* [PATCH v8 01/14] x86/cet/ibt: Add Kconfig option for user-mode Indirect Branch Tracking
From: Yu-cheng Yu @ 2019-08-13 20:53 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205359.12196-1-yu-cheng.yu@intel.com>
The user-mode indirect branch tracking support is done mostly by GCC
to insert ENDBR64/ENDBR32 instructions at branch targets. The kernel
provides CPUID enumeration and feature setup.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/Kconfig | 16 ++++++++++++++++
arch/x86/Makefile | 7 +++++++
2 files changed, 23 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7d13ba326962..666dc66a382e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1940,6 +1940,9 @@ config X86_INTEL_CET
config ARCH_HAS_SHSTK
def_bool n
+config ARCH_HAS_AS_LIMIT
+ def_bool n
+
config X86_INTEL_SHADOW_STACK_USER
prompt "Intel Shadow Stack for user-mode"
def_bool n
@@ -1961,6 +1964,19 @@ config X86_INTEL_SHADOW_STACK_USER
If unsure, say y.
+config X86_INTEL_BRANCH_TRACKING_USER
+ prompt "Intel Indirect Branch Tracking for user-mode"
+ def_bool n
+ depends on CPU_SUP_INTEL && X86_64
+ select X86_INTEL_CET
+ select ARCH_HAS_AS_LIMIT
+ select ARCH_USE_GNU_PROPERTY
+ ---help---
+ Indirect Branch Tracking provides hardware protection against return-/jmp-
+ oriented programming attacks.
+
+ If unsure, say y
+
config EFI
bool "EFI runtime service support"
depends on ACPI
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 0b2e9df48907..25372cc4a303 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -155,6 +155,13 @@ ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
endif
endif
+# Check compiler ibt support
+ifdef CONFIG_X86_INTEL_BRANCH_TRACKING_USER
+ ifeq ($(call cc-option-yn, -fcf-protection=branch), n)
+ $(error CONFIG_X86_INTEL_BRANCH_TRACKING_USER not supported by compiler)
+ endif
+endif
+
#
# If the function graph tracer is used with mcount instead of fentry,
# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
--
2.17.1
^ permalink raw reply related
* [PATCH v8 02/14] x86/cet/ibt: User-mode indirect branch tracking support
From: Yu-cheng Yu @ 2019-08-13 20:53 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205359.12196-1-yu-cheng.yu@intel.com>
Add user-mode indirect branch tracking enabling/disabling and
supporting routines.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/cet.h | 6 ++++
arch/x86/include/asm/disabled-features.h | 8 ++++-
arch/x86/kernel/cet.c | 36 +++++++++++++++++++
arch/x86/kernel/cpu/common.c | 17 +++++++++
.../arch/x86/include/asm/disabled-features.h | 8 ++++-
5 files changed, 73 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/cet.h b/arch/x86/include/asm/cet.h
index 2df357dffd24..2561efe081ad 100644
--- a/arch/x86/include/asm/cet.h
+++ b/arch/x86/include/asm/cet.h
@@ -16,6 +16,8 @@ struct cet_status {
unsigned long shstk_size;
unsigned int locked:1;
unsigned int shstk_enabled:1;
+ unsigned int ibt_enabled:1;
+ unsigned int ibt_bitmap_used:1;
};
#ifdef CONFIG_X86_INTEL_CET
@@ -27,6 +29,8 @@ void cet_disable_shstk(void);
void cet_disable_free_shstk(struct task_struct *p);
int cet_restore_signal(bool ia32, struct sc_ext *sc);
int cet_setup_signal(bool ia32, unsigned long rstor, struct sc_ext *sc);
+int cet_setup_ibt(void);
+void cet_disable_ibt(void);
#else
static inline int prctl_cet(int option, unsigned long arg2) { return -EINVAL; }
static inline int cet_setup_shstk(void) { return -EINVAL; }
@@ -37,6 +41,8 @@ static inline void cet_disable_free_shstk(struct task_struct *p) {}
static inline int cet_restore_signal(bool ia32, struct sc_ext *sc) { return -EINVAL; }
static inline int cet_setup_signal(bool ia32, unsigned long rstor,
struct sc_ext *sc) { return -EINVAL; }
+static inline int cet_setup_ibt(void) { return -EINVAL; }
+static inline void cet_disable_ibt(void) {}
#endif
#define cpu_x86_cet_enabled() \
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 06323ebed643..fc7d3d5a1bf4 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -68,6 +68,12 @@
#define DISABLE_SHSTK (1<<(X86_FEATURE_SHSTK & 31))
#endif
+#ifdef CONFIG_X86_INTEL_BRANCH_TRACKING_USER
+#define DISABLE_IBT 0
+#else
+#define DISABLE_IBT (1<<(X86_FEATURE_IBT & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -89,7 +95,7 @@
#define DISABLED_MASK15 0
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP|DISABLE_SHSTK)
#define DISABLED_MASK17 0
-#define DISABLED_MASK18 0
+#define DISABLED_MASK18 (DISABLE_IBT)
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
index e4e20d6ab07b..505a69f476e1 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -13,6 +13,8 @@
#include <linux/uaccess.h>
#include <linux/sched/signal.h>
#include <linux/compat.h>
+#include <linux/vmalloc.h>
+#include <linux/bitops.h>
#include <asm/msr.h>
#include <asm/user.h>
#include <asm/fpu/internal.h>
@@ -325,3 +327,37 @@ int cet_setup_signal(bool ia32, unsigned long rstor_addr, struct sc_ext *sc_ext)
modify_fpu_regs_end();
return 0;
}
+
+int cet_setup_ibt(void)
+{
+ u64 r;
+
+ if (!cpu_feature_enabled(X86_FEATURE_IBT))
+ return -EOPNOTSUPP;
+
+ modify_fpu_regs_begin();
+ rdmsrl(MSR_IA32_U_CET, r);
+ r |= (MSR_IA32_CET_ENDBR_EN | MSR_IA32_CET_NO_TRACK_EN);
+ wrmsrl(MSR_IA32_U_CET, r);
+ modify_fpu_regs_end();
+
+ current->thread.cet.ibt_enabled = 1;
+ return 0;
+}
+
+void cet_disable_ibt(void)
+{
+ u64 r;
+
+ if (!cpu_feature_enabled(X86_FEATURE_IBT))
+ return;
+
+ modify_fpu_regs_begin();
+ rdmsrl(MSR_IA32_U_CET, r);
+ r &= ~(MSR_IA32_CET_ENDBR_EN | MSR_IA32_CET_LEG_IW_EN |
+ MSR_IA32_CET_NO_TRACK_EN | MSR_IA32_CET_BITMAP_MASK);
+ wrmsrl(MSR_IA32_U_CET, r);
+ modify_fpu_regs_end();
+
+ current->thread.cet.ibt_enabled = 0;
+}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d3addbd3f4d4..092979715d16 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -512,6 +512,23 @@ static __init int setup_disable_shstk(char *s)
__setup("no_cet_shstk", setup_disable_shstk);
#endif
+#ifdef CONFIG_X86_INTEL_BRANCH_TRACKING_USER
+static __init int setup_disable_ibt(char *s)
+{
+ /* require an exact match without trailing characters */
+ if (s[0] != '\0')
+ return 0;
+
+ if (!boot_cpu_has(X86_FEATURE_IBT))
+ return 1;
+
+ setup_clear_cpu_cap(X86_FEATURE_IBT);
+ pr_info("x86: 'no_cet_ibt' specified, disabling Branch Tracking\n");
+ return 1;
+}
+__setup("no_cet_ibt", setup_disable_ibt);
+#endif
+
/*
* Some CPU features depend on higher CPUID levels, which may not always
* be available due to CPUID level capping or broken virtualization
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 06323ebed643..fc7d3d5a1bf4 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -68,6 +68,12 @@
#define DISABLE_SHSTK (1<<(X86_FEATURE_SHSTK & 31))
#endif
+#ifdef CONFIG_X86_INTEL_BRANCH_TRACKING_USER
+#define DISABLE_IBT 0
+#else
+#define DISABLE_IBT (1<<(X86_FEATURE_IBT & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -89,7 +95,7 @@
#define DISABLED_MASK15 0
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP|DISABLE_SHSTK)
#define DISABLED_MASK17 0
-#define DISABLED_MASK18 0
+#define DISABLED_MASK18 (DISABLE_IBT)
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
--
2.17.1
^ permalink raw reply related
* [PATCH v8 05/14] x86/cet/ibt: ELF header parsing for IBT
From: Yu-cheng Yu @ 2019-08-13 20:53 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205359.12196-1-yu-cheng.yu@intel.com>
Look in .note.gnu.property of an ELF file and check if Indirect
Branch Tracking needs to be enabled for the task.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/Kconfig | 1 +
arch/x86/kernel/process_64.c | 5 +++++
2 files changed, 6 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 666dc66a382e..7edb544cef00 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1971,6 +1971,7 @@ config X86_INTEL_BRANCH_TRACKING_USER
select X86_INTEL_CET
select ARCH_HAS_AS_LIMIT
select ARCH_USE_GNU_PROPERTY
+ select ARCH_BINFMT_ELF_STATE
---help---
Indirect Branch Tracking provides hardware protection against return-/jmp-
oriented programming attacks.
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 7ec60b14e96d..a051cfc5242f 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -856,6 +856,11 @@ int arch_setup_property(struct arch_elf_state *state)
return r;
}
+ if (cpu_feature_enabled(X86_FEATURE_IBT)) {
+ if (state->gnu_property & GNU_PROPERTY_X86_FEATURE_1_IBT)
+ r = cet_setup_ibt();
+ }
+
return r;
}
#endif
--
2.17.1
^ permalink raw reply related
* [PATCH v8 06/14] x86/cet/ibt: Add arch_prctl functions for IBT
From: Yu-cheng Yu @ 2019-08-13 20:53 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205359.12196-1-yu-cheng.yu@intel.com>
From: "H.J. Lu" <hjl.tools@gmail.com>
Update ARCH_X86_CET_STATUS and ARCH_X86_CET_DISABLE to include
Indirect Branch Tracking features.
Signed-off-by: H.J. Lu <hjl.tools@gmail.com>
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/uapi/asm/prctl.h | 2 ++
arch/x86/kernel/cet_prctl.c | 4 ++++
2 files changed, 6 insertions(+)
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index d962f0ec9ccf..02243127dcf6 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -18,5 +18,7 @@
#define ARCH_X86_CET_DISABLE 0x3002
#define ARCH_X86_CET_LOCK 0x3003
#define ARCH_X86_CET_ALLOC_SHSTK 0x3004
+#define ARCH_X86_CET_GET_LEGACY_BITMAP 0x3005 /* deprecated */
+#define ARCH_X86_CET_SET_LEGACY_BITMAP 0x3006 /* deprecated */
#endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/kernel/cet_prctl.c b/arch/x86/kernel/cet_prctl.c
index 9c9d4262b07e..09d8c4ea935c 100644
--- a/arch/x86/kernel/cet_prctl.c
+++ b/arch/x86/kernel/cet_prctl.c
@@ -20,6 +20,8 @@ static int handle_get_status(unsigned long arg2)
if (current->thread.cet.shstk_enabled)
features |= GNU_PROPERTY_X86_FEATURE_1_SHSTK;
+ if (current->thread.cet.ibt_enabled)
+ features |= GNU_PROPERTY_X86_FEATURE_1_IBT;
shstk_base = current->thread.cet.shstk_base;
shstk_size = current->thread.cet.shstk_size;
@@ -69,6 +71,8 @@ int prctl_cet(int option, unsigned long arg2)
return -EPERM;
if (arg2 & GNU_PROPERTY_X86_FEATURE_1_SHSTK)
cet_disable_free_shstk(current);
+ if (arg2 & GNU_PROPERTY_X86_FEATURE_1_IBT)
+ cet_disable_ibt();
return 0;
--
2.17.1
^ permalink raw reply related
* [PATCH v8 17/27] mm: Update can_follow_write_pte/pmd for shadow stack
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
can_follow_write_pte/pmd look for the (RO & DIRTY) PTE/PMD to
verify an exclusive RO page still exists after a broken COW.
A shadow stack PTE is RO & PAGE_DIRTY_SW when it is shared,
otherwise RO & PAGE_DIRTY_HW.
Introduce pte_exclusive() and pmd_exclusive() to also verify a
shadow stack PTE is exclusive.
Also rename can_follow_write_pte/pmd() to can_follow_write() to
make their meaning clear; i.e. "Can we write to the page?", not
"Is the PTE writable?"
