@@ -140,7 +140,8 @@ static inline int pte_exec(pte_t pte)
static inline int pte_special(pte_t pte)
{
- return pte_flags(pte) & _PAGE_SPECIAL;
+ return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) ==
+ (_PAGE_PRESENT|_PAGE_SPECIAL);
}
/* Entries that were set to PROT_NONE are inverted */
@@ -500,6 +501,12 @@ static inline int pte_present(pte_t a)
_PAGE_NUMA);
}
+#define pte_present_nonuma pte_present_nonuma
+static inline int pte_present_nonuma(pte_t a)
+{
+ return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+}
+
#define pte_accessible pte_accessible
static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
{
@@ -926,19 +933,19 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
- VM_BUG_ON(pte_present(pte));
+ VM_BUG_ON(pte_present_nonuma(pte));
return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}
static inline int pte_swp_soft_dirty(pte_t pte)
{
- VM_BUG_ON(pte_present(pte));
+ VM_BUG_ON(pte_present_nonuma(pte));
return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
}
static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
- VM_BUG_ON(pte_present(pte));
+ VM_BUG_ON(pte_present_nonuma(pte));
return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}
@@ -186,7 +186,12 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
* physical bits set.
*/
#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
+#ifdef CONFIG_NUMA_BALANCING
+/* Automatic NUMA balancing needs to be distinguishable from swap entries */
+#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 2)
+#else
#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
+#endif
/* We always extract/encode the offset by shifting it all the way up, and then down again */
#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)
@@ -16,15 +16,26 @@
#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
#define _PAGE_BIT_PAT 7 /* on 4KB pages */
#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
-#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
-#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */
-#define _PAGE_BIT_HIDDEN 11 /* hidden by kmemcheck */
+#define _PAGE_BIT_SOFTW1 9 /* available for programmer */
+#define _PAGE_BIT_SOFTW2 10 /* " */
+#define _PAGE_BIT_SOFTW3 11 /* " */
#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */
-#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1
-#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1
-#define _PAGE_BIT_SPLITTING _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */
+#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1
+#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1
+#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */
+#define _PAGE_BIT_IOMAP _PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */
+#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
+#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */
#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
+/*
+ * Swap offsets on configurations that allow automatic NUMA balancing use the
+ * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from
+ * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the
+ * maximum possible swap space from 16TB to 8TB.
+ */
+#define _PAGE_BIT_NUMA (_PAGE_BIT_GLOBAL+1)
+
/* 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
@@ -40,7 +51,7 @@
#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
-#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
+#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
#define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
@@ -61,14 +72,27 @@
* they do not conflict with each other.
*/
-#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_HIDDEN
-
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
#else
#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0))
#endif
+/*
+ * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page
+ * that is not present. The hinting fault gathers numa placement statistics
+ * (see pte_numa()). The bit is always zero when the PTE is not present.
+ *
+ * The bit picked must be always zero when the pmd is present and not
+ * present, so that we don't lose information when we set it while
+ * atomically clearing the present bit.
+ */
+#ifdef CONFIG_NUMA_BALANCING
+#define _PAGE_NUMA (_AT(pteval_t, 1) << _PAGE_BIT_NUMA)
+#else
+#define _PAGE_NUMA (_AT(pteval_t, 0))
+#endif
+
/*
* Tracking soft dirty bit when a page goes to a swap is tricky.
* We need a bit which can be stored in pte _and_ not conflict
@@ -94,26 +118,6 @@
#define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
-/*
- * _PAGE_NUMA indicates that this page will trigger a numa hinting
- * minor page fault to gather numa placement statistics (see
- * pte_numa()). The bit picked (8) is within the range between
- * _PAGE_FILE (6) and _PAGE_PROTNONE (8) bits. Therefore, it doesn't
- * require changes to the swp entry format because that bit is always
- * zero when the pte is not present.
- *
- * The bit picked must be always zero when the pmd is present and not
- * present, so that we don't lose information when we set it while
- * atomically clearing the present bit.
- *
- * Because we shared the same bit (8) with _PAGE_PROTNONE this can be
- * interpreted as _PAGE_NUMA only in places that _PAGE_PROTNONE
- * couldn't reach, like handle_mm_fault() (see access_error in
- * arch/x86/mm/fault.c, the vma protection must not be PROT_NONE for
- * handle_mm_fault() to be invoked).
- */
-#define _PAGE_NUMA _PAGE_PROTNONE
-
#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_DIRTY)
#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \
@@ -122,8 +126,8 @@
/* Set of bits not changed in pte_modify */
#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \
- _PAGE_SOFT_DIRTY)
-#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
+ _PAGE_SOFT_DIRTY | _PAGE_NUMA)
+#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA)
/* The ASID is the lower 12 bits of CR3 */
#define X86_CR3_PCID_ASID_MASK (_AC((1<<12)-1,UL))
@@ -36,7 +36,7 @@ enum {
static int pte_testbit(pte_t pte)
{
- return pte_flags(pte) & _PAGE_UNUSED1;
+ return pte_flags(pte) & _PAGE_SOFTW1;
}
struct split_state {
@@ -220,6 +220,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
+#ifndef pte_present_nonuma
+#define pte_present_nonuma(pte) pte_present(pte)
+#endif
+
#ifndef flush_tlb_fix_spurious_fault
#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
#endif
@@ -657,7 +661,7 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
static inline int pte_numa(pte_t pte)
{
return (pte_flags(pte) &
- (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+ (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
}
#endif
@@ -665,7 +669,7 @@ static inline int pte_numa(pte_t pte)
static inline int pmd_numa(pmd_t pmd)
{
return (pmd_flags(pmd) &
- (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+ (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
}
#endif
@@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry)
/* check whether a pte points to a swap entry */
static inline int is_swap_pte(pte_t pte)
{
- return !pte_none(pte) && !pte_present(pte) && !pte_file(pte);
+ return !pte_none(pte) && !pte_present_nonuma(pte) && !pte_file(pte);
}
#endif
@@ -745,7 +745,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn = pte_pfn(pte);
if (HAVE_PTE_SPECIAL) {
- if (likely(!pte_special(pte)))
+ if (likely(!pte_special(pte) || pte_numa(pte)))
goto check_pfn;
if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return NULL;
@@ -771,14 +771,15 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
}
}
- if (is_zero_pfn(pfn))
- return NULL;
check_pfn:
if (unlikely(pfn > highest_memmap_pfn)) {
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
+ if (is_zero_pfn(pfn))
+ return NULL;
+
/*
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.
@@ -1716,13 +1717,9 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
/*
- * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault
- * would be called on PROT_NONE ranges. We must never invoke
- * handle_mm_fault on PROT_NONE ranges or the NUMA hinting
- * page faults would unprotect the PROT_NONE ranges if
- * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd
- * bitflag. So to avoid that, don't set FOLL_NUMA if
- * FOLL_FORCE is set.
+ * If FOLL_FORCE is set then do not force a full fault as the hinting
+ * fault information is unrelated to the reference behaviour of a task
+ * using the address space
*/
if (!(gup_flags & FOLL_FORCE))
gup_flags |= FOLL_NUMA;