[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20201110162211.9207-25-yu-cheng.yu@intel.com>
Date: Tue, 10 Nov 2020 08:22:09 -0800
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>,
Vedvyas Shanbhogue <vedvyas.shanbhogue@...el.com>,
Dave Martin <Dave.Martin@....com>,
Weijiang Yang <weijiang.yang@...el.com>,
Pengfei Xu <pengfei.xu@...el.com>
Cc: Yu-cheng Yu <yu-cheng.yu@...el.com>
Subject: [PATCH v15 24/26] x86/cet/shstk: Handle thread shadow stack
The kernel allocates (and frees on thread exit) a new shadow stack for a
pthread child.
It is possible for the kernel to complete the clone syscall and set the
child's shadow stack pointer to NULL and let the child thread allocate
a shadow stack for itself. There are two issues in this approach: It
is not compatible with existing code that does inline syscall and it
cannot handle signals before the child can successfully allocate a
shadow stack.
A 64-bit shadow stack has a size of min(RLIMIT_STACK, 4 GB). A compat-mode
thread shadow stack has a size of 1/4 min(RLIMIT_STACK, 4 GB). This allows
more threads to run in a 32-bit address space.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@...el.com>
---
arch/x86/include/asm/cet.h | 3 ++
arch/x86/include/asm/mmu_context.h | 3 ++
arch/x86/kernel/cet.c | 44 ++++++++++++++++++++++++++++++
arch/x86/kernel/process.c | 7 +++++
4 files changed, 57 insertions(+)
diff --git a/arch/x86/include/asm/cet.h b/arch/x86/include/asm/cet.h
index 73435856ce54..ec4b5e62d0ce 100644
--- a/arch/x86/include/asm/cet.h
+++ b/arch/x86/include/asm/cet.h
@@ -18,12 +18,15 @@ struct cet_status {
#ifdef CONFIG_X86_CET
int cet_setup_shstk(void);
+int cet_setup_thread_shstk(struct task_struct *p, unsigned long clone_flags);
void cet_disable_shstk(void);
void cet_free_shstk(struct task_struct *p);
int cet_verify_rstor_token(bool ia32, unsigned long ssp, unsigned long *new_ssp);
void cet_restore_signal(struct sc_ext *sc);
int cet_setup_signal(bool ia32, unsigned long rstor, struct sc_ext *sc);
#else
+static inline int cet_setup_thread_shstk(struct task_struct *p,
+ unsigned long clone_flags) { return 0; }
static inline void cet_disable_shstk(void) {}
static inline void cet_free_shstk(struct task_struct *p) {}
static inline void cet_restore_signal(struct sc_ext *sc) { return; }
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index d98016b83755..ceb593e405e1 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -11,6 +11,7 @@
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
+#include <asm/cet.h>
#include <asm/debugreg.h>
extern atomic64_t last_mm_ctx_id;
@@ -142,6 +143,8 @@ do { \
#else
#define deactivate_mm(tsk, mm) \
do { \
+ if (!tsk->vfork_done) \
+ cet_free_shstk(tsk); \
load_gs_index(0); \
loadsegment(fs, 0); \
} while (0)
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
index 728d9baceb74..d57f3a433af9 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -172,6 +172,50 @@ int cet_setup_shstk(void)
return 0;
}
+int cet_setup_thread_shstk(struct task_struct *tsk, unsigned long clone_flags)
+{
+ unsigned long addr, size;
+ struct cet_user_state *state;
+ struct cet_status *cet = &tsk->thread.cet;
+
+ if (!cet->shstk_size)
+ return 0;
+
+ if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM)
+ return 0;
+
+ state = get_xsave_addr(&tsk->thread.fpu.state.xsave,
+ XFEATURE_CET_USER);
+
+ if (!state)
+ return -EINVAL;
+
+ /* Cap shadow stack size to 4 GB */
+ size = min(rlimit(RLIMIT_STACK), 1UL << 32);
+
+ /*
+ * Compat-mode pthreads share a limited address space.
+ * If each function call takes an average of four slots
+ * stack space, we need 1/4 of stack size for shadow stack.
+ */
+ if (in_compat_syscall())
+ size /= 4;
+ size = round_up(size, PAGE_SIZE);
+ addr = alloc_shstk(size, 0);
+
+ if (IS_ERR_VALUE(addr)) {
+ cet->shstk_base = 0;
+ cet->shstk_size = 0;
+ return PTR_ERR((void *)addr);
+ }
+
+ fpu__prepare_write(&tsk->thread.fpu);
+ state->user_ssp = (u64)(addr + size);
+ cet->shstk_base = addr;
+ cet->shstk_size = size;
+ return 0;
+}
+
void cet_disable_shstk(void)
{
struct cet_status *cet = ¤t->thread.cet;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ff3b44d6740b..67632ba893b7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -110,6 +110,7 @@ void exit_thread(struct task_struct *tsk)
free_vm86(t);
+ cet_free_shstk(tsk);
fpu__drop(fpu);
}
@@ -182,6 +183,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
if (clone_flags & CLONE_SETTLS)
ret = set_new_tls(p, tls);
+#ifdef CONFIG_X86_64
+ /* Allocate a new shadow stack for pthread */
+ if (!ret)
+ ret = cet_setup_thread_shstk(p, clone_flags);
+#endif
+
if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
io_bitmap_share(p);
--
2.21.0
Powered by blists - more mailing lists