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/mm/pgtable.c | 18 ++++++++++++++++++
include/asm-generic/pgtable.h | 12 ++++++++++++
mm/gup.c | 8 +++++---
mm/huge_memory.c | 8 +++++---
4 files changed, 40 insertions(+), 6 deletions(-)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 6f3959ca2a08..326715fd0c50 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -898,4 +898,22 @@ inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
{
return (vm_flags & VM_SHSTK);
}
+
+inline bool pte_exclusive(pte_t pte, struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & VM_SHSTK)
+ return pte_dirty_hw(pte);
+ else
+ return pte_dirty(pte);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+inline bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & VM_SHSTK)
+ return pmd_dirty_hw(pmd);
+ else
+ return pmd_dirty(pmd);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* CONFIG_X86_INTEL_SHADOW_STACK_USER */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 438ce73b57ea..b58f40525ebc 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1203,10 +1203,22 @@ static inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
{
return false;
}
+
+static inline bool pte_exclusive(pte_t pte, struct vm_area_struct *vma)
+{
+ return pte_dirty(pte);
+}
+
+static inline bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma)
+{
+ return pmd_dirty(pmd);
+}
#else
pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma);
pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma);
bool arch_copy_pte_mapping(vm_flags_t vm_flags);
+bool pte_exclusive(pte_t pte, struct vm_area_struct *vma);
+bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma);
#endif
#endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/mm/gup.c b/mm/gup.c
index 98f13ab37bac..d7b298c5f6cb 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -179,10 +179,12 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
* FOLL_FORCE can write to even unwritable pte's, but only
* after we've gone through a COW cycle and they are dirty.
*/
-static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
+static inline bool can_follow_write(pte_t pte, unsigned int flags,
+ struct vm_area_struct *vma)
{
return pte_write(pte) ||
- ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+ pte_exclusive(pte, vma));
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
@@ -220,7 +222,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
}
if ((flags & FOLL_NUMA) && pte_protnone(pte))
goto no_page;
- if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
+ if ((flags & FOLL_WRITE) && !can_follow_write(pte, flags, vma)) {
pte_unmap_unlock(ptep, ptl);
return NULL;
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 39d66c628121..947eb0121671 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1444,10 +1444,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
* FOLL_FORCE can write to even unwritable pmd's, but only
* after we've gone through a COW cycle and they are dirty.
*/
-static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+static inline bool can_follow_write(pmd_t pmd, unsigned int flags,
+ struct vm_area_struct *vma)
{
return pmd_write(pmd) ||
- ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+ pmd_exclusive(pmd, vma));
}
struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -1460,7 +1462,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
assert_spin_locked(pmd_lockptr(mm, pmd));
- if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
+ if (flags & FOLL_WRITE && !can_follow_write(*pmd, flags, vma))
goto out;
/* Avoid dumping huge zero page */
--
2.17.1
^ permalink raw reply related
* [PATCH v8 19/27] x86/cet/shstk: User-mode shadow stack support
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
This patch adds basic shadow stack enabling/disabling routines.
A task's shadow stack is allocated from memory with VM_SHSTK flag set
and read-only protection. It has a fixed size of RLIMIT_STACK.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/cet.h | 34 +++++
arch/x86/include/asm/disabled-features.h | 8 +-
arch/x86/include/asm/processor.h | 5 +
arch/x86/kernel/Makefile | 2 +
arch/x86/kernel/cet.c | 116 ++++++++++++++++++
arch/x86/kernel/cpu/common.c | 25 ++++
arch/x86/kernel/process.c | 1 +
.../arch/x86/include/asm/disabled-features.h | 8 +-
8 files changed, 197 insertions(+), 2 deletions(-)
create mode 100644 arch/x86/include/asm/cet.h
create mode 100644 arch/x86/kernel/cet.c
diff --git a/arch/x86/include/asm/cet.h b/arch/x86/include/asm/cet.h
new file mode 100644
index 000000000000..c952a2ec65fe
--- /dev/null
+++ b/arch/x86/include/asm/cet.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CET_H
+#define _ASM_X86_CET_H
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+struct task_struct;
+/*
+ * Per-thread CET status
+ */
+struct cet_status {
+ unsigned long shstk_base;
+ unsigned long shstk_size;
+ unsigned int shstk_enabled:1;
+};
+
+#ifdef CONFIG_X86_INTEL_CET
+int cet_setup_shstk(void);
+void cet_disable_shstk(void);
+void cet_disable_free_shstk(struct task_struct *p);
+#else
+static inline int cet_setup_shstk(void) { return -EINVAL; }
+static inline void cet_disable_shstk(void) {}
+static inline void cet_disable_free_shstk(struct task_struct *p) {}
+#endif
+
+#define cpu_x86_cet_enabled() \
+ (cpu_feature_enabled(X86_FEATURE_SHSTK) || \
+ cpu_feature_enabled(X86_FEATURE_IBT))
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_CET_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index a5ea841cc6d2..06323ebed643 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -62,6 +62,12 @@
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+#define DISABLE_SHSTK 0
+#else
+#define DISABLE_SHSTK (1<<(X86_FEATURE_SHSTK & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -81,7 +87,7 @@
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP|DISABLE_SHSTK)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6e0a3b43d027..0f9bc7fd1351 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -24,6 +24,7 @@ struct vm86;
#include <asm/special_insns.h>
#include <asm/fpu/types.h>
#include <asm/unwind_hints.h>
+#include <asm/cet.h>
#include <linux/personality.h>
#include <linux/cache.h>
@@ -490,6 +491,10 @@ struct thread_struct {
unsigned int sig_on_uaccess_err:1;
unsigned int uaccess_err:1; /* uaccess failed */
+#ifdef CONFIG_X86_INTEL_CET
+ struct cet_status cet;
+#endif
+
/* Floating point and extended processor state */
struct fpu fpu;
/*
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 3578ad248bc9..c7d918a87cac 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -140,6 +140,8 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o
obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o
obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o
+obj-$(CONFIG_X86_INTEL_CET) += cet.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
new file mode 100644
index 000000000000..5e7af0cc75f9
--- /dev/null
+++ b/arch/x86/kernel/cet.c
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * cet.c - Control-flow Enforcement (CET)
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ * Yu-cheng Yu <yu-cheng.yu@intel.com>
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/sched/signal.h>
+#include <linux/compat.h>
+#include <asm/msr.h>
+#include <asm/user.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/xstate.h>
+#include <asm/fpu/types.h>
+#include <asm/cet.h>
+
+static int set_shstk_ptr(unsigned long addr)
+{
+ u64 r;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SHSTK))
+ return -1;
+
+ if ((addr >= TASK_SIZE_MAX) || (!IS_ALIGNED(addr, 4)))
+ return -1;
+
+ modify_fpu_regs_begin();
+ rdmsrl(MSR_IA32_U_CET, r);
+ wrmsrl(MSR_IA32_PL3_SSP, addr);
+ wrmsrl(MSR_IA32_U_CET, r | MSR_IA32_CET_SHSTK_EN);
+ modify_fpu_regs_end();
+ return 0;
+}
+
+static unsigned long get_shstk_addr(void)
+{
+ unsigned long ptr;
+
+ if (!current->thread.cet.shstk_enabled)
+ return 0;
+
+ modify_fpu_regs_begin();
+ rdmsrl(MSR_IA32_PL3_SSP, ptr);
+ modify_fpu_regs_end();
+ return ptr;
+}
+
+int cet_setup_shstk(void)
+{
+ unsigned long addr, size;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SHSTK))
+ return -EOPNOTSUPP;
+
+ size = rlimit(RLIMIT_STACK);
+ addr = do_mmap_locked(NULL, 0, size, PROT_READ,
+ MAP_ANONYMOUS | MAP_PRIVATE, VM_SHSTK, NULL);
+
+ /*
+ * Return actual error from do_mmap().
+ */
+ if (addr >= TASK_SIZE_MAX)
+ return addr;
+
+ set_shstk_ptr(addr + size - sizeof(u64));
+ current->thread.cet.shstk_base = addr;
+ current->thread.cet.shstk_size = size;
+ current->thread.cet.shstk_enabled = 1;
+ return 0;
+}
+
+void cet_disable_shstk(void)
+{
+ u64 r;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SHSTK))
+ return;
+
+ modify_fpu_regs_begin();
+ rdmsrl(MSR_IA32_U_CET, r);
+ r &= ~(MSR_IA32_CET_SHSTK_EN);
+ wrmsrl(MSR_IA32_U_CET, r);
+ wrmsrl(MSR_IA32_PL3_SSP, 0);
+ modify_fpu_regs_end();
+ current->thread.cet.shstk_enabled = 0;
+}
+
+void cet_disable_free_shstk(struct task_struct *tsk)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SHSTK) ||
+ !tsk->thread.cet.shstk_enabled)
+ return;
+
+ if (tsk->mm && (tsk == current))
+ cet_disable_shstk();
+
+ /*
+ * Free only when tsk is current or shares mm
+ * with current but has its own shstk.
+ */
+ if (tsk->mm && (tsk->mm == current->mm) &&
+ (tsk->thread.cet.shstk_base)) {
+ vm_munmap(tsk->thread.cet.shstk_base,
+ tsk->thread.cet.shstk_size);
+ tsk->thread.cet.shstk_base = 0;
+ tsk->thread.cet.shstk_size = 0;
+ }
+
+ tsk->thread.cet.shstk_enabled = 0;
+}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f125bf7ecb6f..d3addbd3f4d4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -53,6 +53,7 @@
#include <asm/microcode_intel.h>
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
+#include <asm/cet.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/uv/uv.h>
@@ -488,6 +489,29 @@ static __init int setup_disable_pku(char *arg)
__setup("nopku", setup_disable_pku);
#endif /* CONFIG_X86_64 */
+static __always_inline void setup_cet(struct cpuinfo_x86 *c)
+{
+ if (cpu_x86_cet_enabled())
+ cr4_set_bits(X86_CR4_CET);
+}
+
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+static __init int setup_disable_shstk(char *s)
+{
+ /* require an exact match without trailing characters */
+ if (s[0] != '\0')
+ return 0;
+
+ if (!boot_cpu_has(X86_FEATURE_SHSTK))
+ return 1;
+
+ setup_clear_cpu_cap(X86_FEATURE_SHSTK);
+ pr_info("x86: 'no_cet_shstk' specified, disabling Shadow Stack\n");
+ return 1;
+}
+__setup("no_cet_shstk", setup_disable_shstk);
+#endif
+
/*
* Some CPU features depend on higher CPUID levels, which may not always
* be available due to CPUID level capping or broken virtualization
@@ -1481,6 +1505,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
x86_init_rdrand(c);
x86_init_cache_qos(c);
setup_pku(c);
+ setup_cet(c);
/*
* Clear/Set all flags overridden by options, need do it
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d360bf4d696b..a4deb79b1089 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -42,6 +42,7 @@
#include <asm/prctl.h>
#include <asm/spec-ctrl.h>
#include <asm/proto.h>
+#include <asm/cet.h>
#include "process.h"
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index a5ea841cc6d2..06323ebed643 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -62,6 +62,12 @@
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+#define DISABLE_SHSTK 0
+#else
+#define DISABLE_SHSTK (1<<(X86_FEATURE_SHSTK & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -81,7 +87,7 @@
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP|DISABLE_SHSTK)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
--
2.17.1
^ permalink raw reply related
* [PATCH v8 00/14] Control-flow Enforcement: Branch Tracking, PTRACE
From: Yu-cheng Yu @ 2019-08-13 20:53 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
The previous version of CET Branch Tracking/PTRACE patches is here:
https://lkml.org/lkml/2019/6/6/1030
Summary of changes from v7:
Change legacy bitmap to a special mapping (patch #14).
Rebase to v5.3-rc4.
Small fixes in response to comments.
