Skip to contentSkip to conversation

Control-flow Enforcement: Indirect Branch Tracking

PATCH Superseded Yu-cheng Yu 5 participants 29 messages Apr 27, 2021 – Apr 28, 2021

Subsystems (7)

v26 of 30 Superseded Latest is v30 →

lore
Share & tools
lore
#0 lore raw

v26 cover Control-flow Enforcement: Indirect Branch Tracking

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

This is the second part of CET and enables Indirect Branch Tracking (IBT). It is built on top of the shadow stack series.

Changes in v26:
- Rebase to Linus tree v5.12.

Changes in v25:
- Make updates to Kconfig and CPU feature flags for the removal of Kconfig X86_CET and software-defined X86_FEATURE_CET.
- Update ENDBR definition.
- Rebase to Linus tree v5.12-rc7.

[1] Intel 64 and IA-32 Architectures Software Developer's Manual:

    https://software.intel.com/en-us/download/intel-64-and-ia-32-
    architectures-sdm-combined-volumes-1-2a-2b-2c-2d-3a-3b-3c-3d-and-4

[2] Indirect Branch Tracking patches v25:

    https://lore.kernel.org/r/[email protected]/

H.J. Lu (3):
x86/cet/ibt: Update arch_prctl functions for Indirect Branch Tracking x86/vdso: Insert endbr32/endbr64 to vDSO
x86/vdso/32: Add ENDBR to __kernel_vsyscall entry point

Yu-cheng Yu (6):
x86/cet/ibt: Add Kconfig option for Indirect Branch Tracking x86/cet/ibt: Add user-mode Indirect Branch Tracking support x86/cet/ibt: Handle signals for Indirect Branch Tracking x86/cet/ibt: Update ELF header parsing for Indirect Branch Tracking x86/vdso: Introduce ENDBR macro
x86/vdso: Add ENDBR to __vdso_sgx_enter_enclave

 arch/x86/Kconfig                         | 21 +++++++++
 arch/x86/entry/vdso/Makefile             |  4 ++
 arch/x86/entry/vdso/vdso32/system_call.S |  2 +
 arch/x86/entry/vdso/vsgx.S               |  4 ++
 arch/x86/include/asm/cet.h               |  9 ++++
 arch/x86/include/asm/disabled-features.h |  8 +++-
 arch/x86/include/asm/vdso.h              | 20 ++++++++-
 arch/x86/include/uapi/asm/sigcontext.h   |  1 +
 arch/x86/kernel/Makefile                 |  1 +
 arch/x86/kernel/cet_prctl.c              |  5 +++
 arch/x86/kernel/fpu/signal.c             | 33 ++++++++++++--
 arch/x86/kernel/ibt.c                    | 57 ++++++++++++++++++++++++
 arch/x86/kernel/process_64.c             |  8 ++++
 13 files changed, 168 insertions(+), 5 deletions(-)
 create mode 100644 arch/x86/kernel/ibt.c
Signature · 1 line
2.21.0
#1 lore raw

PATCH v26 1/9 x86/cet/ibt: Add Kconfig option for Indirect Branch Tracking

Indirect Branch Tracking (IBT) provides protection against CALL-/JMP- oriented programming attacks. It is active when the kernel has this feature enabled, and the processor and the application support it. When this feature is enabled, legacy non-IBT applications continue to work, but without IBT protection.

---
v25:
- Make CONFIG_X86_IBT depend on CONFIG_X86_SHADOW_STACK.

 arch/x86/Kconfig                         | 19 +++++++++++++++++++
 arch/x86/include/asm/disabled-features.h |  8 +++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)
arch/x86/Kconfig +19 -0
index 77d2e44995d7..6bb69fba0dad 100644
@@ -1965,6 +1965,25 @@ config X86_SHADOW_STACK
 
 	  If unsure, say N.
 
+config X86_IBT
+	prompt "Intel Indirect Branch Tracking"
+	def_bool n
+	depends on X86_SHADOW_STACK
+	depends on $(cc-option,-fcf-protection)
+	help
+	  Indirect Branch Tracking (IBT) provides protection against
+	  CALL-/JMP-oriented programming attacks.  It is active when
+	  the kernel has this feature enabled, and the processor and
+	  the application support it.  When this feature is enabled,
+	  legacy non-IBT applications continue to work, but without
+	  IBT protection.
+	  Support for this feature is present on Tiger Lake family of
+	  processors released in 2020 or later.  Enabling this feature
+	  increases kernel text size by 3.7 KB.
+	  See Documentation/x86/intel_cet.rst for more information.
+
+	  If unsure, say N.
+
 config EFI
 	bool "EFI runtime service support"
 	depends on ACPI
arch/x86/include/asm/disabled-features.h +7 -1
index e5c6ed9373e8..07cc40d49947 100644
@@ -74,6 +74,12 @@
 #define DISABLE_SHSTK	(1 << (X86_FEATURE_SHSTK & 31))
 #endif
 
+#ifdef CONFIG_X86_IBT
+#define DISABLE_IBT	0
+#else
+#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -96,7 +102,7 @@
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
 			 DISABLE_ENQCMD|DISABLE_SHSTK)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK18	0
+#define DISABLED_MASK18	(DISABLE_IBT)
 #define DISABLED_MASK19	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
 
Signature · 1 line
2.21.0
Reviewed-by on v26 1/9
#2 lore raw

Re: [PATCH v26 1/9] x86/cet/ibt: Add Kconfig option for Indirect Branch Tracking

Quoted 7 lines · Yu-cheng Yu

Indirect Branch Tracking (IBT) provides protection against CALL-/JMP- oriented programming attacks. It is active when the kernel has this feature enabled, and the processor and the application support it. When this feature is enabled, legacy non-IBT applications continue to work, but without IBT protection.

