From: john.hubbard@gmail.com
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
Anna Schumaker <anna.schumaker@netapp.com>,
"David S . Miller" <davem@davemloft.net>,
Dominique Martinet <asmadeus@codewreck.org>,
Eric Van Hensbergen <ericvh@gmail.com>,
Jason Gunthorpe <jgg@ziepe.ca>, Jason Wang <jasowang@redhat.com>,
Jens Axboe <axboe@kernel.dk>, Latchesar Ionkov <lucho@ionkov.net>,
"Michael S . Tsirkin" <mst@redhat.com>,
Miklos Szeredi <miklos@szeredi.hu>,
Trond Myklebust <trond.myklebust@hammerspace.com>,
Christoph Hellwig <hch@lst.de>,
Matthew Wilcox <willy@infradead.org>,
linux-mm@kvack.org, LKML <linux-kernel@vger.kernel.org>,
ceph-devel@vger.kernel.org, kvm@vger.kernel.org,
linux-block@vger.kernel.org, linux-cifs@vger.kernel.org,
linux-fsdevel@vger.kernel.org, linux-nfs@vger.kernel.org,
linux-rdma@vger.kernel.org, netdev@vger.kernel.org,
samba-technical@lists.samba.org,
v9fs-developer@lists.sourceforge.net,
virtualization@lists.linux-foundation.org,
John Hubbard <jhubbard@nvidia.com>, Jan Kara <jack@suse.cz>,
Ira Weiny <ira.weiny@intel.com>
Subject: [PATCH 01/12] mm/gup: add make_dirty arg to put_user_pages_dirty_lock()
Date: Tue, 23 Jul 2019 21:25:07 -0700 [thread overview]
Message-ID: <20190724042518.14363-2-jhubbard@nvidia.com> (raw)
In-Reply-To: <20190724042518.14363-1-jhubbard@nvidia.com>
From: John Hubbard <jhubbard@nvidia.com>
Provide more capable variation of put_user_pages_dirty_lock(),
and delete put_user_pages_dirty(). This is based on the
following:
1. Lots of call sites become simpler if a bool is passed
into put_user_page*(), instead of making the call site
choose which put_user_page*() variant to call.
2. Christoph Hellwig's observation that set_page_dirty_lock()
is usually correct, and set_page_dirty() is usually a
bug, or at least questionable, within a put_user_page*()
calling chain.
This leads to the following API choices:
* put_user_pages_dirty_lock(page, npages, make_dirty)
* There is no put_user_pages_dirty(). You have to
hand code that, in the rare case that it's
required.
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
drivers/infiniband/core/umem.c | 5 +-
drivers/infiniband/hw/hfi1/user_pages.c | 5 +-
drivers/infiniband/hw/qib/qib_user_pages.c | 5 +-
drivers/infiniband/hw/usnic/usnic_uiom.c | 5 +-
drivers/infiniband/sw/siw/siw_mem.c | 8 +-
include/linux/mm.h | 5 +-
mm/gup.c | 115 +++++++++------------
7 files changed, 58 insertions(+), 90 deletions(-)
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 08da840ed7ee..965cf9dea71a 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -54,10 +54,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
page = sg_page_iter_page(&sg_iter);
- if (umem->writable && dirty)
- put_user_pages_dirty_lock(&page, 1);
- else
- put_user_page(page);
+ put_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
}
sg_free_table(&umem->sg_head);
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index b89a9b9aef7a..469acb961fbd 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -118,10 +118,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
size_t npages, bool dirty)
{
- if (dirty)
- put_user_pages_dirty_lock(p, npages);
- else
- put_user_pages(p, npages);
+ put_user_pages_dirty_lock(p, npages, dirty);
if (mm) { /* during close after signal, mm can be NULL */
atomic64_sub(npages, &mm->pinned_vm);
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index bfbfbb7e0ff4..6bf764e41891 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -40,10 +40,7 @@
static void __qib_release_user_pages(struct page **p, size_t num_pages,
int dirty)
{
- if (dirty)
- put_user_pages_dirty_lock(p, num_pages);
- else
- put_user_pages(p, num_pages);
+ put_user_pages_dirty_lock(p, num_pages, dirty);
}
/**
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 0b0237d41613..62e6ffa9ad78 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -75,10 +75,7 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
for_each_sg(chunk->page_list, sg, chunk->nents, i) {
page = sg_page(sg);
pa = sg_phys(sg);
- if (dirty)
- put_user_pages_dirty_lock(&page, 1);
- else
- put_user_page(page);
+ put_user_pages_dirty_lock(&page, 1, dirty);
usnic_dbg("pa: %pa\n", &pa);
}
kfree(chunk);
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index 67171c82b0c4..358d440efa11 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -65,13 +65,7 @@ static void siw_free_plist(struct siw_page_chunk *chunk, int num_pages,
{
struct page **p = chunk->plist;
- while (num_pages--) {
- if (!PageDirty(*p) && dirty)
- put_user_pages_dirty_lock(p, 1);
- else
- put_user_page(*p);
- p++;
- }