H.J. Lu (5):
x86/cet/ibt: Add arch_prctl functions for IBT
x86/vdso: Insert endbr32/endbr64 to vDSO
x86/vdso/32: Add ENDBR32 to __kernel_vsyscall entry point
x86/vsyscall/64: Add ENDBR64 to vsyscall entry points
x86: Discard .note.gnu.property sections
Yu-cheng Yu (9):
x86/cet/ibt: Add Kconfig option for user-mode Indirect Branch Tracking
x86/cet/ibt: User-mode indirect branch tracking support
x86/cet/ibt: Handle signals for end branch
mm/mmap: Add IBT bitmap size to address space limit check
x86/cet/ibt: ELF header parsing for IBT
x86/cet/ibt: Add ENDBR to op-code-map
x86/vsyscall/64: Fixup shadow stack and branch tracking for vsyscall
x86/cet: Add PTRACE interface for CET
Introduce arch_prctl(ARCH_X86_CET_MARK_LEGACY_CODE)
arch/x86/Kconfig | 17 ++
arch/x86/Makefile | 7 +
arch/x86/entry/vdso/Makefile | 12 +-
arch/x86/entry/vdso/vdso-layout.lds.S | 1 +
arch/x86/entry/vdso/vdso32/system_call.S | 3 +
arch/x86/entry/vsyscall/vsyscall_64.c | 29 +++
arch/x86/entry/vsyscall/vsyscall_emu_64.S | 9 +
arch/x86/entry/vsyscall/vsyscall_trace.h | 1 +
arch/x86/include/asm/cet.h | 9 +
arch/x86/include/asm/disabled-features.h | 8 +-
arch/x86/include/asm/fpu/regset.h | 7 +-
arch/x86/include/asm/mmu_context.h | 10 +
arch/x86/include/asm/processor.h | 13 +-
arch/x86/include/uapi/asm/prctl.h | 3 +
arch/x86/kernel/Makefile | 2 +-
arch/x86/kernel/cet.c | 54 +++++
arch/x86/kernel/cet_bitmap.c | 210 ++++++++++++++++++
arch/x86/kernel/cet_prctl.c | 19 ++
arch/x86/kernel/cpu/common.c | 17 ++
arch/x86/kernel/fpu/regset.c | 41 ++++
arch/x86/kernel/process_64.c | 5 +
arch/x86/kernel/ptrace.c | 16 ++
arch/x86/kernel/vmlinux.lds.S | 10 +
arch/x86/lib/x86-opcode-map.txt | 13 +-
include/uapi/linux/elf.h | 1 +
mm/memory.c | 8 +
mm/mmap.c | 19 +-
.../arch/x86/include/asm/disabled-features.h | 8 +-
tools/objtool/arch/x86/lib/x86-opcode-map.txt | 13 +-
29 files changed, 552 insertions(+), 13 deletions(-)
create mode 100644 arch/x86/kernel/cet_bitmap.c
--
2.17.1
^ permalink raw reply
* [PATCH v8 03/14] x86/cet/ibt: Handle signals for end branch
From: Yu-cheng Yu @ 2019-08-13 20:53 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205359.12196-1-yu-cheng.yu@intel.com>
Restore end branch tracking setting from thread header.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/kernel/cet.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
index 505a69f476e1..db542bd423cc 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -281,6 +281,15 @@ int cet_restore_signal(bool ia32, struct sc_ext *sc_ext)
msr_ia32_u_cet |= MSR_IA32_CET_SHSTK_EN;
}
+ if (current->thread.cet.ibt_enabled) {
+ if (current->thread.cet.ibt_bitmap_used)
+ msr_ia32_u_cet |= (IBT_BITMAP_ADDR |
+ MSR_IA32_CET_LEG_IW_EN);
+
+ msr_ia32_u_cet |= (MSR_IA32_CET_ENDBR_EN |
+ MSR_IA32_CET_NO_TRACK_EN);
+ }
+
wrmsrl(MSR_IA32_PL3_SSP, new_ssp);
wrmsrl(MSR_IA32_U_CET, msr_ia32_u_cet);
return 0;
@@ -321,6 +330,15 @@ int cet_setup_signal(bool ia32, unsigned long rstor_addr, struct sc_ext *sc_ext)
sc_ext->ssp = new_ssp;
}
+ if (current->thread.cet.ibt_enabled) {
+ if (current->thread.cet.ibt_bitmap_used)
+ msr_ia32_u_cet |= (IBT_BITMAP_ADDR |
+ MSR_IA32_CET_LEG_IW_EN);
+
+ msr_ia32_u_cet |= (MSR_IA32_CET_ENDBR_EN |
+ MSR_IA32_CET_NO_TRACK_EN);
+ }
+
modify_fpu_regs_begin();
wrmsrl(MSR_IA32_PL3_SSP, ssp);
wrmsrl(MSR_IA32_U_CET, msr_ia32_u_cet);
--
2.17.1
^ permalink raw reply related
* [PATCH v8 18/27] mm: Introduce do_mmap_locked()
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
There are a few places that need do_mmap() with mm->mmap_sem held.
Create an in-line function for that.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
include/linux/mm.h | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bc58585014c9..275c385f53c6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2394,6 +2394,24 @@ static inline void mm_populate(unsigned long addr, unsigned long len)
static inline void mm_populate(unsigned long addr, unsigned long len) {}
#endif
+static inline unsigned long do_mmap_locked(struct file *file,
+ unsigned long addr, unsigned long len, unsigned long prot,
+ unsigned long flags, vm_flags_t vm_flags, struct list_head *uf)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long populate;
+
+ down_write(&mm->mmap_sem);
+ addr = do_mmap(file, addr, len, prot, flags, vm_flags, 0,
+ &populate, uf);
+ up_write(&mm->mmap_sem);
+
+ if (populate)
+ mm_populate(addr, populate);
+
+ return addr;
+}
+
/* These take the mm semaphore themselves */
extern int __must_check vm_brk(unsigned long, unsigned long);
extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long);
--
2.17.1
^ permalink raw reply related
* [PATCH v8 14/27] x86/mm: Shadow stack page fault error checking
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
If a page fault is triggered by a shadow stack access (e.g. call/ret)
or shadow stack management instructions (e.g. wrussq), then bit[6] of
the page fault error code is set.
In access_error(), verify a shadow stack page fault is within a
shadow stack memory area. It is always an error otherwise.
For a valid shadow stack access, set FAULT_FLAG_WRITE to effect
copy-on-write.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/traps.h | 2 ++
arch/x86/mm/fault.c | 18 ++++++++++++++++++
2 files changed, 20 insertions(+)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 8691261faeb0..918b0e48b2eb 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -166,6 +166,7 @@ enum {
* bit 3 == 1: use of reserved bit detected
* bit 4 == 1: fault was an instruction fetch
* bit 5 == 1: protection keys block access
+ * bit 6 == 1: shadow stack access fault
*/
enum x86_pf_error_code {
X86_PF_PROT = 1 << 0,
@@ -174,5 +175,6 @@ enum x86_pf_error_code {
X86_PF_RSVD = 1 << 3,
X86_PF_INSTR = 1 << 4,
X86_PF_PK = 1 << 5,
+ X86_PF_SHSTK = 1 << 6,
};
#endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ceacd1156db..75ec38d125fc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1187,6 +1187,17 @@ access_error(unsigned long error_code, struct vm_area_struct *vma)
(error_code & X86_PF_INSTR), foreign))
return 1;
+ /*
+ * Verify X86_PF_SHSTK is within a shadow stack VMA.
+ * It is always an error if there is a shadow stack
+ * fault outside a shadow stack VMA.
+ */
+ if (error_code & X86_PF_SHSTK) {
+ if (!(vma->vm_flags & VM_SHSTK))
+ return 1;
+ return 0;
+ }
+
if (error_code & X86_PF_WRITE) {
/* write, present and write, not present: */
if (unlikely(!(vma->vm_flags & VM_WRITE)))
@@ -1344,6 +1355,13 @@ void do_user_addr_fault(struct pt_regs *regs,
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+ /*
+ * If the fault is caused by a shadow stack access,
+ * i.e. CALL/RET/SAVEPREVSSP/RSTORSSP, then set
+ * FAULT_FLAG_WRITE to effect copy-on-write.
+ */
+ if (hw_error_code & X86_PF_SHSTK)
+ flags |= FAULT_FLAG_WRITE;
if (hw_error_code & X86_PF_WRITE)
flags |= FAULT_FLAG_WRITE;
if (hw_error_code & X86_PF_INSTR)
--
2.17.1
^ permalink raw reply related
* [PATCH v8 15/27] mm: Handle shadow stack page fault
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
When a task does fork(), its shadow stack (SHSTK) must be duplicated
for the child. This patch implements a flow similar to copy-on-write
of an anonymous page, but for SHSTK.
A SHSTK PTE must be RO and dirty. This dirty bit requirement is used
to effect the copying. In copy_one_pte(), clear the dirty bit from a
SHSTK PTE to cause a page fault upon the next SHSTK access. At that
time, fix the PTE and copy/re-use the page.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/mm/pgtable.c | 15 +++++++++++++++
include/asm-generic/pgtable.h | 15 +++++++++++++++
mm/memory.c | 7 ++++++-
3 files changed, 36 insertions(+), 1 deletion(-)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 44816ff6411f..0c10d0c5e329 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -876,3 +876,18 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
#endif /* CONFIG_X86_64 */
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & VM_SHSTK)
+ return pte_mkdirty_shstk(pte);
+ else
+ return pte;
+}
+
+inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
+{
+ return (vm_flags & VM_SHSTK);
+}
+#endif /* CONFIG_X86_INTEL_SHADOW_STACK_USER */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 75d9d68a6de7..89b0fa132f1f 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1188,4 +1188,19 @@ static inline bool arch_has_pfn_modify_check(void)
#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED)
#endif
+#ifndef CONFIG_ARCH_HAS_SHSTK
+static inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
+{
+ return pte;
+}
+
+static inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
+{
+ return false;
+}
+#else
+pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma);
+bool arch_copy_pte_mapping(vm_flags_t vm_flags);
+#endif
+
#endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/mm/memory.c b/mm/memory.c
index e2bb51b6242e..be93a73b5152 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -754,7 +754,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
* If it's a COW mapping, write protect it both
* in the parent and the child
*/
- if (is_cow_mapping(vm_flags) && pte_write(pte)) {
+ if ((is_cow_mapping(vm_flags) && pte_write(pte)) ||
+ arch_copy_pte_mapping(vm_flags)) {
ptep_set_wrprotect(src_mm, addr, src_pte);
pte = pte_wrprotect(pte);
}
@@ -2273,6 +2274,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = pte_mkyoung(vmf->orig_pte);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ entry = pte_set_vma_features(entry, vma);
if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
update_mmu_cache(vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2348,6 +2350,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = mk_pte(new_page, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ entry = pte_set_vma_features(entry, vma);
/*
* Clear the pte entry and flush it first, before updating the
* pte with the new entry. This will avoid a race condition
@@ -2866,6 +2869,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
pte = mk_pte(page, vma->vm_page_prot);
if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
+ pte = pte_set_vma_features(pte, vma);
vmf->flags &= ~FAULT_FLAG_WRITE;
ret |= VM_FAULT_WRITE;
exclusive = RMAP_EXCLUSIVE;
@@ -3008,6 +3012,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
entry = mk_pte(page, vma->vm_page_prot);
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));
+ entry = pte_set_vma_features(entry, vma);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
--
2.17.1
^ permalink raw reply related
* [PATCH v8 16/27] mm: Handle THP/HugeTLB shadow stack page fault
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
This patch implements THP shadow stack (SHSTK) copying in the same
way as in the previous patch for regular PTE.
In copy_huge_pmd(), clear the dirty bit from the PMD to cause a page
fault upon the next SHSTK access to the PMD. At that time, fix the
PMD and copy/re-use the page.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/mm/pgtable.c | 8 ++++++++
include/asm-generic/pgtable.h | 6 ++++++
mm/huge_memory.c | 4 ++++
3 files changed, 18 insertions(+)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 0c10d0c5e329..6f3959ca2a08 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -886,6 +886,14 @@ inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
return pte;
}
+inline pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & VM_SHSTK)
+ return pmd_mkdirty_shstk(pmd);
+ else
+ return pmd;
+}
+
inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
{
return (vm_flags & VM_SHSTK);
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 89b0fa132f1f..438ce73b57ea 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1194,12 +1194,18 @@ static inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
return pte;
}
+static inline pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma)
+{
+ return pmd;
+}
+
static inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
{
return false;
}
#else
pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma);
+pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma);
bool arch_copy_pte_mapping(vm_flags_t vm_flags);
#endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1334ede667a8..39d66c628121 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -611,6 +611,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
entry = mk_huge_pmd(page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ entry = pmd_set_vma_features(entry, vma);
page_add_new_anon_rmap(page, vma, haddr, true);
mem_cgroup_commit_charge(page, memcg, false, true);
lru_cache_add_active_or_unevictable(page, vma);
@@ -1253,6 +1254,7 @@ static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf,
pte_t entry;
entry = mk_pte(pages[i], vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ entry = pte_set_vma_features(entry, vma);
memcg = (void *)page_private(pages[i]);
set_page_private(pages[i], 0);
page_add_new_anon_rmap(pages[i], vmf->vma, haddr, false);
@@ -1335,6 +1337,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
pmd_t entry;
entry = pmd_mkyoung(orig_pmd);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ entry = pmd_set_vma_features(entry, vma);
if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1))
update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
ret |= VM_FAULT_WRITE;
@@ -1407,6 +1410,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
pmd_t entry;
entry = mk_huge_pmd(new_page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ entry = pmd_set_vma_features(entry, vma);
pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
page_add_new_anon_rmap(new_page, vma, haddr, true);
mem_cgroup_commit_charge(new_page, memcg, false, true);
--
2.17.1
^ permalink raw reply related
* [PATCH v8 12/27] drm/i915/gvt: Update _PAGE_DIRTY to _PAGE_DIRTY_BITS
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
Update _PAGE_DIRTY to _PAGE_DIRTY_BITS in split_2MB_gtt_entry().
