diff options
Diffstat (limited to 'arch/x86/include/asm')
| -rw-r--r-- | arch/x86/include/asm/cpufeatures.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/disabled-features.h | 16 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/api.h | 9 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/regset.h | 7 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/sched.h | 3 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/types.h | 16 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/xstate.h | 6 | ||||
| -rw-r--r-- | arch/x86/include/asm/idtentry.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/mmu_context.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable.h | 302 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable_types.h | 44 | ||||
| -rw-r--r-- | arch/x86/include/asm/processor.h | 8 | ||||
| -rw-r--r-- | arch/x86/include/asm/shstk.h | 38 | ||||
| -rw-r--r-- | arch/x86/include/asm/special_insns.h | 13 | ||||
| -rw-r--r-- | arch/x86/include/asm/tlbflush.h | 3 | ||||
| -rw-r--r-- | arch/x86/include/asm/trap_pf.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/traps.h | 15 |
17 files changed, 431 insertions, 57 deletions
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 7b4ecbf78d8b..2061ed1c398f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -307,6 +307,7 @@ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ #define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ #define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ +#define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ @@ -383,6 +384,7 @@ #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 */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index fafe9be7a6f4..702d93fdd10e 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -105,6 +105,18 @@ # define DISABLE_TDX_GUEST (1 << (X86_FEATURE_TDX_GUEST & 31)) #endif +#ifdef CONFIG_X86_USER_SHADOW_STACK +#define DISABLE_USER_SHSTK 0 +#else +#define DISABLE_USER_SHSTK (1 << (X86_FEATURE_USER_SHSTK & 31)) +#endif + +#ifdef CONFIG_X86_KERNEL_IBT +#define DISABLE_IBT 0 +#else +#define DISABLE_IBT (1 << (X86_FEATURE_IBT & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -120,7 +132,7 @@ #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ - DISABLE_CALL_DEPTH_TRACKING) + DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK) #define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 @@ -128,7 +140,7 @@ #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \ DISABLE_ENQCMD) #define DISABLED_MASK17 0 -#define DISABLED_MASK18 0 +#define DISABLED_MASK18 (DISABLE_IBT) #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index b475d9a582b8..31089b851c4f 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -82,6 +82,15 @@ static inline void fpregs_unlock(void) preempt_enable(); } +/* + * FPU state gets lazily restored before returning to userspace. So when in the + * kernel, the valid FPU state may be kept in the buffer. This function will force + * restore all the fpu state to the registers early if needed, and lock them from + * being automatically saved/restored. Then FPU state can be modified safely in the + * registers, before unlocking with fpregs_unlock(). + */ +void fpregs_lock_and_load(void); + #ifdef CONFIG_X86_DEBUG_FPU extern void fpregs_assert_state_consistent(void); #else diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h index 4f928d6a367b..697b77e96025 100644 --- a/arch/x86/include/asm/fpu/regset.h +++ b/arch/x86/include/asm/fpu/regset.h @@ -7,11 +7,12 @@ #include <linux/regset.h> -extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active; +extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active, + ssp_active; extern user_regset_get2_fn fpregs_get, xfpregs_get, fpregs_soft_get, - xstateregs_get; + xstateregs_get, ssp_get; extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, - xstateregs_set; + xstateregs_set, ssp_set; /* * xstateregs_active == regset_fpregs_active. Please refer to the comment diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index 78fcde7b1f07..ca6e5e5f16b2 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -11,7 +11,8 @@ extern void save_fpregs_to_fpstate(struct fpu *fpu); extern void fpu__drop(struct fpu *fpu); -extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal); +extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal, + unsigned long shstk_addr); extern void fpu_flush_thread(void); /* diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 7f6d858ff47a..eb810074f1e7 