summaryrefslogtreecommitdiffstats
path: root/mm/shmem.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/shmem.c')
-rw-r--r--mm/shmem.c148
1 files changed, 114 insertions, 34 deletions
diff --git a/mm/shmem.c b/mm/shmem.c
index 5402481c28d..af68b15a8fc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -80,11 +80,12 @@ static struct vfsmount *shm_mnt;
#define SHORT_SYMLINK_LEN 128
/*
- * shmem_fallocate and shmem_writepage communicate via inode->i_private
- * (with i_mutex making sure that it has only one user at a time):
- * we would prefer not to enlarge the shmem inode just for that.
+ * shmem_fallocate communicates with shmem_fault or shmem_writepage via
+ * inode->i_private (with i_mutex making sure that it has only one user at
+ * a time): we would prefer not to enlarge the shmem inode just for that.
*/
struct shmem_falloc {
+ wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
pgoff_t start; /* start of range currently being fallocated */
pgoff_t next; /* the next page offset to be fallocated */
pgoff_t nr_falloced; /* how many new pages have been fallocated */
@@ -467,23 +468,20 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
return;
index = start;
- for ( ; ; ) {
+ while (index < end) {
cond_resched();
pvec.nr = find_get_entries(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr) {
- if (index == start || unfalloc)
+ /* If all gone or hole-punch or unfalloc, we're done */
+ if (index == start || end != -1)
break;
+ /* But if truncating, restart to make sure all gone */
index = start;
continue;
}
- if ((index == start || unfalloc) && indices[0] >= end) {
- pagevec_remove_exceptionals(&pvec);
- pagevec_release(&pvec);
- break;
- }
mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
@@ -495,8 +493,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
if (radix_tree_exceptional_entry(page)) {
if (unfalloc)
continue;
- nr_swaps_freed += !shmem_free_swap(mapping,
- index, page);
+ if (shmem_free_swap(mapping, index, page)) {
+ /* Swap was replaced by page: retry */
+ index--;
+ break;
+ }
+ nr_swaps_freed++;
continue;
}
@@ -505,6 +507,11 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
if (page->mapping == mapping) {
VM_BUG_ON_PAGE(PageWriteback(page), page);
truncate_inode_page(mapping, page);
+ } else {
+ /* Page was replaced by swap: retry */
+ unlock_page(page);
+ index--;
+ break;
}
}
unlock_page(page);
@@ -759,6 +766,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
spin_lock(&inode->i_lock);
shmem_falloc = inode->i_private;
if (shmem_falloc &&
+ !shmem_falloc->waitq &&
index >= shmem_falloc->start &&
index < shmem_falloc->next)
shmem_falloc->nr_unswapped++;
@@ -1027,6 +1035,9 @@ repeat:
goto failed;
}
+ if (page && sgp == SGP_WRITE)
+ mark_page_accessed(page);
+
/* fallocated page? */
if (page && !PageUptodate(page)) {
if (sgp != SGP_READ)
@@ -1108,6 +1119,9 @@ repeat:
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
+ if (sgp == SGP_WRITE)
+ mark_page_accessed(page);
+
delete_from_swap_cache(page);
set_page_dirty(page);
swap_free(swap);
@@ -1134,6 +1148,9 @@ repeat:
__SetPageSwapBacked(page);
__set_page_locked(page);
+ if (sgp == SGP_WRITE)
+ init_page_accessed(page);
+
error = mem_cgroup_charge_file(page, current->mm,
gfp & GFP_RECLAIM_MASK);
if (error)
@@ -1233,6 +1250,64 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
int error;
int ret = VM_FAULT_LOCKED;
+ /*
+ * Trinity finds that probing a hole which tmpfs is punching can
+ * prevent the hole-punch from ever completing: which in turn
+ * locks writers out with its hold on i_mutex. So refrain from
+ * faulting pages into the hole while it's being punched. Although
+ * shmem_undo_range() does remove the additions, it may be unable to
+ * keep up, as each new page needs its own unmap_mapping_range() call,
+ * and the i_mmap tree grows ever slower to scan if new vmas are added.
+ *
+ * It does not matter if we sometimes reach this check just before the
+ * hole-punch begins, so that one fault then races with the punch:
+ * we just need to make racing faults a rare case.
+ *
+ * The implementation below would be much simpler if we just used a
+ * standard mutex or completion: but we cannot take i_mutex in fault,
+ * and bloating every shmem inode for this unlikely case would be sad.
