diff options
| -rw-r--r-- | arch/x86/include/asm/pgtable.h | 83 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable_types.h | 34 | ||||
| -rw-r--r-- | arch/x86/include/asm/tlbflush.h | 3 |
3 files changed, 115 insertions, 5 deletions
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5f6e4ac1aad8..0c0747cbad3e 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -302,6 +302,53 @@ 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); @@ -414,6 +461,24 @@ 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); @@ -485,6 +550,24 @@ 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); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index ba3e2554799a..93796471a8fa 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) /* @@ -125,9 +145,9 @@ * 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 | \ - _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC | \ +#define _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 _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) @@ -188,10 +208,16 @@ 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_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 80450e1d5385..2deae4dd71da 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -286,7 +286,8 @@ 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 | |