summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-12-18 19:05:00 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-12-18 19:05:00 -0800
commit86fbf1617a6522379815d34b90fef2aa9068f89d (patch)
tree5282028f32ec63b16c81968050b3648a766c13c1
parenta36c160cbbf35aaabf47916e5ea39c519aa80068 (diff)
parent98398c32f6687ee1e1f3ae084effb4b75adb0747 (diff)
downloadlinux-86fbf1617a6522379815d34b90fef2aa9068f89d.tar.gz
Merge branch 'akpm' (incoming from Andrew)
Merge patches from Andrew Morton: "23 fixes and a MAINTAINERS update" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (24 commits) mm/hugetlb: check for pte NULL pointer in __page_check_address() fix build with make 3.80 mm/mempolicy: fix !vma in new_vma_page() MAINTAINERS: add Davidlohr as GPT maintainer mm/memory-failure.c: recheck PageHuge() after hugetlb page migrate successfully mm/compaction: respect ignore_skip_hint in update_pageblock_skip mm/mempolicy: correct putback method for isolate pages if failed mm: add missing dependency in Kconfig sh: always link in helper functions extracted from libgcc mm: page_alloc: exclude unreclaimable allocations from zone fairness policy mm: numa: defer TLB flush for THP migration as long as possible mm: numa: guarantee that tlb_flush_pending updates are visible before page table updates mm: fix TLB flush race between migration, and change_protection_range mm: numa: avoid unnecessary disruption of NUMA hinting during migration mm: numa: clear numa hinting information on mprotect sched: numa: skip inaccessible VMAs mm: numa: avoid unnecessary work on the failure path mm: numa: ensure anon_vma is locked to prevent parallel THP splits mm: numa: do not clear PTE for pte_numa update mm: numa: do not clear PMD during PTE update scan ...
-rw-r--r--MAINTAINERS6
-rw-r--r--Makefile20
-rw-r--r--arch/sh/lib/Makefile2
-rw-r--r--arch/sparc/include/asm/pgtable_64.h4
-rw-r--r--arch/x86/include/asm/pgtable.h11
-rw-r--r--arch/x86/mm/gup.c13
-rw-r--r--include/asm-generic/pgtable.h2
-rw-r--r--include/linux/migrate.h9
-rw-r--r--include/linux/mm_types.h49
-rw-r--r--include/linux/reboot.h1
-rw-r--r--kernel/fork.c1
-rw-r--r--kernel/kexec.c1
-rw-r--r--kernel/reboot.c2
-rw-r--r--kernel/sched/fair.c7
-rw-r--r--mm/Kconfig2
-rw-r--r--mm/compaction.c4
-rw-r--r--mm/huge_memory.c45
-rw-r--r--mm/memory-failure.c14
-rw-r--r--mm/mempolicy.c16
-rw-r--r--mm/migrate.c69
-rw-r--r--mm/mprotect.c13
-rw-r--r--mm/page_alloc.c3
-rw-r--r--mm/pgtable-generic.c8
-rw-r--r--mm/rmap.c4
24 files changed, 249 insertions, 57 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 49c3674294a1..52f761733bfe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3833,6 +3833,12 @@ T: git git://linuxtv.org/media_tree.git
S: Maintained
F: drivers/media/usb/gspca/
+GUID PARTITION TABLE (GPT)
