From: Yu-cheng Yu <yu-cheng.yu@intel.com>
To: x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
linux-mm@kvack.org, linux-arch@vger.kernel.org,
linux-api@vger.kernel.org, Arnd Bergmann <arnd@arndb.de>,
Andy Lutomirski <luto@kernel.org>,
Balbir Singh <bsingharora@gmail.com>,
Borislav Petkov <bp@alien8.de>,
Cyrill Gorcunov <gorcunov@gmail.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
Eugene Syromiatnikov <esyr@redhat.com>,
Florian Weimer <fweimer@redhat.com>,
"H.J. Lu" <hjl.tools@gmail.com>, Jann Horn <jannh@google.com>,
Jonathan Corbet <corbet@lwn.net>,
Kees Cook <keescook@chromium.org>,
Mike Kravetz <mike.kravetz@oracle.com>,
Nadav Amit <nadav.amit@gmail.com>,
Oleg Nesterov <oleg@redhat.com>, Pavel Machek <pavel@ucw.cz>,
Peter Zijlstra <peterz@infradead.org>,
Randy Dunlap <rdunlap@infradead.org>,
"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com>,
Dave Martin <Dave.Martin@arm.com>,
Weijiang Yang <weijiang.yang@intel.com>,
Pengfei Xu <pengfei.xu@intel.com>,
Haitao Huang <haitao.huang@intel.com>
Cc: Yu-cheng Yu <yu-cheng.yu@intel.com>
Subject: [PATCH v26 23/30] x86/cet/shstk: Handle thread shadow stack
Date: Tue, 27 Apr 2021 13:43:08 -0700 [thread overview]
Message-ID: <20210427204315.24153-24-yu-cheng.yu@intel.com> (raw)
In-Reply-To: <20210427204315.24153-1-yu-cheng.yu@intel.com>
For clone() with CLONE_VM specified, 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,
but cap it to min(RLIMIT_STACK, 4 GB). 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.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/cet.h | 5 +++
arch/x86/include/asm/mmu_context.h | 3 ++
arch/x86/kernel/process.c | 15 ++++++--
arch/x86/kernel/shstk.c | 57 +++++++++++++++++++++++++++++-
4 files changed, 76 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/cet.h b/arch/x86/include/asm/cet.h
index aa85d599b184..8b83ded577cc 100644
--- a/arch/x86/include/asm/cet.h
+++ b/arch/x86/include/asm/cet.h
@@ -16,10 +16,15 @@ struct cet_status {
#ifdef CONFIG_X86_SHADOW_STACK
int shstk_setup(void);
+int shstk_setup_thread(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_setup_thread(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..53569114aa01 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;
@@ -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 9c214d7085a4..fa01e8679d01 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"
@@ -109,6 +110,7 @@ void exit_thread(struct task_struct *tsk)
free_vm86(t);
+ shstk_free(tsk);
fpu__drop(fpu);
}
@@ -122,8 +124,9 @@ static int set_new_tls(struct task_struct *p, unsigned long tls)
return do_set_thread_area_64(p, ARCH_SET_FS, tls);
}
-int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
- struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long sp,
+ unsigned long stack_size, struct task_struct *p,
+ unsigned long tls)
{
struct inactive_task_frame *frame;
struct fork_frame *fork_frame;
@@ -163,7 +166,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
/* Kernel thread ? */
if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
memset(childregs, 0, sizeof(struct pt_regs));
- kthread_frame_init(frame, sp, arg);
+ kthread_frame_init(frame, sp, stack_size);
return 0;
}
@@ -181,6 +184,12 @@ 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 = shstk_setup_thread(p, clone_flags, stack_size);
+#endif
+
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 c815c7507830..d387df84b7f1 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -70,6 +70,55 @@ int shstk_setup(void)
return 0;
}
+int shstk_setup_thread(struct task_struct *tsk, unsigned long clone_flags,
+ unsigned long stack_size)
+{
+ 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;
+
+ if (stack_size == 0)
+ return -EINVAL;
+
+ /* Cap shadow stack size to 4 GB */
+ size = min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G);
+ size = min(size, stack_size);
+
+ /*
+ * 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())
+ size /= 4;
+ size = round_up(size, PAGE_SIZE);
+ addr = alloc_shstk(size);
+
+ 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 shstk_free(struct task_struct *tsk)
{
struct cet_status *cet = &tsk->thread.cet;
@@ -79,7 +128,13 @@ void shstk_free(struct task_struct *tsk)
!cet->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 is
+ * sharing the same mm struct.
