summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/cma_debug.c2
-rw-r--r--mm/early_ioremap.c28
-rw-r--r--mm/filemap.c22
-rw-r--r--mm/huge_memory.c42
-rw-r--r--mm/kasan/kasan.c4
-rw-r--r--mm/madvise.c8
-rw-r--r--mm/memblock.c38
-rw-r--r--mm/memcontrol.c43
-rw-r--r--mm/memory-failure.c2
-rw-r--r--mm/memory.c62
-rw-r--r--mm/mempolicy.c5
-rw-r--r--mm/migrate.c11
-rw-r--r--mm/mmu_notifier.c14
-rw-r--r--mm/nobootmem.c16
-rw-r--r--mm/page-writeback.c15
-rw-r--r--mm/page_alloc.c82
-rw-r--r--mm/rmap.c77
-rw-r--r--mm/shmem.c4
-rw-r--r--mm/slab.h6
-rw-r--r--mm/slob.c6
-rw-r--r--mm/slub.c3
-rw-r--r--mm/vmalloc.c13
-rw-r--r--mm/vmscan.c13
23 files changed, 335 insertions, 181 deletions
diff --git a/mm/cma_debug.c b/mm/cma_debug.c
index 595b757bef72..c03ccbc405a0 100644
--- a/mm/cma_debug.c
+++ b/mm/cma_debug.c
@@ -167,7 +167,7 @@ static void cma_debugfs_add_one(struct cma *cma, int idx)
char name[16];
int u32s;
- sprintf(name, "cma-%s", cma->name);
+ scnprintf(name, sizeof(name), "cma-%s", cma->name);
tmp = debugfs_create_dir(name, cma_debugfs_root);
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 6d5717bd7197..b1dd4a948fc0 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -30,6 +30,13 @@ early_param("early_ioremap_debug", early_ioremap_debug_setup);
static int after_paging_init __initdata;
+pgprot_t __init __weak early_memremap_pgprot_adjust(resource_size_t phys_addr,
+ unsigned long size,
+ pgprot_t prot)
+{
+ return prot;
+}
+
void __init __weak early_ioremap_shutdown(void)
{
}
@@ -215,14 +222,29 @@ early_ioremap(resource_size_t phys_addr, unsigned long size)
void __init *
early_memremap(resource_size_t phys_addr, unsigned long size)
{
- return (__force void *)__early_ioremap(phys_addr, size,
- FIXMAP_PAGE_NORMAL);
+ pgprot_t prot = early_memremap_pgprot_adjust(phys_addr, size,
+ FIXMAP_PAGE_NORMAL);
+
+ return (__force void *)__early_ioremap(phys_addr, size, prot);
}
#ifdef FIXMAP_PAGE_RO
void __init *
early_memremap_ro(resource_size_t phys_addr, unsigned long size)
{
- return (__force void *)__early_ioremap(phys_addr, size, FIXMAP_PAGE_RO);
+ pgprot_t prot = early_memremap_pgprot_adjust(phys_addr, size,
+ FIXMAP_PAGE_RO);
+
+ return (__force void *)__early_ioremap(phys_addr, size, prot);
+}
+#endif
+
+#ifdef CONFIG_ARCH_USE_MEMREMAP_PROT
+void __init *
+early_memremap_prot(resource_size_t phys_addr, unsigned long size,
+ unsigned long prot_val)
+{
+ return (__force void *)__early_ioremap(phys_addr, size,
+ __pgprot(prot_val));
}
#endif
diff --git a/mm/filemap.c b/mm/filemap.c
index a49702445ce0..65b4b6e7f7bd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -885,6 +885,7 @@ void __init pagecache_init(void)
page_writeback_init();
}
+/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
struct wait_page_key {
struct page *page;
int bit_nr;
@@ -909,8 +910,10 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
if (wait_page->bit_nr != key->bit_nr)
return 0;
+
+ /* Stop walking if it's locked */
if (test_bit(key->bit_nr, &key->page->flags))
- return 0;
+ return -1;
return autoremove_wake_function(wait, mode, sync, key);
}
@@ -964,6 +967,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
int ret = 0;
init_wait(wait);
+ wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
wait->func = wake_page_function;
wait_page.page = page;
wait_page.bit_nr = bit_nr;
@@ -972,10 +976,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
spin_lock_irq(&q->lock);
if (likely(list_empty(&wait->entry))) {
- if (lock)
- __add_wait_queue_entry_tail_exclusive(q, wait);
- else
- __add_wait_queue(q, wait);
+ __add_wait_queue_entry_tail(q, wait);
SetPageWaiters(page);
}
@@ -985,10 +986,6 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
if (likely(test_bit(bit_nr, &page->flags))) {
io_schedule();
- if (unlikely(signal_pending_state(state, current))) {
- ret = -EINTR;
- break;
- }
}
if (lock) {
@@ -998,6 +995,11 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
if (!test_bit(bit_nr, &page->flags))
break;
}
+
+ if (unlikely(signal_pending_state(state, current))) {
+ ret = -EINTR;
+ break;
+ }
}
finish_wait(q, wait);
@@ -1039,7 +1041,7 @@ void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
- __add_wait_queue(q, waiter);
+ __add_wait_queue_entry_tail(q, waiter);
SetPageWaiters(page);
spin_unlock_irqrestore(&q->lock, flags);
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 216114f6ef0b..3644ff918434 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -32,6 +32,7 @@
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
+#include <linux/oom.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -550,6 +551,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
struct mem_cgroup *memcg;
pgtable_t pgtable;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+ int ret = 0;
VM_BUG_ON_PAGE(!PageCompound(page), page);
@@ -561,9 +563,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
pgtable = pte_alloc_one(vma->vm_mm, haddr);
if (unlikely(!pgtable)) {
- mem_cgroup_cancel_charge(page, memcg, true);
- put_page(page);
- return VM_FAULT_OOM;
+ ret = VM_FAULT_OOM;
+ goto release;
}
clear_huge_page(page, haddr, HPAGE_PMD_NR);
@@ -576,13 +577,14 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_none(*vmf->pmd))) {
