#ifndef _ASM_X86_MMU_CONTEXT_H
#define _ASM_X86_MMU_CONTEXT_H
#include <asm/desc.h>
#include <linux/atomic.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
#include <asm/mpx.h>
#include <linux/pkeys.h>
#include <asm/spec_ctrl.h>
#ifndef CONFIG_PARAVIRT
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
}
#endif /* !CONFIG_PARAVIRT */
/*
* ldt_structs can be allocated, used, and freed, but they are never
* modified while live.
*/
struct ldt_struct {
/*
* Xen requires page-aligned LDTs with special permissions. This is
* needed to prevent us from installing evil descriptors such as
* call gates. On native, we could merge the ldt_struct and LDT
* allocations, but it's not worth trying to optimize.
*/
struct desc_struct *entries;
unsigned int size;
};
static inline void load_mm_ldt(struct mm_struct *mm)
{
struct ldt_struct *ldt;
/* lockless_dereference synchronizes with smp_store_release */
ldt = lockless_dereference(mm->context.ldt);
/*
* Any change to mm->context.ldt is followed by an IPI to all
* CPUs with the mm active. The LDT will not be freed until
* after the IPI is handled by all such CPUs. This means that,
* if the ldt_struct changes before we return, the values we see
* will be safe, and the new values will be loaded before we run
* any user code.
*
* NB: don't try to convert this to use RCU without extreme care.
* We would still need IRQs off, because we don't want to change
* the local LDT after an IPI loaded a newer value than the one
* that we can see.
*/
if (unlikely(ldt))
set_ldt(ldt->entries, ldt->size);
else
clear_LDT();
DEBUG_LOCKS_WARN_ON(preemptible());
}
/*
* Used for LDT copy/destruction.
*/
int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context_ldt(struct mm_struct *mm);
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
#ifdef CONFIG_SMP
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
#endif
}
static inline void load_cr3(pgd_t *pgdir)
{
__load_cr3(__sme_pa(pgdir));
}
/*
* Init a new mm. Used on mm copies, like at fork()
* and on mm's that are brand-new, like at execve().
*/
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
/* pkey 0 is the default and allocated implicitly */
mm->pkey_allocation_map = 0x1;
/* -1 means unallocated or invalid */
mm->execute_only_pkey = -1;
}
#endif
return init_new_context_ldt(tsk, mm);
}
static inline void destroy_context(struct mm_struct *mm)
{
destroy_context_ldt(mm);
}
extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk);
extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk);
#define switch_mm_irqs_off switch_mm_irqs_off
#define activate_mm(prev, next) \
do { \
paravirt_activate_mm((prev), (next)); \
switch_mm((prev), (next), NULL); \
} while (0);
#ifdef CONFIG_X86_32
#define deactivate_mm(tsk, mm) \
do { \
lazy_load_gs(0); \
} while (0)
#else
#define deactivate_mm(tsk, mm) \
do { \
load_gs_index(0); \
loadsegment(fs, 0); \
} while (0)
#endif
#ifdef CONFIG_X86_64
static inline bool is_64bit_mm(struct mm_struct *mm)
{
return !config_enabled(CONFIG_IA32_EMULATION) ||
!(mm->context.ia32_compat == TIF_IA32);
}
#else
static inline bool is_64bit_mm(struct mm_struct *mm)
{
return false;
}
#endif
static inline void arch_dup_pkeys(struct mm_struct *oldmm,
struct mm_struct *mm)
{
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
return;
/* Duplicate the oldmm pkey state in mm: */
mm->pkey_allocation_map = oldmm->pkey_allocation_map;
mm->execute_only_pkey = oldmm->execute_only_pkey;
#endif
}
static inline void arch_dup_mmap(struct mm_struct *oldmm,
struct mm_struct *mm)
{
arch_dup_pkeys(oldmm, mm);
paravirt_arch_dup_mmap(oldmm, mm);
}
static inline void arch_exit_mmap(struct mm_struct *mm)
{
paravirt_arch_exit_mmap(mm);
}
static inline void arch_bprm_mm_init(struct mm_struct *mm,
struct vm_area_struct *vma)
{
mpx_mm_init(mm);
}
static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
mpx_notify_unmap(mm, vma, start, end);
}
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
static inline int vma_pkey(struct vm_area_struct *vma)
{
unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 |
VM_PKEY_BIT2 | VM_PKEY_BIT3;
return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT;
}
#else
static inline int vma_pkey(struct vm_area_struct *vma)
{
return 0;
}
#endif
static inline bool __pkru_allows_pkey(u16 pkey, bool write)
{
u32 pkru = read_pkru();
if (!__pkru_allows_read(pkru, pkey))
return false;
if (write && !__pkru_allows_write(pkru, pkey))
return false;
return true;
}
/*
* We only want to enforce protection keys on the current process
* because we effectively have no access to PKRU for other
* processes or any way to tell *which * PKRU in a threaded
* process we could use.
*
* So do not enforce things if the VMA is not from the current
* mm, or if we are in a kernel thread.
*/
static inline bool vma_is_foreign(struct vm_area_struct *vma)
{
if (!current->mm)
return true;
/*
* Should PKRU be enforced on the access to this VMA? If
* the VMA is from another process, then PKRU has no
* relevance and should not be enforced.
*/
if (current->mm != vma->vm_mm)
return true;
return false;
}
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
bool write, bool execute, bool foreign)
{
/* pkeys never affect instruction fetches */
if (execute)
return true;
/* allow access if the VMA is not one from this process */
if (foreign || vma_is_foreign(vma))
return true;
return __pkru_allows_pkey(vma_pkey(vma), write);
}
static inline bool arch_pte_access_permitted(pte_t pte, bool write)
{
return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write);
}
#endif /* _ASM_X86_MMU_CONTEXT_H */
|