In order to support Control-flow Enforcement (CET), _PAGE_DIRTY is
now _PAGE_DIRTY_HW or _PAGE_DIRTY_SW.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
drivers/gpu/drm/i915/gvt/gtt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 4b04af569c05..e467ca182633 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1201,7 +1201,7 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
}
/* Clear dirty field. */
- se->val64 &= ~_PAGE_DIRTY;
+ se->val64 &= ~_PAGE_DIRTY_BITS;
ops->clear_pse(se);
ops->clear_ips(se);
--
2.17.1
^ permalink raw reply related
* [PATCH v8 13/27] x86/mm: Modify ptep_set_wrprotect and pmdp_set_wrprotect for _PAGE_DIRTY_SW
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
When Shadow Stack is enabled, the [R/O + PAGE_DIRTY_HW] setting is
reserved only for the Shadow Stack. Non-Shadow Stack R/O PTEs use
[R/O + PAGE_DIRTY_SW].
When a PTE goes from [R/W + PAGE_DIRTY_HW] to [R/O + PAGE_DIRTY_SW],
it could become a transient Shadow Stack PTE in two cases.
The first case is that some processors can start a write but end up
seeing a read-only PTE by the time they get to the Dirty bit,
creating a transient Shadow Stack PTE. However, this will not occur
on processors supporting Shadow Stack therefore we don't need a TLB
flush here.
The second case is that when the software, without atomic, tests &
replaces PAGE_DIRTY_HW with PAGE_DIRTY_SW, a transient Shadow Stack
PTE can exist. This is prevented with cmpxchg.
Dave Hansen, Jann Horn, Andy Lutomirski, and Peter Zijlstra provided
many insights to the issue. Jann Horn provided the cmpxchg solution.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/pgtable.h | 58 ++++++++++++++++++++++++++++++++++
1 file changed, 58 insertions(+)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1448fb38f248..81c8c5ec221e 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1222,7 +1222,36 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
static inline void ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+ pte_t new_pte, pte = READ_ONCE(*ptep);
+
+ /*
+ * Some processors can start a write, but end up
+ * seeing a read-only PTE by the time they get
+ * to the Dirty bit. In this case, they will
+ * set the Dirty bit, leaving a read-only, Dirty
+ * PTE which looks like a Shadow Stack PTE.
+ *
+ * However, this behavior has been improved and
+ * will not occur on processors supporting
+ * Shadow Stacks. Without this guarantee, a
+ * transition to a non-present PTE and flush the
+ * TLB would be needed.
+ *
+ * When changing a writable PTE to read-only and
+ * if the PTE has _PAGE_DIRTY_HW set, we move
+ * that bit to _PAGE_DIRTY_SW so that the PTE is
+ * not a valid Shadow Stack PTE.
+ */
+ do {
+ new_pte = pte_wrprotect(pte);
+ new_pte.pte |= (new_pte.pte & _PAGE_DIRTY_HW) >>
+ _PAGE_BIT_DIRTY_HW << _PAGE_BIT_DIRTY_SW;
+ new_pte.pte &= ~_PAGE_DIRTY_HW;
+ } while (!try_cmpxchg(ptep, &pte, new_pte));
+#else
clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
+#endif
}
#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
@@ -1285,7 +1314,36 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
{
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+ pmd_t new_pmd, pmd = READ_ONCE(*pmdp);
+
+ /*
+ * Some processors can start a write, but end up
+ * seeing a read-only PMD by the time they get
+ * to the Dirty bit. In this case, they will
+ * set the Dirty bit, leaving a read-only, Dirty
+ * PMD which looks like a Shadow Stack PMD.
+ *
+ * However, this behavior has been improved and
+ * will not occur on processors supporting
+ * Shadow Stacks. Without this guarantee, a
+ * transition to a non-present PMD and flush the
+ * TLB would be needed.
+ *
+ * When changing a writable PMD to read-only and
+ * if the PMD has _PAGE_DIRTY_HW set, we move
+ * that bit to _PAGE_DIRTY_SW so that the PMD is
+ * not a valid Shadow Stack PMD.
+ */
+ do {
+ new_pmd = pmd_wrprotect(pmd);
+ new_pmd.pmd |= (new_pmd.pmd & _PAGE_DIRTY_HW) >>
+ _PAGE_BIT_DIRTY_HW << _PAGE_BIT_DIRTY_SW;
+ new_pmd.pmd &= ~_PAGE_DIRTY_HW;
+ } while (!try_cmpxchg(pmdp, &pmd, new_pmd));
+#else
clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
+#endif
}
#define pud_write pud_write
--
2.17.1
^ permalink raw reply related
* [PATCH v8 11/27] x86/mm: Introduce _PAGE_DIRTY_SW
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
A RO and dirty PTE exists in the following cases:
(a) A page is modified and then shared with a fork()'ed child;
(b) A R/O page that has been COW'ed;
(c) A SHSTK page.
The processor does not read the dirty bit for (a) and (b), but
checks the dirty bit for (c). To prevent the use of non-SHSTK
memory as SHSTK, we introduce a spare bit of the 64-bit PTE as
_PAGE_BIT_DIRTY_SW and use that for (a) and (b). This results
to the following possible PTE settings:
Modified PTE: (R/W + DIRTY_HW)
Modified and shared PTE: (R/O + DIRTY_SW)
R/O PTE COW'ed: (R/O + DIRTY_SW)
SHSTK PTE: (R/O + DIRTY_HW)
SHSTK PTE COW'ed: (R/O + DIRTY_HW)
SHSTK PTE shared: (R/O + DIRTY_SW)
Note that _PAGE_BIT_DRITY_SW is only used in R/O PTEs but
not R/W PTEs.
When this patch is applied, there are six free bits left in
the 64-bit PTE. There is no more free bit in the 32-bit
PTE (except for PAE) and shadow stack is not implemented
for the 32-bit kernel.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/pgtable.h | 129 ++++++++++++++++++++++-----
arch/x86/include/asm/pgtable_types.h | 21 ++++-
2 files changed, 128 insertions(+), 22 deletions(-)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 8e38d87fce6e..1448fb38f248 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -120,9 +120,9 @@ extern pmdval_t early_pmd_flags;
* The following only work if pte_present() is true.
* Undefined behaviour if not..
*/
-static inline int pte_dirty(pte_t pte)
+static inline bool pte_dirty(pte_t pte)
{
- return pte_flags(pte) & _PAGE_DIRTY;
+ return pte_flags(pte) & _PAGE_DIRTY_BITS;
}
@@ -159,9 +159,9 @@ static inline int pte_young(pte_t pte)
return pte_flags(pte) & _PAGE_ACCESSED;
}
-static inline int pmd_dirty(pmd_t pmd)
+static inline bool pmd_dirty(pmd_t pmd)
{
- return pmd_flags(pmd) & _PAGE_DIRTY;
+ return pmd_flags(pmd) & _PAGE_DIRTY_BITS;
}
static inline int pmd_young(pmd_t pmd)
@@ -169,9 +169,9 @@ static inline int pmd_young(pmd_t pmd)
return pmd_flags(pmd) & _PAGE_ACCESSED;
}
-static inline int pud_dirty(pud_t pud)
+static inline bool pud_dirty(pud_t pud)
{
- return pud_flags(pud) & _PAGE_DIRTY;
+ return pud_flags(pud) & _PAGE_DIRTY_BITS;
}
static inline int pud_young(pud_t pud)
@@ -310,9 +310,23 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
return native_make_pte(v & ~clear);
}
+#if defined(CONFIG_X86_INTEL_SHADOW_STACK_USER)
+static inline pte_t pte_move_flags(pte_t pte, pteval_t from, pteval_t to)
+{
+ if (pte_flags(pte) & from)
+ pte = pte_set_flags(pte_clear_flags(pte, from), to);
+ return pte;
+}
+#else
+static inline pte_t pte_move_flags(pte_t pte, pteval_t from, pteval_t to)
+{
+ return pte;
+}
+#endif
+
static inline pte_t pte_mkclean(pte_t pte)
{
- return pte_clear_flags(pte, _PAGE_DIRTY);
+ return pte_clear_flags(pte, _PAGE_DIRTY_BITS);
}
static inline pte_t pte_mkold(pte_t pte)
@@ -322,6 +336,7 @@ static inline pte_t pte_mkold(pte_t pte)
static inline pte_t pte_wrprotect(pte_t pte)
{
+ pte = pte_move_flags(pte, _PAGE_DIRTY_HW, _PAGE_DIRTY_SW);
return pte_clear_flags(pte, _PAGE_RW);
}
@@ -332,9 +347,24 @@ static inline pte_t pte_mkexec(pte_t pte)
static inline pte_t pte_mkdirty(pte_t pte)
{
+ pteval_t dirty = (!IS_ENABLED(CONFIG_X86_INTEL_SHADOW_STACK_USER) ||
+ pte_write(pte)) ? _PAGE_DIRTY_HW:_PAGE_DIRTY_SW;
+ return pte_set_flags(pte, dirty | _PAGE_SOFT_DIRTY);
+}
+
+#ifdef CONFIG_ARCH_HAS_SHSTK
+static inline pte_t pte_mkdirty_shstk(pte_t pte)
+{
+ pte = pte_clear_flags(pte, _PAGE_DIRTY_SW);
return pte_set_flags(pte, _PAGE_DIRTY_HW | _PAGE_SOFT_DIRTY);
}
+static inline bool pte_dirty_hw(pte_t pte)
+{
+ return pte_flags(pte) & _PAGE_DIRTY_HW;
+}
+#endif
+
static inline pte_t pte_mkyoung(pte_t pte)
{
return pte_set_flags(pte, _PAGE_ACCESSED);
@@ -342,6 +372,7 @@ static inline pte_t pte_mkyoung(pte_t pte)
static inline pte_t pte_mkwrite(pte_t pte)
{
+ pte = pte_move_flags(pte, _PAGE_DIRTY_SW, _PAGE_DIRTY_HW);
return pte_set_flags(pte, _PAGE_RW);
}
@@ -389,6 +420,20 @@ static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
return native_make_pmd(v & ~clear);
}
+#if defined(CONFIG_X86_INTEL_SHADOW_STACK_USER)
+static inline pmd_t pmd_move_flags(pmd_t pmd, pmdval_t from, pmdval_t to)
+{
+ if (pmd_flags(pmd) & from)
+ pmd = pmd_set_flags(pmd_clear_flags(pmd, from), to);
+ return pmd;
+}
+#else
+static inline pmd_t pmd_move_flags(pmd_t pmd, pmdval_t from, pmdval_t to)
+{
+ return pmd;
+}
+#endif
+
static inline pmd_t pmd_mkold(pmd_t pmd)
{
return pmd_clear_flags(pmd, _PAGE_ACCESSED);
@@ -396,19 +441,36 @@ static inline pmd_t pmd_mkold(pmd_t pmd)
static inline pmd_t pmd_mkclean(pmd_t pmd)
{
- return pmd_clear_flags(pmd, _PAGE_DIRTY);
+ return pmd_clear_flags(pmd, _PAGE_DIRTY_BITS);
}
static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
+ pmd = pmd_move_flags(pmd, _PAGE_DIRTY_HW, _PAGE_DIRTY_SW);
return pmd_clear_flags(pmd, _PAGE_RW);
}
static inline pmd_t pmd_mkdirty(pmd_t pmd)
{
+ pmdval_t dirty = (!IS_ENABLED(CONFIG_X86_INTEL_SHADOW_STACK_USER) ||
+ (pmd_flags(pmd) & _PAGE_RW)) ?
+ _PAGE_DIRTY_HW:_PAGE_DIRTY_SW;
+ return pmd_set_flags(pmd, dirty | _PAGE_SOFT_DIRTY);
+}
+
+#ifdef CONFIG_ARCH_HAS_SHSTK
+static inline pmd_t pmd_mkdirty_shstk(pmd_t pmd)
+{
+ pmd = pmd_clear_flags(pmd, _PAGE_DIRTY_SW);
return pmd_set_flags(pmd, _PAGE_DIRTY_HW | _PAGE_SOFT_DIRTY);
}
+static inline bool pmd_dirty_hw(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_DIRTY_HW;
+}
+#endif
+
static inline pmd_t pmd_mkdevmap(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_DEVMAP);
@@ -426,6 +488,7 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd)
static inline pmd_t pmd_mkwrite(pmd_t pmd)
{
+ pmd = pmd_move_flags(pmd, _PAGE_DIRTY_SW, _PAGE_DIRTY_HW);
return pmd_set_flags(pmd, _PAGE_RW);
}
@@ -443,6 +506,20 @@ static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
return native_make_pud(v & ~clear);
}
+#if defined(CONFIG_X86_INTEL_SHADOW_STACK_USER)
+static inline pud_t pud_move_flags(pud_t pud, pudval_t from, pudval_t to)
+{
+ if (pud_flags(pud) & from)
+ pud = pud_set_flags(pud_clear_flags(pud, from), to);
+ return pud;
+}
+#else
+static inline pud_t pud_move_flags(pud_t pud, pudval_t from, pudval_t to)
+{
+ return pud;
+}
+#endif
+
static inline pud_t pud_mkold(pud_t pud)
{
return pud_clear_flags(pud, _PAGE_ACCESSED);
@@ -450,17 +527,22 @@ static inline pud_t pud_mkold(pud_t pud)
static inline pud_t pud_mkclean(pud_t pud)
{
- return pud_clear_flags(pud, _PAGE_DIRTY);
+ return pud_clear_flags(pud, _PAGE_DIRTY_BITS);
}
static inline pud_t pud_wrprotect(pud_t pud)
{
+ pud = pud_move_flags(pud, _PAGE_DIRTY_HW, _PAGE_DIRTY_SW);
return pud_clear_flags(pud, _PAGE_RW);
}
static inline pud_t pud_mkdirty(pud_t pud)
{
- return pud_set_flags(pud, _PAGE_DIRTY_HW | _PAGE_SOFT_DIRTY);
+ pudval_t dirty = (!IS_ENABLED(CONFIG_X86_INTEL_SHADOW_STACK_USER) ||
+ (pud_flags(pud) & _PAGE_RW)) ?