- spin_unlock(vmf->ptl);
- mem_cgroup_cancel_charge(page, memcg, true);
- put_page(page);
- pte_free(vma->vm_mm, pgtable);
+ goto unlock_release;
} else {
pmd_t entry;
+ ret = check_stable_address_space(vma->vm_mm);
+ if (ret)
+ goto unlock_release;
+
/* Deliver the page fault to userland */
if (userfaultfd_missing(vma)) {
int ret;
@@ -610,6 +612,15 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
}
return 0;
+unlock_release:
+ spin_unlock(vmf->ptl);
+release:
+ if (pgtable)
+ pte_free(vma->vm_mm, pgtable);
+ mem_cgroup_cancel_charge(page, memcg, true);
+ put_page(page);
+ return ret;
+
}
/*
@@ -688,7 +699,10 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf)
ret = 0;
set = false;
if (pmd_none(*vmf->pmd)) {
- if (userfaultfd_missing(vma)) {
+ ret = check_stable_address_space(vma->vm_mm);
+ if (ret) {
+ spin_unlock(vmf->ptl);
+ } else if (userfaultfd_missing(vma)) {
spin_unlock(vmf->ptl);
ret = handle_userfault(vmf, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
@@ -1496,8 +1510,15 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
}
/*
- * The page_table_lock above provides a memory barrier
- * with change_protection_range.
+ * Since we took the NUMA fault, we must have observed the !accessible
+ * bit. Make sure all other CPUs agree with that, to avoid them
+ * modifying the page we're about to migrate.
+ *
+ * Must be done under PTL such that we'll observe the relevant
+ * inc_tlb_flush_pending().
+ *
+ * We are not sure a pending tlb flush here is for a huge page
+ * mapping or not. Hence use the tlb range variant
*/
if (mm_tlb_flush_pending(vma->vm_mm))
flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
@@ -1507,6 +1528,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
* and access rights restored.
*/
spin_unlock(vmf->ptl);
+
migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
vmf->pmd, pmd, vmf->address, page, target_nid);
if (migrated) {
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index ca11bc4ce205..6f319fb81718 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -267,13 +267,13 @@ static void check_memory_region(unsigned long addr,
check_memory_region_inline(addr, size, write, ret_ip);
}
-void kasan_check_read(const void *p, unsigned int size)
+void kasan_check_read(const volatile void *p, unsigned int size)
{
check_memory_region((unsigned long)p, size, false, _RET_IP_);
}
EXPORT_SYMBOL(kasan_check_read);
-void kasan_check_write(const void *p, unsigned int size)
+void kasan_check_write(const volatile void *p, unsigned int size)
{
check_memory_region((unsigned long)p, size, true, _RET_IP_);
}
diff --git a/mm/madvise.c b/mm/madvise.c
index 47d8d8a25eae..4d7d1e5ddba9 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -368,8 +368,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
pte_offset_map_lock(mm, pmd, addr, &ptl);
goto out;
}
- put_page(page);
unlock_page(page);
+ put_page(page);
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
pte--;
addr -= PAGE_SIZE;
@@ -613,6 +613,7 @@ static int madvise_inject_error(int behavior,
unsigned long start, unsigned long end)
{
struct page *page;
+ struct zone *zone;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -646,6 +647,11 @@ static int madvise_inject_error(int behavior,
if (ret)
return ret;
}
+
+ /* Ensure that all poisoned pages are removed from per-cpu lists */
+ for_each_populated_zone(zone)
+ drain_all_pages(zone);
+
return 0;
}
#endif
diff --git a/mm/memblock.c b/mm/memblock.c
index 2cb25fe4452c..91205780e6b1 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -285,31 +285,27 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
}
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
-
-phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
- phys_addr_t *addr)
-{
- if (memblock.reserved.regions == memblock_reserved_init_regions)
- return 0;
-
- *addr = __pa(memblock.reserved.regions);
-
- return PAGE_ALIGN(sizeof(struct memblock_region) *
- memblock.reserved.max);
-}
-
-phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info(
- phys_addr_t *addr)
+/**
+ * Discard memory and reserved arrays if they were allocated
+ */
+void __init memblock_discard(void)
{
- if (memblock.memory.regions == memblock_memory_init_regions)
- return 0;
+ phys_addr_t addr, size;
- *addr = __pa(memblock.memory.regions);
+ if (memblock.reserved.regions != memblock_reserved_init_regions) {
+ addr = __pa(memblock.reserved.regions);
+ size = PAGE_ALIGN(sizeof(struct memblock_region) *
+ memblock.reserved.max);
+ __memblock_free_late(addr, size);
+ }
- return PAGE_ALIGN(sizeof(struct memblock_region) *
- memblock.memory.max);
+ if (memblock.memory.regions != memblock_memory_init_regions) {
+ addr = __pa(memblock.memory.regions);
+ size = PAGE_ALIGN(sizeof(struct memblock_region) *
+ memblock.memory.max);
+ __memblock_free_late(addr, size);
+ }
}
-
#endif
/**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3df3c04d73ab..e09741af816f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1611,9 +1611,13 @@ cleanup:
* @page: the page
*
* This function protects unlocked LRU pages from being moved to
- * another cgroup and stabilizes their page->mem_cgroup binding.
