@@ -121,6 +121,7 @@ config X86
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
+ select GUP_GET_PTE_LOW_HIGH if X86_PAE
select HARDLOCKUP_CHECK_TIMESTAMP if X86_64
select HAVE_ACPI_APEI if ACPI
select HAVE_ACPI_APEI_NMI if ACPI
@@ -285,53 +285,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
#define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \
__pteval_swp_offset(pte)))
-#define gup_get_pte gup_get_pte
-/*
- * WARNING: only to be used in the get_user_pages_fast() implementation.
- *
- * With get_user_pages_fast(), we walk down the pagetables without taking
- * any locks. For this we would like to load the pointers atomically,
- * but that is not possible (without expensive cmpxchg8b) on PAE. What
- * we do have is the guarantee that a PTE will only either go from not
- * present to present, or present to not present or both -- it will not
- * switch to a completely different present page without a TLB flush in
- * between; something that we are blocking by holding interrupts off.
- *
- * Setting ptes from not present to present goes:
- *
- * ptep->pte_high = h;
- * smp_wmb();
- * ptep->pte_low = l;
- *
- * And present to not present goes:
- *
- * ptep->pte_low = 0;
- * smp_wmb();
- * ptep->pte_high = 0;
- *
- * We must ensure here that the load of pte_low sees 'l' iff pte_high
- * sees 'h'. We load pte_high *after* loading pte_low, which ensures we
- * don't see an older value of pte_high. *Then* we recheck pte_low,
- * which ensures that we haven't picked up a changed pte high. We might
- * have gotten rubbish values from pte_low and pte_high, but we are
- * guaranteed that pte_low will not have the present bit set *unless*
- * it is 'l'. Because get_user_pages_fast() only operates on present ptes
- * we're safe.
- */
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
- pte_t pte;
-
- do {
- pte.pte_low = ptep->pte_low;
- smp_rmb();
- pte.pte_high = ptep->pte_high;
- smp_rmb();
- } while (unlikely(pte.pte_low != ptep->pte_low));
-
- return pte;
-}
-
#include <asm/pgtable-invert.h>
#endif /* _ASM_X86_PGTABLE_3LEVEL_H */
@@ -653,7 +653,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
/*
* The idea using the light way get the spte on x86_32 guest is from
- * gup_get_pte(arch/x86/mm/gup.c).
+ * gup_get_pte (mm/gup.c).
*
* An spte tlb flush may be pending, because kvm_set_pte_rmapp
* coalesces them and we are running out of the MMU lock. Therefore
@@ -762,6 +762,9 @@ config GUP_BENCHMARK
See tools/testing/selftests/vm/gup_benchmark.c
+config GUP_GET_PTE_LOW_HIGH
+ bool
+
config ARCH_HAS_PTE_SPECIAL
bool
@@ -1683,17 +1683,60 @@ struct page *get_dump_page(unsigned long addr)
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
#ifdef CONFIG_HAVE_GENERIC_GUP
+#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
+/*
+ * WARNING: only to be used in the get_user_pages_fast() implementation.
+ *
+ * With get_user_pages_fast(), we walk down the pagetables without taking any
+ * locks. For this we would like to load the pointers atomically, but sometimes
+ * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What
+ * we do have is the guarantee that a PTE will only either go from not present
+ * to present, or present to not present or both -- it will not switch to a
+ * completely different present page without a TLB flush in between; something
+ * that we are blocking by holding interrupts off.
+ *
+ * Setting ptes from not present to present goes:
+ *
+ * ptep->pte_high = h;
+ * smp_wmb();
+ * ptep->pte_low = l;
+ *
+ * And present to not present goes:
+ *
+ * ptep->pte_low = 0;
+ * smp_wmb();
+ * ptep->pte_high = 0;
+ *
+ * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
+ * We load pte_high *after* loading pte_low, which ensures we don't see an older
+ * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't
+ * picked up a changed pte high. We might have gotten rubbish values from
+ * pte_low and pte_high, but we are guaranteed that pte_low will not have the
+ * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
+ * operates on present ptes we're safe.
+ */
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+ pte_t pte;
-#ifndef gup_get_pte
+ do {
+ pte.pte_low = ptep->pte_low;
+ smp_rmb();
+ pte.pte_high = ptep->pte_high;
+ smp_rmb();
+ } while (unlikely(pte.pte_low != ptep->pte_low));
+
+ return pte;
+}
+#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */
/*
- * We assume that the PTE can be read atomically. If this is not the case for
- * your architecture, please provide the helper.
+ * We require that the PTE can be read atomically.
*/
static inline pte_t gup_get_pte(pte_t *ptep)
{
return READ_ONCE(*ptep);
}
-#endif
+#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
{
The split low/high access is the only non-READ_ONCE version of gup_get_pte that did show up in the various arch implemenations. Lift it to common code and drop the ifdef based arch override. Signed-off-by: Christoph Hellwig <hch@lst.de> --- arch/x86/Kconfig | 1 + arch/x86/include/asm/pgtable-3level.h | 47 ------------------------ arch/x86/kvm/mmu.c | 2 +- mm/Kconfig | 3 ++ mm/gup.c | 51 ++++++++++++++++++++++++--- 5 files changed, 52 insertions(+), 52 deletions(-)