+ _PAGE_DIRTY_HW:_PAGE_DIRTY_SW;
+
+ return pud_set_flags(pud, dirty | _PAGE_SOFT_DIRTY);
}
static inline pud_t pud_mkdevmap(pud_t pud)
@@ -480,6 +562,7 @@ static inline pud_t pud_mkyoung(pud_t pud)
static inline pud_t pud_mkwrite(pud_t pud)
{
+ pud = pud_move_flags(pud, _PAGE_DIRTY_SW, _PAGE_DIRTY_HW);
return pud_set_flags(pud, _PAGE_RW);
}
@@ -611,19 +694,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
val &= _PAGE_CHG_MASK;
val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
+ if ((pte_write(pte) && !(pgprot_val(newprot) & _PAGE_RW)))
+ return pte_move_flags(__pte(val), _PAGE_DIRTY_HW,
+ _PAGE_DIRTY_SW);
return __pte(val);
}
-static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
-{
- pmdval_t val = pmd_val(pmd), oldval = val;
-
- val &= _HPAGE_CHG_MASK;
- val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
- val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
- return __pmd(val);
-}
-
/* mprotect needs to preserve PAT bits when updating vm_page_prot */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
@@ -1178,6 +1254,19 @@ static inline int pmd_write(pmd_t pmd)
return pmd_flags(pmd) & _PAGE_RW;
}
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+ pmdval_t val = pmd_val(pmd), oldval = val;
+
+ val &= _HPAGE_CHG_MASK;
+ val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
+ val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
+ if ((pmd_write(pmd) && !(pgprot_val(newprot) & _PAGE_RW)))
+ return pmd_move_flags(__pmd(val), _PAGE_DIRTY_HW,
+ _PAGE_DIRTY_SW);
+ return __pmd(val);
+}
+
#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index e647e3c75578..cd95afc82e9f 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -23,6 +23,7 @@
#define _PAGE_BIT_SOFTW2 10 /* " */
#define _PAGE_BIT_SOFTW3 11 /* " */
#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */
+#define _PAGE_BIT_SOFTW5 57 /* available for programmer */
#define _PAGE_BIT_SOFTW4 58 /* available for programmer */
#define _PAGE_BIT_PKEY_BIT0 59 /* Protection Keys, bit 1/4 */
#define _PAGE_BIT_PKEY_BIT1 60 /* Protection Keys, bit 2/4 */
@@ -34,6 +35,7 @@
#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1
#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */
#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4
+#define _PAGE_BIT_DIRTY_SW _PAGE_BIT_SOFTW5 /* was written to */
/* If _PAGE_BIT_PRESENT is clear, we use these: */
/* - if the user mapped it with PROT_NONE; pte_present gives true */
@@ -108,6 +110,21 @@
#define _PAGE_DEVMAP (_AT(pteval_t, 0))
#endif
+/*
+ * _PAGE_DIRTY_HW: set by the processor when a page is written.
+ * _PAGE_DIRTY_SW: a spare bit tracking a written, but now R/O page.
+ * [R/W + _PAGE_DIRTY_HW] <-> [R/O + _PAGE_DIRTY_SW].
+ * _PAGE_SOFT_DIRTY: a spare bit used to track written pages since a time point
+ * set by the system admin; see Documentation/admin-guide/mm/soft-dirty.rst.
+ */
+#if defined(CONFIG_X86_INTEL_SHADOW_STACK_USER)
+#define _PAGE_DIRTY_SW (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY_SW)
+#else
+#define _PAGE_DIRTY_SW (_AT(pteval_t, 0))
+#endif
+
+#define _PAGE_DIRTY_BITS (_PAGE_DIRTY_HW | _PAGE_DIRTY_SW)
+
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
#define _PAGE_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\
@@ -121,9 +138,9 @@
* instance, and is *not* included in this mask since
* pte_modify() does modify it.
*/
-#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
+#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY_HW | \
- _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+ _PAGE_DIRTY_SW | _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
/*
--
2.17.1
^ permalink raw reply related
* [PATCH v8 10/27] x86/mm: Change _PAGE_DIRTY to _PAGE_DIRTY_HW
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
Before introducing _PAGE_DIRTY_SW for non-hardware, memory management
purposes in the next patch, rename _PAGE_DIRTY to _PAGE_DIRTY_HW and
_PAGE_BIT_DIRTY to _PAGE_BIT_DIRTY_HW to make these PTE dirty bits
more clear. There are no functional changes in this patch.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/pgtable.h | 6 +++---
arch/x86/include/asm/pgtable_types.h | 17 +++++++++--------
arch/x86/kernel/relocate_kernel_64.S | 2 +-
arch/x86/kvm/vmx/vmx.c | 2 +-
4 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0bc530c4eb13..8e38d87fce6e 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -332,7 +332,7 @@ static inline pte_t pte_mkexec(pte_t pte)
static inline pte_t pte_mkdirty(pte_t pte)
{
- return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+ return pte_set_flags(pte, _PAGE_DIRTY_HW | _PAGE_SOFT_DIRTY);
}
static inline pte_t pte_mkyoung(pte_t pte)
@@ -406,7 +406,7 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd)
static inline pmd_t pmd_mkdirty(pmd_t pmd)
{
- return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+ return pmd_set_flags(pmd, _PAGE_DIRTY_HW | _PAGE_SOFT_DIRTY);
}
static inline pmd_t pmd_mkdevmap(pmd_t pmd)
@@ -460,7 +460,7 @@ static inline pud_t pud_wrprotect(pud_t pud)
static inline pud_t pud_mkdirty(pud_t pud)
{
- return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+ return pud_set_flags(pud, _PAGE_DIRTY_HW | _PAGE_SOFT_DIRTY);
}
static inline pud_t pud_mkdevmap(pud_t pud)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b5e49e6bac63..e647e3c75578 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -15,7 +15,7 @@
#define _PAGE_BIT_PWT 3 /* page write through */
#define _PAGE_BIT_PCD 4 /* page cache disabled */
#define _PAGE_BIT_ACCESSED 5 /* was accessed (raised by CPU) */
-#define _PAGE_BIT_DIRTY 6 /* was written to (raised by CPU) */
+#define _PAGE_BIT_DIRTY_HW 6 /* was written to (raised by CPU) */
#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
#define _PAGE_BIT_PAT 7 /* on 4KB pages */
#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
@@ -45,7 +45,7 @@
#define _PAGE_PWT (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
#define _PAGE_PCD (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
-#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
+#define _PAGE_DIRTY_HW (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY_HW)
#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
@@ -73,7 +73,7 @@
_PAGE_PKEY_BIT3)
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-#define _PAGE_KNL_ERRATUM_MASK (_PAGE_DIRTY | _PAGE_ACCESSED)
+#define _PAGE_KNL_ERRATUM_MASK (_PAGE_DIRTY_HW | _PAGE_ACCESSED)
#else
#define _PAGE_KNL_ERRATUM_MASK 0
#endif
@@ -111,9 +111,9 @@
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
#define _PAGE_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\
- _PAGE_ACCESSED | _PAGE_DIRTY)
+ _PAGE_ACCESSED | _PAGE_DIRTY_HW)
#define _KERNPG_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | \
- _PAGE_ACCESSED | _PAGE_DIRTY)
+ _PAGE_ACCESSED | _PAGE_DIRTY_HW)
/*
* Set of bits not changed in pte_modify. The pte's
@@ -122,7 +122,7 @@
* pte_modify() does modify it.
*/
#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
- _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \
+ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY_HW | \
_PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
@@ -167,7 +167,8 @@ enum page_cache_mode {
_PAGE_ACCESSED)
#define __PAGE_KERNEL_EXEC \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY_HW | _PAGE_ACCESSED | \
+ _PAGE_GLOBAL)
#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC | _PAGE_NX)
#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
@@ -186,7 +187,7 @@ enum page_cache_mode {
#define _PAGE_ENC (_AT(pteval_t, sme_me_mask))
#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \
- _PAGE_DIRTY | _PAGE_ENC)
+ _PAGE_DIRTY_HW | _PAGE_ENC)
#define _PAGE_TABLE (_KERNPG_TABLE | _PAGE_USER)
#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC)
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index c51ccff5cd01..60b75e8f4c14 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -15,7 +15,7 @@
*/
#define PTR(x) (x << 3)
-#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY_HW)
/*
* control_page + KEXEC_CONTROL_CODE_MAX_SIZE
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 42ed3faa6af8..226875fbfa45 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3395,7 +3395,7 @@ static int init_rmode_identity_map(struct kvm *kvm)
/* Set up identity-mapping pagetable for EPT in real mode */
for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
- _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
+ _PAGE_ACCESSED | _PAGE_DIRTY_HW | _PAGE_PSE);
r = kvm_write_guest_page(kvm, identity_map_pfn,
&tmp, i * sizeof(tmp), sizeof(tmp));
if (r < 0)
--
2.17.1
^ permalink raw reply related
* [PATCH v8 09/27] mm/mmap: Prevent Shadow Stack VMA merges
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
To prevent function call/return spills into the next shadow stack
area, do not merge shadow stack areas.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
mm/mmap.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/mm/mmap.c b/mm/mmap.c
index 7e8c3e8ae75f..b1a921c0de63 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1149,6 +1149,12 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
if (vm_flags & VM_SPECIAL)
return NULL;
+ /*
+ * Do not merge shadow stack areas.
+ */
+ if (vm_flags & VM_SHSTK)
+ return NULL;
+
if (prev)
next = prev->vm_next;
else
--
2.17.1
^ permalink raw reply related
* [PATCH v8 04/27] x86/fpu/xstate: Introduce XSAVES system states
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
Control-flow Enforcement (CET) MSR contents are XSAVES system states.
To support CET, introduce XSAVES system states first.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/fpu/internal.h | 23 +++++++-
arch/x86/include/asm/fpu/xstate.h | 4 +-
arch/x86/kernel/fpu/core.c | 26 +++++++--
arch/x86/kernel/fpu/init.c | 10 ----
arch/x86/kernel/fpu/signal.c | 4 +-
arch/x86/kernel/fpu/xstate.c | 90 +++++++++++++++++++----------
arch/x86/kernel/process.c | 2 +-
arch/x86/kernel/signal.c | 2 +-
8 files changed, 106 insertions(+), 55 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 652be3853b40..2ca5c36a77d5 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -31,7 +31,8 @@ extern void fpu__save(struct fpu *fpu);
extern int fpu__restore_sig(void __user *buf, int ia32_frame);
extern void fpu__drop(struct fpu *fpu);
extern int fpu__copy(struct task_struct *dst, struct task_struct *src);
-extern void fpu__clear(struct fpu *fpu);
+extern void fpu__clear_user_states(struct fpu *fpu);
+extern void fpu__clear_all(struct fpu *fpu);
extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
@@ -44,7 +45,6 @@ extern void fpu__init_cpu_xstate(void);
extern void fpu__init_system(struct cpuinfo_x86 *c);
extern void fpu__init_check_bugs(void);
extern void fpu__resume_cpu(void);
-extern u64 fpu__get_supported_xfeatures_mask(void);
/*
* Debugging facility:
@@ -92,7 +92,7 @@ static inline void fpstate_init_xstate(struct xregs_state *xsave)
* XRSTORS requires these bits set in xcomp_bv, or it will
* trigger #GP:
*/
- xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_user;
+ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
}
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
@@ -615,6 +615,23 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
__write_pkru(pkru_val);
}
+/*
+ * On context switches, XSAVE states are not restored until returning
+ * to user-mode. FPU registers need to be restored before any changes,
+ * and protected by fpregs_lock()/fpregs_unlock().