+ */
+ if (!tsk->mm || tsk->mm != current->mm)
return;
while (1) {
--
2.21.0
next prev parent reply other threads:[~2021-04-27 20:45 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-27 20:42 [PATCH v26 00/30] Control-flow Enforcement: Shadow Stack Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 01/30] Documentation/x86: Add CET description Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 02/30] x86/cet/shstk: Add Kconfig option for Shadow Stack Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 03/30] x86/cpufeatures: Add CET CPU feature flags for Control-flow Enforcement Technology (CET) Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 04/30] x86/cpufeatures: Introduce CPU setup and option parsing for CET Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 05/30] x86/fpu/xstate: Introduce CET MSR and XSAVES supervisor states Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 06/30] x86/cet: Add control-protection fault handler Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 07/30] x86/mm: Remove _PAGE_DIRTY from kernel RO pages Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 08/30] x86/mm: Move pmd_write(), pud_write() up in the file Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 09/30] x86/mm: Introduce _PAGE_COW Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 10/30] drm/i915/gvt: Change _PAGE_DIRTY to _PAGE_DIRTY_BITS Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 11/30] x86/mm: Update pte_modify for _PAGE_COW Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 12/30] x86/mm: Update ptep_set_wrprotect() and pmdp_set_wrprotect() for transition from _PAGE_DIRTY to _PAGE_COW Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 13/30] mm: Introduce VM_SHADOW_STACK for shadow stack memory Yu-cheng Yu
2021-04-27 20:42 ` [PATCH v26 14/30] x86/mm: Shadow Stack page fault error checking Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 15/30] x86/mm: Update maybe_mkwrite() for shadow stack Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 16/30] mm: Fixup places that call pte_mkwrite() directly Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 17/30] mm: Add guard pages around a shadow stack Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 18/30] mm/mmap: Add shadow stack pages to memory accounting Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 19/30] mm: Update can_follow_write_pte() for shadow stack Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 20/30] mm/mprotect: Exclude shadow stack from preserve_write Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 21/30] mm: Re-introduce vm_flags to do_mmap() Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 22/30] x86/cet/shstk: Add user-mode shadow stack support Yu-cheng Yu
2021-04-28 17:52 ` Borislav Petkov
2021-04-28 18:39 ` Yu, Yu-cheng
2021-04-29 9:12 ` Borislav Petkov
2021-04-29 16:17 ` Yu, Yu-cheng
2021-04-29 16:45 ` Borislav Petkov
2021-04-27 20:43 ` Yu-cheng Yu [this message]
2021-05-10 14:15 ` [PATCH v26 23/30] x86/cet/shstk: Handle thread shadow stack Borislav Petkov
2021-05-10 22:57 ` Yu, Yu-cheng
2021-05-11 17:09 ` Borislav Petkov
2021-05-12 8:12 ` David Laight
2021-05-11 18:35 ` Yu, Yu-cheng