+ * another cgroup.
+ *
+ * It ensures lifetime of the returned memcg. Caller is responsible
+ * for the lifetime of the page; __unlock_page_memcg() is available
+ * when @page might get freed inside the locked section.
*/
-void lock_page_memcg(struct page *page)
+struct mem_cgroup *lock_page_memcg(struct page *page)
{
struct mem_cgroup *memcg;
unsigned long flags;
@@ -1622,18 +1626,24 @@ void lock_page_memcg(struct page *page)
* The RCU lock is held throughout the transaction. The fast
* path can get away without acquiring the memcg->move_lock
* because page moving starts with an RCU grace period.
- */
+ *
+ * The RCU lock also protects the memcg from being freed when
+ * the page state that is going to change is the only thing
+ * preventing the page itself from being freed. E.g. writeback
+ * doesn't hold a page reference and relies on PG_writeback to
+ * keep off truncation, migration and so forth.
+ */
rcu_read_lock();
if (mem_cgroup_disabled())
- return;
+ return NULL;
again:
memcg = page->mem_cgroup;
if (unlikely(!memcg))
- return;
+ return NULL;
if (atomic_read(&memcg->moving_account) <= 0)
- return;
+ return memcg;
spin_lock_irqsave(&memcg->move_lock, flags);
if (memcg != page->mem_cgroup) {
@@ -1649,18 +1659,18 @@ again:
memcg->move_lock_task = current;
memcg->move_lock_flags = flags;
- return;
+ return memcg;
}
EXPORT_SYMBOL(lock_page_memcg);
/**
- * unlock_page_memcg - unlock a page->mem_cgroup binding
- * @page: the page
+ * __unlock_page_memcg - unlock and unpin a memcg
+ * @memcg: the memcg
+ *
+ * Unlock and unpin a memcg returned by lock_page_memcg().
*/
-void unlock_page_memcg(struct page *page)
+void __unlock_page_memcg(struct mem_cgroup *memcg)
{
- struct mem_cgroup *memcg = page->mem_cgroup;
-
if (memcg && memcg->move_lock_task == current) {
unsigned long flags = memcg->move_lock_flags;
@@ -1672,6 +1682,15 @@ void unlock_page_memcg(struct page *page)
rcu_read_unlock();
}
+
+/**
+ * unlock_page_memcg - unlock a page->mem_cgroup binding
+ * @page: the page
+ */
+void unlock_page_memcg(struct page *page)
+{
+ __unlock_page_memcg(page->mem_cgroup);
+}
EXPORT_SYMBOL(unlock_page_memcg);
/*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 1cd3b3569af8..88366626c0b7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1146,6 +1146,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
return 0;
}
+ arch_unmap_kpfn(pfn);
+
orig_head = hpage = compound_head(p);
num_poisoned_pages_inc();
diff --git a/mm/memory.c b/mm/memory.c
index e158f7ac6730..56e48e4593cb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -68,6 +68,7 @@
#include <linux/debugfs.h>
#include <linux/userfaultfd_k.h>
#include <linux/dax.h>
+#include <linux/oom.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
@@ -2893,6 +2894,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
struct vm_area_struct *vma = vmf->vma;
struct mem_cgroup *memcg;
struct page *page;
+ int ret = 0;
pte_t entry;
/* File mapping without ->vm_ops ? */
@@ -2925,6 +2927,9 @@ static int do_anonymous_page(struct vm_fault *vmf)
vmf->address, &vmf->ptl);
if (!pte_none(*vmf->pte))
goto unlock;
+ ret = check_stable_address_space(vma->vm_mm);
+ if (ret)
+ goto unlock;
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2959,6 +2964,10 @@ static int do_anonymous_page(struct vm_fault *vmf)
if (!pte_none(*vmf->pte))
goto release;
+ ret = check_stable_address_space(vma->vm_mm);
+ if (ret)
+ goto release;
+
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2978,7 +2987,7 @@ setpte:
update_mmu_cache(vma, vmf->address, vmf->pte);
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
- return 0;
+ return ret;
release:
mem_cgroup_cancel_charge(page, memcg, false);
put_page(page);
@@ -3252,7 +3261,7 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
int finish_fault(struct vm_fault *vmf)
{
struct page *page;
- int ret;
+ int ret = 0;
/* Did we COW the page? */
if ((vmf->flags & FAULT_FLAG_WRITE) &&
@@ -3260,7 +3269,15 @@ int finish_fault(struct vm_fault *vmf)
page = vmf->cow_page;
else
page = vmf->page;
- ret = alloc_set_pte(vmf, vmf->memcg, page);
+
+ /*
+ * check even for read faults because we might have lost our CoWed
+ * page
+ */