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -115,8 +115,8 @@ enum xfeature { XFEATURE_PT_UNIMPLEMENTED_SO_FAR, XFEATURE_PKRU, XFEATURE_PASID, - XFEATURE_RSRVD_COMP_11, - XFEATURE_RSRVD_COMP_12, + XFEATURE_CET_USER, + XFEATURE_CET_KERNEL_UNUSED, XFEATURE_RSRVD_COMP_13, XFEATURE_RSRVD_COMP_14, XFEATURE_LBR, @@ -138,6 +138,8 @@ enum xfeature { #define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR) #define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU) #define XFEATURE_MASK_PASID (1 << XFEATURE_PASID) +#define XFEATURE_MASK_CET_USER (1 << XFEATURE_CET_USER) +#define XFEATURE_MASK_CET_KERNEL (1 << XFEATURE_CET_KERNEL_UNUSED) #define XFEATURE_MASK_LBR (1 << XFEATURE_LBR) #define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG) #define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA) @@ -253,6 +255,16 @@ struct pkru_state { } __packed; /* + * State component 11 is Control-flow Enforcement user states + */ +struct cet_user_state { + /* user control-flow settings */ + u64 user_cet; + /* user shadow stack pointer */ + u64 user_ssp; +}; + +/* * State component 15: Architectural LBR configuration state. * The size of Arch LBR state depends on the number of LBRs (lbr_depth). */ diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index cd3dd170e23a..d4427b88ee12 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -50,7 +50,8 @@ #define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA /* All currently supported supervisor features */ -#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID) +#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID | \ + XFEATURE_MASK_CET_USER) /* * A supervisor state component may not always contain valuable information, @@ -77,7 +78,8 @@ * Unsupported supervisor features. When a supervisor feature in this mask is * supported in the future, move it to the supported supervisor feature mask. */ -#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT) +#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT | \ + XFEATURE_MASK_CET_KERNEL) /* All supervisor states including supported and unsupported states. */ #define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index cd5c10a74071..05fd175cec7d 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -614,7 +614,7 @@ DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_DF, xenpv_exc_double_fault); #endif /* #CP */ -#ifdef CONFIG_X86_KERNEL_IBT +#ifdef CONFIG_X86_CET DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_CP, exc_control_protection); #endif diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 1d29dc791f5a..416901d406f8 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -186,6 +186,8 @@ do { \ #else #define deactivate_mm(tsk, mm) \ do { \ + if (!tsk->vfork_done) \ + shstk_free(tsk); \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index dbf8af70b7c2..d6ad98ca1288 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -125,9 +125,15 @@ 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; +} + +static inline bool pte_shstk(pte_t pte) +{ + return cpu_feature_enabled(X86_FEATURE_SHSTK) && + (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY; } static inline int pte_young(pte_t pte) @@ -135,9 +141,16 @@ 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_BITS; +} + +static inline bool pmd_shstk(pmd_t pmd) { - return pmd_flags(pmd) & _PAGE_DIRTY; + return cpu_feature_enabled(X86_FEATURE_SHSTK) && + (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == + (_PAGE_DIRTY | _PAGE_PSE); } #define pmd_young pmd_young @@ -146,9 +159,9 @@ 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) @@ -158,7 +171,27 @@ static inline int pud_young(pud_t pud) static inline int pte_write(pte_t pte) { - return pte_flags(pte) & _PAGE_RW; + /* + * Shadow stack pages are logically writable, but do not have + * _PAGE_RW. Check for them separately from _PAGE_RW itself. + */ + return (pte_flags(pte) & _PAGE_RW) || pte_shstk(pte); +} + +#define pmd_write pmd_write +static inline int pmd_write(pmd_t pmd) +{ + /* + * Shadow stack pages are logically writable, but do not have + * _PAGE_RW. Check for them separately from _PAGE_RW itself. + */ + return (pmd_flags(pmd) & _PAGE_RW) || pmd_shstk(pmd); +} + +#define pud_write pud_write +static inline int pud_write(pud_t pud) +{ + return pud_flags(pud) & _PAGE_RW; } static inline int pte_huge(pte_t pte) @@ -292,9 +325,63 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) return native_make_pte(v & ~clear); } +/* + * Write protection operations can result in Dirty=1,Write=0 PTEs. But in