+ put_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
}
void siw_umem_release(struct siw_umem *umem, bool dirty)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0334ca97c584..9759b6a24420 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1057,8 +1057,9 @@ static inline void put_user_page(struct page *page)
put_page(page);
}
-void put_user_pages_dirty(struct page **pages, unsigned long npages);
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages);
+void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+ bool make_dirty);
+
void put_user_pages(struct page **pages, unsigned long npages);
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
diff --git a/mm/gup.c b/mm/gup.c
index 98f13ab37bac..7fefd7ab02c4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -29,85 +29,70 @@ struct follow_page_context {
unsigned int page_mask;
};
-typedef int (*set_dirty_func_t)(struct page *page);
-
-static void __put_user_pages_dirty(struct page **pages,
- unsigned long npages,
- set_dirty_func_t sdf)
-{
- unsigned long index;
-
- for (index = 0; index < npages; index++) {
- struct page *page = compound_head(pages[index]);
-
- /*
- * Checking PageDirty at this point may race with
- * clear_page_dirty_for_io(), but that's OK. Two key cases:
- *
- * 1) This code sees the page as already dirty, so it skips
- * the call to sdf(). That could happen because
- * clear_page_dirty_for_io() called page_mkclean(),
- * followed by set_page_dirty(). However, now the page is
- * going to get written back, which meets the original
- * intention of setting it dirty, so all is well:
- * clear_page_dirty_for_io() goes on to call
- * TestClearPageDirty(), and write the page back.
- *
- * 2) This code sees the page as clean, so it calls sdf().
- * The page stays dirty, despite being written back, so it
- * gets written back again in the next writeback cycle.
- * This is harmless.
- */
- if (!PageDirty(page))
- sdf(page);
-
- put_user_page(page);
- }
-}
-
/**
- * put_user_pages_dirty() - release and dirty an array of gup-pinned pages
- * @pages: array of pages to be marked dirty and released.
+ * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * @pages: array of pages to be maybe marked dirty, and definitely released.
* @npages: number of pages in the @pages array.
+ * @make_dirty: whether to mark the pages dirty
*
* "gup-pinned page" refers to a page that has had one of the get_user_pages()
* variants called on that page.
*
* For each page in the @pages array, make that page (or its head page, if a
- * compound page) dirty, if it was previously listed as clean. Then, release
- * the page using put_user_page().
+ * compound page) dirty, if @make_dirty is true, and if the page was previously
+ * listed as clean. In any case, releases all pages using put_user_page(),
+ * possibly via put_user_pages(), for the non-dirty case.
*
* Please see the put_user_page() documentation for details.
*
- * set_page_dirty(), which does not lock the page, is used here.
- * Therefore, it is the caller's responsibility to ensure that this is
- * safe. If not, then put_user_pages_dirty_lock() should be called instead.
+ * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
+ * required, then the caller should a) verify that this is really correct,
+ * because _lock() is usually required, and b) hand code it:
+ * set_page_dirty_lock(), put_user_page().
*
*/
-void put_user_pages_dirty(struct page **pages, unsigned long npages)
+void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+ bool make_dirty)
{
- __put_user_pages_dirty(pages, npages, set_page_dirty);
-}
-EXPORT_SYMBOL(put_user_pages_dirty);
+ unsigned long index;
-/**
- * put_user_pages_dirty_lock() - release and dirty an array of gup-pinned pages
- * @pages: array of pages to be marked dirty and released.
- * @npages: number of pages in the @pages array.
- *
- * For each page in the @pages array, make that page (or its head page, if a
- * compound page) dirty, if it was previously listed as clean. Then, release
- * the page using put_user_page().
- *
- * Please see the put_user_page() documentation for details.
- *
- * This is just like put_user_pages_dirty(), except that it invokes
- * set_page_dirty_lock(), instead of set_page_dirty().
- *
- */
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages)
-{
- __put_user_pages_dirty(pages, npages, set_page_dirty_lock);
+ /*
+ * TODO: this can be optimized for huge pages: if a series of pages is
+ * physically contiguous and part of the same compound page, then a
+ * single operation to the head page should suffice.