+ if (!(vmf->vma->vm_flags & VM_SHARED))
+ ret = check_stable_address_space(vmf->vma->vm_mm);
+ if (!ret)
+ ret = alloc_set_pte(vmf, vmf->memcg, page);
if (vmf->pte)
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
@@ -3900,19 +3917,6 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
mem_cgroup_oom_synchronize(false);
}
- /*
- * This mm has been already reaped by the oom reaper and so the
- * refault cannot be trusted in general. Anonymous refaults would
- * lose data and give a zero page instead e.g. This is especially
- * problem for use_mm() because regular tasks will just die and
- * the corrupted data will not be visible anywhere while kthread
- * will outlive the oom victim and potentially propagate the date
- * further.
- */
- if (unlikely((current->flags & PF_KTHREAD) && !(ret & VM_FAULT_ERROR)
- && test_bit(MMF_UNSTABLE, &vma->vm_mm->flags)))
- ret = VM_FAULT_SIGBUS;
-
return ret;
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
@@ -4004,7 +4008,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
#endif /* __PAGETABLE_PMD_FOLDED */
static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
- pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+ unsigned long *start, unsigned long *end,
+ pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
{
pgd_t *pgd;
p4d_t *p4d;
@@ -4031,17 +4036,29 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
if (!pmdpp)
goto out;
+ if (start && end) {
+ *start = address & PMD_MASK;
+ *end = *start + PMD_SIZE;
+ mmu_notifier_invalidate_range_start(mm, *start, *end);
+ }
*ptlp = pmd_lock(mm, pmd);
if (pmd_huge(*pmd)) {
*pmdpp = pmd;
return 0;
}
spin_unlock(*ptlp);
+ if (start && end)
+ mmu_notifier_invalidate_range_end(mm, *start, *end);
}
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
goto out;
+ if (start && end) {
+ *start = address & PAGE_MASK;
+ *end = *start + PAGE_SIZE;
+ mmu_notifier_invalidate_range_start(mm, *start, *end);
+ }
ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
if (!pte_present(*ptep))
goto unlock;
@@ -4049,6 +4066,8 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
return 0;
unlock:
pte_unmap_unlock(ptep, *ptlp);
+ if (start && end)
+ mmu_notifier_invalidate_range_end(mm, *start, *end);
out:
return -EINVAL;
}
@@ -4060,20 +4079,21 @@ static inline int follow_pte(struct mm_struct *mm, unsigned long address,
/* (void) is needed to make gcc happy */
(void) __cond_lock(*ptlp,
- !(res = __follow_pte_pmd(mm, address, ptepp, NULL,
- ptlp)));
+ !(res = __follow_pte_pmd(mm, address, NULL, NULL,
+ ptepp, NULL, ptlp)));
return res;
}
int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+ unsigned long *start, unsigned long *end,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
{
int res;
/* (void) is needed to make gcc happy */
(void) __cond_lock(*ptlp,
- !(res = __follow_pte_pmd(mm, address, ptepp, pmdpp,
- ptlp)));
+ !(res = __follow_pte_pmd(mm, address, start, end,
+ ptepp, pmdpp, ptlp)));
return res;
}
EXPORT_SYMBOL(follow_pte_pmd);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d911fa5cb2a7..618ab125228b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -861,11 +861,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
*policy |= (pol->flags & MPOL_MODE_FLAGS);
}
- if (vma) {
- up_read(&current->mm->mmap_sem);
- vma = NULL;
- }
-
err = 0;
if (nmask) {
if (mpol_store_user_nodemask(pol)) {
diff --git a/mm/migrate.c b/mm/migrate.c
index d68a41da6abb..e84eeb4e4356 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -41,6 +41,7 @@
#include <linux/page_idle.h>
#include <linux/page_owner.h>
#include <linux/sched/mm.h>
+#include <linux/ptrace.h>
#include <asm/tlbflush.h>
@@ -1652,7 +1653,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
const int __user *, nodes,
int __user *, status, int, flags)
{
- const struct cred *cred = current_cred(), *tcred;
struct task_struct *task;
struct mm_struct *mm;
int err;
@@ -1676,14 +1676,9 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
/*
* Check if this process has the right to modify the specified
- * process. The right exists if the process has administrative
- * capabilities, superuser privileges or the same
- * userid as the target process.