Signature · 1 line
Kees Cook
#3 lore raw

PATCH v26 2/9 x86/cet/ibt: Add user-mode Indirect Branch Tracking support

In reply to Yu-cheng Yu

Introduce user-mode Indirect Branch Tracking (IBT) support. Add routines for the setup/disable of IBT.

---
v24:
- Move IBT routines to a separate ibt.c, update related areas accordingly.

 arch/x86/include/asm/cet.h |  9 ++++++
 arch/x86/kernel/Makefile   |  1 +
 arch/x86/kernel/ibt.c      | 57 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 67 insertions(+)
 create mode 100644 arch/x86/kernel/ibt.c
arch/x86/include/asm/cet.h +9 -0
index 662335ceb57f..17afcc9ea4d1 100644
@@ -15,6 +15,7 @@ struct cet_status {
 	unsigned long	shstk_base;
 	unsigned long	shstk_size;
 	unsigned int	locked:1;
+	unsigned int	ibt_enabled:1;
 };
 
 #ifdef CONFIG_X86_SHADOW_STACK
@@ -41,6 +42,14 @@ static inline int shstk_check_rstor_token(bool ia32, unsigned long token_addr,
 					  unsigned long *new_ssp) { return 0; }
 #endif
 
+#ifdef CONFIG_X86_IBT
+int ibt_setup(void);
+void ibt_disable(void);
+#else
+static inline int ibt_setup(void) { return 0; }
+static inline void ibt_disable(void) {}
+#endif
+
 #ifdef CONFIG_X86_SHADOW_STACK
 int prctl_cet(int option, u64 arg2);
 #else
arch/x86/kernel/Makefile +1 -0
index eb13d578ad36..e10e007c1d80 100644
@@ -151,6 +151,7 @@ obj-$(CONFIG_UNWINDER_GUESS)		+= unwind_guess.o
 
 obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev-es.o
 obj-$(CONFIG_X86_SHADOW_STACK)		+= shstk.o cet_prctl.o
+obj-$(CONFIG_X86_IBT)			+= ibt.o
 
 ###
 # 64 bit specific files
arch/x86/kernel/ibt.c new file +57 -0

57 lines not on this page · raw message

Signature · 1 line
2.21.0
#5 lore raw

PATCH v26 3/9 x86/cet/ibt: Handle signals for Indirect Branch Tracking

In reply to Yu-cheng Yu

When an indirect CALL/JMP instruction is executed and before it reaches the target, it is in 'WAIT_ENDBR' status, which can be read from MSR_IA32_U_CET. The status is part of a task's status before a signal is raised and preserved in the signal frame. It is restored for sigreturn.

IBT state machine is described in Intel SDM Vol. 1, Sec. 18.3.

---
v25:
- Move the addition of sc_ext.wait_endbr from an earlier shadow stack patch to here.
- Change X86_FEATURE_CET to X86_FEATURE_SHSTK.
- Change wrmsrl() to wrmsrl_safe() and handle error.

v24:
- Update for changes from splitting shadow stack and ibt.

 arch/x86/include/uapi/asm/sigcontext.h |  1 +
 arch/x86/kernel/fpu/signal.c           | 33 +++++++++++++++++++++++---
 2 files changed, 31 insertions(+), 3 deletions(-)
arch/x86/include/uapi/asm/sigcontext.h +1 -0
index 10d7fa192d48..ee5bacce7d87 100644
@@ -203,6 +203,7 @@ struct _xstate {
 struct sc_ext {
 	unsigned long total_size;
 	unsigned long ssp;
+	unsigned long wait_endbr;
 };
 
 /*
arch/x86/kernel/fpu/signal.c +30 -3
index 0488407bec81..0ed01e70b09e 100644
@@ -71,16 +71,29 @@ int save_extra_state_to_sigframe(int ia32, void __user *fp, void __user *restore
 			return err;
 
 		ext.ssp = token_addr;
+	}
 
+	if (new_ssp || cet->ibt_enabled) {
 		fpregs_lock();
 		if (test_thread_flag(TIF_NEED_FPU_LOAD))
 			__fpregs_load_activate();
 		if (new_ssp)
 			err = wrmsrl_safe(MSR_IA32_PL3_SSP, new_ssp);
+
+		if (!err && cet->ibt_enabled) {
+			u64 msr_val;
+
+			err = rdmsrl_safe(MSR_IA32_U_CET, &msr_val);
+			if (!err && (msr_val & CET_WAIT_ENDBR)) {
+				ext.wait_endbr = 1;
+				msr_val &= ~CET_WAIT_ENDBR;
+				err = wrmsrl_safe(MSR_IA32_U_CET, msr_val);
+			}
+		}
 		fpregs_unlock();
 	}
 
