[PATCH v10 25/26] x86/cet/shstk: Handle thread shadow stack

[Yu-cheng Yu]

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@xxxxxxxxx>
---
v10:
- Limit shadow stack size to 4 GB.

 arch/x86/include/asm/cet.h         |  2 ++
 arch/x86/include/asm/mmu_context.h |  3 +++
 arch/x86/kernel/cet.c              | 41 ++++++++++++++++++++++++++++++
 arch/x86/kernel/process.c          |  7 +++++
 4 files changed, 53 insertions(+)

diff --git a/arch/x86/include/asm/cet.h b/arch/x86/include/asm/cet.h
index 56fe08eebae6..71dc92acd2f2 100644
--- a/arch/x86/include/asm/cet.h
+++ b/arch/x86/include/asm/cet.h
@@ -18,11 +18,13 @@ struct cet_status {
 
 #ifdef CONFIG_X86_INTEL_CET
 int cet_setup_shstk(void);
+int cet_setup_thread_shstk(struct task_struct *p);
 void cet_disable_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) { return 0; }
 static inline void cet_disable_free_shstk(struct task_struct *p) {}
 static inline void cet_restore_signal(struct sc_ext *sc) { return; }
 static inline int cet_setup_signal(bool ia32, unsigned long rstor,
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 4e55370e48e8..bb7a4a2d6923 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -12,6 +12,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
+#include <asm/cet.h>
 #include <asm/debugreg.h>
 
 extern atomic64_t last_mm_ctx_id;
@@ -155,6 +156,8 @@ do {						\
 #else
 #define deactivate_mm(tsk, mm)			\
 do {						\
+	if (!tsk->vfork_done)			\
+		cet_disable_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 274fecdd9669..121552047b86 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -169,6 +169,47 @@ int cet_setup_shstk(void)
 	return 0;
 }
 
+int cet_setup_thread_shstk(struct task_struct *tsk)
+{
+	unsigned long addr, size;
+	struct cet_user_state *state;
+	struct cet_status *cet = &tsk->thread.cet;
+
+	if (!cet->shstk_size)
+		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);
+
+	if (IS_ERR((void *)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_free_shstk(struct task_struct *tsk)
 {
 	struct cet_status *cet = &tsk->thread.cet;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9d9cff2c1018..ef1c2b8086a2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -109,6 +109,7 @@ void exit_thread(struct task_struct *tsk)
 
 	free_vm86(t);
 
+	cet_disable_free_shstk(tsk);
 	fpu__drop(fpu);
 }
 
@@ -179,6 +180,12 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	if (clone_flags & CLONE_SETTLS)
 		ret = set_new_tls(p, tls);
 
+#ifdef CONFIG_X86_64
+	/* Allocate a new shadow stack for pthread */
+	if (!ret && (clone_flags & (CLONE_VFORK | CLONE_VM)) == CLONE_VM)
+		ret = cet_setup_thread_shstk(p);
+#endif
+
 	if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
 		io_bitmap_share(p);
 
-- 
2.21.0