+ * process. Use the regular "ptrace_may_access()" checks.
*/
- tcred = __task_cred(task);
- if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) &&
- !capable(CAP_SYS_NICE)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
rcu_read_unlock();
err = -EPERM;
goto out;
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 54ca54562928..314285284e6e 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -174,20 +174,6 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
srcu_read_unlock(&srcu, id);
}
-void __mmu_notifier_invalidate_page(struct mm_struct *mm,
- unsigned long address)
-{
- struct mmu_notifier *mn;
- int id;
-
- id = srcu_read_lock(&srcu);
- hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
- if (mn->ops->invalidate_page)
- mn->ops->invalidate_page(mn, mm, address);
- }
- srcu_read_unlock(&srcu, id);
-}
-
void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 36454d0f96ee..3637809a18d0 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -146,22 +146,6 @@ static unsigned long __init free_low_memory_core_early(void)
NULL)
count += __free_memory_core(start, end);
-#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
- {
- phys_addr_t size;
-
- /* Free memblock.reserved array if it was allocated */
- size = get_allocated_memblock_reserved_regions_info(&start);
- if (size)
- count += __free_memory_core(start, start + size);
-
- /* Free memblock.memory array if it was allocated */
- size = get_allocated_memblock_memory_regions_info(&start);
- if (size)
- count += __free_memory_core(start, start + size);
- }
-#endif
-
return count;
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 96e93b214d31..bf050ab025b7 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2724,9 +2724,12 @@ EXPORT_SYMBOL(clear_page_dirty_for_io);
int test_clear_page_writeback(struct page *page)
{
struct address_space *mapping = page_mapping(page);
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
int ret;
- lock_page_memcg(page);
+ memcg = lock_page_memcg(page);
+ lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
if (mapping && mapping_use_writeback_tags(mapping)) {
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -2754,12 +2757,18 @@ int test_clear_page_writeback(struct page *page)
} else {
ret = TestClearPageWriteback(page);
}
+ /*
+ * NOTE: Page might be free now! Writeback doesn't hold a page
+ * reference on its own, it relies on truncation to wait for
+ * the clearing of PG_writeback. The below can only access
+ * page state that is static across allocation cycles.
+ */
if (ret) {
- dec_lruvec_page_state(page, NR_WRITEBACK);
+ dec_lruvec_state(lruvec, NR_WRITEBACK);
dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
inc_node_page_state(page, NR_WRITTEN);
}
- unlock_page_memcg(page);
+ __unlock_page_memcg(memcg);
return ret;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6d00f746c2fd..9327a940e373 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -66,6 +66,8 @@
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
+#include <linux/lockdep.h>
+#include <linux/nmi.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
@@ -1584,6 +1586,10 @@ void __init page_alloc_init_late(void)
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
#endif
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+ /* Discard memblock private memory */
+ memblock_discard();
+#endif
for_each_populated_zone(zone)
set_zone_contiguous(zone);
@@ -2531,9 +2537,14 @@ void drain_all_pages(struct zone *zone)
#ifdef CONFIG_HIBERNATION
+/*
+ * Touch the watchdog for every WD_PAGE_COUNT pages.
+ */
+#define WD_PAGE_COUNT (128*1024)
+
void mark_free_pages(struct zone *zone)
{
- unsigned long pfn, max_zone_pfn;
+ unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
unsigned long flags;
unsigned int order, t;
struct page *page;
@@ -2548,6 +2559,11 @@ void mark_free_pages(struct zone *zone)
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
+ if (!--page_count) {
+ touch_nmi_watchdog();
+ page_count = WD_PAGE_COUNT;
+ }
+
if (page_zone(page) != zone)
continue;
@@ -2561,8 +2577,13 @@ void mark_free_pages(struct zone *zone)
unsigned long i;
pfn = page_to_pfn(page);
- for (i = 0; i < (1UL << order); i++)
+ for (i = 0; i < (1UL << order); i++) {
+ if (!--page_count) {
+ touch_nmi_watchdog();
+ page_count = WD_PAGE_COUNT;
+ }
swsusp_set_page_free(pfn_to_page(pfn + i));
+ }
}
}
spin_unlock_irqrestore(&zone->lock, flags);
@@ -3271,10 +3292,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
/*
* Go through the zonelist yet one more time, keep very high watermark
* here, this is only to catch a parallel oom killing, we must fail if
- * we're still under heavy pressure.
