#ifndef __ASSEMBLY__
+#include <asm/cmpxchg.h>
#include <asm/fixmap.h>
#include <linux/mmdebug.h>
(__boundary - 1 < (end) - 1) ? __boundary : (end); \
})
-#ifdef CONFIG_ARM64_HW_AFDBM
#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
-#else
-#define pte_hw_dirty(pte) (0)
-#endif
#define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY))
#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte))
static inline pte_t pte_wrprotect(pte_t pte)
{
- return clear_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+ return pte;
}
static inline pte_t pte_mkwrite(pte_t pte)
{
- return set_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+ return pte;
}
static inline pte_t pte_mkclean(pte_t pte)
return clear_pte_bit(pte, __pgprot(PTE_CONT));
}
-static inline pte_t pte_clear_rdonly(pte_t pte)
-{
- return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
-}
-
static inline pte_t pte_mkpresent(pte_t pte)
{
return set_pte_bit(pte, __pgprot(PTE_VALID));
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
- if (pte_present(pte)) {
- if (pte_sw_dirty(pte) && pte_write(pte))
- pte_val(pte) &= ~PTE_RDONLY;
- else
- pte_val(pte) |= PTE_RDONLY;
- if (pte_user_exec(pte) && !pte_special(pte))
- __sync_icache_dcache(pte, addr);
- }
+ if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
+ __sync_icache_dcache(pte, addr);
/*
* If the existing pte is valid, check for potential race with
* hardware updates of the pte (ptep_set_access_flags safely changes
* valid ptes without going through an invalid entry).
*/
- if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
- pte_valid(*ptep) && pte_valid(pte)) {
+ if (pte_valid(*ptep) && pte_valid(pte)) {
VM_WARN_ONCE(!pte_young(pte),
"%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
__func__, pte_val(*ptep), pte_val(pte));
/* Find an entry in the third-level page table. */
#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_phys(dir,addr) (pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t))
+#define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t))
#define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr))))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
}
-#ifdef CONFIG_ARM64_HW_AFDBM
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int __ptep_test_and_clear_young(pte_t *ptep)
{
- pteval_t pteval;
- unsigned int tmp, res;
+ pte_t old_pte, pte;
- asm volatile("// __ptep_test_and_clear_young\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " ubfx %w3, %w0, %5, #1 // extract PTE_AF (young)\n"
- " and %0, %0, %4 // clear PTE_AF\n"
- " stxr %w1, %0, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)), "=&r" (res)
- : "L" (~PTE_AF), "I" (ilog2(PTE_AF)));
+ pte = READ_ONCE(*ptep);
+ do {
+ old_pte = pte;
+ pte = pte_mkold(pte);
+ pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+ pte_val(old_pte), pte_val(pte));
+ } while (pte_val(pte) != pte_val(old_pte));
- return res;
+ return pte_young(pte);
}
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long address, pte_t *ptep)
{
- pteval_t old_pteval;
- unsigned int tmp;
-
- asm volatile("// ptep_get_and_clear\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " stxr %w1, xzr, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)));
-
- return __pte(old_pteval);
+ return __pte(xchg_relaxed(&pte_val(*ptep), 0));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * ptep_set_wrprotect - mark read-only while trasferring potential hardware
- * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
+ * ptep_set_wrprotect - mark read-only while preserving the hardware update of
+ * the Access Flag.
*/
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
{
- pteval_t pteval;
- unsigned long tmp;
+ pte_t old_pte, pte;
- asm volatile("// ptep_set_wrprotect\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " tst %0, %4 // check for hw dirty (!PTE_RDONLY)\n"
- " csel %1, %3, xzr, eq // set PTE_DIRTY|PTE_RDONLY if dirty\n"
- " orr %0, %0, %1 // if !dirty, PTE_RDONLY is already set\n"
- " and %0, %0, %5 // clear PTE_WRITE/PTE_DBM\n"
- " stxr %w1, %0, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
- : "r" (PTE_DIRTY|PTE_RDONLY), "L" (PTE_RDONLY), "L" (~PTE_WRITE)
- : "cc");
+ /*
+ * ptep_set_wrprotect() is only called on CoW mappings which are
+ * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE &&
+ * PTE_RDONLY) or writable and software-dirty (PTE_WRITE &&
+ * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and
+ * protection_map[]. There is no race with the hardware update of the
+ * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM)
+ * is set.
+ */
+ VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep),
+ "%s: potential race with hardware DBM", __func__);
+ pte = READ_ONCE(*ptep);
+ do {
+ old_pte = pte;
+ pte = pte_wrprotect(pte);
+ pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+ pte_val(old_pte), pte_val(pte));
+ } while (pte_val(pte) != pte_val(old_pte));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
}
#endif
-#endif /* CONFIG_ARM64_HW_AFDBM */
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_dir[PTRS_PER_PGD];