+ */
+
+ if (!make_dirty) {
+ put_user_pages(pages, npages);
+ return;
+ }
+
+ for (index = 0; index < npages; index++) {
+ struct page *page = compound_head(pages[index]);
+ /*
+ * Checking PageDirty at this point may race with
+ * clear_page_dirty_for_io(), but that's OK. Two key
+ * cases:
+ *
+ * 1) This code sees the page as already dirty, so it
+ * skips the call to set_page_dirty(). That could happen
+ * because clear_page_dirty_for_io() called
+ * page_mkclean(), followed by set_page_dirty().
+ * However, now the page is going to get written back,
+ * which meets the original intention of setting it
+ * dirty, so all is well: clear_page_dirty_for_io() goes
+ * on to call TestClearPageDirty(), and write the page
+ * back.
+ *
+ * 2) This code sees the page as clean, so it calls
+ * set_page_dirty(). The page stays dirty, despite being
+ * written back, so it gets written back again in the
+ * next writeback cycle. This is harmless.
+ */
+ if (!PageDirty(page))
+ set_page_dirty_lock(page);
+ put_user_page(page);
+ }
}
EXPORT_SYMBOL(put_user_pages_dirty_lock);
--
2.22.0
next prev parent reply other threads:[~2019-07-24 4:27 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-24 4:25 [PATCH 00/12] block/bio, fs: convert put_page() to put_user_page*() john.hubbard
2019-07-24 4:25 ` john.hubbard [this message]
2019-07-24 4:25 ` [PATCH 02/12] iov_iter: add helper to test if an iter would use GUP v2 john.hubbard
2019-07-24 4:25 ` [PATCH 03/12] block: bio_release_pages: use flags arg instead of bool john.hubbard
2019-07-24 5:30 ` Christoph Hellwig
2019-07-29 20:57 ` Jerome Glisse
2019-07-30 10:25 ` Christoph Hellwig
2019-07-30 15:57 ` Jerome Glisse
2019-08-01 8:20 ` Christoph Hellwig
2019-07-24 4:25 ` [PATCH 04/12] block: bio_release_pages: convert put_page() to put_user_page*() john.hubbard
2019-07-24 4:25 ` [PATCH 05/12] block_dev: " john.hubbard
2019-07-24 4:25 ` [PATCH 06/12] fs/nfs: " john.hubbard
2019-07-24 4:25 ` [PATCH 07/12] vhost-scsi: " john.hubbard
2019-07-24 4:34 ` John Hubbard
2019-07-24 8:07 ` Michael S. Tsirkin
2019-07-24 4:25 ` [PATCH 08/12] fs/cifs: " john.hubbard
2019-07-24 4:25 ` [PATCH 09/12] fs/fuse: " john.hubbard
2019-07-24 4:25 ` [PATCH 10/12] fs/ceph: " john.hubbard
2019-07-24 4:25 ` [PATCH 11/12] 9p/net: " john.hubbard
2019-07-24 4:25 ` [PATCH 12/12] fs/ceph: fix a build warning: returning a value from void function john.hubbard
2019-07-24 6:17 ` [PATCH 00/12] block/bio, fs: convert put_page() to put_user_page*() Christoph Hellwig
2019-07-24 23:23 ` John Hubbard
2019-08-05 22:54 ` John Hubbard
2019-08-07 6:34 ` Christoph Hellwig
2019-08-07 6:38 ` John Hubbard
2019-07-25 0:41 ` Bob Liu
2019-07-26 1:24 ` John Hubbard
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=20190724042518.14363-2-jhubbard@nvidia.com \
--to=john.hubbard@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=anna.schumaker@netapp.com \
--cc=asmadeus@codewreck.org \
--cc=axboe@kernel.dk \
--cc=ceph-devel@vger.kernel.org \
--cc=davem@davemloft.net \
--cc=ericvh@gmail.com \
--cc=hch@lst.de \
--cc=ira.weiny@intel.com \
--cc=jack@suse.cz \
--cc=jasowang@redhat.com \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=kvm@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=lucho@ionkov.net \
--cc=miklos@szeredi.hu \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=samba-technical@lists.samba.org \
--cc=trond.myklebust@hammerspace.com \
--cc=v9fs-developer@lists.sourceforge.net \
--cc=viro@zeniv.linux.org.uk \
--cc=virtualization@lists.linux-foundation.org \
--cc=willy@infradead.org \
/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).