-	if (!err && ext.ssp) {
+	if (!err && (ext.ssp || cet->ibt_enabled)) {
 		void __user *p = fp;
 
 		ext.total_size = sizeof(ext);
@@ -110,7 +123,8 @@ static int get_extra_state_from_sigframe(int ia32, void __user *fp, struct sc_ex
 	if (!cpu_feature_enabled(X86_FEATURE_SHSTK))
 		return 0;
 
-	if (!cet->shstk_size)
+	if (!cet->shstk_size &&
+	    !cet->ibt_enabled)
 		return 0;
 
 	memset(ext, 0, sizeof(*ext));
@@ -149,6 +163,19 @@ static int restore_extra_state_to_xregs(struct sc_ext *sc_ext)
 
 	if (cet->shstk_size)
 		err = wrmsrl_safe(MSR_IA32_PL3_SSP, sc_ext->ssp);
+
+	if (err)
+		return err;
+
+	if (cet->ibt_enabled && sc_ext->wait_endbr) {
+		u64 msr_val;
+
+		err = rdmsrl_safe(MSR_IA32_U_CET, &msr_val);
+		if (!err) {
+			msr_val |= CET_WAIT_ENDBR;
+			err = wrmsrl_safe(MSR_IA32_U_CET, msr_val);
+		}
+	}
 #endif
 	return err;
 }
@@ -616,7 +643,7 @@ static unsigned long fpu__alloc_sigcontext_ext(unsigned long sp)
 	 * sigcontext_ext is at: fpu + fpu_user_xstate_size +
 	 * FP_XSTATE_MAGIC2_SIZE, then aligned to 8.
 	 */
-	if (cet->shstk_size)
+	if (cet->shstk_size || cet->ibt_enabled)
 		sp -= (sizeof(struct sc_ext) + 8);
 #endif
 	return sp;
Signature · 1 line
2.21.0
Reviewed-by on v26 3/9
#6 lore raw

Re: [PATCH v26 3/9] x86/cet/ibt: Handle signals for Indirect Branch Tracking

Quoted 8 lines · Yu-cheng Yu

When an indirect CALL/JMP instruction is executed and before it reaches the target, it is in 'WAIT_ENDBR' status, which can be read from MSR_IA32_U_CET. The status is part of a task's status before a signal is raised and preserved in the signal frame. It is restored for sigreturn.

IBT state machine is described in Intel SDM Vol. 1, Sec. 18.3.

Signature · 1 line
Kees Cook
#7 lore raw

PATCH v26 4/9 x86/cet/ibt: Update ELF header parsing for Indirect Branch Tracking

In reply to Yu-cheng Yu

An ELF file's .note.gnu.property indicates features the file supports. The property is parsed at loading time and passed to arch_setup_elf_ property(). Update it for Indirect Branch Tracking.

---
v24:
- Update for changes introduced from splitting shadow stack and ibt.

 arch/x86/Kconfig             | 2 ++
 arch/x86/kernel/process_64.c | 8 ++++++++
 2 files changed, 10 insertions(+)
arch/x86/Kconfig +2 -0
index 6bb69fba0dad..7436e3a608e8 100644
@@ -1970,6 +1970,8 @@ config X86_IBT
 	def_bool n
 	depends on X86_SHADOW_STACK
 	depends on $(cc-option,-fcf-protection)
+	select ARCH_USE_GNU_PROPERTY
+	select ARCH_BINFMT_ELF_STATE
 	help
 	  Indirect Branch Tracking (IBT) provides protection against
 	  CALL-/JMP-oriented programming attacks.  It is active when
arch/x86/kernel/process_64.c +8 -0
index d71045b29475..bf8ef10e5b78 100644
@@ -864,6 +864,14 @@ int arch_setup_elf_property(struct arch_elf_state *state)
 			r = shstk_setup();
 	}
 
+	if (r < 0)
+		return r;
+
+	if (cpu_feature_enabled(X86_FEATURE_IBT)) {
+		if (state->gnu_property & GNU_PROPERTY_X86_FEATURE_1_IBT)
+			r = ibt_setup();
+	}
+
 	return r;
 }
 #endif
Signature · 1 line
2.21.0
Reviewed-by on v26 4/9
#8 lore raw

Re: [PATCH v26 4/9] x86/cet/ibt: Update ELF header parsing for Indirect Branch Tracking

Quoted 5 lines · Yu-cheng Yu

An ELF file's .note.gnu.property indicates features the file supports. The property is parsed at loading time and passed to arch_setup_elf_ property(). Update it for Indirect Branch Tracking.