2021-05-12 15:56 ` Borislav Petkov
2021-04-27 20:43 ` [PATCH v26 24/30] x86/cet/shstk: Introduce shadow stack token setup/verify routines Yu-cheng Yu
2021-05-17 7:45 ` Borislav Petkov
2021-05-17 20:55 ` Yu, Yu-cheng
2021-05-18 0:14 ` Eugene Syromiatnikov
2021-05-18 17:58 ` Borislav Petkov
2021-05-18 19:45 ` Yu, Yu-cheng
2021-05-18 18:05 ` Yu, Yu-cheng
2021-05-18 5:56 ` Borislav Petkov
2021-05-21 16:17 ` Yu, Yu-cheng
2021-05-21 18:40 ` Borislav Petkov
2021-04-27 20:43 ` [PATCH v26 25/30] x86/cet/shstk: Handle signals for shadow stack Yu-cheng Yu
2021-04-28 23:03 ` extending ucontext (Re: [PATCH v26 25/30] x86/cet/shstk: Handle signals for shadow stack) Andy Lutomirski
2021-04-28 23:20 ` Yu, Yu-cheng
2021-04-29 7:28 ` Cyrill Gorcunov
2021-04-29 14:44 ` Andy Lutomirski
2021-04-29 15:35 ` Cyrill Gorcunov
2021-04-30 6:45 ` Florian Weimer
2021-04-30 17:00 ` Yu, Yu-cheng
2021-04-30 17:47 ` Andy Lutomirski
2021-04-30 18:32 ` Yu, Yu-cheng
2021-05-04 20:49 ` Yu, Yu-cheng
2021-05-06 22:05 ` Yu, Yu-cheng
2021-05-06 23:31 ` Andy Lutomirski
2021-05-02 23:23 ` Andy Lutomirski
2021-05-03 6:03 ` H. Peter Anvin
2021-05-03 15:13 ` Yu, Yu-cheng
2021-05-03 15:29 ` Andy Lutomirski
2021-05-03 20:25 ` Yu, Yu-cheng
2021-04-27 20:43 ` [PATCH v26 26/30] ELF: Introduce arch_setup_elf_property() Yu-cheng Yu
2021-05-19 18:10 ` Borislav Petkov
2021-05-19 22:14 ` Yu, Yu-cheng
2021-05-20 9:26 ` Borislav Petkov
2021-05-20 17:18 ` Yu, Yu-cheng
2021-05-20 17:35 ` Borislav Petkov
2021-05-20 17:51 ` Yu, Yu-cheng
2021-05-20 17:38 ` Matthew Wilcox
2021-05-20 17:52 ` Yu, Yu-cheng
2021-05-20 21:06 ` Yu, Yu-cheng
2021-04-27 20:43 ` [PATCH v26 27/30] x86/cet/shstk: Add arch_prctl functions for shadow stack Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 28/30] mm: Move arch_calc_vm_prot_bits() to arch/x86/include/asm/mman.h Yu-cheng Yu
2021-04-27 20:43 ` [PATCH v26 29/30] mm: Update arch_validate_flags() to test vma anonymous Yu-cheng Yu
2021-05-11 11:35 ` Kirill A. Shutemov
2021-04-27 20:43 ` [PATCH v26 30/30] mm: Introduce PROT_SHADOW_STACK for shadow stack Yu-cheng Yu
2021-05-11 11:48 ` Kirill A. Shutemov
2021-05-11 14:44 ` Yu, Yu-cheng
2021-04-29 17:13 ` [PATCH v26 00/30] Control-flow Enforcement: Shadow Stack Borislav Petkov
2021-04-29 17:32 ` Yu, Yu-cheng
2021-04-29 17:49 ` Borislav Petkov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210427204315.24153-24-yu-cheng.yu@intel.com \
--to=yu-cheng.yu@intel.com \
--cc=Dave.Martin@arm.com \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=bsingharora@gmail.com \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=esyr@redhat.com \
--cc=fweimer@redhat.com \
--cc=gorcunov@gmail.com \
--cc=haitao.huang@intel.com \
--cc=hjl.tools@gmail.com \
--cc=hpa@zytor.com \
--cc=jannh@google.com \
--cc=keescook@chromium.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mike.kravetz@oracle.com \
--cc=mingo@redhat.com \
--cc=nadav.amit@gmail.com \
--cc=oleg@redhat.com \
--cc=pavel@ucw.cz \
--cc=pengfei.xu@intel.com \
--cc=peterz@infradead.org \
--cc=ravi.v.shankar@intel.com \
--cc=rdunlap@infradead.org \
--cc=tglx@linutronix.de \
--cc=vedvyas.shanbhogue@intel.com \
--cc=weijiang.yang@intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).