When serving a page fault, maybe_mkwrite() makes a PTE writable if there is
a write access to it, and its vma has VM_WRITE. Shadow stack accesses to
shadow stack vma's are also treated as write accesses by the fault handler.
This is because setting shadow stack memory makes it writable via some
instructions, so COW has to happen even for shadow stack reads.
So maybe_mkwrite() should continue to set VM_WRITE vma's as normally
writable, but also set VM_WRITE|VM_SHADOW_STACK vma's as shadow stack.
Do this by adding a pte_mkwrite_shstk() and a cross-arch stub. Check for
VM_SHADOW_STACK in maybe_mkwrite() and call pte_mkwrite_shstk()
accordingly.
Apply the same changes to maybe_pmd_mkwrite().
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@...el.com>
Co-developed-by: Rick Edgecombe <rick.p.edgecombe@...el.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@...el.com>
Cc: Kees Cook <keescook@...omium.org>
---
v2:
- Change to handle shadow stacks that are VM_WRITE|VM_SHADOW_STACK
- Ditch arch specific maybe_mkwrite(), and make the code generic
Yu-cheng v29:
- Remove likely()'s.
arch/x86/include/asm/pgtable.h | 2 ++
include/linux/mm.h | 14 +++++++++++++-
include/linux/pgtable.h | 14 ++++++++++++++
mm/huge_memory.c | 9 ++++++++-
mm/memory.c | 3 +--
5 files changed, 38 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 58c7bf9d7392..7a769c4dbc1c 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -419,6 +419,7 @@ static inline pte_t pte_mkdirty(pte_t pte)
return pte_set_flags(pte, dirty | _PAGE_SOFT_DIRTY);
}
+#define pte_mkwrite_shstk pte_mkwrite_shstk
static inline pte_t pte_mkwrite_shstk(pte_t pte)
{
/* pte_clear_cow() also sets Dirty=1 */
@@ -555,6 +556,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
return pmd_set_flags(pmd, dirty | _PAGE_SOFT_DIRTY);
}
+#define pmd_mkwrite_shstk pmd_mkwrite_shstk
static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
{
return pmd_clear_cow(pmd);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8cd413c5a329..fef14ab3abcb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -981,13 +981,25 @@ void free_compound_page(struct page *page);
* servicing faults for write access. In the normal case, do always want
* pte_mkwrite. But get_user_pages can cause write faults for mappings
* that do not have writing enabled, when used by access_process_vm.
+ *
+ * If a vma is shadow stack (a type of writable memory), mark the pte shadow
+ * stack.
*/
+#ifndef maybe_mkwrite
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
- if (likely(vma->vm_flags & VM_WRITE))
+ if (!(vma->vm_flags & VM_WRITE))
+ goto out;
+
+ if (vma->vm_flags & VM_SHADOW_STACK)
+ pte = pte_mkwrite_shstk(pte);
+ else
pte = pte_mkwrite(pte);
+
+out:
return pte;
}
+#endif
vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 014ee8f0fbaa..21115b4895ca 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -480,6 +480,13 @@ static inline pte_t pte_sw_mkyoung(pte_t pte)
#define pte_mk_savedwrite pte_mkwrite
#endif
+#ifndef pte_mkwrite_shstk
+static inline pte_t pte_mkwrite_shstk(pte_t pte)
+{
+ return pte;
+}
+#endif
+
#ifndef pte_clear_savedwrite
#define pte_clear_savedwrite pte_wrprotect
#endif
@@ -488,6 +495,13 @@ static inline pte_t pte_sw_mkyoung(pte_t pte)
#define pmd_savedwrite pmd_write
#endif
+#ifndef pmd_mkwrite_shstk
+static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
+{
+ return pmd;
+}
+#endif
+
#ifndef pmd_mk_savedwrite
#define pmd_mk_savedwrite pmd_mkwrite
#endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e9414ee57c5b..11fc69eb4717 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -554,8 +554,15 @@ __setup("transparent_hugepage=", setup_transparent_hugepage);
pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
- if (likely(vma->vm_flags & VM_WRITE))
+ if (!(vma->vm_flags & VM_WRITE))
+ goto out;
+
+ if (vma->vm_flags & VM_SHADOW_STACK)
+ pmd = pmd_mkwrite_shstk(pmd);
+ else
pmd = pmd_mkwrite(pmd);
+
+out:
return pmd;
}
diff --git a/mm/memory.c b/mm/memory.c
index 4ba73f5aa8bb..6e8379f6793c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4098,8 +4098,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
entry = mk_pte(page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
- if (vma->vm_flags & VM_WRITE)
- entry = pte_mkwrite(pte_mkdirty(entry));
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
--
2.17.1
Powered by blists - more mailing lists