| 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: <20210830181528.1569-26-yu-cheng.yu@intel.com>
Date: Mon, 30 Aug 2021 11:15:21 -0700
From: Yu-cheng Yu <yu-cheng.yu@...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>,
Dave Martin <Dave.Martin@....com>,
Weijiang Yang <weijiang.yang@...el.com>,
Pengfei Xu <pengfei.xu@...el.com>,
Haitao Huang <haitao.huang@...el.com>,
Rick P Edgecombe <rick.p.edgecombe@...el.com>
Cc: Yu-cheng Yu <yu-cheng.yu@...el.com>
Subject: [PATCH v30 25/32] x86/cet/shstk: Handle thread shadow stack
For clone() with CLONE_VM, except vfork, the child and the parent must have
separate shadow stacks. Thus, the kernel allocates, and frees on thread
exit a new shadow stack for the child.
Use stack_size passed from clone3() syscall for thread shadow stack size.
A compat-mode thread shadow stack size is further reduced to 1/4. This
allows more threads to run in a 32-bit address space.
The clone() does not pass stack_size, which was added to clone3().
In that case, use RLIMIT_STACK size and cap to 4 GB.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@...el.com>
---
v30:
- Update comments about clone()/clone3(). (Borislav Petkov)
v29:
- WARN_ON_ONCE() when get_xsave_addr() returns NULL, and update comments.
(Dave Hansen)
v28:
- Split out copy_thread() argument name changes to a new patch.
- Add compatibility for earlier clone(), which does not pass stack_size.
- Add comment for get_xsave_addr(), explain the handling of null return
value.
---
arch/x86/include/asm/cet.h | 5 +++
arch/x86/include/asm/mmu_context.h | 3 ++
arch/x86/kernel/process.c | 6 +++
arch/x86/kernel/shstk.c | 63 +++++++++++++++++++++++++++++-
4 files changed, 76 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/cet.h b/arch/x86/include/asm/cet.h
index 9dce4914d03d..cae76b8241b0 100644
--- a/arch/x86/include/asm/cet.h
+++ b/arch/x86/include/asm/cet.h
@@ -14,10 +14,15 @@ struct thread_shstk {
#ifdef CONFIG_X86_SHADOW_STACK
int shstk_setup(void);
+int shstk_alloc_thread_stack(struct task_struct *p, unsigned long clone_flags,
+ unsigned long stack_size);
void shstk_free(struct task_struct *p);
void shstk_disable(void);
#else
static inline int shstk_setup(void) { return 0; }
+static inline int shstk_alloc_thread_stack(struct task_struct *p,
+ unsigned long clone_flags,
+ unsigned long stack_size) { return 0; }
static inline void shstk_free(struct task_struct *p) {}
static inline void shstk_disable(void) {}
#endif
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 27516046117a..e1dd083261a5 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -12,6 +12,7 @@
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
#include <asm/debugreg.h>
+#include <asm/cet.h>
extern atomic64_t last_mm_ctx_id;
@@ -146,6 +147,8 @@ do { \
#else
#define deactivate_mm(tsk, mm) \
do { \
+ if (!tsk->vfork_done) \
+ shstk_free(tsk); \
load_gs_index(0); \
loadsegment(fs, 0); \
} while (0)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e6e4d8bc9023..bade6a594d63 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -43,6 +43,7 @@
#include <asm/io_bitmap.h>
#include <asm/proto.h>
#include <asm/frame.h>
+#include <asm/cet.h>
#include "process.h"
@@ -103,6 +104,7 @@ void exit_thread(struct task_struct *tsk)
free_vm86(t);
+ shstk_free(tsk);
fpu__drop(fpu);
}
@@ -200,6 +202,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
if (clone_flags & CLONE_SETTLS)
ret = set_new_tls(p, tls);
+ /* Allocate a new shadow stack for pthread */
+ if (!ret)
+ ret = shstk_alloc_thread_stack(p, clone_flags, stack_size);
+
if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
io_bitmap_share(p);
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 583dd3fa8c3f..ee80ed0316da 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -75,6 +75,61 @@ int shstk_setup(void)
return err;
}
+int shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long clone_flags,
+ unsigned long stack_size)
+{
+ struct thread_shstk *shstk = &tsk->thread.shstk;
+ struct cet_user_state *state;
+ unsigned long addr;
+
+ if (!shstk->size)
+ return 0;
+
+ /*
+ * clone() does not pass stack_size, which was added to clone3().
+ * Use RLIMIT_STACK and cap to 4 GB.
+ */
+ if (!stack_size)
+ stack_size = min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G);
+
+ /*
+ * For CLONE_VM, except vfork, the child needs a separate shadow
+ * stack.
+ */
+ if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM)
+ return 0;
+
+ /*
+ * 'tsk' is configured with a shadow stack and the fpu.state is
+ * up to date since it was just copied from the parent. There
+ * must be a valid non-init CET state location in the buffer.
+ */
+ state = get_xsave_addr(&tsk->thread.fpu.state.xsave, XFEATURE_CET_USER);
+ if (WARN_ON_ONCE(!state))
+ return -EINVAL;
+
+ /*
+ * Compat-mode pthreads share a limited address space.
+ * If each function call takes an average of four slots
+ * stack space, allocate 1/4 of stack size for shadow stack.
+ */
+ if (in_compat_syscall())
+ stack_size /= 4;
+
+ stack_size = round_up(stack_size, PAGE_SIZE);
+ addr = alloc_shstk(stack_size);
+ if (IS_ERR_VALUE(addr)) {
+ shstk->base = 0;
+ shstk->size = 0;
+ return PTR_ERR((void *)addr);
+ }
+
+ state->user_ssp = (u64)(addr + stack_size);
+ shstk->base = addr;
+ shstk->size = stack_size;
+ return 0;
+}
+
void shstk_free(struct task_struct *tsk)
{
struct thread_shstk *shstk = &tsk->thread.shstk;
@@ -84,7 +139,13 @@ void shstk_free(struct task_struct *tsk)
!shstk->base)
return;
- if (!tsk->mm)
+ /*
+ * When fork() with CLONE_VM fails, the child (tsk) already has a
+ * shadow stack allocated, and exit_thread() calls this function to
+ * free it. In this case the parent (current) and the child share
+ * the same mm struct.
+ */
+ if (!tsk->mm || tsk->mm != current->mm)
return;
while (1) {
--
2.21.0
Powered by blists - more mailing lists