From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
To: linux-mm@kvack.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
John Hubbard <jhubbard@nvidia.com>,
Christoph Hellwig <hch@infradead.org>,
William Kucharski <william.kucharski@oracle.com>,
linux-kernel@vger.kernel.org, Jason Gunthorpe <jgg@ziepe.ca>
Subject: [PATCH v2 15/28] gup: Add try_get_folio() and try_grab_folio()
Date: Mon, 10 Jan 2022 04:23:53 +0000 [thread overview]
Message-ID: <20220110042406.499429-16-willy@infradead.org> (raw)
In-Reply-To: <20220110042406.499429-1-willy@infradead.org>
Convert try_get_compound_head() into try_get_folio() and convert
try_grab_compound_head() into try_grab_folio(). Also convert
hpage_pincount_add() to folio_pincount_add(). Add a temporary
try_grab_compound_head() wrapper around try_grab_folio() to
let us convert callers individually.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
mm/gup.c | 104 +++++++++++++++++++++++++-------------------------
mm/internal.h | 5 +++
2 files changed, 56 insertions(+), 53 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index 1282d29357b7..9e581201d679 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -30,21 +30,19 @@ struct follow_page_context {
};
/*
- * When pinning a compound page, use an exact count to track it, via
- * page_pincount_add/_sub().
+ * When pinning a large folio, use an exact count to track it.
*
- * However, be sure to *also* increment the normal page refcount field
- * at least once, so that the page really is pinned. That's why the
- * refcount from the earlier try_get_compound_head() is left intact.
+ * However, be sure to *also* increment the normal folio refcount
+ * field at least once, so that the folio really is pinned.
+ * That's why the refcount from the earlier
+ * try_get_folio() is left intact.
*/
-static void page_pincount_add(struct page *page, int refs)
+static void folio_pincount_add(struct folio *folio, int refs)
{
- VM_BUG_ON_PAGE(page != compound_head(page), page);
-
- if (PageHead(page))
- atomic_add(refs, compound_pincount_ptr(page));
+ if (folio_test_large(folio))
+ atomic_add(refs, folio_pincount_ptr(folio));
else
- page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1));
+ folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1));
}
static int page_pincount_sub(struct page *page, int refs)
@@ -76,75 +74,70 @@ static void put_page_refs(struct page *page, int refs)
}
/*
- * Return the compound head page with ref appropriately incremented,
+ * Return the folio with ref appropriately incremented,
* or NULL if that failed.
*/
-static inline struct page *try_get_compound_head(struct page *page, int refs)
+static inline struct folio *try_get_folio(struct page *page, int refs)
{
- struct page *head;
+ struct folio *folio;
retry:
- head = compound_head(page);
-
- if (WARN_ON_ONCE(page_ref_count(head) < 0))
+ folio = page_folio(page);
+ if (WARN_ON_ONCE(folio_ref_count(folio) < 0))
return NULL;
- if (unlikely(!page_cache_add_speculative(head, refs)))
+ if (unlikely(!folio_ref_try_add_rcu(folio, refs)))
return NULL;
/*
- * At this point we have a stable reference to the head page; but it
- * could be that between the compound_head() lookup and the refcount
- * increment, the compound page was split, in which case we'd end up
- * holding a reference on a page that has nothing to do with the page
+ * At this point we have a stable reference to the folio; but it
+ * could be that between calling page_folio() and the refcount
+ * increment, the folio was split, in which case we'd end up
+ * holding a reference on a folio that has nothing to do with the page
* we were given anymore.
- * So now that the head page is stable, recheck that the pages still
- * belong together.
+ * So now that the folio is stable, recheck that the page still
+ * belongs to this folio.
*/
- if (unlikely(compound_head(page) != head)) {
- put_page_refs(head, refs);
+ if (unlikely(page_folio(page) != folio)) {
+ folio_put_refs(folio, refs);
goto retry;
}
- return head;
+ return folio;
}
/**
- * try_grab_compound_head() - attempt to elevate a page's refcount, by a
- * flags-dependent amount.
- *
- * Even though the name includes "compound_head", this function is still
- * appropriate for callers that have a non-compound @page to get.
- *
+ * try_grab_folio() - Attempt to get or pin a folio.
* @page: pointer to page to be grabbed
- * @refs: the value to (effectively) add to the page's refcount
+ * @refs: the value to (effectively) add to the folio's refcount
* @flags: gup flags: these are the FOLL_* flag values.
*
* "grab" names in this file mean, "look at flags to decide whether to use
- * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
*
* Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
* same time. (That's true throughout the get_user_pages*() and
* pin_user_pages*() APIs.) Cases:
*
- * FOLL_GET: page's refcount will be incremented by @refs.
+ * FOLL_GET: folio's refcount will be incremented by @refs.
