summaryrefslogtreecommitdiff
path: root/mm/madvise.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/madvise.c')
-rw-r--r--mm/madvise.c101
1 files changed, 77 insertions, 24 deletions
diff --git a/mm/madvise.c b/mm/madvise.c
index b17f684322ad..8433ac9b27e0 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -48,6 +48,11 @@ struct madvise_walk_private {
bool pageout;
};
+struct madvise_behavior {
+ int behavior;
+ struct mmu_gather *tlb;
+};
+
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
* take mmap_lock for writing. Others, which simply traverse vmas, need
@@ -794,12 +799,13 @@ static const struct mm_walk_ops madvise_free_walk_ops = {
.walk_lock = PGWALK_RDLOCK,
};
-static int madvise_free_single_vma(struct vm_area_struct *vma,
+static int madvise_free_single_vma(struct madvise_behavior *madv_behavior,
+ struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_notifier_range range;
- struct mmu_gather tlb;
+ struct mmu_gather *tlb = madv_behavior->tlb;
/* MADV_FREE works for only anon vma at the moment */
if (!vma_is_anonymous(vma))
@@ -815,17 +821,14 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
range.start, range.end);
lru_add_drain();
- tlb_gather_mmu(&tlb, mm);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(&range);
- tlb_start_vma(&tlb, vma);
+ tlb_start_vma(tlb, vma);
walk_page_range(vma->vm_mm, range.start, range.end,
- &madvise_free_walk_ops, &tlb);
- tlb_end_vma(&tlb, vma);
+ &madvise_free_walk_ops, tlb);
+ tlb_end_vma(tlb, vma);
mmu_notifier_invalidate_range_end(&range);
- tlb_finish_mmu(&tlb);
-
return 0;
}
@@ -848,7 +851,8 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
* An interface that causes the system to free clean pages and flush
* dirty pages is already available as msync(MS_INVALIDATE).
*/
-static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
+static long madvise_dontneed_single_vma(struct madvise_behavior *madv_behavior,
+ struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct zap_details details = {
@@ -856,7 +860,8 @@ static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
.even_cows = true,
};
- zap_page_range_single(vma, start, end - start, &details);
+ zap_page_range_single_batched(
+ madv_behavior->tlb, vma, start, end - start, &details);
return 0;
}
@@ -893,8 +898,9 @@ static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,
static long madvise_dontneed_free(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end,
- int behavior)
+ struct madvise_behavior *madv_behavior)
{
+ int behavior = madv_behavior->behavior;
struct mm_struct *mm = vma->vm_mm;
*prev = vma;
@@ -946,9 +952,10 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
}
if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED)
- return madvise_dontneed_single_vma(vma, start, end);
+ return madvise_dontneed_single_vma(
+ madv_behavior, vma, start, end);
else if (behavior == MADV_FREE)
- return madvise_free_single_vma(vma, start, end);
+ return madvise_free_single_vma(madv_behavior, vma, start, end);
else
return -EINVAL;
}
@@ -1249,8 +1256,10 @@ static long madvise_guard_remove(struct vm_area_struct *vma,
static int madvise_vma_behavior(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end,
- unsigned long behavior)
+ void *behavior_arg)
{
+ struct madvise_behavior *arg = behavior_arg;
+ int behavior = arg->behavior;
int error;
struct anon_vma_name *anon_name;
unsigned long new_flags = vma->vm_flags;
@@ -1270,7 +1279,7 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
case MADV_FREE:
case MADV_DONTNEED:
case MADV_DONTNEED_LOCKED:
- return madvise_dontneed_free(vma, prev, start, end, behavior);
+ return madvise_dontneed_free(vma, prev, start, end, arg);
case MADV_NORMAL:
new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
break;
@@ -1487,10 +1496,10 @@ static bool process_madvise_remote_valid(int behavior)
*/
static
int madvise_walk_vmas(struct mm_struct *mm, unsigned long start,
- unsigned long end, unsigned long arg,
+ unsigned long end, void *arg,
int (*visit)(struct vm_area_struct *vma,
struct vm_area_struct **prev, unsigned long start,
- unsigned long end, unsigned long arg))
+ unsigned long end, void *arg))
{
struct vm_area_struct *vma;
struct vm_area_struct *prev;