+ */
+static inline void modify_fpu_regs_begin(void)
+{
+ fpregs_lock();
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ __fpregs_load_activate();
+}
+
+static inline void modify_fpu_regs_end(void)
+{
+ fpregs_unlock();
+}
+
/*
* MXCSR and XCR definitions:
*/
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 9ded9532257d..970bbd303cfb 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -21,9 +21,6 @@
#define XSAVE_YMM_SIZE 256
#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-/* Supervisor features */
-#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
-
/* All currently supported features */
#define SUPPORTED_XFEATURES_MASK (XFEATURE_MASK_FP | \
XFEATURE_MASK_SSE | \
@@ -42,6 +39,7 @@
#endif
extern u64 xfeatures_mask_user;
+extern u64 xfeatures_mask_all;
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 12c70840980e..31d3cd70b5df 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -294,12 +294,16 @@ void fpu__drop(struct fpu *fpu)
* Clear FPU registers by setting them up from
* the init fpstate:
*/
-static inline void copy_init_fpstate_to_fpregs(void)
+static inline void copy_init_fpstate_to_fpregs(u64 features_mask)
{
fpregs_lock();
+ /*
+ * Only XSAVES user states are copied.
+ * System states are preserved.
+ */
if (use_xsave())
- copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+ copy_kernel_to_xregs(&init_fpstate.xsave, features_mask);
else if (static_cpu_has(X86_FEATURE_FXSR))
copy_kernel_to_fxregs(&init_fpstate.fxsave);
else
@@ -318,7 +322,21 @@ static inline void copy_init_fpstate_to_fpregs(void)
* Called by sys_execve(), by the signal handler code and by various
* error paths.
*/
-void fpu__clear(struct fpu *fpu)
+void fpu__clear_user_states(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */
+
+ fpu__drop(fpu);
+
+ /*
+ * Make sure fpstate is cleared and initialized.
+ */
+ fpu__initialize(fpu);
+ if (static_cpu_has(X86_FEATURE_FPU))
+ copy_init_fpstate_to_fpregs(xfeatures_mask_user);
+}
+
+void fpu__clear_all(struct fpu *fpu)
{
WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */
@@ -329,7 +347,7 @@ void fpu__clear(struct fpu *fpu)
*/
fpu__initialize(fpu);
if (static_cpu_has(X86_FEATURE_FPU))
- copy_init_fpstate_to_fpregs();
+ copy_init_fpstate_to_fpregs(xfeatures_mask_all);
}
/*
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 73fed33e5bda..0a0ba584a533 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -217,16 +217,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
fpu_user_xstate_size = fpu_kernel_xstate_size;
}
-/*
- * Find supported xfeatures based on cpu features and command-line input.
- * This must be called after fpu__init_parse_early_param() is called and
- * xfeatures_mask is enumerated.
- */
-u64 __init fpu__get_supported_xfeatures_mask(void)
-{
- return SUPPORTED_XFEATURES_MASK;
-}
-
/* Legacy code to initialize eager fpu mode. */
static void __init fpu__init_system_ctx_switch(void)
{
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 8a63f07cf400..4ecf1764a971 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -285,7 +285,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
IS_ENABLED(CONFIG_IA32_EMULATION));
if (!buf) {
- fpu__clear(fpu);
+ fpu__clear_user_states(fpu);
return 0;
}
@@ -407,7 +407,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
err_out:
if (ret)
- fpu__clear(fpu);
+ fpu__clear_user_states(fpu);
return ret;
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d560e8861a3c..9fbe73c546df 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -61,9 +61,19 @@ static short xsave_cpuid_features[] __initdata = {
*/
u64 xfeatures_mask_user __read_mostly;
+/*
+ * Supported XSAVES system states.
+ */
+static u64 xfeatures_mask_system __read_mostly;
+
+/*
+ * Combined XSAVES system and user states.
+ */
+u64 xfeatures_mask_all __read_mostly;
+
static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
static unsigned int xstate_sizes[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
-static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask_user)*8];
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask_all)*8];
/*
* The XSAVE area of kernel can be in standard or compacted format;
@@ -79,7 +89,7 @@ unsigned int fpu_user_xstate_size;
*/
int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
{
- u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_user;
+ u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all;
if (unlikely(feature_name)) {
long xfeature_idx, max_idx;
@@ -158,7 +168,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
* None of the feature bits are in init state. So nothing else
* to do for us, as the memory layout is up to date.
*/
- if ((xfeatures & xfeatures_mask_user) == xfeatures_mask_user)
+ if ((xfeatures & xfeatures_mask_all) == xfeatures_mask_all)
return;
/*
@@ -213,28 +223,27 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
*/
void fpu__init_cpu_xstate(void)
{
- if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_user)
+ if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all)
return;
/*
* XCR_XFEATURE_ENABLED_MASK sets the features that are managed
* by XSAVE{C, OPT} and XRSTOR. Only XSAVE user states can be
* set here.
*/
-
- xfeatures_mask_user &= ~XFEATURE_MASK_SUPERVISOR;
-
cr4_set_bits(X86_CR4_OSXSAVE);
xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user);
+
+ /*
+ * MSR_IA32_XSS controls which system (not user) states are
+ * to be managed by XSAVES.
+ */
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_system);
}
-/*
- * Note that in the future we will likely need a pair of
- * functions here: one for user xstates and the other for
- * system xstates. For now, they are the same.
- */
static int xfeature_enabled(enum xfeature xfeature)
{
- return !!(xfeatures_mask_user & BIT_ULL(xfeature));
+ return !!(xfeatures_mask_all & BIT_ULL(xfeature));
}
/*
@@ -340,7 +349,7 @@ static int xfeature_is_aligned(int xfeature_nr)
*/
static void __init setup_xstate_comp(void)
{
- unsigned int xstate_comp_sizes[sizeof(xfeatures_mask_user)*8];
+ unsigned int xstate_comp_sizes[sizeof(xfeatures_mask_all)*8];
int i;
/*
@@ -413,7 +422,7 @@ static void __init setup_init_fpu_buf(void)
print_xstate_features();
if (boot_cpu_has(X86_FEATURE_XSAVES))
- init_fpstate.xsave.header.xcomp_bv = BIT_ULL(63) | xfeatures_mask_user;
+ init_fpstate.xsave.header.xcomp_bv = BIT_ULL(63) | xfeatures_mask_all;
/*
* Init all the features state with header.xfeatures being 0x0
@@ -436,7 +445,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
* format. Checking a system state's uncompacted offset is
* an error.
*/
- if (XFEATURE_MASK_SUPERVISOR & BIT_ULL(xfeature_nr)) {
+ if (~xfeatures_mask_user & BIT_ULL(xfeature_nr)) {
WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
return -1;
}
@@ -608,15 +617,12 @@ static void do_extra_xstate_size_checks(void)
/*
- * Get total size of enabled xstates in XCR0/xfeatures_mask_user.
+ * Get total size of enabled xstates in XCR0 | IA32_XSS.
*
* Note the SDM's wording here. "sub-function 0" only enumerates
* the size of the *user* states. If we use it to size a buffer
* that we use 'XSAVES' on, we could potentially overflow the
* buffer because 'XSAVES' saves system states too.
- *
- * Note that we do not currently set any bits on IA32_XSS so
- * 'XCR0 | IA32_XSS == XCR0' for now.
*/
static unsigned int __init get_xsaves_size(void)
{
@@ -698,6 +704,7 @@ static int __init init_xstate_size(void)
*/
static void fpu__init_disable_system_xstate(void)
{
+ xfeatures_mask_all = 0;
xfeatures_mask_user = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
@@ -733,10 +740,23 @@ void __init fpu__init_system_xstate(void)
return;
}
+ /*
+ * Find user states supported by the processor.
+ * Only these bits can be set in XCR0.
+ */
cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
xfeatures_mask_user = eax + ((u64)edx << 32);
- if ((xfeatures_mask_user & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+ /*
+ * Find system states supported by the processor.
+ * Only these bits can be set in IA32_XSS MSR.
+ */
+ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+ xfeatures_mask_system = ecx + ((u64)edx << 32);
+
+ xfeatures_mask_all = xfeatures_mask_user | xfeatures_mask_system;
+
+ if ((xfeatures_mask_all & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
/*
* This indicates that something really unexpected happened
* with the enumeration. Disable XSAVE and try to continue
@@ -751,10 +771,12 @@ void __init fpu__init_system_xstate(void)
*/
for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
if (!boot_cpu_has(xsave_cpuid_features[i]))
- xfeatures_mask_user &= ~BIT_ULL(i);
+ xfeatures_mask_all &= ~BIT_ULL(i);
}
- xfeatures_mask_user &= fpu__get_supported_xfeatures_mask();
+ xfeatures_mask_all &= SUPPORTED_XFEATURES_MASK;
+ xfeatures_mask_user &= xfeatures_mask_all;
+ xfeatures_mask_system &= xfeatures_mask_all;
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
@@ -766,7 +788,7 @@ void __init fpu__init_system_xstate(void)
* Update info used for ptrace frames; use standard-format size and no
* system xstates:
*/
- update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user & ~XFEATURE_MASK_SUPERVISOR);
+ update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user);
fpu__init_prepare_fx_sw_frame();
setup_init_fpu_buf();
@@ -774,7 +796,7 @@ void __init fpu__init_system_xstate(void)
print_xstate_offset_size();
pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
- xfeatures_mask_user,
+ xfeatures_mask_all,
fpu_kernel_xstate_size,
boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
return;
@@ -794,6 +816,12 @@ void fpu__resume_cpu(void)
*/
if (boot_cpu_has(X86_FEATURE_XSAVE))
xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user);
+
+ /*
+ * Restore IA32_XSS
+ */
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_system);
}
/*
@@ -839,9 +867,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
/*
* We should not ever be requesting features that we
* have not enabled. Remember that pcntxt_mask is
- * what we write to the XCR0 register.
+ * what we write to the XCR0 | IA32_XSS registers.
*/
- WARN_ONCE(!(xfeatures_mask_user & BIT_ULL(xfeature_nr)),
+ WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)),
"get of unsupported state");
/*
* This assumes the last 'xsave*' instruction to
@@ -989,7 +1017,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
*/
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
- header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+ header.xfeatures &= xfeatures_mask_user;
/*
* Copy xregs_state->header:
@@ -1073,7 +1101,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i
*/
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
- header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+ header.xfeatures &= xfeatures_mask_user;
/*
* Copy xregs_state->header:
@@ -1166,7 +1194,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
* The state that came in from userspace was user-state only.
* Mask all the user states out of 'xfeatures':
*/
- xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+ xsave->header.xfeatures &= xfeatures_mask_system;
/*
* Add back in the features that came in from userspace:
@@ -1222,7 +1250,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
* The state that came in from userspace was user-state only.
* Mask all the user states out of 'xfeatures':
*/
- xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+ xsave->header.xfeatures &= xfeatures_mask_system;
/*
* Add back in the features that came in from userspace:
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 75fea0d48c0e..d360bf4d696b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -139,7 +139,7 @@ void flush_thread(void)
flush_ptrace_hw_breakpoint(tsk);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
- fpu__clear(&tsk->thread.fpu);
+ fpu__clear_all(&tsk->thread.fpu);
}
void disable_TSC(void)
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 8eb7193e158d..ce9421ec285f 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -763,7 +763,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
/*
* Ensure the signal handler starts with the new fpu state.
*/
- fpu__clear(fpu);
+ fpu__clear_user_states(fpu);
}
signal_setup_done(failed, ksig, stepping);
}
--
2.17.1
^ permalink raw reply related
* [PATCH v8 07/27] x86/cet/shstk: Add Kconfig option for user-mode shadow stack
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
Introduce Kconfig option X86_INTEL_SHADOW_STACK_USER.
An application has shadow stack protection when all the following are
true:
(1) The kernel has X86_INTEL_SHADOW_STACK_USER enabled,
(2) The running processor supports the shadow stack,
(3) The application is built with shadow stack enabled tools & libs
and, and at runtime, all dependent shared libs can support
shadow stack.
If this kernel config option is enabled, but (2) or (3) above is not
true, the application runs without the shadow stack protection.
Existing legacy applications will continue to work without the shadow
stack protection.
The user-mode shadow stack protection is only implemented for the
64-bit kernel. Thirty-two bit applications are supported under the
compatibility mode.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/Kconfig | 25 +++++++++++++++++++++++++
arch/x86/Makefile | 7 +++++++
2 files changed, 32 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 222855cc0158..eaf86ef13348 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1934,6 +1934,31 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS
If unsure, say y.
+config X86_INTEL_CET
+ def_bool n
+
+config ARCH_HAS_SHSTK
+ def_bool n
+
+config X86_INTEL_SHADOW_STACK_USER
+ prompt "Intel Shadow Stack for user-mode"
+ def_bool n
+ depends on CPU_SUP_INTEL && X86_64
+ select ARCH_USES_HIGH_VMA_FLAGS
+ select X86_INTEL_CET
+ select ARCH_HAS_SHSTK
+ ---help---
+ Shadow stack provides hardware protection against program stack
+ corruption. Only when all the following are true will an application
+ have the shadow stack protection: the kernel supports it (i.e. this
+ feature is enabled), the application is compiled and linked with
+ shadow stack enabled, and the processor supports this feature.
