Linux-RDMA Archive on lore.kernel.org
 help / color / Atom feed
From: John Hubbard <jhubbard@nvidia.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Al Viro" <viro@zeniv.linux.org.uk>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Benjamin Herrenschmidt" <benh@kernel.crashing.org>,
	"Björn Töpel" <bjorn.topel@intel.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Dan Williams" <dan.j.williams@intel.com>,
	"Daniel Vetter" <daniel@ffwll.ch>,
	"Dave Chinner" <david@fromorbit.com>,
	"David Airlie" <airlied@linux.ie>,
	"David S . Miller" <davem@davemloft.net>,
	"Ira Weiny" <ira.weiny@intel.com>, "Jan Kara" <jack@suse.cz>,
	"Jason Gunthorpe" <jgg@ziepe.ca>, "Jens Axboe" <axboe@kernel.dk>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>,
	"Mauro Carvalho Chehab" <mchehab@kernel.org>,
	"Michael Ellerman" <mpe@ellerman.id.au>,
	"Michal Hocko" <mhocko@suse.com>,
	"Mike Kravetz" <mike.kravetz@oracle.com>,
	"Paul Mackerras" <paulus@samba.org>,
	"Shuah Khan" <shuah@kernel.org>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	bpf@vger.kernel.org, dri-devel@lists.freedesktop.org,
	kvm@vger.kernel.org, linux-block@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kselftest@vger.kernel.org, linux-media@vger.kernel.org,
	linux-rdma@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	netdev@vger.kernel.org, linux-mm@kvack.org,
	LKML <linux-kernel@vger.kernel.org>,
	"John Hubbard" <jhubbard@nvidia.com>,
	"Christoph Hellwig" <hch@lst.de>,
	"Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Subject: [PATCH 01/19] mm/gup: factor out duplicate code from four routines
Date: Sun, 24 Nov 2019 20:19:53 -0800
Message-ID: <20191125042011.3002372-2-jhubbard@nvidia.com> (raw)
In-Reply-To: <20191125042011.3002372-1-jhubbard@nvidia.com>

There are four locations in gup.c that have a fair amount of code
duplication. This means that changing one requires making the same
changes in four places, not to mention reading the same code four
times, and wondering if there are subtle differences.

Factor out the common code into static functions, thus reducing the
overall line count and the code's complexity.

Also, take the opportunity to slightly improve the efficiency of the
error cases, by doing a mass subtraction of the refcount, surrounded
by get_page()/put_page().

Also, further simplify (slightly), by waiting until the the successful
end of each routine, to increment *nr.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 mm/gup.c | 91 ++++++++++++++++++++++----------------------------------
 1 file changed, 36 insertions(+), 55 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 7646bf993b25..f764432914c4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1978,6 +1978,25 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
+static int record_subpages(struct page *page, unsigned long addr,
+			   unsigned long end, struct page **pages)
+{
+	int nr;
+
+	for (nr = 0; addr != end; addr += PAGE_SIZE)
+		pages[nr++] = page++;
+
+	return nr;
+}
+
+static void put_compound_head(struct page *page, int refs)
+{
+	/* Do a get_page() first, in case refs == page->_refcount */
+	get_page(page);
+	page_ref_sub(page, refs);
+	put_page(page);
+}
+
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
@@ -2007,32 +2026,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	/* hugepages are never "special" */
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-	refs = 0;
 	head = pte_page(pte);
-
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(head, refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2079,28 +2086,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pmd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2120,28 +2118,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pud_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2157,28 +2146,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 
 	BUILD_BUG_ON(pgd_devmap(orig));
-	refs = 0;
+
 	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pgd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
-- 
2.24.0


  reply index

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-25  4:19 [PATCH 00/19] pin_user_pages(): reduced-risk series for Linux 5.5 John Hubbard
2019-11-25  4:19 ` John Hubbard [this message]
2019-11-25  4:19 ` [PATCH 02/19] mm/gup: move try_get_compound_head() to top, fix minor issues John Hubbard
2019-11-25  4:19 ` [PATCH 03/19] mm: Cleanup __put_devmap_managed_page() vs ->page_free() John Hubbard
2019-11-25  4:19 ` [PATCH 04/19] goldish_pipe: rename local pin_user_pages() routine John Hubbard
2019-11-25  4:19 ` [PATCH 05/19] mm: fix get_user_pages_remote()'s handling of FOLL_LONGTERM John Hubbard
2019-11-25  4:19 ` [PATCH 06/19] vfio: fix FOLL_LONGTERM use, simplify get_user_pages_remote() call John Hubbard
2019-11-25  4:19 ` [PATCH 07/19] mm/gup: introduce pin_user_pages*() and FOLL_PIN John Hubbard
2019-11-25  7:47   ` kbuild test robot
2019-11-25  8:44   ` kbuild test robot
2019-11-25 20:13     ` John Hubbard
2019-11-25  4:20 ` [PATCH 08/19] goldish_pipe: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-25  4:20 ` [PATCH 09/19] IB/{core,hw,umem}: set FOLL_PIN via pin_user_pages*(), fix up ODP John Hubbard
2019-11-25  4:20 ` [PATCH 10/19] mm/process_vm_access: set FOLL_PIN via pin_user_pages_remote() John Hubbard
2019-11-25  4:20 ` [PATCH 11/19] drm/via: set FOLL_PIN via pin_user_pages_fast() John Hubbard
2019-11-25  4:20 ` [PATCH 12/19] fs/io_uring: set FOLL_PIN via pin_user_pages() John Hubbard
2019-11-25  4:20 ` [PATCH 13/19] net/xdp: " John Hubbard
2019-11-25  4:20 ` [PATCH 14/19] media/v4l2-core: set pages dirty upon releasing DMA buffers John Hubbard
2019-11-25  4:20 ` [PATCH 15/19] media/v4l2-core: pin_user_pages (FOLL_PIN) and put_user_page() conversion John Hubbard
2019-11-25  4:20 ` [PATCH 16/19] vfio, mm: " John Hubbard
2019-11-25  4:20 ` [PATCH 17/19] powerpc: book3s64: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-25  8:59   ` Jan Kara
2019-11-25 20:46     ` John Hubbard
2019-11-25  4:20 ` [PATCH 18/19] mm/gup_benchmark: use proper FOLL_WRITE flags instead of hard-coding "1" John Hubbard
2019-11-25  4:20 ` [PATCH 19/19] mm, tree-wide: rename put_user_page*() to unpin_user_page*() John Hubbard

Reply instructions:

You may reply publically 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=20191125042011.3002372-2-jhubbard@nvidia.com \
    --to=jhubbard@nvidia.com \
    --cc=airlied@linux.ie \
    --cc=akpm@linux-foundation.org \
    --cc=alex.williamson@redhat.com \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=axboe@kernel.dk \
    --cc=benh@kernel.crashing.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=daniel@ffwll.ch \
    --cc=davem@davemloft.net \
    --cc=david@fromorbit.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hch@infradead.org \
    --cc=hch@lst.de \
    --cc=ira.weiny@intel.com \
    --cc=jack@suse.cz \
    --cc=jgg@ziepe.ca \
    --cc=jglisse@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=magnus.karlsson@intel.com \
    --cc=mchehab@kernel.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=mpe@ellerman.id.au \
    --cc=netdev@vger.kernel.org \
    --cc=paulus@samba.org \
    --cc=shuah@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    /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

Linux-RDMA Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rdma/0 linux-rdma/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rdma linux-rdma/ https://lore.kernel.org/linux-rdma \
		linux-rdma@vger.kernel.org
	public-inbox-index linux-rdma

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rdma


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git