+M: Davidlohr Bueso <davidlohr@hp.com>
+L: linux-efi@vger.kernel.org
+S: Maintained
+F: block/partitions/efi.*
+
STK1160 USB VIDEO CAPTURE DRIVER
M: Ezequiel Garcia <elezegarcia@gmail.com>
L: linux-media@vger.kernel.org
diff --git a/Makefile b/Makefile
index 858a147fd836..89cee8625651 100644
--- a/Makefile
+++ b/Makefile
@@ -732,19 +732,13 @@ export mod_strip_cmd
# Select initial ramdisk compression format, default is gzip(1).
# This shall be used by the dracut(8) tool while creating an initramfs image.
#
-INITRD_COMPRESS=gzip
-ifeq ($(CONFIG_RD_BZIP2), y)
- INITRD_COMPRESS=bzip2
-else ifeq ($(CONFIG_RD_LZMA), y)
- INITRD_COMPRESS=lzma
-else ifeq ($(CONFIG_RD_XZ), y)
- INITRD_COMPRESS=xz
-else ifeq ($(CONFIG_RD_LZO), y)
- INITRD_COMPRESS=lzo
-else ifeq ($(CONFIG_RD_LZ4), y)
- INITRD_COMPRESS=lz4
-endif
-export INITRD_COMPRESS
+INITRD_COMPRESS-y := gzip
+INITRD_COMPRESS-$(CONFIG_RD_BZIP2) := bzip2
+INITRD_COMPRESS-$(CONFIG_RD_LZMA) := lzma
+INITRD_COMPRESS-$(CONFIG_RD_XZ) := xz
+INITRD_COMPRESS-$(CONFIG_RD_LZO) := lzo
+INITRD_COMPRESS-$(CONFIG_RD_LZ4) := lz4
+export INITRD_COMPRESS := $(INITRD_COMPRESS-y)
ifdef CONFIG_MODULE_SIG_ALL
MODSECKEY = ./signing_key.priv
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index 7b95f29e3174..3baff31e58cf 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -6,7 +6,7 @@ lib-y = delay.o memmove.o memchr.o \
checksum.o strlen.o div64.o div64-generic.o
# Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
udiv_qrnnd.o
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 8358dc144959..0f9e94537eee 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -619,7 +619,7 @@ static inline unsigned long pte_present(pte_t pte)
}
#define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
{
return pte_val(a) & _PAGE_VALID;
}
@@ -847,7 +847,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
* SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
* and SUN4V pte layout, so this inline test is fine.
*/
- if (likely(mm != &init_mm) && pte_accessible(orig))
+ if (likely(mm != &init_mm) && pte_accessible(mm, orig))
tlb_batch_add(mm, addr, ptep, orig, fullmm);
}
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3d1999458709..bbc8b12fa443 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -452,9 +452,16 @@ static inline int pte_present(pte_t a)
}
#define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
{
- return pte_flags(a) & _PAGE_PRESENT;
+ if (pte_flags(a) & _PAGE_PRESENT)
+ return true;
+
+ if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+ mm_tlb_flush_pending(mm))
+ return true;
+
+ return false;
}
static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46828c0..0596e8e0cc19 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
pte_t pte = gup_get_pte(ptep);
struct page *page;
+ /* Similar to the PMD case, NUMA hinting must take slow path */
+ if (pte_numa(pte)) {
+ pte_unmap(ptep);
+ return 0;
+ }
+
if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
pte_unmap(ptep);
return 0;
@@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
if (pmd_none(pmd) || pmd_trans_splitting(pmd))
return 0;
if (unlikely(pmd_large(pmd))) {
+ /*
+ * NUMA hinting faults need to be handled in the GUP
+ * slowpath for accounting purposes and so that they
+ * can be serialised against THP migration.
+ */
+ if (pmd_numa(pmd))
+ return 0;
if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
return 0;
} else {
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f330d28e4d0e..b12079afbd5f 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -217,7 +217,7 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
#endif
#ifndef pte_accessible
-# define pte_accessible(pte) ((void)(pte),1)
+# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
#ifndef flush_tlb_fix_spurious_fault
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f5096b58b20d..b7717d74da7f 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -90,10 +90,19 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_NUMA_BALANCING
+extern bool pmd_trans_migrating(pmd_t pmd);
+extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
extern int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node);
extern bool migrate_ratelimited(int node);
#else
+static inline bool pmd_trans_migrating(pmd_t pmd)
+{
+ return false;
+}
+static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+}
static inline int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node)
{
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bd299418a934..ad0616f2fe2c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -443,6 +443,14 @@ struct mm_struct {
/* numa_scan_seq prevents two threads setting pte_numa */
int numa_scan_seq;
#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+ /*
+ * An operation with batched TLB flushing is going on. Anything that
+ * can move process memory needs to flush the TLB when moving a
+ * PROT_NONE or PROT_NUMA mapped page.
+ */
+ bool tlb_flush_pending;
+#endif
struct uprobes_state uprobes_state;
};
@@ -459,4 +467,45 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
return mm->cpu_vm_mask_var;
}
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+ mm->tlb_flush_pending = true;
+
+ /*
+ * Guarantee that the tlb_flush_pending store does not leak into the
+ * critical section updating the page tables
+ */
+ smp_mb__before_spinlock();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
#endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 8e00f9f6f963..9e7db9e73cc1 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -43,6 +43,7 @@ extern int unregister_reboot_notifier(struct notifier_block *);
* Architecture-specific implementations of sys_reboot commands.