+ * we're still under heavy pressure. But make sure that this reclaim
+ * attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY
+ * allocation which will never fail due to oom_lock already held.
*/
- page = get_page_from_freelist(gfp_mask | __GFP_HARDWALL, order,
- ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
+ page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) &
+ ~__GFP_DIRECT_RECLAIM, order,
+ ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
if (page)
goto out;
@@ -3490,6 +3514,47 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
}
#endif /* CONFIG_COMPACTION */
+#ifdef CONFIG_LOCKDEP
+struct lockdep_map __fs_reclaim_map =
+ STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
+
+static bool __need_fs_reclaim(gfp_t gfp_mask)
+{
+ gfp_mask = current_gfp_context(gfp_mask);
+
+ /* no reclaim without waiting on it */
+ if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
+ return false;
+
+ /* this guy won't enter reclaim */
+ if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+ return false;
+
+ /* We're only interested __GFP_FS allocations for now */
+ if (!(gfp_mask & __GFP_FS))
+ return false;
+
+ if (gfp_mask & __GFP_NOLOCKDEP)
+ return false;
+
+ return true;
+}
+
+void fs_reclaim_acquire(gfp_t gfp_mask)
+{
+ if (__need_fs_reclaim(gfp_mask))
+ lock_map_acquire(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
+
+void fs_reclaim_release(gfp_t gfp_mask)
+{
+ if (__need_fs_reclaim(gfp_mask))
+ lock_map_release(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_release);
+#endif
+
/* Perform direct synchronous page reclaim */
static int
__perform_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -3504,7 +3569,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
noreclaim_flag = memalloc_noreclaim_save();
- lockdep_set_current_reclaim_state(gfp_mask);
+ fs_reclaim_acquire(gfp_mask);
reclaim_state.reclaimed_slab = 0;
current->reclaim_state = &reclaim_state;
@@ -3512,7 +3577,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
ac->nodemask);
current->reclaim_state = NULL;
- lockdep_clear_current_reclaim_state();
+ fs_reclaim_release(gfp_mask);
memalloc_noreclaim_restore(noreclaim_flag);
cond_resched();
@@ -4041,7 +4106,8 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
*alloc_flags |= ALLOC_CPUSET;
}
- lockdep_trace_alloc(gfp_mask);
+ fs_reclaim_acquire(gfp_mask);
+ fs_reclaim_release(gfp_mask);
might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
diff --git a/mm/rmap.c b/mm/rmap.c
index c1286d47aa1f..c570f82e6827 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -887,11 +887,21 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
.address = address,
.flags = PVMW_SYNC,
};
+ unsigned long start = address, end;
int *cleaned = arg;
- bool invalidation_needed = false;
+
+ /*
+ * We have to assume the worse case ie pmd for invalidation. Note that
+ * the page can not be free from this function.
+ */
+ end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page)));
+ mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
while (page_vma_mapped_walk(&pvmw)) {
+ unsigned long cstart, cend;
int ret = 0;
+
+ cstart = address = pvmw.address;
if (pvmw.pte) {
pte_t entry;
pte_t *pte = pvmw.pte;
@@ -899,11 +909,12 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
if (!pte_dirty(*pte) && !pte_write(*pte))
continue;
- flush_cache_page(vma, pvmw.address, pte_pfn(*pte));
- entry = ptep_clear_flush(vma, pvmw.address, pte);
+ flush_cache_page(vma, address, pte_pfn(*pte));
+ entry = ptep_clear_flush(vma, address, pte);
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
- set_pte_at(vma->vm_mm, pvmw.address, pte, entry);
+ set_pte_at(vma->vm_mm, address, pte, entry);
+ cend = cstart + PAGE_SIZE;
ret = 1;
} else {
#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
@@ -913,11 +924,13 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
continue;
- flush_cache_page(vma, pvmw.address, page_to_pfn(page));
- entry = pmdp_huge_clear_flush(vma, pvmw.address, pmd);
+ flush_cache_page(vma, address, page_to_pfn(page));
+ entry = pmdp_huge_clear_flush(vma, address, pmd);
entry = pmd_wrprotect(entry);
entry = pmd_mkclean(entry);
- set_pmd_at(vma->vm_mm, pvmw.address, pmd, entry);
+ set_pmd_at(vma->vm_mm, address, pmd, entry);
+ cstart &= PMD_MASK;
+ cend = cstart + PMD_SIZE;
ret = 1;
#else
/* unexpected pmd-mapped page? */
@@ -926,15 +939,12 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
}
if (ret) {
+ mmu_notifier_invalidate_range(vma->vm_mm, cstart, cend);
(*cleaned)++;
- invalidation_needed = true;
}
}
- if (invalidation_needed) {
- mmu_notifier_invalidate_range(vma->vm_mm, address,
- address + (1UL << compound_order(page)));
- }
+ mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
return true;
}
@@ -1328,7 +1338,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
};
pte_t pteval;
struct page *subpage;
- bool ret = true, invalidation_needed = false;
+ bool ret = true;
+ unsigned long start = address, end;
enum ttu_flags flags = (enum ttu_flags)arg;
/* munlock has nothing to gain from examining un-locked vmas */
@@ -1340,6 +1351,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
flags & TTU_MIGRATION, page);
}
+ /*
+ * We have to assume the worse case ie pmd for invalidation. Note that
+ * the page can not be free in this function as call of try_to_unmap()
+ * must hold a reference on the page.
