blob: cdaa58c9b39ed3a31054686f68f934e488990e2f [file] [log] [blame]
* Intel Physical Address Extension (PAE) Mode - three-level page
* tables on PPro+ CPUs.
* Copyright (C) 1999 Ingo Molnar <>
#define pte_ERROR(e) \
pr_err("%s:%d: bad pte %p(%08lx%08lx)\n", \
__FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
#define pmd_ERROR(e) \
pr_err("%s:%d: bad pmd %p(%016Lx)\n", \
__FILE__, __LINE__, &(e), pmd_val(e))
#define pgd_ERROR(e) \
pr_err("%s:%d: bad pgd %p(%016Lx)\n", \
__FILE__, __LINE__, &(e), pgd_val(e))
/* Rules for using set_pte: the pte being assigned *must* be
* either not present or in a state where the hardware will
* not attempt to update the pte. In places where this is
* not possible, use pte_get_and_clear to obtain the old pte
* value and then use set_pte to update it. -ben
static inline void native_set_pte(pte_t *ptep, pte_t pte)
ptep->pte_high = pte.pte_high;
ptep->pte_low = pte.pte_low;
#define pmd_read_atomic pmd_read_atomic
* pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with
* a "*pmdp" dereference done by gcc. Problem is, in certain places
* where pte_offset_map_lock is called, concurrent page faults are
* allowed, if the mmap_sem is hold for reading. An example is mincore
* vs page faults vs MADV_DONTNEED. On the page fault side
* pmd_populate rightfully does a set_64bit, but if we're reading the
* pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
* because gcc will not read the 64bit of the pmd atomically. To fix
* this all places running pmd_offset_map_lock() while holding the
* mmap_sem in read mode, shall read the pmdp pointer using this
* function to know if the pmd is null nor not, and in turn to know if
* they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
* operations.
* Without THP if the mmap_sem is hold for reading, the pmd can only
* transition from null to not null while pmd_read_atomic runs. So
* we can always return atomic pmd values with this function.
* With THP if the mmap_sem is hold for reading, the pmd can become
* trans_huge or none or point to a pte (and in turn become "stable")
* at any time under pmd_read_atomic. We could read it really
* atomically here with a atomic64_read for the THP enabled case (and
* it would be a whole lot simpler), but to avoid using cmpxchg8b we
* only return an atomic pmdval if the low part of the pmdval is later
* found stable (i.e. pointing to a pte). And we're returning a none
* pmdval if the low part of the pmd is none. In some cases the high
* and low part of the pmdval returned may not be consistent if THP is
* enabled (the low part may point to previously mapped hugepage,
* while the high part may point to a more recently mapped hugepage),
* but pmd_none_or_trans_huge_or_clear_bad() only needs the low part
* of the pmd to be read atomically to decide if the pmd is unstable
* or not, with the only exception of when the low part of the pmd is
* zero in which case we return a none pmd.
static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
pmdval_t ret;
u32 *tmp = (u32 *)pmdp;
ret = (pmdval_t) (*tmp);
if (ret) {
* If the low part is null, we must not read the high part
* or we can end up with a partial pmd.
ret |= ((pmdval_t)*(tmp + 1)) << 32;
return (pmd_t) { ret };
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
set_64bit((unsigned long long *)(pmdp), native_pmd_val(pmd));
static inline void native_set_pud(pud_t *pudp, pud_t pud)
set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
* For PTEs and PDEs, we must clear the P-bit first when clearing a page table
* entry, so clear the bottom half first and enforce ordering with a compiler
* barrier.
static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
ptep->pte_low = 0;
ptep->pte_high = 0;
static inline void native_pmd_clear(pmd_t *pmd)
u32 *tmp = (u32 *)pmd;
*tmp = 0;
*(tmp + 1) = 0;
static inline void pud_clear(pud_t *pudp)
set_pud(pudp, __pud(0));
* According to Intel App note "TLBs, Paging-Structure Caches,
* and Their Invalidation", April 2007, document 317080-001,
* section 8.1: in PAE mode we explicitly have to flush the
* TLB via cr3 if the top-level pgd is changed...
* Currently all places where pud_clear() is called either have
* flush_tlb_mm() followed or don't need TLB flush (x86_64 code or
* pud_clear_bad()), so we don't need TLB flush here.
static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
pte_t res;
/* xchg acts as a barrier before the setting of the high bits */
res.pte_low = xchg(&ptep->pte_low, 0);
res.pte_high = ptep->pte_high;
ptep->pte_high = 0;
return res;
#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
union split_pmd {
struct {
u32 pmd_low;
u32 pmd_high;
pmd_t pmd;
static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
union split_pmd res, *orig = (union split_pmd *)pmdp;
/* xchg acts as a barrier before setting of the high bits */
res.pmd_low = xchg(&orig->pmd_low, 0);
res.pmd_high = orig->pmd_high;
orig->pmd_high = 0;
return res.pmd;
#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
/* Encode and de-code a swap entry */
#define __swp_type(x) (((x).val) & 0x1f)
#define __swp_offset(x) ((x).val >> 5)
#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5})
#define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high })
#define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } })
#endif /* _ASM_X86_PGTABLE_3LEVEL_H */