*
- * FOLL_PIN on compound pages: page's refcount will be incremented by
- * @refs, and page[1].compound_pincount will be incremented by @refs.
+ * FOLL_PIN on large folios: folio's refcount will be incremented by
+ * @refs, and its compound_pincount will be incremented by @refs.
*
- * FOLL_PIN on normal pages: page's refcount will be incremented by
+ * FOLL_PIN on single-page folios: folio's refcount will be incremented by
* @refs * GUP_PIN_COUNTING_BIAS.
*
- * Return: head page (with refcount appropriately incremented) for success, or
- * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's
- * considered failure, and furthermore, a likely bug in the caller, so a warning
- * is also emitted.
+ * Return: The folio containing @page (with refcount appropriately
+ * incremented) for success, or NULL upon failure. If neither FOLL_GET
+ * nor FOLL_PIN was set, that's considered failure, and furthermore,
+ * a likely bug in the caller, so a warning is also emitted.
*/
-struct page *try_grab_compound_head(struct page *page,
- int refs, unsigned int flags)
+struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
{
if (flags & FOLL_GET)
- return try_get_compound_head(page, refs);
+ return try_get_folio(page, refs);
else if (flags & FOLL_PIN) {
+ struct folio *folio;
+
/*
* Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
* right zone, so fail and let the caller fall back to the slow
@@ -158,21 +151,26 @@ struct page *try_grab_compound_head(struct page *page,
* CAUTION: Don't use compound_head() on the page before this
* point, the result won't be stable.
*/
- page = try_get_compound_head(page, refs);
- if (!page)
+ folio = try_get_folio(page, refs);
+ if (!folio)
return NULL;
- page_pincount_add(page, refs);
- mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED,
- refs);
+ folio_pincount_add(folio, refs);
+ node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
- return page;
+ return folio;
}
WARN_ON_ONCE(1);
return NULL;
}
+struct page *try_grab_compound_head(struct page *page,
+ int refs, unsigned int flags)
+{
+ return &try_grab_folio(page, refs, flags)->page;
+}
+
static void put_compound_head(struct page *page, int refs, unsigned int flags)
{
if (flags & FOLL_PIN) {
@@ -196,7 +194,7 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags)
* @flags: gup flags: these are the FOLL_* flag values.
*
* Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
- * time. Cases: please see the try_grab_compound_head() documentation, with
+ * time. Cases: please see the try_grab_folio() documentation, with
* "refs=1".
*
* Return: true for success, or if no action was required (if neither FOLL_PIN
diff --git a/mm/internal.h b/mm/internal.h
index 26af8a5a5be3..9a72d1ecdab4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -723,4 +723,9 @@ void vunmap_range_noflush(unsigned long start, unsigned long end);
int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
unsigned long addr, int page_nid, int *flags);
+/*
+ * mm/gup.c
+ */
+struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags);
+
#endif /* __MM_INTERNAL_H */
--
2.33.0
next prev parent reply other threads:[~2022-01-10 4:24 UTC|newest]
Thread overview: 96+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-10 4:23 [PATCH v2 00/28] Convert GUP to folios Matthew Wilcox (Oracle)
2022-01-10 4:23 ` [PATCH v2 01/28] gup: Remove for_each_compound_range() Matthew Wilcox (Oracle)
2022-01-10 8:22 ` Christoph Hellwig
2022-01-11 1:07 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 02/28] gup: Remove for_each_compound_head() Matthew Wilcox (Oracle)
2022-01-10 8:23 ` Christoph Hellwig
2022-01-11 1:11 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 03/28] gup: Change the calling convention for compound_range_next() Matthew Wilcox (Oracle)
2022-01-10 8:25 ` Christoph Hellwig
2022-01-11 1:14 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 04/28] gup: Optimise compound_range_next() Matthew Wilcox (Oracle)
2022-01-10 8:26 ` Christoph Hellwig
2022-01-11 1:16 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 05/28] gup: Change the calling convention for compound_next() Matthew Wilcox (Oracle)
2022-01-10 8:27 ` Christoph Hellwig
2022-01-10 13:28 ` Matthew Wilcox
2022-01-11 1:18 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 06/28] gup: Fix some contiguous memmap assumptions Matthew Wilcox (Oracle)
2022-01-10 8:29 ` Christoph Hellwig
2022-01-10 13:37 ` Matthew Wilcox
2022-01-10 19:05 ` [External] : " Mike Kravetz