+ */
+ end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page)));
+ mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
+
while (page_vma_mapped_walk(&pvmw)) {
/*
* If the page is mlock()d, we cannot swap it out.
@@ -1368,9 +1387,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
VM_BUG_ON_PAGE(!pvmw.pte, page);
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+ address = pvmw.address;
+
if (!(flags & TTU_IGNORE_ACCESS)) {
- if (ptep_clear_flush_young_notify(vma, pvmw.address,
+ if (ptep_clear_flush_young_notify(vma, address,
pvmw.pte)) {
ret = false;
page_vma_mapped_walk_done(&pvmw);
@@ -1379,7 +1400,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
/* Nuke the page table entry. */
- flush_cache_page(vma, pvmw.address, pte_pfn(*pvmw.pte));
+ flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
if (should_defer_flush(mm, flags)) {
/*
* We clear the PTE but do not flush so potentially
@@ -1389,12 +1410,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* transition on a cached TLB entry is written through
* and traps if the PTE is unmapped.
*/
- pteval = ptep_get_and_clear(mm, pvmw.address,
- pvmw.pte);
+ pteval = ptep_get_and_clear(mm, address, pvmw.pte);
set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
} else {
- pteval = ptep_clear_flush(vma, pvmw.address, pvmw.pte);
+ pteval = ptep_clear_flush(vma, address, pvmw.pte);
}
/* Move the dirty bit to the page. Now the pte is gone. */
@@ -1409,12 +1429,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
if (PageHuge(page)) {
int nr = 1 << compound_order(page);
hugetlb_count_sub(nr, mm);
- set_huge_swap_pte_at(mm, pvmw.address,
+ set_huge_swap_pte_at(mm, address,
pvmw.pte, pteval,
vma_mmu_pagesize(vma));
} else {
dec_mm_counter(mm, mm_counter(page));
- set_pte_at(mm, pvmw.address, pvmw.pte, pteval);
+ set_pte_at(mm, address, pvmw.pte, pteval);
}
} else if (pte_unused(pteval)) {
@@ -1438,7 +1458,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
- set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
+ set_pte_at(mm, address, pvmw.pte, swp_pte);
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(subpage) };
pte_t swp_pte;
@@ -1449,6 +1469,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) {
WARN_ON_ONCE(1);
ret = false;
+ /* We have to invalidate as we cleared the pte */
page_vma_mapped_walk_done(&pvmw);
break;
}
@@ -1464,7 +1485,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* If the page was redirtied, it cannot be
* discarded. Remap the page to page table.
*/
- set_pte_at(mm, pvmw.address, pvmw.pte, pteval);
+ set_pte_at(mm, address, pvmw.pte, pteval);
SetPageSwapBacked(page);
ret = false;
page_vma_mapped_walk_done(&pvmw);
@@ -1472,7 +1493,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
if (swap_duplicate(entry) < 0) {
- set_pte_at(mm, pvmw.address, pvmw.pte, pteval);
+ set_pte_at(mm, address, pvmw.pte, pteval);
ret = false;
page_vma_mapped_walk_done(&pvmw);
break;
@@ -1488,18 +1509,18 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
- set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
+ set_pte_at(mm, address, pvmw.pte, swp_pte);
} else
dec_mm_counter(mm, mm_counter_file(page));
discard:
page_remove_rmap(subpage, PageHuge(page));
put_page(page);
- invalidation_needed = true;
+ mmu_notifier_invalidate_range(mm, address,
+ address + PAGE_SIZE);
}
- if (invalidation_needed)
- mmu_notifier_invalidate_range(mm, address,
- address + (1UL << compound_order(page)));
+ mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
+
return ret;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 6540e5982444..fbcb3c96a186 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3967,7 +3967,7 @@ int __init shmem_init(void)
}
#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
- if (has_transparent_hugepage() && shmem_huge < SHMEM_HUGE_DENY)
+ if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY)
SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
else
shmem_huge = 0; /* just in case it was patched */
@@ -4028,7 +4028,7 @@ static ssize_t shmem_enabled_store(struct kobject *kobj,
return -EINVAL;
shmem_huge = huge;
- if (shmem_huge < SHMEM_HUGE_DENY)
+ if (shmem_huge > SHMEM_HUGE_DENY)
SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
return count;
}
diff --git a/mm/slab.h b/mm/slab.h
index 6885e1192ec5..073362816acc 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -43,6 +43,7 @@ struct kmem_cache {
#include <linux/kasan.h>
#include <linux/kmemleak.h>
#include <linux/random.h>
+#include <linux/sched/mm.h>
/*
* State of the slab allocator.