*/
+extern void migrate_to_reboot_cpu(void);
extern void machine_restart(char *cmd);
extern void machine_halt(void);
extern void machine_power_off(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index 728d5be9548c..5721f0e3f2da 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -537,6 +537,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
spin_lock_init(&mm->page_table_lock);
mm_init_aio(mm);
mm_init_owner(mm, p);
+ clear_tlb_flush_pending(mm);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index d0d8fca54065..9c970167e402 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1680,6 +1680,7 @@ int kernel_kexec(void)
{
kexec_in_progress = true;
kernel_restart_prepare(NULL);
+ migrate_to_reboot_cpu();
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f813b3474646..662c83fc16b7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_reboot_notifier);
-static void migrate_to_reboot_cpu(void)
+void migrate_to_reboot_cpu(void)
{
/* The boot cpu is always logical cpu 0 */
int cpu = reboot_cpu;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9030da7bcb15..c7395d97e4cb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1738,6 +1738,13 @@ void task_numa_work(struct callback_head *work)
(vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
continue;
+ /*
+ * Skip inaccessible VMAs to avoid any confusion between
+ * PROT_NONE and NUMA hinting ptes
+ */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+ continue;
+
do {
start = max(start, vma->vm_start);
end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
diff --git a/mm/Kconfig b/mm/Kconfig
index eb69f352401d..723bbe04a0b0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -543,7 +543,7 @@ config ZSWAP
config MEM_SOFT_DIRTY
bool "Track memory changes"
- depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
+ depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
select PROC_PAGE_MONITOR
help
This option enables memory changes tracking by introducing a
diff --git a/mm/compaction.c b/mm/compaction.c
index 805165bcd3dd..f58bcd016f43 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -134,6 +134,10 @@ static void update_pageblock_skip(struct compact_control *cc,
bool migrate_scanner)
{
struct zone *zone = cc->zone;
+
+ if (cc->ignore_skip_hint)
+ return;
+
if (!page)
return;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 33a5dc492810..7de1bf85f683 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -882,6 +882,10 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
ret = 0;
goto out_unlock;
}
+
+ /* mmap_sem prevents this happening but warn if that changes */
+ WARN_ON(pmd_trans_migrating(pmd));
+
if (unlikely(pmd_trans_splitting(pmd))) {
/* split huge page running from under us */
spin_unlock(src_ptl);
@@ -1243,6 +1247,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
return ERR_PTR(-EFAULT);
+ /* Full NUMA hinting faults to serialise migration in fault paths */
+ if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+ goto out;
+
page = pmd_page(*pmd);
VM_BUG_ON(!PageHead(page));
if (flags & FOLL_TOUCH) {
@@ -1295,6 +1303,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (unlikely(!pmd_same(pmd, *pmdp)))
goto out_unlock;
+ /*
+ * If there are potential migrations, wait for completion and retry
+ * without disrupting NUMA hinting information. Do not relock and
+ * check_same as the page may no longer be mapped.
+ */
+ if (unlikely(pmd_trans_migrating(*pmdp))) {
+ spin_unlock(ptl);
+ wait_migrate_huge_page(vma->anon_vma, pmdp);
+ goto out;
+ }
+
page = pmd_page(pmd);
BUG_ON(is_huge_zero_page(page));
page_nid = page_to_nid(page);
@@ -1323,23 +1342,22 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
/* If the page was locked, there are no parallel migrations */
if (page_locked)
goto clear_pmdnuma;
+ }
- /*
- * Otherwise wait for potential migrations and retry. We do
- * relock and check_same as the page may no longer be mapped.
- * As the fault is being retried, do not account for it.
- */
+ /* Migration could have started since the pmd_trans_migrating check */
+ if (!page_locked) {
spin_unlock(ptl);
wait_on_page_locked(page);
page_nid = -1;
goto out;
}
- /* Page is misplaced, serialise migrations and parallel THP splits */
+ /*
+ * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+ * to serialises splits
+ */
get_page(page);
spin_unlock(ptl);
- if (!page_locked)
- lock_page(page);
anon_vma = page_lock_anon_vma_read(page);
/* Confirm the PMD did not change while page_table_lock was released */
@@ -1351,6 +1369,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
goto out_unlock;
}
+ /* Bail if we fail to protect against THP splits for any reason */
+ if (unlikely(!anon_vma)) {
+ put_page(page);
+ page_nid = -1;
+ goto clear_pmdnuma;
+ }
+
/*
* Migrate the THP to the requested node, returns with page unlocked
* and pmd_numa cleared.