+ When the kernel has this configuration enabled, existing non shadow
+ stack applications will continue to work, but without shadow stack
+ protection.
+
+ If unsure, say y.
+
config EFI
bool "EFI runtime service support"
depends on ACPI
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 56e748a7679f..0b2e9df48907 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -148,6 +148,13 @@ ifdef CONFIG_X86_X32
endif
export CONFIG_X86_X32_ABI
+# Check assembler shadow stack suppot
+ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+ ifeq ($(call as-instr, saveprevssp, y),)
+ $(error CONFIG_X86_INTEL_SHADOW_STACK_USER not supported by the assembler)
+ endif
+endif
+
#
# If the function graph tracer is used with mcount instead of fentry,
# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
--
2.17.1
^ permalink raw reply related
* [PATCH v8 05/27] x86/fpu/xstate: Introduce CET MSR system states
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
Intel Control-flow Enforcement Technology (CET) introduces the
following MSRs.
MSR_IA32_U_CET (user-mode CET settings),
MSR_IA32_PL3_SSP (user-mode shadow stack),
MSR_IA32_PL0_SSP (kernel-mode shadow stack),
MSR_IA32_PL1_SSP (Privilege Level 1 shadow stack),
MSR_IA32_PL2_SSP (Privilege Level 2 shadow stack).
Introduce them into XSAVES system states.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/fpu/types.h | 22 ++++++++++++++++++
arch/x86/include/asm/fpu/xstate.h | 4 +++-
arch/x86/include/asm/msr-index.h | 18 +++++++++++++++
arch/x86/include/uapi/asm/processor-flags.h | 2 ++
arch/x86/kernel/fpu/xstate.c | 25 +++++++++++++++++++--
5 files changed, 68 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index f098f6cab94b..d7ef4d9c7ad5 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -114,6 +114,9 @@ enum xfeature {
XFEATURE_Hi16_ZMM,
XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
XFEATURE_PKRU,
+ XFEATURE_RESERVED,
+ XFEATURE_CET_USER,
+ XFEATURE_CET_KERNEL,
XFEATURE_MAX,
};
@@ -128,6 +131,8 @@ enum xfeature {
#define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM)
#define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
+#define XFEATURE_MASK_CET_USER (1 << XFEATURE_CET_USER)
+#define XFEATURE_MASK_CET_KERNEL (1 << XFEATURE_CET_KERNEL)
#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \
@@ -229,6 +234,23 @@ struct pkru_state {
u32 pad;
} __packed;
+/*
+ * State component 11 is Control-flow Enforcement user states
+ */
+struct cet_user_state {
+ u64 user_cet; /* user control-flow settings */
+ u64 user_ssp; /* user shadow stack pointer */
+};
+
+/*
+ * State component 12 is Control-flow Enforcement kernel states
+ */
+struct cet_kernel_state {
+ u64 kernel_ssp; /* kernel shadow stack */
+ u64 pl1_ssp; /* privilege level 1 shadow stack */
+ u64 pl2_ssp; /* privilege level 2 shadow stack */
+};
+
struct xstate_header {
u64 xfeatures;
u64 xcomp_bv;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 970bbd303cfb..ebf5979b21e7 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -30,7 +30,9 @@
XFEATURE_MASK_Hi16_ZMM | \
XFEATURE_MASK_PKRU | \
XFEATURE_MASK_BNDREGS | \
- XFEATURE_MASK_BNDCSR)
+ XFEATURE_MASK_BNDCSR | \
+ XFEATURE_MASK_CET_USER | \
+ XFEATURE_MASK_CET_KERNEL)
#ifdef CONFIG_X86_64
#define REX_PREFIX "0x48, "
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6b4fc2788078..e06c1e3fde2f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -848,4 +848,22 @@
#define MSR_VM_IGNNE 0xc0010115
#define MSR_VM_HSAVE_PA 0xc0010117
+/* Control-flow Enforcement Technology MSRs */
+#define MSR_IA32_U_CET 0x6a0 /* user mode cet setting */
+#define MSR_IA32_S_CET 0x6a2 /* kernel mode cet setting */
+#define MSR_IA32_PL0_SSP 0x6a4 /* kernel shstk pointer */
+#define MSR_IA32_PL1_SSP 0x6a5 /* ring-1 shstk pointer */
+#define MSR_IA32_PL2_SSP 0x6a6 /* ring-2 shstk pointer */
+#define MSR_IA32_PL3_SSP 0x6a7 /* user shstk pointer */
+#define MSR_IA32_INT_SSP_TAB 0x6a8 /* exception shstk table */
+
+/* MSR_IA32_U_CET and MSR_IA32_S_CET bits */
+#define MSR_IA32_CET_SHSTK_EN 0x0000000000000001ULL
+#define MSR_IA32_CET_WRSS_EN 0x0000000000000002ULL
+#define MSR_IA32_CET_ENDBR_EN 0x0000000000000004ULL
+#define MSR_IA32_CET_LEG_IW_EN 0x0000000000000008ULL
+#define MSR_IA32_CET_NO_TRACK_EN 0x0000000000000010ULL
+#define MSR_IA32_CET_WAIT_ENDBR 0x00000000000000800UL
+#define MSR_IA32_CET_BITMAP_MASK 0xfffffffffffff000ULL
+
#endif /* _ASM_X86_MSR_INDEX_H */
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index bcba3c643e63..a8df907e8017 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -130,6 +130,8 @@
#define X86_CR4_SMAP _BITUL(X86_CR4_SMAP_BIT)
#define X86_CR4_PKE_BIT 22 /* enable Protection Keys support */
#define X86_CR4_PKE _BITUL(X86_CR4_PKE_BIT)
+#define X86_CR4_CET_BIT 23 /* enable Control-flow Enforcement */
+#define X86_CR4_CET _BITUL(X86_CR4_CET_BIT)
/*
* x86-64 Task Priority Register, CR8
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 9fbe73c546df..63374bb19066 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -38,6 +38,9 @@ static const char *xfeature_names[] =
"Processor Trace (unused)" ,
"Protection Keys User registers",
"unknown xstate feature" ,
+ "Control-flow User registers" ,
+ "Control-flow Kernel registers" ,
+ "unknown xstate feature" ,
};
static short xsave_cpuid_features[] __initdata = {
@@ -51,6 +54,9 @@ static short xsave_cpuid_features[] __initdata = {
X86_FEATURE_AVX512F,
X86_FEATURE_INTEL_PT,
X86_FEATURE_PKU,
+ -1, /* Unused */
+ X86_FEATURE_SHSTK, /* XFEATURE_CET_USER */
+ X86_FEATURE_SHSTK, /* XFEATURE_CET_KERNEL */
};
/*
@@ -313,6 +319,8 @@ static void __init print_xstate_features(void)
print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
print_xstate_feature(XFEATURE_MASK_PKRU);
+ print_xstate_feature(XFEATURE_MASK_CET_USER);
+ print_xstate_feature(XFEATURE_MASK_CET_KERNEL);
}
/*
@@ -559,6 +567,8 @@ static void check_xstate_against_struct(int nr)
XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state);
XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state);
+ XCHECK_SZ(sz, nr, XFEATURE_CET_USER, struct cet_user_state);
+ XCHECK_SZ(sz, nr, XFEATURE_CET_KERNEL, struct cet_kernel_state);
/*
* Make *SURE* to add any feature numbers in below if
@@ -770,8 +780,19 @@ void __init fpu__init_system_xstate(void)
* Clear XSAVE features that are disabled in the normal CPUID.
*/
for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
- if (!boot_cpu_has(xsave_cpuid_features[i]))
- xfeatures_mask_all &= ~BIT_ULL(i);
+ if (xsave_cpuid_features[i] == X86_FEATURE_SHSTK) {
+ /*
+ * X86_FEATURE_SHSTK and X86_FEATURE_IBT share
+ * same states, but can be enabled separately.
+ */
+ if (!boot_cpu_has(X86_FEATURE_SHSTK) &&
+ !boot_cpu_has(X86_FEATURE_IBT))
+ xfeatures_mask_all &= ~BIT_ULL(i);
+ } else {
+ if ((xsave_cpuid_features[i] == -1) ||
+ !boot_cpu_has(xsave_cpuid_features[i]))
+ xfeatures_mask_all &= ~BIT_ULL(i);
+ }
}
xfeatures_mask_all &= SUPPORTED_XFEATURES_MASK;
--
2.17.1
^ permalink raw reply related
* [PATCH v8 01/27] Documentation/x86: Add CET description
From: Yu-cheng Yu @ 2019-08-13 20:51 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
Explain how CET works and the no_cet_shstk/no_cet_ibt kernel
parameters.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
.../admin-guide/kernel-parameters.txt | 6 +
Documentation/x86/index.rst | 1 +
Documentation/x86/intel_cet.rst | 269 ++++++++++++++++++
3 files changed, 276 insertions(+)
create mode 100644 Documentation/x86/intel_cet.rst
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 47d981a86e2f..31ba7b408407 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2935,6 +2935,12 @@
noexec=on: enable non-executable mappings (default)
noexec=off: disable non-executable mappings
+ no_cet_ibt [X86-64] Disable indirect branch tracking for user-mode
+ applications
+
+ no_cet_shstk [X86-64] Disable shadow stack support for user-mode
+ applications
+
nosmap [X86,PPC]
Disable SMAP (Supervisor Mode Access Prevention)
even if it is supported by processor.
diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst
index af64c4bb4447..4be2d34ee631 100644
--- a/Documentation/x86/index.rst
+++ b/Documentation/x86/index.rst
@@ -19,6 +19,7 @@ x86-specific Documentation
tlb
mtrr
pat
+ intel_cet
intel_mpx
intel-iommu
intel_txt
diff --git a/Documentation/x86/intel_cet.rst b/Documentation/x86/intel_cet.rst
new file mode 100644
index 000000000000..a6a34a92987e
--- /dev/null
+++ b/Documentation/x86/intel_cet.rst
@@ -0,0 +1,269 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================
+Control-flow Enforcement Technology (CET)
+=========================================
+
+[1] Overview
+============
+
+Control-flow Enforcement Technology (CET) provides protection against
+return/jump-oriented programming (ROP) attacks. It can be setup to
+protect both the kernel and applications. In the first phase,
+only the user-mode protection is implemented in 64-bit mode; 32-bit
+applications are supported in compatibility mode.
+
+CET introduces shadow stack (SHSTK) and indirect branch tracking
+(IBT). SHSTK is a secondary stack allocated from memory and cannot
+be directly modified by applications. When executing a CALL, the
+processor pushes a copy of the return address to SHSTK. Upon
+function return, the processor pops the SHSTK copy and compares it
+to the one from the program stack. If the two copies differ, the
+processor raises a control-protection exception. IBT verifies all
+indirect CALL/JMP targets are intended as marked by the compiler
+with 'ENDBR' opcodes (see CET instructions below).
+
+There are two kernel configuration options:
+
+ INTEL_X86_SHADOW_STACK_USER, and
+ INTEL_X86_BRANCH_TRACKING_USER.
+
+To build a CET-enabled kernel, Binutils v2.31 and GCC v8.1 or later
+are required. To build a CET-enabled application, GLIBC v2.28 or
+later is also required.
+
+There are two command-line options for disabling CET features:
+
+ no_cet_shstk - disables SHSTK, and
+ no_cet_ibt - disables IBT.
+
+At run time, /proc/cpuinfo shows the availability of SHSTK and IBT.
+
+[2] CET assembly instructions
+=============================
+
+RDSSP %r
+ Read the SHSTK pointer into %r.
+
+INCSSP %r
+ Unwind (increment) the SHSTK pointer (0 ~ 255) steps as indicated
+ in the operand register. The GLIBC longjmp uses INCSSP to unwind
+ the SHSTK until that matches the program stack. When it is
+ necessary to unwind beyond 255 steps, longjmp divides and repeats
+ the process.
+
+RSTORSSP (%r)
+ Switch to the SHSTK indicated in the 'restore token' pointed by
+ the operand register and replace the 'restore token' with a new
+ token to be saved (with SAVEPREVSSP) for the outgoing SHSTK.
+
+::
+
+ Before RSTORSSP
+
+ Incoming SHSTK Current/Outgoing SHSTK
+
+ |----------------------| |----------------------|
+ addr=x | | ssp-> | |
+ |----------------------| |----------------------|
+ (%r)-> | rstor_token=(x|Lg) | addr=y-8 | |
+ |----------------------| |----------------------|
+
+ After RSTORSSP
+
+ |----------------------| |----------------------|
+ | | | |
+ |----------------------| |----------------------|
+ ssp-> | rstor_token=(y|Bz|Lg)| addr=y-8 | |
+ |----------------------| |----------------------|
+
+ note:
+ 1. Only valid addresses and restore tokens can be on the
+ user-mode SHSTK.