the + * case of X86_FEATURE_USER_SHSTK, these PTEs denote shadow stack memory. So + * when creating dirty, write-protected memory, a software bit is used: + * _PAGE_BIT_SAVED_DIRTY. The following functions take a PTE and transition the + * Dirty bit to SavedDirty, and vice-vesra. + * + * This shifting is only done if needed. In the case of shifting + * Dirty->SavedDirty, the condition is if the PTE is Write=0. In the case of + * shifting SavedDirty->Dirty, the condition is Write=1. + */ +static inline pgprotval_t mksaveddirty_shift(pgprotval_t v) +{ + pgprotval_t cond = (~v >> _PAGE_BIT_RW) & 1; + + v |= ((v >> _PAGE_BIT_DIRTY) & cond) << _PAGE_BIT_SAVED_DIRTY; + v &= ~(cond << _PAGE_BIT_DIRTY); + + return v; +} + +static inline pgprotval_t clear_saveddirty_shift(pgprotval_t v) +{ + pgprotval_t cond = (v >> _PAGE_BIT_RW) & 1; + + v |= ((v >> _PAGE_BIT_SAVED_DIRTY) & cond) << _PAGE_BIT_DIRTY; + v &= ~(cond << _PAGE_BIT_SAVED_DIRTY); + + return v; +} + +static inline pte_t pte_mksaveddirty(pte_t pte) +{ + pteval_t v = native_pte_val(pte); + + v = mksaveddirty_shift(v); + return native_make_pte(v); +} + +static inline pte_t pte_clear_saveddirty(pte_t pte) +{ + pteval_t v = native_pte_val(pte); + + v = clear_saveddirty_shift(v); + return native_make_pte(v); +} + static inline pte_t pte_wrprotect(pte_t pte) { - return pte_clear_flags(pte, _PAGE_RW); + pte = pte_clear_flags(pte, _PAGE_RW); + + /* + * Blindly clearing _PAGE_RW might accidentally create + * a shadow stack PTE (Write=0,Dirty=1). Move the hardware + * dirty value to the software bit, if present. + */ + return pte_mksaveddirty(pte); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP @@ -332,7 +419,7 @@ static inline pte_t pte_clear_uffd_wp(pte_t pte) 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) @@ -347,7 +434,16 @@ 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); + pte = pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + + return pte_mksaveddirty(pte); +} + +static inline pte_t pte_mkwrite_shstk(pte_t pte) +{ + pte = pte_clear_flags(pte, _PAGE_RW); + + return pte_set_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) @@ -355,11 +451,15 @@ static inline pte_t pte_mkyoung(pte_t pte) return pte_set_flags(pte, _PAGE_ACCESSED); } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { return pte_set_flags(pte, _PAGE_RW); } +struct vm_area_struct; +pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma); +#define pte_mkwrite pte_mkwrite + static inline pte_t pte_mkhuge(pte_t pte) { return pte_set_flags(pte, _PAGE_PSE); @@ -404,9 +504,34 @@ static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) return native_make_pmd(v & ~clear); } +/* See comments above mksaveddirty_shift() */ +static inline pmd_t pmd_mksaveddirty(pmd_t pmd) +{ + pmdval_t v = native_pmd_val(pmd); + + v = mksaveddirty_shift(v); + return native_make_pmd(v); +} + +/* See comments above mksaveddirty_shift() */ +static inline pmd_t pmd_clear_saveddirty(pmd_t pmd) +{ + pmdval_t v = native_pmd_val(pmd); + + v = clear_saveddirty_shift(v); + return native_make_pmd(v); +} + static inline pmd_t pmd_wrprotect(pmd_t pmd) { - return pmd_clear_flags(pmd, _PAGE_RW); + pmd = pmd_clear_flags(pmd, _PAGE_RW); + + /* + * Blindly clearing _PAGE_RW might accidentally create + * a shadow stack PMD (RW=0, Dirty=1). Move the hardware + * dirty value to the software bit. + */ + return pmd_mksaveddirty(pmd); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP @@ -433,12 +558,21 @@ 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_mkdirty(pmd_t pmd) { - return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + pmd = pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + + return pmd_mksaveddirty(pmd); +} + +static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd) +{ + pmd = pmd_clear_flags(pmd, _PAGE_RW); + + return pmd_set_flags(pmd, _PAGE_DIRTY); } static inline pmd_t pmd_mkdevmap(pmd_t pmd) @@ -456,11 +590,14 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_ACCESSED); } -static inline pmd_t pmd_mkwrite(pmd_t pmd) +static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_RW); } +pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); +#define pmd_mkwrite pmd_mkwrite + static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); @@ -475,6 +612,24 @@ static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) return native_make_pud(v & ~clear); } +/* See comments above mksaveddirty_shift() */ +static inline pud_t pud_mksaveddirty(pud_t pud) +{ + pudval_t v = native_pud_val(pud); + + v = mksaveddirty_shift(v); + return native_make_pud(v); +} + +/* See comments above mksaveddirty_shift() */ +static inline pud_t pud_clear_saveddirty(pud_t pud) +{ + pudval_t v = native_pud_val(pud); + + v = clear_saveddirty_shift(v); + return native_make_pud(v); +} + static inline pud_t pud_mkold(pud_t pud) { return pud_clear_flags(pud, _PAGE_ACCESSED); @@ -482,17 +637,26 @@ 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) { - return pud_clear_flags(pud, _PAGE_RW); + pud = pud_clear_flags(pud, _PAGE_RW); + + /* + * Blindly clearing _PAGE_RW might accidentally create + * a shadow stack PUD (RW=0, Dirty=1). Move the hardware + * dirty value to the software bit. + */ + return pud_mksaveddirty(pud); } static inline pud_t pud_mkdirty(pud_t pud) { - return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + pud = pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + + return pud_mksaveddirty(pud); } static inline pud_t pud_mkdevmap(pud_t pud) @@ -512,7 +676,9 @@ static inline pud_t pud_mkyoung(pud_t pud) static inline pud_t pud_mkwrite(pud_t pud) { - return pud_set_flags(pud, _PAGE_RW); + pud = pud_set_flags(pud, _PAGE_RW); + + return pud_clear_saveddirty(pud); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY @@ -629,6 +795,7 @@ static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte), oldval = val; + pte_t pte_result; /* * Chop off the NX bit (if present), and add the NX portion of @@ -637,17 +804,54 @@ 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); - return __pte(val); + + pte_result = __pte(val); + + /* + * To avoid creating Write=0,Dirty=1 PTEs, pte_modify() needs to avoid: + * 1. Marking Write=0 PTEs Dirty=1 + * 2. Marking Dirty=1 PTEs Write=0 + * + * The first case cannot happen because the _PAGE_CHG_MASK will filter + * out any Dirty bit passed in newprot. Handle the second case by + * going through the mksaveddirty exercise. Only do this if the old + * value was Write=1 to avoid doing this on Shadow Stack PTEs. + */ + if (oldval & _PAGE_RW) + pte_result = pte_mksaveddirty(pte_result); + else + pte_result = pte_clear_saveddirty(pte_result); + + return pte_result; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { pmdval_t val = pmd_val(pmd), oldval = val; + pmd_t pmd_result; - val &= _HPAGE_CHG_MASK; + val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY); val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); - return __pmd(val); + + pmd_result = __pmd(val); + + /* + * To avoid creating Write=0,Dirty=1 PMDs, pte_modify() needs to avoid: + * 1. Marking Write=0 PMDs Dirty=1 + * 2. Marking Dirty=1 PMDs Write=0 + * + * The first case cannot happen because the _PAGE_CHG_MASK will filter + * out any Dirty bit passed in newprot. Handle the second case by + * going through the mksaveddirty exercise. Only do this if the old + * value was Write=1 to avoid doing this on Shadow Stack PTEs. + */ + if (oldval & _PAGE_RW) + pmd_result = pmd_mksaveddirty(pmd_result); + else + pmd_result = pmd_clear_saveddirty(pmd_result); + + return pmd_result; } /* @@ -831,7 +1035,14 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) * (Currently stuck as a macro because of indirect forward reference * to linux/mm.h:page_to_nid()) */ -#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) +#define mk_pte(page, pgprot) \ +({ \ + pgprot_t __pgprot = pgprot; \ + \ + WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \ + _PAGE_DIRTY); \ + pfn_pte(page_to_pfn(page), __pgprot); \ +}) static inline int pmd_bad(pmd_t pmd) { @@ -1090,7 +1301,17 @@ 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) { - clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte); + /* + * Avoid accidentally creating shadow stack PTEs + * (Write=0,Dirty=1). Use cmpxchg() to prevent races with + * the hardware setting Dirty=1. + */ + pte_t old_pte, new_pte; + + old_pte = READ_ONCE(*ptep); + do { + new_pte = pte_wrprotect(old_pte); + } while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte)); } #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) @@ -1116,12 +1337,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); -#define pmd_write pmd_write -static inline int pmd_write(pmd_t pmd) -{ - return pmd_flags(pmd) & _PAGE_RW; -} - #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) @@ -1148,13 +1363,17 @@ 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) { - clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); -} + /* + * Avoid accidentally creating shadow stack PTEs + * (Write=0,Dirty=1). Use cmpxchg() to