@@ -1548,7 +1557,7 @@ int madvise_walk_vmas(struct mm_struct *mm, unsigned long start,
static int madvise_vma_anon_name(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end,
- unsigned long anon_name)
+ void *anon_name)
{
int error;
@@ -1557,7 +1566,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma,
return -EBADF;
error = madvise_update_vma(vma, prev, start, end, vma->vm_flags,
- (struct anon_vma_name *)anon_name);
+ anon_name);
/*
* madvise() returns EAGAIN if kernel resources, such as
@@ -1589,7 +1598,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
if (end == start)
return 0;
- return madvise_walk_vmas(mm, start, end, (unsigned long)anon_name,
+ return madvise_walk_vmas(mm, start, end, anon_name,
madvise_vma_anon_name);
}
#endif /* CONFIG_ANON_VMA_NAME */
@@ -1619,6 +1628,31 @@ static void madvise_unlock(struct mm_struct *mm, int behavior)
mmap_read_unlock(mm);
}
+static bool madvise_batch_tlb_flush(int behavior)
+{
+ switch (behavior) {
+ case MADV_DONTNEED:
+ case MADV_DONTNEED_LOCKED:
+ case MADV_FREE:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static void madvise_init_tlb(struct madvise_behavior *madv_behavior,
+ struct mm_struct *mm)
+{
+ if (madvise_batch_tlb_flush(madv_behavior->behavior))
+ tlb_gather_mmu(madv_behavior->tlb, mm);
+}
+
+static void madvise_finish_tlb(struct madvise_behavior *madv_behavior)
+{
+ if (madvise_batch_tlb_flush(madv_behavior->behavior))
+ tlb_finish_mmu(madv_behavior->tlb);
+}
+
static bool is_valid_madvise(unsigned long start, size_t len_in, int behavior)
{
size_t len;
@@ -1677,8 +1711,10 @@ static bool is_madvise_populate(int behavior)
}
static int madvise_do_behavior(struct mm_struct *mm,
- unsigned long start, size_t len_in, int behavior)
+ unsigned long start, size_t len_in,
+ struct madvise_behavior *madv_behavior)
{
+ int behavior = madv_behavior->behavior;
struct blk_plug plug;
unsigned long end;
int error;
@@ -1692,7 +1728,7 @@ static int madvise_do_behavior(struct mm_struct *mm,
if (is_madvise_populate(behavior))
error = madvise_populate(mm, start, end, behavior);
else
- error = madvise_walk_vmas(mm, start, end, behavior,
+ error = madvise_walk_vmas(mm, start, end, madv_behavior,
madvise_vma_behavior);
blk_finish_plug(&plug);
return error;
@@ -1773,13 +1809,20 @@ static int madvise_do_behavior(struct mm_struct *mm,
int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior)
{
int error;
+ struct mmu_gather tlb;
+ struct madvise_behavior madv_behavior = {
+ .behavior = behavior,
+ .tlb = &tlb,
+ };
if (madvise_should_skip(start, len_in, behavior, &error))
return error;
error = madvise_lock(mm, behavior);
if (error)
return error;
- error = madvise_do_behavior(mm, start, len_in, behavior);
+ madvise_init_tlb(&madv_behavior, mm);
+ error = madvise_do_behavior(mm, start, len_in, &madv_behavior);
+ madvise_finish_tlb(&madv_behavior);
madvise_unlock(mm, behavior);
return error;
@@ -1796,12 +1839,18 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
{
ssize_t ret = 0;
size_t total_len;
+ struct mmu_gather tlb;
+ struct madvise_behavior madv_behavior = {
+ .behavior = behavior,
+ .tlb = &tlb,
+ };
total_len = iov_iter_count(iter);
ret = madvise_lock(mm, behavior);
if (ret)
return ret;
+ madvise_init_tlb(&madv_behavior, mm);
while (iov_iter_count(iter)) {
unsigned long start = (unsigned long)iter_iov_addr(iter);
@@ -1811,7 +1860,8 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
if (madvise_should_skip(start, len_in, behavior, &error))
ret = error;
else
- ret = madvise_do_behavior(mm, start, len_in, behavior);
+ ret = madvise_do_behavior(mm, start, len_in,
+ &madv_behavior);
/*
* An madvise operation is attempting to restart the syscall,
* but we cannot proceed as it would not be correct to repeat
@@ -1829,14 +1879,17 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
}
/* Drop and reacquire lock to unwind race. */
+ madvise_finish_tlb(&madv_behavior);
madvise_unlock(mm, behavior);
madvise_lock(mm, behavior);
+ madvise_init_tlb(&madv_behavior, mm);
continue;
}
if (ret < 0)
break;
iov_iter_advance(iter, iter_iov_len(iter));
}
+ madvise_finish_tlb(&madv_behavior);
madvise_unlock(mm, behavior);
ret = (total_len - iov_iter_count(iter)) ? : ret;