@@ -1517,6 +1542,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
ret = 1;
if (!prot_numa) {
entry = pmdp_get_and_clear(mm, addr, pmd);
+ if (pmd_numa(entry))
+ entry = pmd_mknonnuma(entry);
entry = pmd_modify(entry, newprot);
ret = HPAGE_PMD_NR;
BUG_ON(pmd_write(entry));
@@ -1531,7 +1558,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
*/
if (!is_huge_zero_page(page) &&
!pmd_numa(*pmd)) {
- entry = pmdp_get_and_clear(mm, addr, pmd);
+ entry = *pmd;
entry = pmd_mknuma(entry);
ret = HPAGE_PMD_NR;
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b7c171602ba1..db08af92c6fc 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1505,10 +1505,16 @@ static int soft_offline_huge_page(struct page *page, int flags)
if (ret > 0)
ret = -EIO;
} else {
- set_page_hwpoison_huge_page(hpage);
- dequeue_hwpoisoned_huge_page(hpage);
- atomic_long_add(1 << compound_order(hpage),
- &num_poisoned_pages);
+ /* overcommit hugetlb page will be freed to buddy */
+ if (PageHuge(page)) {
+ set_page_hwpoison_huge_page(hpage);
+ dequeue_hwpoisoned_huge_page(hpage);
+ atomic_long_add(1 << compound_order(hpage),
+ &num_poisoned_pages);
+ } else {
+ SetPageHWPoison(page);
+ atomic_long_inc(&num_poisoned_pages);
+ }
}
return ret;
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index eca4a3129129..0cd2c4d4e270 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1197,14 +1197,16 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int *
break;
vma = vma->vm_next;
}
+
+ if (PageHuge(page)) {
+ if (vma)
+ return alloc_huge_page_noerr(vma, address, 1);
+ else
+ return NULL;
+ }
/*
- * queue_pages_range() confirms that @page belongs to some vma,
- * so vma shouldn't be NULL.
+ * if !vma, alloc_page_vma() will use task or system default policy
*/
- BUG_ON(!vma);
-
- if (PageHuge(page))
- return alloc_huge_page_noerr(vma, address, 1);
return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
}
#else
@@ -1318,7 +1320,7 @@ static long do_mbind(unsigned long start, unsigned long len,
if (nr_failed && (flags & MPOL_MF_STRICT))
err = -EIO;
} else
- putback_lru_pages(&pagelist);
+ putback_movable_pages(&pagelist);
up_write(&mm->mmap_sem);
mpol_out:
diff --git a/mm/migrate.c b/mm/migrate.c
index bb940045fe85..e9b710201335 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,6 +36,7 @@
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
#include <linux/balloon_compaction.h>
+#include <linux/mmu_notifier.h>
#include <asm/tlbflush.h>
@@ -1654,6 +1655,18 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
return 1;
}
+bool pmd_trans_migrating(pmd_t pmd)
+{
+ struct page *page = pmd_page(pmd);
+ return PageLocked(page);
+}
+
+void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+ struct page *page = pmd_page(*pmd);
+ wait_on_page_locked(page);
+}
+
/*
* Attempt to migrate a misplaced page to the specified destination
* node. Caller is expected to have an elevated reference count on
@@ -1716,12 +1729,14 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
struct page *page, int node)
{
spinlock_t *ptl;
- unsigned long haddr = address & HPAGE_PMD_MASK;
pg_data_t *pgdat = NODE_DATA(node);
int isolated = 0;
struct page *new_page = NULL;
struct mem_cgroup *memcg = NULL;
int page_lru = page_is_file_cache(page);
+ unsigned long mmun_start = address & HPAGE_PMD_MASK;
+ unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
+ pmd_t orig_entry;
/*
* Rate-limit the amount of data that is being migrated to a node.
@@ -1744,6 +1759,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
goto out_fail;
}
+ if (mm_tlb_flush_pending(mm))
+ flush_tlb_range(vma, mmun_start, mmun_end);
+
/* Prepare a page as a migration target */
__set_page_locked(new_page);
SetPageSwapBacked(new_page);
@@ -1755,9 +1773,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
WARN_ON(PageLRU(new_page));
/* Recheck the target PMD */
+ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
ptl = pmd_lock(mm, pmd);
- if (unlikely(!pmd_same(*pmd, entry))) {
+ if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
+fail_putback:
spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
/* Reverse changes made by migrate_page_copy() */
if (TestClearPageActive(new_page))
@@ -1774,7 +1795,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
putback_lru_page(page);
mod_zone_page_state(page_zone(page),
NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
- goto out_fail;
+
+ goto out_unlock;
}
/*
@@ -1786,16 +1808,35 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
*/
mem_cgroup_prepare_migration(page, new_page, &memcg);
+ orig_entry = *pmd;
entry = mk_pmd(new_page, vma->vm_page_prot);
- entry = pmd_mknonnuma(entry);
- entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
entry = pmd_mkhuge(entry);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
- pmdp_clear_flush(vma, haddr, pmd);
- set_pmd_at(mm, haddr, pmd, entry);
- page_add_new_anon_rmap(new_page, vma, haddr);
+ /*
+ * Clear the old entry under pagetable lock and establish the new PTE.