+ 2. A token is always of type u64 and must align to u64.
+ 3. The incoming SHSTK pointer in a rstor_token must point to
+ immediately above the token.
+ 4. 'Lg' is bit[0] of a rstor_token indicating a 64-bit SHSTK.
+ 5. 'Bz' is bit[1] of a rstor_token indicating the token is to
+ be used only for the next SAVEPREVSSP and invalid for the
+ RSTORSSP.
+
+SAVEPREVSSP
+ Store the SHSTK 'restore token' pointed by
+ (current_SHSTK_pointer + 8).
+
+::
+
+ After SAVEPREVSSP
+
+ |----------------------| |----------------------|
+ ssp-> | | | |
+ |----------------------| |----------------------|
+ | rstor_token=(y|Bz|Lg)| addr=y-8 | rstor_token(y|Lg) |
+ |----------------------| |----------------------|
+
+WRUSS %r0, (%r1)
+ Write the value in %r0 to the SHSTK address pointed by (%r1).
+ This is a kernel-mode only instruction.
+
+ENDBR
+ The compiler inserts an ENDBR at all valid branch targets. Any
+ CALL/JMP to a target without an ENDBR triggers a control
+ protection fault.
+
+[3] Application Enabling
+========================
+
+An application's CET capability is marked in its ELF header and can
+be verified from the following command output, in the
+NT_GNU_PROPERTY_TYPE_0 field:
+
+ readelf -n <application>
+
+If an application supports CET and is statically linked, it will run
+with CET protection. If the application needs any shared libraries,
+the loader checks all dependencies and enables CET only when all
+requirements are met.
+
+[4] Legacy Libraries
+====================
+
+GLIBC provides a few tunables for backward compatibility.
+
+GLIBC_TUNABLES=glibc.tune.hwcaps=-SHSTK,-IBT
+ Turn off SHSTK/IBT for the current shell.
+
+GLIBC_TUNABLES=glibc.tune.x86_shstk=<on, permissive>
+ This controls how dlopen() handles SHSTK legacy libraries:
+ on: continue with SHSTK enabled;
+ permissive: continue with SHSTK off.
+
+[5] CET system calls
+====================
+
+The following arch_prctl() system calls are added for CET:
+
+arch_prctl(ARCH_X86_CET_STATUS, unsigned long *addr)
+ Return CET feature status.
+
+ The parameter 'addr' is a pointer to a user buffer.
+ On returning to the caller, the kernel fills the following
+ information:
+
+ *addr = SHSTK/IBT status
+ *(addr + 1) = SHSTK base address
+ *(addr + 2) = SHSTK size
+
+arch_prctl(ARCH_X86_CET_DISABLE, unsigned long features)
+ Disable SHSTK and/or IBT specified in 'features'. Return -EPERM
+ if CET is locked.
+
+arch_prctl(ARCH_X86_CET_LOCK)
+ Lock in CET feature.
+
+arch_prctl(ARCH_X86_CET_ALLOC_SHSTK, unsigned long *addr)
+ Allocate a new SHSTK and put a restore token at top.
+
+ The parameter 'addr' is a pointer to a user buffer and indicates
+ the desired SHSTK size to allocate. On returning to the caller,
+ the kernel fills *addr with the base address of the new SHSTK.
+
+arch_prctl(ARCH_X86_CET_MARK_LEGACY_CODE, unsigned long *addr)
+ Mark an address range as IBT legacy code.
+
+ The parameter 'addr' is a pointer to a user buffer that has the
+ following information:
+
+ *addr = starting linear address of the legacy code
+ *(addr + 1) = size of the legacy code
+ *(addr + 2): set (1); clear (0)
+
+Note:
+ There is no CET enabling arch_prctl function. By design, CET is
+ enabled automatically if the binary and the system can support it.
+
+ The parameters passed are always unsigned 64-bit. When an ia32
+ application passing pointers, it should only use the lower 32 bits.
+
+[6] The implementation of the SHSTK
+===================================
+
+SHSTK size
+----------
+
+A task's SHSTK is allocated from memory to a fixed size of
+RLIMIT_STACK. A compat-mode thread's SHSTK size is 1/4 of
+RLIMIT_STACK. The smaller 32-bit thread SHSTK allows more threads to
+share a 32-bit address space.
+
+Signal
+------
+
+The main program and its signal handlers use the same SHSTK. Because
+the SHSTK stores only return addresses, a large SHSTK will cover the
+condition that both the program stack and the sigaltstack run out.
+
+The kernel creates a restore token at the SHSTK restoring address and
+verifies that token when restoring from the signal handler.
+
+Fork
+----
+
+The SHSTK's vma has VM_SHSTK flag set; its PTEs are required to be
+read-only and dirty. When a SHSTK PTE is not present, RO, and dirty,
+a SHSTK access triggers a page fault with an additional SHSTK bit set
+in the page fault error code.
+
+When a task forks a child, its SHSTK PTEs are copied and both the
+parent's and the child's SHSTK PTEs are cleared of the dirty bit.
+Upon the next SHSTK access, the resulting SHSTK page fault is handled
+by page copy/re-use.
+
+When a pthread child is created, the kernel allocates a new SHSTK for
+the new thread.
+
+Setjmp/Longjmp
+--------------
+
+Longjmp unwinds SHSTK until it matches the program stack.
+
+Ucontext
+--------
+
+In GLIBC, getcontext/setcontext is implemented in similar way as
+setjmp/longjmp.
+
+When makecontext creates a new ucontext, a new SHSTK is allocated for
+that context with ARCH_X86_CET_ALLOC_SHSTK the syscall. The kernel
+creates a restore token at the top of the new SHSTK and the user-mode
+code switches to the new SHSTK with the RSTORSSP instruction.
+
+[7] The management of read-only & dirty PTEs for SHSTK
+======================================================
+
+A RO and dirty PTE exists in the following cases:
+
+(a) A page is modified and then shared with a fork()'ed child;
+(b) A R/O page that has been COW'ed;
+(c) A SHSTK page.
+
+The processor only checks the dirty bit for (c). To prevent the use
+of non-SHSTK memory as SHSTK, we use a spare bit of the 64-bit PTE as
+DIRTY_SW for (a) and (b) above. This results to the following PTE
+settings:
+
+Modified PTE: (R/W + DIRTY_HW)
+Modified and shared PTE: (R/O + DIRTY_SW)
+R/O PTE, COW'ed: (R/O + DIRTY_SW)
+SHSTK PTE: (R/O + DIRTY_HW)
+SHSTK PTE, COW'ed: (R/O + DIRTY_HW)
+SHSTK PTE, shared: (R/O + DIRTY_SW)
+
+Note that DIRTY_SW is only used in R/O PTEs but not R/W PTEs.
+
+[8] The implementation of IBT
+=============================
+
+The kernel provides IBT support in mmap() of the legacy code bit map.
+However, the management of the bitmap is done in the GLIBC or the
+application.
--
2.17.1
^ permalink raw reply related
* [PATCH v8 02/27] x86/cpufeatures: Add CET CPU feature flags for Control-flow Enforcement Technology (CET)
From: Yu-cheng Yu @ 2019-08-13 20:52 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Borislav Petkov, Cyrill Gorcunov,
Dave Hansen, Eugene Syromiatnikov, Florian Weimer, H.J. Lu,
Jann Horn, Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pavel Machek, Peter Zijlstra, Randy Dunlap,
Ravi V. Shankar, Vedvyas Shanbhogue, Dave Martin
Cc: Yu-cheng Yu
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>
Add CPU feature flags for Control-flow Enforcement Technology (CET).
CPUID.(EAX=7,ECX=0):ECX[bit 7] Shadow stack
CPUID.(EAX=7,ECX=0):EDX[bit 20] Indirect branch tracking
Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/cpufeatures.h | 2 ++
arch/x86/kernel/cpu/cpuid-deps.c | 2 ++
2 files changed, 4 insertions(+)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index e880f2408e29..122265ab46c1 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -334,6 +334,7 @@
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow Stack */
#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */
#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */
@@ -358,6 +359,7 @@
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
+#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index b5353244749b..9bf35f081080 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -68,6 +68,8 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_SHSTK, X86_FEATURE_XSAVES },
+ { X86_FEATURE_IBT, X86_FEATURE_XSAVES },
{}
};
--
2.17.1
^ permalink raw reply related
* Re: [PATCH 1/1] kbuild: recursive build of external kernel modules
From: Shaun Tancheff @ 2019-08-13 22:10 UTC (permalink / raw)
To: Masahiro Yamada
Cc: Shaun Tancheff, Linux Kbuild mailing list, Joe Lawrence,
James E . J . Bottomley, Jonathan Corbet, Martin K . Petersen,
Michal Marek, Shuah Khan, Thomas Renninger,
open list:DOCUMENTATION, Linux Kernel Mailing List,
Linux PM mailing list, linux-scsi
In-Reply-To: <CAK7LNAT5OVcw9tJtaR8VE_JEemAzkqV6FeSHPEy38wotxjhkZg@mail.gmail.com>
On Mon, Aug 12, 2019 at 8:07 PM Masahiro Yamada
<yamada.masahiro@socionext.com> wrote:
>
> On Tue, Aug 13, 2019 at 2:34 AM Shaun Tancheff <shaun@tancheff.com> wrote:
> >
> > On Mon, Aug 12, 2019 at 10:24 AM Masahiro Yamada
> > <yamada.masahiro@socionext.com> wrote:
> > >
> > > On Fri, Aug 9, 2019 at 9:21 AM Shaun Tancheff <shaun@tancheff.com> wrote:
> > > >
> > > > When building a tree of external modules stage 2 fails
> > > > silently as the root modules.order is empty.
> > > >
> > > > Modify the modules.order location to be fixed to the
> > > > root when KBUILD_EXTMOD is specified and write all
> > > > module paths to the single modules.order file.
> > >
> > > Could you try v5.3-rc4 please?
> >
> > So it seems we are using 'subdir-m' but that is now gone?
> >
> > Is there a recommend pattern for backward compatibility?
> >
> > Thanks!
>
>
> Please convert
>
> subdir-m += dir1
> subdir-m += dir2
>
> into
>
> obj-m += dir1/
> obj-m += dir2/
After working through some local quirks everything is working now.
Thanks!
>
>
> Thanks.
>
> --
> Best Regards
> Masahiro Yamada
^ permalink raw reply
* Re: [PATCH] devicetree: Expose dtbs_check and dt_binding_check some more
From: Rob Herring @ 2019-08-13 22:32 UTC (permalink / raw)
To: Stephen Boyd
Cc: linux-kernel@vger.kernel.org, Masahiro Yamada,
Linux Kbuild mailing list, devicetree, Linux Doc Mailing List
In-Reply-To: <20190813183825.9605-1-sboyd@kernel.org>
On Tue, Aug 13, 2019 at 12:38 PM Stephen Boyd <sboyd@kernel.org> wrote:
>
> It wasn't obvious that this was a command to run based on 'make help',
> so add it to the top-level help for devicetree builds. Also, add an
> example to the documentation to show that db_binding_check can be run
> with DT_SCHEMA_FILES= to only check one schema file instead of all of
> them.
>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: <linux-kbuild@vger.kernel.org>
> Cc: <devicetree@vger.kernel.org>
> Cc: <linux-doc@vger.kernel.org>
> Signed-off-by: Stephen Boyd <sboyd@kernel.org>
> ---
>
> I didn't find this sent, so sending again!
You had. :)
>
> Documentation/devicetree/writing-schema.md | 1 +
> Makefile | 6 ++++--
> 2 files changed, 5 insertions(+), 2 deletions(-)
writing-schema.md got converted to rst, so I fixed up and applied.
Rob
^ permalink raw reply
* Re: [PATCH v8 09/27] mm/mmap: Prevent Shadow Stack VMA merges
From: Dave Hansen @ 2019-08-13 22:34 UTC (permalink / raw)
To: Yu-cheng Yu, x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar,
linux-kernel, linux-doc, linux-mm, linux-arch, linux-api,
Arnd Bergmann, Andy Lutomirski, Balbir Singh, Borislav Petkov,
Cyrill Gorcunov, Dave Hansen, Eugene Syromiatnikov,
Florian Weimer, H.J. Lu, Jann Horn, Jonathan Corbet, Kees Cook,
Mike Kravetz, Nadav Amit, Oleg Nesterov, Pavel Machek,
Peter Zijlstra, Randy Dunlap, Ravi V. Shankar, Vedvyas Shanbhogue,
Dave Martin
In-Reply-To: <20190813205225.12032-10-yu-cheng.yu@intel.com>
On 8/13/19 1:52 PM, Yu-cheng Yu wrote:
> To prevent function call/return spills into the next shadow stack
> area, do not merge shadow stack areas.
How does this prevent call/return spills?
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox