The patch titled
Subject: filemap-drop-the-mmap_sem-for-all-blocking-operations-v6
has been added to the -mm tree. Its filename is
filemap-drop-the-mmap_sem-for-all-blocking-operations-v6.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/filemap-drop-the-mmap_sem-for-all-blocking-operations-v6.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/filemap-drop-the-mmap_sem-for-all-blocking-operations-v6.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Josef Bacik <josef@xxxxxxxxxxxxxx>
Subject: filemap-drop-the-mmap_sem-for-all-blocking-operations-v6
- added more comments as per Andrew's suggestion.
- fixed the fpin leaks in the two error paths that were pointed out.
Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@xxxxxxxxxxxxxx
Signed-off-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reviewed-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- a/mm/filemap.c~filemap-drop-the-mmap_sem-for-all-blocking-operations-v6
+++ a/mm/filemap.c
@@ -2371,6 +2371,12 @@ static struct file *maybe_unlock_mmap_fo
int flags = vmf->flags;
if (fpin)
return fpin;
+
+ /*
+ * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
+ * anything, so we only pin the file and drop the mmap_sem if only
+ * FAULT_FLAG_ALLOW_RETRY is set.
+ */
if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
FAULT_FLAG_ALLOW_RETRY) {
fpin = get_file(vmf->vma->vm_file);
@@ -2380,10 +2386,15 @@ static struct file *maybe_unlock_mmap_fo
}
/*
- * Works similar to lock_page_or_retry, except it will pin the file and drop the
- * mmap_sem if necessary and then lock the page, and return 1 in this case.
- * This means the caller needs to deal with the fpin appropriately. 0 return is
- * the same as in lock_page_or_retry.
+ * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem
+ * @vmf - the vm_fault for this fault.
+ * @page - the page to lock.
+ * @fpin - the pointer to the file we may pin (or is already pinned).
+ *
+ * This works similar to lock_page_or_retry in that it can drop the mmap_sem.
+ * It differs in that it actually returns the page locked if it returns 1 and 0
+ * if it couldn't lock the page. If we did have to drop the mmap_sem then fpin
+ * will point to the pinned file and needs to be fput()'ed at a later point.
*/
static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
struct file **fpin)
@@ -2391,9 +2402,10 @@ static int lock_page_maybe_drop_mmap(str
if (trylock_page(page))
return 1;
- *fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
return 0;
+
+ *fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
if (vmf->flags & FAULT_FLAG_KILLABLE) {
if (__lock_page_killable(page)) {
/*
@@ -2413,8 +2425,11 @@ static int lock_page_maybe_drop_mmap(str
/*
- * Synchronous readahead happens when we don't even find
- * a page in the page cache at all.
+ * Synchronous readahead happens when we don't even find a page in the page
+ * cache at all. We don't want to perform IO under the mmap sem, so if we have
+ * to drop the mmap sem we return the file that was pinned in order for us to do
+ * that. If we didn't pin a file then we return NULL. The file that is
+ * returned needs to be fput()'ed when we're done with it.
*/
static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
{
@@ -2461,7 +2476,8 @@ static struct file *do_sync_mmap_readahe
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
- * so we want to possibly extend the readahead further..
+ * so we want to possibly extend the readahead further. We return the file that
+ * was pinned if we have to drop the mmap_sem in order to do IO.
*/
static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
struct page *page)
@@ -2545,14 +2561,15 @@ retry_find:
page = pagecache_get_page(mapping, offset,
FGP_CREAT|FGP_FOR_MMAP,
vmf->gfp_mask);
- if (!page)
+ if (!page) {
+ if (fpin)
+ goto out_retry;
return vmf_error(-ENOMEM);
+ }
}
- if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) {
- put_page(page);
- return ret | VM_FAULT_RETRY;
- }
+ if (!lock_page_maybe_drop_mmap(vmf, page, &fpin))
+ goto out_retry;
/* Did it get truncated? */
if (unlikely(page->mapping != mapping)) {
_
Patches currently in -mm which might be from josef@xxxxxxxxxxxxxx are
filemap-kill-page_cache_read-usage-in-filemap_fault.patch
filemap-pass-vm_fault-to-the-mmap-ra-helpers.patch
filemap-drop-the-mmap_sem-for-all-blocking-operations.patch
filemap-drop-the-mmap_sem-for-all-blocking-operations-v6.patch