2022-01-11 1:47 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 07/28] gup: Remove an assumption of a contiguous memmap Matthew Wilcox (Oracle)
2022-01-10 8:30 ` Christoph Hellwig
2022-01-11 3:27 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 08/28] gup: Handle page split race more efficiently Matthew Wilcox (Oracle)
2022-01-10 8:31 ` Christoph Hellwig
2022-01-11 3:30 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 09/28] gup: Turn hpage_pincount_add() into page_pincount_add() Matthew Wilcox (Oracle)
2022-01-10 8:31 ` Christoph Hellwig
2022-01-11 3:35 ` John Hubbard
2022-01-11 4:32 ` John Hubbard
2022-01-11 13:46 ` Matthew Wilcox
2022-01-10 4:23 ` [PATCH v2 10/28] gup: Turn hpage_pincount_sub() into page_pincount_sub() Matthew Wilcox (Oracle)
2022-01-10 8:32 ` Christoph Hellwig
2022-01-11 6:40 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 11/28] mm: Make compound_pincount always available Matthew Wilcox (Oracle)
2022-01-11 4:06 ` John Hubbard
2022-01-11 4:38 ` Matthew Wilcox
2022-01-11 5:10 ` John Hubbard
2022-01-20 9:15 ` Christoph Hellwig
2022-01-10 4:23 ` [PATCH v2 12/28] mm: Add folio_put_refs() Matthew Wilcox (Oracle)
2022-01-10 8:32 ` Christoph Hellwig
2022-01-11 4:14 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 13/28] mm: Add folio_pincount_ptr() Matthew Wilcox (Oracle)
2022-01-10 8:33 ` Christoph Hellwig
2022-01-11 4:22 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 14/28] mm: Convert page_maybe_dma_pinned() to use a folio Matthew Wilcox (Oracle)
2022-01-10 8:33 ` Christoph Hellwig
2022-01-11 4:27 ` John Hubbard
2022-01-10 4:23 ` Matthew Wilcox (Oracle) [this message]
2022-01-10 8:34 ` [PATCH v2 15/28] gup: Add try_get_folio() and try_grab_folio() Christoph Hellwig
2022-01-11 5:00 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 16/28] mm: Remove page_cache_add_speculative() and page_cache_get_speculative() Matthew Wilcox (Oracle)
2022-01-10 8:35 ` Christoph Hellwig
2022-01-11 5:14 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 17/28] gup: Add gup_put_folio() Matthew Wilcox (Oracle)
2022-01-10 8:35 ` Christoph Hellwig
2022-01-11 6:44 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 18/28] hugetlb: Use try_grab_folio() instead of try_grab_compound_head() Matthew Wilcox (Oracle)
2022-01-10 8:36 ` Christoph Hellwig
2022-01-11 6:47 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 19/28] gup: Convert try_grab_page() to call try_grab_folio() Matthew Wilcox (Oracle)
2022-01-10 8:36 ` Christoph Hellwig
2022-01-11 7:01 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 20/28] gup: Convert gup_pte_range() to use a folio Matthew Wilcox (Oracle)
2022-01-10 8:37 ` Christoph Hellwig
2022-01-11 7:06 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 21/28] gup: Convert gup_hugepte() " Matthew Wilcox (Oracle)
2022-01-10 8:37 ` Christoph Hellwig
2022-01-11 7:33 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 22/28] gup: Convert gup_huge_pmd() " Matthew Wilcox (Oracle)
2022-01-10 8:37 ` Christoph Hellwig
2022-01-11 7:36 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 23/28] gup: Convert gup_huge_pud() " Matthew Wilcox (Oracle)
2022-01-10 8:38 ` Christoph Hellwig
2022-01-11 7:38 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 24/28] gup: Convert gup_huge_pgd() " Matthew Wilcox (Oracle)
2022-01-10 8:38 ` Christoph Hellwig
2022-01-11 7:38 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 25/28] gup: Convert compound_next() to gup_folio_next() Matthew Wilcox (Oracle)
2022-01-10 8:39 ` Christoph Hellwig
2022-01-11 7:41 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 26/28] gup: Convert compound_range_next() to gup_folio_range_next() Matthew Wilcox (Oracle)
2022-01-10 8:41 ` Christoph Hellwig
2022-01-10 13:41 ` Matthew Wilcox
2022-01-11 7:44 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 27/28] mm: Add isolate_lru_folio() Matthew Wilcox (Oracle)
2022-01-10 8:42 ` Christoph Hellwig
2022-01-11 7:49 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 28/28] gup: Convert check_and_migrate_movable_pages() to use a folio Matthew Wilcox (Oracle)
2022-01-10 8:42 ` Christoph Hellwig
2022-01-11 7:52 ` John Hubbard
2022-01-10 15:31 ` [PATCH v2 00/28] Convert GUP to folios Jason Gunthorpe
2022-01-10 16:09 ` Matthew Wilcox
2022-01-10 17:26 ` William Kucharski
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220110042406.499429-16-willy@infradead.org \
--to=willy@infradead.org \
--cc=hch@infradead.org \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=william.kucharski@oracle.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).