prevent races with + * the hardware setting Dirty=1. + */ + pmd_t old_pmd, new_pmd; -#define pud_write pud_write -static inline int pud_write(pud_t pud) -{ - return pud_flags(pud) & _PAGE_RW; + old_pmd = READ_ONCE(*pmdp); + do { + new_pmd = pmd_wrprotect(old_pmd); + } while (!try_cmpxchg((long *)pmdp, (long *)&old_pmd, *(long *)&new_pmd)); } #ifndef pmdp_establish @@ -1412,6 +1631,11 @@ static inline bool __pte_access_permitted(unsigned long pteval, bool write) { unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; + /* + * Write=0,Dirty=1 PTEs are shadow stack, which the kernel + * shouldn't generally allow access to, but since they + * are already Write=0, the below logic covers both cases. + */ if (write) need_pte_bits |= _PAGE_RW; @@ -1453,6 +1677,12 @@ static inline bool arch_has_hw_pte_young(void) return true; } +#define arch_check_zapped_pte arch_check_zapped_pte +void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); + +#define arch_check_zapped_pmd arch_check_zapped_pmd +void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); + #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a6deb67cfbb2..0b748ee16b3d 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -21,7 +21,8 @@ #define _PAGE_BIT_SOFTW2 10 /* " */ #define _PAGE_BIT_SOFTW3 11 /* " */ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ -#define _PAGE_BIT_SOFTW4 58 /* available for programmer */ +#define _PAGE_BIT_SOFTW4 57 /* available for programmer */ +#define _PAGE_BIT_SOFTW5 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 */ #define _PAGE_BIT_PKEY_BIT2 61 /* Protection Keys, bit 3/4 */ @@ -34,6 +35,13 @@ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 +#ifdef CONFIG_X86_64 +#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW5 /* Saved Dirty bit */ +#else +/* Shared with _PAGE_BIT_UFFD_WP which is not supported on 32 bit */ +#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW2 /* Saved Dirty bit */ +#endif + /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ #define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL @@ -117,6 +125,18 @@ #define _PAGE_SOFTW4 (_AT(pteval_t, 0)) #endif +/* + * The hardware requires shadow stack to be Write=0,Dirty=1. However, + * there are valid cases where the kernel might create read-only PTEs that + * are dirty (e.g., fork(), mprotect(), uffd-wp(), soft-dirty tracking). In + * this case, the _PAGE_SAVED_DIRTY bit is used instead of the HW-dirty bit, + * to avoid creating a wrong "shadow stack" PTEs. Such PTEs have + * (Write=0,SavedDirty=1,Dirty=0) set. + */ +#define _PAGE_SAVED_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SAVED_DIRTY) + +#define _PAGE_DIRTY_BITS (_PAGE_DIRTY | _PAGE_SAVED_DIRTY) + #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) /* @@ -125,10 +145,10 @@ * instance, and is *not* included in this mask since * pte_modify() does modify it. */ -#define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ - _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |\ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC | \ - _PAGE_UFFD_WP) +#define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ + _PAGE_SPECIAL | _PAGE_ACCESSED | \ + _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ + _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -189,14 +209,22 @@ enum page_cache_mode { #define __PAGE_KERNEL (__PP|__RW| 0|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_EXEC (__PP|__RW| 0|___A| 0|___D| 0|___G) + +/* + * Page tables needs to have Write=1 in order for any lower PTEs to be + * writable. This includes shadow stack memory (Write=0, Dirty=1) + */ #define _KERNPG_TABLE_NOENC (__PP|__RW| 0|___A| 0|___D| 0| 0) #define _KERNPG_TABLE (__PP|__RW| 0|___A| 0|___D| 0| 0| _ENC) #define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) #define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) -#define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) -#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0|___D| 0|___G) + +#define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX| 0| 0|___G) +#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0| 0| 0|___G) +#define __PAGE_KERNEL (__PP|__RW| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_EXEC (__PP|__RW| 0|___A| 0|___D| 0|___G) #define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) -#define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX| 0| 0|___G) #define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) #define __PAGE_KERNEL_LARGE_EXEC (__PP|__RW| 0|___A| 