LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Jason Gunthorpe <jgg@nvidia.com>
To: <linux-kernel@vger.kernel.org>, Peter Xu <peterx@redhat.com>,
	Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Ahmed S. Darwish" <a.darwish@linutronix.de>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Christoph Hellwig <hch@lst.de>, Hugh Dickins <hughd@google.com>,
	Jan Kara <jack@suse.cz>, Jann Horn <jannh@google.com>,
	John Hubbard <jhubbard@nvidia.com>,
	Kirill Shutemov <kirill@shutemov.name>,
	Kirill Tkhai <ktkhai@virtuozzo.com>,
	Linux-MM <linux-mm@kvack.org>, Michal Hocko <mhocko@suse.com>,
	Oleg Nesterov <oleg@redhat.com>
Subject: [PATCH v4 1/2] mm: reorganize internal_get_user_pages_fast()
Date: Tue, 10 Nov 2020 19:44:08 -0400
Message-ID: <1-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com> (raw)
In-Reply-To: <0-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com>

The next patch in this series makes the lockless flow a little more
complex, so move the entire block into a new function and remove a level
of indention. Tidy a bit of cruft:

 - addr is always the same as start, so use start

 - Use the modern check_add_overflow() for computing end = start + len

 - nr_pinned/pages << PAGE_SHIFT needs the LHS to be unsigned long to
   avoid shift overflow, make the variables unsigned long to avoid coding
   casts in both places. nr_pinned was missing its cast

 - The handling of ret and nr_pinned can be streamlined a bit

No functional change.

Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 mm/gup.c | 99 ++++++++++++++++++++++++++++++--------------------------
 1 file changed, 54 insertions(+), 45 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 98eb8e6d2609c3..c7e24301860abb 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2677,13 +2677,43 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
 	return ret;
 }
 
-static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
+static unsigned long lockless_pages_from_mm(unsigned long start,
+					    unsigned long end,
+					    unsigned int gup_flags,
+					    struct page **pages)
+{
+	unsigned long flags;
+	int nr_pinned = 0;
+
+	if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
+	    !gup_fast_permitted(start, end))
+		return 0;
+
+	/*
+	 * Disable interrupts. The nested form is used, in order to allow full,
+	 * general purpose use of this routine.
+	 *
+	 * With interrupts disabled, we block page table pages from being freed
+	 * from under us. See struct mmu_table_batch comments in
+	 * include/asm-generic/tlb.h for more details.
+	 *
+	 * We do not adopt an rcu_read_lock() here as we also want to block IPIs
+	 * that come from THPs splitting.
+	 */
+	local_irq_save(flags);
+	gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
+	local_irq_restore(flags);
+	return nr_pinned;
+}
+
+static int internal_get_user_pages_fast(unsigned long start,
+					unsigned long nr_pages,
 					unsigned int gup_flags,
 					struct page **pages)
 {
-	unsigned long addr, len, end;
-	unsigned long flags;
-	int nr_pinned = 0, ret = 0;
+	unsigned long len, end;
+	unsigned long nr_pinned;
+	int ret;
 
 	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
 				       FOLL_FORCE | FOLL_PIN | FOLL_GET |
@@ -2697,54 +2727,33 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
 		might_lock_read(&current->mm->mmap_lock);
 
 	start = untagged_addr(start) & PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-
-	if (end <= start)
+	len = nr_pages << PAGE_SHIFT;
+	if (check_add_overflow(start, len, &end))
 		return 0;
 	if (unlikely(!access_ok((void __user *)start, len)))
 		return -EFAULT;
 
-	/*
-	 * Disable interrupts. The nested form is used, in order to allow
-	 * full, general purpose use of this routine.
-	 *
-	 * With interrupts disabled, we block page table pages from being
-	 * freed from under us. See struct mmu_table_batch comments in
-	 * include/asm-generic/tlb.h for more details.
-	 *
-	 * We do not adopt an rcu_read_lock(.) here as we also want to
-	 * block IPIs that come from THPs splitting.
-	 */
-	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) {
-		unsigned long fast_flags = gup_flags;
-
-		local_irq_save(flags);
-		gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned);
-		local_irq_restore(flags);
-		ret = nr_pinned;
-	}
-
-	if (nr_pinned < nr_pages && !(gup_flags & FOLL_FAST_ONLY)) {
-		/* Try to get the remaining pages with get_user_pages */
-		start += nr_pinned << PAGE_SHIFT;
-		pages += nr_pinned;
+	nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages);
+	if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY)
+		return nr_pinned;
 
-		ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned,
-					      gup_flags, pages);
-
-		/* Have to be a bit careful with return values */
-		if (nr_pinned > 0) {
-			if (ret < 0)
-				ret = nr_pinned;
-			else
-				ret += nr_pinned;
-		}
+	/* Slow path: try to get the remaining pages with get_user_pages */
+	start += nr_pinned << PAGE_SHIFT;
+	pages += nr_pinned;
+	ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, gup_flags,
+				      pages);
+	if (ret < 0) {
+		/*
+		 * The caller has to unpin the pages we already pinned so
+		 * returning -errno is not an option
+		 */
+		if (nr_pinned)
+			return nr_pinned;
+		return ret;
 	}
-
-	return ret;
+	return ret + nr_pinned;
 }
+
 /**
  * get_user_pages_fast_only() - pin user pages in memory
  * @start:      starting user address
-- 
2.29.2


       reply index

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <0-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com>
2020-11-10 23:44 ` Jason Gunthorpe [this message]
2020-11-11 18:27 ` [PATCH v4 0/2] Add a seqcount between gup_fast and copy_page_range() Linus Torvalds
     [not found] ` <2-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com>
2020-11-11 19:59   ` [PATCH v4 2/2] mm: prevent gup_fast from racing with COW during fork Peter Xu
2020-11-12  7:41   ` Ahmed S. Darwish

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=1-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com \
    --to=jgg@nvidia.com \
    --cc=a.darwish@linutronix.de \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=hch@lst.de \
    --cc=hughd@google.com \
    --cc=jack@suse.cz \
    --cc=jannh@google.com \
    --cc=jhubbard@nvidia.com \
    --cc=kirill@shutemov.name \
    --cc=ktkhai@virtuozzo.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=oleg@redhat.com \
    --cc=peterx@redhat.com \
    --cc=torvalds@linux-foundation.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lkml.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lkml.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lkml.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lkml.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lkml.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lkml.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lkml.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lkml.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lkml.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lkml.kernel.org/lkml/9 lkml/git/9.git

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

Example config snippet for mirrors

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


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