Signature · 1 line
Kees Cook
#9 lore raw

PATCH v26 5/9 x86/cet/ibt: Update arch_prctl functions for Indirect Branch Tracking

In reply to Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

Update ARCH_X86_CET_STATUS and ARCH_X86_CET_DISABLE for Indirect Branch Tracking.

---
v24:
- Update for function name changes introduced from splitting shadow stack and ibt.

 arch/x86/kernel/cet_prctl.c | 5 +++++
 1 file changed, 5 insertions(+)
arch/x86/kernel/cet_prctl.c +5 -0
index 3bb9f32ca70d..ab05597545c5 100644
@@ -22,6 +22,9 @@ static int cet_copy_status_to_user(struct cet_status *cet, u64 __user *ubuf)
 		buf[2] = cet->shstk_size;
 	}
 
+	if (cet->ibt_enabled)
+		buf[0] |= GNU_PROPERTY_X86_FEATURE_1_IBT;
+
 	return copy_to_user(ubuf, buf, sizeof(buf));
 }
 
@@ -46,6 +49,8 @@ int prctl_cet(int option, u64 arg2)
 			return -EINVAL;
 		if (arg2 & GNU_PROPERTY_X86_FEATURE_1_SHSTK)
 			shstk_disable();
+		if (arg2 & GNU_PROPERTY_X86_FEATURE_1_IBT)
+			ibt_disable();
 		return 0;
 
 	case ARCH_X86_CET_LOCK:
Signature · 1 line
2.21.0
#10 lore raw

PATCH v26 6/9 x86/vdso: Insert endbr32/endbr64 to vDSO

In reply to Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

When Indirect Branch Tracking (IBT) is enabled, vDSO functions may be called indirectly, and must have ENDBR32 or ENDBR64 as the first instruction. The compiler must support -fcf-protection=branch so that it can be used to compile vDSO.

Cc Andy Lutomirski <[email protected]>
Cc Kees Cook <[email protected]>

---
v24:
- Replace CONFIG_X86_CET with CONFIG_X86_IBT to reflect splitting of shadow stack and ibt.

 arch/x86/entry/vdso/Makefile | 4 ++++
 1 file changed, 4 insertions(+)
arch/x86/entry/vdso/Makefile +4 -0
index 05c4abc2fdfd..a773a5f03b63 100644
@@ -93,6 +93,10 @@ endif
 
 $(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
+ifdef CONFIG_X86_IBT
+$(vobjs) $(vobjs32): KBUILD_CFLAGS += -fcf-protection=branch
+endif
+
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
 #
Signature · 1 line
2.21.0
Reviewed-by on v26 6/9
#11 lore raw

Re: [PATCH v26 6/9] x86/vdso: Insert endbr32/endbr64 to vDSO

Quoted 6 lines · Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

When Indirect Branch Tracking (IBT) is enabled, vDSO functions may be called indirectly, and must have ENDBR32 or ENDBR64 as the first instruction. The compiler must support -fcf-protection=branch so that it can be used to compile vDSO.

If you respin this, you can maybe rephrase this since CONFIG_X86_IBT has already tested for the compiler support.

Quoted 5 lines
Cc Andy Lutomirski <[email protected]>
Cc Kees Cook <[email protected]>

-Kees

Quoted 26 lines

---
v24:
- Replace CONFIG_X86_CET with CONFIG_X86_IBT to reflect splitting of shadow stack and ibt.

 arch/x86/entry/vdso/Makefile | 4 ++++
 1 file changed, 4 insertions(+)
arch/x86/entry/vdso/Makefile +4 -0
index 05c4abc2fdfd..a773a5f03b63 100644
@@ -93,6 +93,10 @@ endif
 
 $(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
+ifdef CONFIG_X86_IBT
+$(vobjs) $(vobjs32): KBUILD_CFLAGS += -fcf-protection=branch
+endif
+
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
 #
Signature · 1 line
2.21.0
Signature · 1 line
Kees Cook
#12 lore raw

Re: [PATCH v26 6/9] x86/vdso: Insert endbr32/endbr64 to vDSO

Quoted 11 lines · Kees Cook
Quoted 6 lines · Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

When Indirect Branch Tracking (IBT) is enabled, vDSO functions may be called indirectly, and must have ENDBR32 or ENDBR64 as the first instruction. The compiler must support -fcf-protection=branch so that it can be used to compile vDSO.

If you respin this, you can maybe rephrase this since CONFIG_X86_IBT has already tested for the compiler support.

Yes, I will fix this. Thanks for reviewing!

Yu-cheng

Quoted 37 lines
Quoted 5 lines
Cc Andy Lutomirski <[email protected]>
Cc Kees Cook <[email protected]>

-Kees

Quoted 26 lines

---
v24:
- Replace CONFIG_X86_CET with CONFIG_X86_IBT to reflect splitting of shadow stack and ibt.

  arch/x86/entry/vdso/Makefile | 4 ++++
  1 file changed, 4 insertions(+)
arch/x86/entry/vdso/Makefile +4 -0
index 05c4abc2fdfd..a773a5f03b63 100644
@@ -93,6 +93,10 @@ endif
 
  $(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
+ifdef CONFIG_X86_IBT
+$(vobjs) $(vobjs32): KBUILD_CFLAGS += -fcf-protection=branch
+endif
+
  #
  # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
  #
Signature · 1 line
2.21.0
Reviewed-by on v26 6/9
#13 lore raw

Re: [PATCH v26 6/9] x86/vdso: Insert endbr32/endbr64 to vDSO

In reply to Yu-cheng Yu
Quoted 8 lines · Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

When Indirect Branch Tracking (IBT) is enabled, vDSO functions may be called indirectly, and must have ENDBR32 or ENDBR64 as the first instruction. The compiler must support -fcf-protection=branch so that it can be used to compile vDSO.

Signature · 1 line
Kees Cook
#14 lore raw

PATCH v26 7/9 x86/vdso: Introduce ENDBR macro

In reply to Yu-cheng Yu

ENDBR is a special new instruction for the Indirect Branch Tracking (IBT) component of CET. IBT prevents attacks by ensuring that (most) indirect branches and function calls may only land at ENDBR instructions. Branches that don't follow the rules will result in control flow (#CF) exceptions.

ENDBR is a noop when IBT is unsupported or disabled. Most ENDBR instructions are inserted automatically by the compiler, but branch targets written in assembly must have ENDBR added manually.

Introduce ENDBR64/ENDBR32 macros.

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Jarkko Sakkinen <[email protected]>
Cc Peter Zijlstra <[email protected]>

---
v25:
- Change from using the compiler's cet.h back to just ENDBR64/ENDBR32, since the information is already known, and keep it simple.

 arch/x86/include/asm/vdso.h | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)
arch/x86/include/asm/vdso.h +19 -1
index 98aa103eb4ab..97358246e4c7 100644
@@ -52,6 +52,24 @@ extern int map_vdso_once(const struct vdso_image *image, unsigned long addr);
 extern bool fixup_vdso_exception(struct pt_regs *regs, int trapnr,
 				 unsigned long error_code,
 				 unsigned long fault_addr);
-#endif /* __ASSEMBLER__ */
+#else /* __ASSEMBLER__ */
+
+/*
+ * ENDBR is an instruction for the Indirect Branch Tracking (IBT) component
+ * of CET.  IBT prevents attacks by ensuring that (most) indirect branches
+ * function calls may only land at ENDBR instructions.  Branches that don't
+ * follow the rules will result in control flow (#CF) exceptions.
+ * ENDBR is a noop when IBT is unsupported or disabled.  Most ENDBR
+ * instructions are inserted automatically by the compiler, but branch
+ * targets written in assembly must have ENDBR added manually.
+ */
+#ifdef CONFIG_X86_IBT
+#define ENDBR64 endbr64
+#define ENDBR32 endbr32
+#else
+#define ENDBR64
+#define ENDBR32
+#endif
 
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_VDSO_H */
Signature · 1 line
2.21.0
Reviewed-by on v26 7/9
#15 lore raw

Re: [PATCH v26 7/9] x86/vdso: Introduce ENDBR macro

Quoted 5 lines · Yu-cheng Yu

ENDBR is a special new instruction for the Indirect Branch Tracking (IBT) component of CET. IBT prevents attacks by ensuring that (most) indirect branches and function calls may only land at ENDBR instructions. Branches that don't follow the rules will result in control flow (#CF) exceptions.

Quoted 7 lines

ENDBR is a noop when IBT is unsupported or disabled. Most ENDBR instructions are inserted automatically by the compiler, but branch targets written in assembly must have ENDBR added manually.

Introduce ENDBR64/ENDBR32 macros.

Signature · 1 line
Kees Cook
#16 lore raw

PATCH v26 8/9 x86/vdso/32: Add ENDBR to __kernel_vsyscall entry point

In reply to Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

ENDBR is a special new instruction for the Indirect Branch Tracking (IBT) component of CET. IBT prevents attacks by ensuring that (most) indirect branches and function calls may only land at ENDBR instructions. Branches that don't follow the rules will result in control flow (#CF) exceptions.

ENDBR is a noop when IBT is unsupported or disabled. Most ENDBR instructions are inserted automatically by the compiler, but branch targets written in assembly must have ENDBR added manually.

Add that to __kernel_vsyscall entry point.

Cc Andy Lutomirski <[email protected]>
Cc Kees Cook <[email protected]>
---
 arch/x86/entry/vdso/vdso32/system_call.S | 2 ++
 1 file changed, 2 insertions(+)
arch/x86/entry/vdso/vdso32/system_call.S +2 -0
index de1fff7188aa..7793dc221726 100644
@@ -7,6 +7,7 @@
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
+#include <asm/vdso.h>
 
 	.text
 	.globl __kernel_vsyscall
@@ -14,6 +15,7 @@
 	ALIGN
 __kernel_vsyscall:
 	CFI_STARTPROC
+	ENDBR32
 	/*
 	 * Reshuffle regs so that all of any of the entry instructions
 	 * will preserve enough state.
Signature · 1 line
2.21.0
Reviewed-by on v26 8/9
#17 lore raw

Re: [PATCH v26 8/9] x86/vdso/32: Add ENDBR to __kernel_vsyscall entry point

Quoted 7 lines · Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

ENDBR is a special new instruction for the Indirect Branch Tracking (IBT) component of CET. IBT prevents attacks by ensuring that (most) indirect branches and function calls may only land at ENDBR instructions. Branches that don't follow the rules will result in control flow (#CF) exceptions.

Quoted 7 lines

ENDBR is a noop when IBT is unsupported or disabled. Most ENDBR instructions are inserted automatically by the compiler, but branch targets written in assembly must have ENDBR added manually.

Add that to __kernel_vsyscall entry point.

Signature · 1 line
Kees Cook
Reviewed-by on v26 8/9
#18 lore raw

Re: [PATCH v26 8/9] x86/vdso/32: Add ENDBR to __kernel_vsyscall entry point

In reply to Yu-cheng Yu
Quoted 7 lines · Yu-cheng Yu

From: "H.J. Lu" <[email protected]>

ENDBR is a special new instruction for the Indirect Branch Tracking (IBT) component of CET. IBT prevents attacks by ensuring that (most) indirect branches and function calls may only land at ENDBR instructions. Branches that don't follow the rules will result in control flow (#CF) exceptions.

Quoted 7 lines

ENDBR is a noop when IBT is unsupported or disabled. Most ENDBR instructions are inserted automatically by the compiler, but branch targets written in assembly must have ENDBR added manually.

Add that to __kernel_vsyscall entry point.

Signature · 1 line
Kees Cook
#19 lore raw

PATCH v26 9/9 x86/vdso: Add ENDBR to __vdso_sgx_enter_enclave

In reply to Yu-cheng Yu

ENDBR is a special new instruction for the Indirect Branch Tracking (IBT) component of CET. IBT prevents attacks by ensuring that (most) indirect branches and function calls may only land at ENDBR instructions. Branches that don't follow the rules will result in control flow (#CF) exceptions.

ENDBR is a noop when IBT is unsupported or disabled. Most ENDBR instructions are inserted automatically by the compiler, but branch targets written in assembly must have ENDBR added manually.

Add ENDBR to __vdso_sgx_enter_enclave() branch targets.

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Jarkko Sakkinen <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 arch/x86/entry/vdso/vsgx.S | 4 ++++
 1 file changed, 4 insertions(+)
arch/x86/entry/vdso/vsgx.S +4 -0
index 86a0e94f68df..f3ebd38d1898 100644
@@ -4,6 +4,7 @@
 #include <asm/export.h>
 #include <asm/errno.h>
 #include <asm/enclu.h>
+#include <asm/vdso.h>
 
 #include "extable.h"
 
@@ -27,6 +28,7 @@
 SYM_FUNC_START(__vdso_sgx_enter_enclave)
 	/* Prolog */
 	.cfi_startproc
+	ENDBR64
 	push	%rbp
 	.cfi_adjust_cfa_offset	8
 	.cfi_rel_offset		%rbp, 0
@@ -62,6 +64,7 @@ SYM_FUNC_START(__vdso_sgx_enter_enclave)
 .Lasync_exit_pointer:
 .Lenclu_eenter_eresume:
 	enclu
+	ENDBR64
 
 	/* EEXIT jumps here unless the enclave is doing something fancy. */
 	mov	SGX_ENCLAVE_OFFSET_OF_RUN(%rbp), %rbx
@@ -91,6 +94,7 @@ SYM_FUNC_START(__vdso_sgx_enter_enclave)
 	jmp	.Lout
 
 .Lhandle_exception:
+	ENDBR64
 	mov	SGX_ENCLAVE_OFFSET_OF_RUN(%rbp), %rbx
 
 	/* Set the exception info. */
Signature · 1 line
2.21.0
Reviewed-by on v26 9/9
#20 lore raw

Re: [PATCH v26 9/9] x86/vdso: Add ENDBR to __vdso_sgx_enter_enclave

Quoted 5 lines · Yu-cheng Yu

ENDBR is a special new instruction for the Indirect Branch Tracking (IBT) component of CET. IBT prevents attacks by ensuring that (most) indirect branches and function calls may only land at ENDBR instructions. Branches that don't follow the rules will result in control flow (#CF) exceptions.

Quoted 7 lines

ENDBR is a noop when IBT is unsupported or disabled. Most ENDBR instructions are inserted automatically by the compiler, but branch targets written in assembly must have ENDBR added manually.

Add ENDBR to __vdso_sgx_enter_enclave() branch targets.

Signature · 1 line
Kees Cook
#21 lore raw
In reply to Yu-cheng Yu

From: Yu-cheng Yu

Quoted 5 lines

Sent: 27 April 2021 21:47

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

...

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

If enabled for userspace, what happens if an old .so is dynamically loaded?
Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)

maintainer
#22 lore raw
Quoted 9 lines · David Laight

From: Yu-cheng Yu

Quoted 5 lines

Sent: 27 April 2021 21:47

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

...

Quoted 7 lines

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

If enabled for userspace, what happens if an old .so is dynamically loaded?
Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

If you believe that the userspace tooling for the legacy IBT table actually works, then it should just work. Yu-cheng, etc: how well tested is it?

--Andy

#23 lore raw
Quoted 9 lines · Andy Lutomirski
Quoted 7 lines · David Laight

From: Yu-cheng Yu

Quoted 5 lines

Sent: 27 April 2021 21:47

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

Quoted 7 lines
Quoted 7 lines

...

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

If enabled for userspace, what happens if an old .so is dynamically loaded?

CET will be disabled by ld.so in this case.

Quoted 2 lines
Quoted 2 lines

Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

Correct. ld and ld.so check this.

Quoted 4 lines

If you believe that the userspace tooling for the legacy IBT table actually works, then it should just work. Yu-cheng, etc: how well tested is it?

Legacy IBT bitmap isn't unused since it doesn't cover legacy codes generated by legacy JITs.

Signature · 1 line
H.J.
maintainer
#24 lore raw
Quoted 13 lines · H.J. Lu
Quoted 11 lines · Andy Lutomirski
Quoted 9 lines · David Laight

From: Yu-cheng Yu

Quoted 5 lines

Sent: 27 April 2021 21:47

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

...

Quoted 7 lines
Quoted 5 lines
Quoted 5 lines

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

If enabled for userspace, what happens if an old .so is dynamically loaded?

CET will be disabled by ld.so in this case.

What if a program starts a thread and then dlopens a legacy .so?

Quoted 6 lines
Quoted 3 lines
Quoted 3 lines

Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

Correct. ld and ld.so check this.

Quoted 8 lines
Quoted 4 lines

If you believe that the userspace tooling for the legacy IBT table actually works, then it should just work. Yu-cheng, etc: how well tested is it?

Legacy IBT bitmap isn't unused since it doesn't cover legacy codes generated by legacy JITs.

How does ld.so decide whether a legacy JIT is in use?

#25 lore raw

From: Andy Lutomirski

Quoted 19 lines

Sent: 28 April 2021 16:15

Quoted 16 lines · H.J. Lu
Quoted 14 lines · Andy Lutomirski
Quoted 12 lines · David Laight

From: Yu-cheng Yu

Quoted 5 lines

Sent: 27 April 2021 21:47

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

...

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

Quoted 6 lines
Quoted 4 lines
Quoted 2 lines
Quoted 2 lines

If enabled for userspace, what happens if an old .so is dynamically loaded?

CET will be disabled by ld.so in this case.

What if a program starts a thread and then dlopens a legacy .so?

Or has shadow stack enabled and opens a .so that uses retpolines?

Quoted 10 lines
Quoted 10 lines
Quoted 2 lines
Quoted 2 lines

Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

Correct. ld and ld.so check this.

Quoted 4 lines

If you believe that the userspace tooling for the legacy IBT table actually works, then it should just work. Yu-cheng, etc: how well tested is it?

Quoted 5 lines
Quoted 3 lines

Legacy IBT bitmap isn't unused since it doesn't cover legacy codes generated by legacy JITs.

How does ld.so decide whether a legacy JIT is in use?

What if your malware just precedes its 'jump into the middle of a function' with a %ds segment override?

I may have a real problem here.
We currently release program/library binaries that run on Linux distributions that go back as far as RHEL6 (2.6.32 kernel era). To do this everything is compiled on a userspace of the same vintage. I'm not at all sure a new enough gcc to generate the ENDBR64 instructions will run on the relevant system - and may barf on the system headers even if we got it to run.
I really don't want to have to build multiple copies of everything.

David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)

#26 lore raw
Quoted 20 lines · David Laight

From: Andy Lutomirski

Quoted 19 lines

Sent: 28 April 2021 16:15

Quoted 16 lines · H.J. Lu
Quoted 14 lines · Andy Lutomirski
Quoted 12 lines · David Laight

From: Yu-cheng Yu

Quoted 5 lines

Sent: 27 April 2021 21:47

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

...

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

Quoted 9 lines
Quoted 6 lines
Quoted 4 lines
Quoted 2 lines
Quoted 2 lines

If enabled for userspace, what happens if an old .so is dynamically loaded?

CET will be disabled by ld.so in this case.

What if a program starts a thread and then dlopens a legacy .so?

Or has shadow stack enabled and opens a .so that uses retpolines?

When shadow stack is enabled, retpolines are not necessary. I don't know if glibc has been updated for detection of this case. H.J.?

Quoted 10 lines
Quoted 10 lines
Quoted 10 lines
Quoted 2 lines
Quoted 2 lines

Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

Correct. ld and ld.so check this.

Quoted 4 lines

If you believe that the userspace tooling for the legacy IBT table actually works, then it should just work. Yu-cheng, etc: how well tested is it?

Quoted 9 lines
Quoted 5 lines
Quoted 3 lines

Legacy IBT bitmap isn't unused since it doesn't cover legacy codes generated by legacy JITs.

How does ld.so decide whether a legacy JIT is in use?

What if your malware just precedes its 'jump into the middle of a function' with a %ds segment override?

Do you mean far jump? It is not tracked by ibt, which tracks near indirect jump. The details can be found in Intel SDM.

Quoted 8 lines

I may have a real problem here.
We currently release program/library binaries that run on Linux distributions that go back as far as RHEL6 (2.6.32 kernel era). To do this everything is compiled on a userspace of the same vintage. I'm not at all sure a new enough gcc to generate the ENDBR64 instructions will run on the relevant system - and may barf on the system headers even if we got it to run.
I really don't want to have to build multiple copies of everything.

This is likely OK. We have tested many combinations. Should you run into any issue, please let glibc people know.

Thanks!

Quoted 7 lines

David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)

#27 lore raw
Quoted 67 lines · Yu-cheng
Quoted 20 lines · David Laight

From: Andy Lutomirski

Quoted 19 lines

Sent: 28 April 2021 16:15

Quoted 16 lines · H.J. Lu
Quoted 14 lines · Andy Lutomirski
Quoted 12 lines · David Laight

From: Yu-cheng Yu

Quoted 5 lines

Sent: 27 April 2021 21:47

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

...

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

Quoted 9 lines
Quoted 6 lines
Quoted 4 lines
Quoted 2 lines
Quoted 2 lines

If enabled for userspace, what happens if an old .so is dynamically loaded?

CET will be disabled by ld.so in this case.

What if a program starts a thread and then dlopens a legacy .so?

Or has shadow stack enabled and opens a .so that uses retpolines?

When shadow stack is enabled, retpolines are not necessary. I don't know if glibc has been updated for detection of this case. H.J.?

Quoted 10 lines
Quoted 10 lines
Quoted 10 lines
Quoted 2 lines
Quoted 2 lines

Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

Correct. ld and ld.so check this.

Quoted 4 lines

If you believe that the userspace tooling for the legacy IBT table actually works, then it should just work. Yu-cheng, etc: how well tested is it?

Quoted 9 lines
Quoted 5 lines
Quoted 3 lines

Legacy IBT bitmap isn't unused since it doesn't cover legacy codes generated by legacy JITs.

How does ld.so decide whether a legacy JIT is in use?

What if your malware just precedes its 'jump into the middle of a function' with a %ds segment override?

Do you mean far jump? It is not tracked by ibt, which tracks near indirect jump. The details can be found in Intel SDM.

Quoted 8 lines

I may have a real problem here.
We currently release program/library binaries that run on Linux distributions that go back as far as RHEL6 (2.6.32 kernel era). To do this everything is compiled on a userspace of the same vintage. I'm not at all sure a new enough gcc to generate the ENDBR64 instructions will run on the relevant system - and may barf on the system headers even if we got it to run.
I really don't want to have to build multiple copies of everything.

Quoted 3 lines

This is likely OK. We have tested many combinations. Should you run into any issue, please let glibc people know.

If you have a Tiger Lake laptop, you can install the CET kernel on Fedora 34 or Ubuntu 20.10/21.04.

Signature · 1 line
H.J.
#28 lore raw
In reply to Andy Lutomirski
Quoted 9 lines · Andy Lutomirski
Quoted 8 lines · H.J. Lu
Quoted 6 lines · Andy Lutomirski
Quoted 4 lines · David Laight

From: Yu-cheng Yu

Quoted 2 lines

Sent: 27 April 2021 21:47

Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
Quoted 3 lines

Control-flow Enforcement (CET) is a new Intel processor feature that blocks return/jump-oriented programming attacks. Details are in "Intel 64 and IA-32 Architectures Software Developer's Manual" [1].

...

Does this feature require that 'binary blobs' for out of tree drivers be compiled by a version of gcc that adds the ENDBRA instructions?

David, do you mean kernel loadable drivers here? Do not worry about it for now, since shadow stack/ibt is not enabled for kernel-mode yet.

Quoted 19 lines
Quoted 5 lines
Quoted 3 lines
Quoted 3 lines

If enabled for userspace, what happens if an old .so is dynamically loaded?

CET will be disabled by ld.so in this case.

What if a program starts a thread and then dlopens a legacy .so?

Quoted 11 lines
Quoted 3 lines
Quoted 3 lines

Or do all userspace programs and libraries have to have been compiled with the ENDBRA instructions?

Correct. ld and ld.so check this.

Quoted 4 lines

If you believe that the userspace tooling for the legacy IBT table actually works, then it should just work. Yu-cheng, etc: how well tested is it?

Quoted 6 lines
Quoted 3 lines

Legacy IBT bitmap isn't unused since it doesn't cover legacy codes generated by legacy JITs.

How does ld.so decide whether a legacy JIT is in use?

Let me clarify. IBT bitmap isn't used at all. How dlopen() works depends entirely on the tunable of glibc.cpu.x86_ibt. There are three values: on, off, permissive. On is always on, and off is always off, regardless of the .so having ibt or not. The default is "permissive," which turns off ibt upon dlopen a legacy .so. I hope this also answers Andy's question above.

Yu-cheng