0|___D|_PSE|___G) #define __PAGE_KERNEL_WP (__PP|__RW| 0|___A|__NX|___D| 0|___G| __WP) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cbb943010c1e..0086920cda06 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -28,6 +28,7 @@ struct vm86; #include <asm/unwind_hints.h> #include <asm/vmxfeatures.h> #include <asm/vdso/processor.h> +#include <asm/shstk.h> #include <linux/personality.h> #include <linux/cache.h> @@ -474,6 +475,13 @@ struct thread_struct { */ u32 pkru; +#ifdef CONFIG_X86_USER_SHADOW_STACK + unsigned long features; + unsigned long features_locked; + + struct thread_shstk shstk; +#endif + /* Floating point and extended processor state */ struct fpu fpu; /* diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h new file mode 100644 index 000000000000..42fee8959df7 --- /dev/null +++ b/arch/x86/include/asm/shstk.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHSTK_H +#define _ASM_X86_SHSTK_H + +#ifndef __ASSEMBLY__ +#include <linux/types.h> + +struct task_struct; +struct ksignal; + +#ifdef CONFIG_X86_USER_SHADOW_STACK +struct thread_shstk { + u64 base; + u64 size; +}; + +long shstk_prctl(struct task_struct *task, int option, unsigned long arg2); +void reset_thread_features(void); +unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clone_flags, + unsigned long stack_size); +void shstk_free(struct task_struct *p); +int setup_signal_shadow_stack(struct ksignal *ksig); +int restore_signal_shadow_stack(void); +#else +static inline long shstk_prctl(struct task_struct *task, int option, + unsigned long arg2) { return -EINVAL; } +static inline void reset_thread_features(void) {} +static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p, + unsigned long clone_flags, + unsigned long stack_size) { return 0; } +static inline void shstk_free(struct task_struct *p) {} +static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; } +static inline int restore_signal_shadow_stack(void) { return 0; } +#endif /* CONFIG_X86_USER_SHADOW_STACK */ + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_SHSTK_H */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index de48d1389936..d6cd9344f6c7 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -202,6 +202,19 @@ static inline void clwb(volatile void *__p) : [pax] "a" (p)); } +#ifdef CONFIG_X86_USER_SHADOW_STACK +static inline int write_user_shstk_64(u64 __user *addr, u64 val) +{ + asm_volatile_goto("1: wrussq %[val], (%[addr])\n" + _ASM_EXTABLE(1b, %l[fail]) + :: [addr] "r" (addr), [val] "r" (val) + :: fail); + return 0; +fail: + return -EFAULT; +} +#endif /* CONFIG_X86_USER_SHADOW_STACK */ + #define nop() asm volatile ("nop") static inline void serialize(void) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6ab42caaa67a..25726893c6f4 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -306,7 +306,8 @@ static inline bool pte_flags_need_flush(unsigned long oldflags, const pteval_t flush_on_clear = _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED; const pteval_t software_flags = _PAGE_SOFTW1 | _PAGE_SOFTW2 | - _PAGE_SOFTW3 | _PAGE_SOFTW4; + _PAGE_SOFTW3 | _PAGE_SOFTW4 | + _PAGE_SAVED_DIRTY; const pteval_t flush_on_change = _PAGE_RW | _PAGE_USER | _PAGE_PWT | _PAGE_PCD | _PAGE_PSE | _PAGE_GLOBAL | _PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PKEY_BIT0 | _PAGE_PKEY_BIT1 | diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h index 10b1de500ab1..afa524325e55 100644 --- a/arch/x86/include/asm/trap_pf.h +++ b/arch/x86/include/asm/trap_pf.h @@ -11,6 +11,7 @@ * 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 * bit 15 == 1: SGX MMU page-fault */ enum x86_pf_error_code { @@ -20,6 +21,7 @@ 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, X86_PF_SGX = 1 << 15, }; diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 47ecfff2c83d..b1c9cea6ba88 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -18,7 +18,8 @@ void __init trap_init(void); asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif -extern bool ibt_selftest(void); +extern int ibt_selftest(void); +extern int ibt_selftest_noendbr(void); #ifdef CONFIG_X86_F00F_BUG /* For handling the FOOF bug */ @@ -47,4 +48,16 @@ void __noreturn handle_stack_overflow(struct pt_regs *regs, struct stack_info *info); #endif +static inline void cond_local_irq_enable(struct pt_regs *regs) +{ + if (regs->flags & X86_EFLAGS_IF) + local_irq_enable(); +} + +static inline void cond_local_irq_disable(struct pt_regs *regs) +{ + if (regs->flags & X86_EFLAGS_IF) + local_irq_disable(); +} + #endif /* _ASM_X86_TRAPS_H */ |