@@ -412,7 +413,10 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
gfp_t flags)
{
flags &= gfp_allowed_mask;
- lockdep_trace_alloc(flags);
+
+ fs_reclaim_acquire(flags);
+ fs_reclaim_release(flags);
+
might_sleep_if(gfpflags_allow_blocking(flags));
if (should_failslab(s, flags))
diff --git a/mm/slob.c b/mm/slob.c
index 1bae78d71096..a8bd6fa11a66 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -432,7 +432,8 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
gfp &= gfp_allowed_mask;
- lockdep_trace_alloc(gfp);
+ fs_reclaim_acquire(gfp);
+ fs_reclaim_release(gfp);
if (size < PAGE_SIZE - align) {
if (!size)
@@ -538,7 +539,8 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
flags &= gfp_allowed_mask;
- lockdep_trace_alloc(flags);
+ fs_reclaim_acquire(flags);
+ fs_reclaim_release(flags);
if (c->size < PAGE_SIZE) {
b = slob_alloc(c->size, flags, c->align, node);
diff --git a/mm/slub.c b/mm/slub.c
index 1d3f9835f4ea..e8b4e31162ca 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5642,13 +5642,14 @@ static void sysfs_slab_remove_workfn(struct work_struct *work)
* A cache is never shut down before deactivation is
* complete, so no need to worry about synchronization.
*/
- return;
+ goto out;
#ifdef CONFIG_MEMCG
kset_unregister(s->memcg_kset);
#endif
kobject_uevent(&s->kobj, KOBJ_REMOVE);
kobject_del(&s->kobj);
+out:
kobject_put(&s->kobj);
}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 8698c1c86c4d..a47e3894c775 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1671,7 +1671,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
struct page **pages;
unsigned int nr_pages, array_size, i;
const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
- const gfp_t alloc_mask = gfp_mask | __GFP_HIGHMEM | __GFP_NOWARN;
+ const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
+ const gfp_t highmem_mask = (gfp_mask & (GFP_DMA | GFP_DMA32)) ?
+ 0 :
+ __GFP_HIGHMEM;
nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
array_size = (nr_pages * sizeof(struct page *));
@@ -1679,7 +1682,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
area->nr_pages = nr_pages;
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
- pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM,
+ pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask,
PAGE_KERNEL, node, area->caller);
} else {
pages = kmalloc_node(array_size, nested_gfp, node);
@@ -1700,9 +1703,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
}
if (node == NUMA_NO_NODE)
- page = alloc_page(alloc_mask);
+ page = alloc_page(alloc_mask|highmem_mask);
else
- page = alloc_pages_node(node, alloc_mask, 0);
+ page = alloc_pages_node(node, alloc_mask|highmem_mask, 0);
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in __vunmap() */
@@ -1710,7 +1713,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
goto fail;
}
area->pages[i] = page;
- if (gfpflags_allow_blocking(gfp_mask))
+ if (gfpflags_allow_blocking(gfp_mask|highmem_mask))
cond_resched();
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a1af041930a6..f957afe900ec 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3525,8 +3525,6 @@ static int kswapd(void *p)
};
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
- lockdep_set_current_reclaim_state(GFP_KERNEL);
-
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask);
current->reclaim_state = &reclaim_state;
@@ -3585,14 +3583,15 @@ kswapd_try_sleep:
*/
trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx,
alloc_order);
+ fs_reclaim_acquire(GFP_KERNEL);
reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
+ fs_reclaim_release(GFP_KERNEL);
if (reclaim_order < alloc_order)
goto kswapd_try_sleep;
}
tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
current->reclaim_state = NULL;
- lockdep_clear_current_reclaim_state();
return 0;
}
@@ -3655,14 +3654,14 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
unsigned int noreclaim_flag;
noreclaim_flag = memalloc_noreclaim_save();
- lockdep_set_current_reclaim_state(sc.gfp_mask);
+ fs_reclaim_acquire(sc.gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
p->reclaim_state = NULL;
- lockdep_clear_current_reclaim_state();
+ fs_reclaim_release(sc.gfp_mask);
memalloc_noreclaim_restore(noreclaim_flag);
return nr_reclaimed;
@@ -3847,7 +3846,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
*/
noreclaim_flag = memalloc_noreclaim_save();
p->flags |= PF_SWAPWRITE;
- lockdep_set_current_reclaim_state(sc.gfp_mask);
+ fs_reclaim_acquire(sc.gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
@@ -3862,9 +3861,9 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
}
p->reclaim_state = NULL;
+ fs_reclaim_release(gfp_mask);
current->flags &= ~PF_SWAPWRITE;
memalloc_noreclaim_restore(noreclaim_flag);
- lockdep_clear_current_reclaim_state();
return sc.nr_reclaimed >= nr_pages;
}
OpenPOWER on IntegriCloud