+ */
+ if (unlikely(inode->i_private)) {
+ struct shmem_falloc *shmem_falloc;
+
+ spin_lock(&inode->i_lock);
+ shmem_falloc = inode->i_private;
+ if (shmem_falloc &&
+ shmem_falloc->waitq &&
+ vmf->pgoff >= shmem_falloc->start &&
+ vmf->pgoff < shmem_falloc->next) {
+ wait_queue_head_t *shmem_falloc_waitq;
+ DEFINE_WAIT(shmem_fault_wait);
+
+ ret = VM_FAULT_NOPAGE;
+ if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+ !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+ /* It's polite to up mmap_sem if we can */
+ up_read(&vma->vm_mm->mmap_sem);
+ ret = VM_FAULT_RETRY;
+ }
+
+ shmem_falloc_waitq = shmem_falloc->waitq;
+ prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock(&inode->i_lock);
+ schedule();
+
+ /*
+ * shmem_falloc_waitq points into the shmem_fallocate()
+ * stack of the hole-punching task: shmem_falloc_waitq
+ * is usually invalid by the time we reach here, but
+ * finish_wait() does not dereference it in that case;
+ * though i_lock needed lest racing with wake_up_all().
+ */
+ spin_lock(&inode->i_lock);
+ finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
+ spin_unlock(&inode->i_lock);
+ return ret;
+ }
+ spin_unlock(&inode->i_lock);
+ }
+
error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
@@ -1372,13 +1447,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- int ret;
struct inode *inode = mapping->host;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
- ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
- if (ret == 0 && *pagep)
- init_page_accessed(*pagep);
- return ret;
+ return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
}
static int
@@ -1406,8 +1477,7 @@ shmem_write_end(struct file *file, struct address_space *mapping,
return copied;
}
-static ssize_t shmem_file_aio_read(struct kiocb *iocb,
- const struct iovec *iov, unsigned long nr_segs, loff_t pos)
+static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
@@ -1416,15 +1486,8 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb,
unsigned long offset;
enum sgp_type sgp = SGP_READ;
int error = 0;
- ssize_t retval;
- size_t count;
+ ssize_t retval = 0;
loff_t *ppos = &iocb->ki_pos;
- struct iov_iter iter;
-
- retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
- if (retval)
- return retval;
- iov_iter_init(&iter, iov, nr_segs, count, 0);
/*
* Might this read be for a stacking filesystem? Then when reading
@@ -1500,14 +1563,14 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb,
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
*/
- ret = copy_page_to_iter(page, offset, nr, &iter);
+ ret = copy_page_to_iter(page, offset, nr, to);
retval += ret;
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
page_cache_release(page);
- if (!iov_iter_count(&iter))
+ if (!iov_iter_count(to))
break;
if (ret < nr) {
error = -EFAULT;
@@ -1732,18 +1795,34 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
pgoff_t start, index, end;
int error;
+ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+ return -EOPNOTSUPP;
+
mutex_lock(&inode->i_mutex);
if (mode & FALLOC_FL_PUNCH_HOLE) {
struct address_space *mapping = file->f_mapping;
loff_t unmap_start = round_up(offset, PAGE_SIZE);
loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
+
+ shmem_falloc.waitq = &shmem_falloc_waitq;
+ shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+ shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
+ spin_lock(&inode->i_lock);
+ inode->i_private = &shmem_falloc;
+ spin_unlock(&inode->i_lock);
if ((u64)unmap_end > (u64)unmap_start)
unmap_mapping_range(mapping, unmap_start,
1 + unmap_end - unmap_start, 0);
shmem_truncate_range(inode, offset, offset + len - 1);
/* No need to unmap again: hole-punching leaves COWed pages */
+
+ spin_lock(&inode->i_lock);
+ inode->i_private = NULL;
+ wake_up_all(&shmem_falloc_waitq);
+ spin_unlock(&inode->i_lock);
error = 0;
goto out;
}
@@ -1761,6 +1840,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
goto out;
}
+ shmem_falloc.waitq = NULL;
shmem_falloc.start = start;
shmem_falloc.next = start;
shmem_falloc.nr_falloced = 0;
@@ -2629,13 +2709,13 @@ static const struct file_operations shmem_file_operations = {
.mmap = shmem_mmap,
#ifdef CONFIG_TMPFS
.llseek = shmem_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = shmem_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = shmem_file_read_iter,
+ .write_iter = generic_file_write_iter,
.fsync = noop_fsync,
.splice_read = shmem_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.fallocate = shmem_fallocate,
#endif
};
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-15 00:40:55 +0000