+ * Any parallel GUP will either observe the old page blocking on the
+ * page lock, block on the page table lock or observe the new page.
+ * The SetPageUptodate on the new page and page_add_new_anon_rmap
+ * guarantee the copy is visible before the pagetable update.
+ */
+ flush_cache_range(vma, mmun_start, mmun_end);
+ page_add_new_anon_rmap(new_page, vma, mmun_start);
+ pmdp_clear_flush(vma, mmun_start, pmd);
+ set_pmd_at(mm, mmun_start, pmd, entry);
+ flush_tlb_range(vma, mmun_start, mmun_end);
update_mmu_cache_pmd(vma, address, &entry);
+
+ if (page_count(page) != 2) {
+ set_pmd_at(mm, mmun_start, pmd, orig_entry);
+ flush_tlb_range(vma, mmun_start, mmun_end);
+ update_mmu_cache_pmd(vma, address, &entry);
+ page_remove_rmap(new_page);
+ goto fail_putback;
+ }
+
page_remove_rmap(page);
+
/*
* Finish the charge transaction under the page table lock to
* prevent split_huge_page() from dividing up the charge
@@ -1803,6 +1844,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
*/
mem_cgroup_end_migration(memcg, page, new_page, true);
spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(new_page);
unlock_page(page);
@@ -1820,10 +1862,15 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
out_fail:
count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
out_dropref:
- entry = pmd_mknonnuma(entry);
- set_pmd_at(mm, haddr, pmd, entry);
- update_mmu_cache_pmd(vma, address, &entry);
+ ptl = pmd_lock(mm, pmd);
+ if (pmd_same(*pmd, entry)) {
+ entry = pmd_mknonnuma(entry);
+ set_pmd_at(mm, mmun_start, pmd, entry);
+ update_mmu_cache_pmd(vma, address, &entry);
+ }
+ spin_unlock(ptl);
+out_unlock:
unlock_page(page);
put_page(page);
return 0;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 26667971c824..bb53a6591aea 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -52,17 +52,21 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
pte_t ptent;
bool updated = false;
- ptent = ptep_modify_prot_start(mm, addr, pte);
if (!prot_numa) {
+ ptent = ptep_modify_prot_start(mm, addr, pte);
+ if (pte_numa(ptent))
+ ptent = pte_mknonnuma(ptent);
ptent = pte_modify(ptent, newprot);
updated = true;
} else {
struct page *page;
+ ptent = *pte;
page = vm_normal_page(vma, addr, oldpte);
if (page) {
if (!pte_numa(oldpte)) {
ptent = pte_mknuma(ptent);
+ set_pte_at(mm, addr, pte, ptent);
updated = true;
}
}
@@ -79,7 +83,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
if (updated)
pages++;
- ptep_modify_prot_commit(mm, addr, pte, ptent);
+
+ /* Only !prot_numa always clears the pte */
+ if (!prot_numa)
+ ptep_modify_prot_commit(mm, addr, pte, ptent);
} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
@@ -181,6 +188,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
+ set_tlb_flush_pending(mm);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
@@ -192,6 +200,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
/* Only flush the TLB if we actually modified any entries: */
if (pages)
flush_tlb_range(vma, start, end);
+ clear_tlb_flush_pending(mm);
return pages;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 580a5f075ed0..f861d0257e90 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1920,7 +1920,8 @@ zonelist_scan:
* back to remote zones that do not partake in the
* fairness round-robin cycle of this zonelist.
*/
- if (alloc_flags & ALLOC_WMARK_LOW) {
+ if ((alloc_flags & ALLOC_WMARK_LOW) &&
+ (gfp_mask & GFP_MOVABLE_MASK)) {
if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
continue;
if (zone_reclaim_mode &&
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index cbb38545d9d6..a8b919925934 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -110,9 +110,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep)
{
+ struct mm_struct *mm = (vma)->vm_mm;
pte_t pte;
- pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
- if (pte_accessible(pte))
+ pte = ptep_get_and_clear(mm, address, ptep);
+ if (pte_accessible(mm, pte))
flush_tlb_page(vma, address);
return pte;
}
@@ -191,6 +192,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
+ pmd_t entry = *pmdp;
+ if (pmd_numa(entry))
+ entry = pmd_mknonnuma(entry);
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 55c8b8dc9ffb..068522d8502a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -600,7 +600,11 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
spinlock_t *ptl;
if (unlikely(PageHuge(page))) {
+ /* when pud is not present, pte will be NULL */
pte = huge_pte_offset(mm, address);
+ if (!pte)
+ return NULL;
+
ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
goto check;
}