LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: mst@redhat.com, jasowang@redhat.com, kvm@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Christoph Hellwig <hch@infradead.org>,
	James Bottomley <James.Bottomley@HansenPartnership.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Darren Hart <dvhart@infradead.org>
Subject: [PATCH net] vhost: don't use kmap() to log dirty pages
Date: Mon, 13 May 2019 01:27:45 -0400	[thread overview]
Message-ID: <1557725265-63525-1-git-send-email-jasowang@redhat.com> (raw)

Vhost log dirty pages directly to a userspace bitmap through GUP and
kmap_atomic() since kernel doesn't have a set_bit_to_user()
helper. This will cause issues for the arch that has virtually tagged
caches. The way to fix is to keep using userspace virtual
address. Fortunately, futex has arch_futex_atomic_op_inuser() which
could be used for setting a bit to user.

Note there're several cases that futex helper can fail e.g a page
fault or the arch that doesn't have the support. For those cases, a
simplified get_user()/put_user() pair protected by a global mutex is
provided as a fallback. The fallback may lead false positive that
userspace may see more dirty pages.

Cc: Christoph Hellwig <hch@infradead.org>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Darren Hart <dvhart@infradead.org>
Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
Changes from RFC V2:
- drop GUP and provide get_user()/put_user() fallbacks
- round down log_base
Changes from RFC V1:
- switch to use arch_futex_atomic_op_inuser()
---
 drivers/vhost/vhost.c | 54 ++++++++++++++++++++++++++++-----------------------
 1 file changed, 30 insertions(+), 24 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 351af88..7fa05ba 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -31,6 +31,7 @@
 #include <linux/sched/signal.h>
 #include <linux/interval_tree_generic.h>
 #include <linux/nospec.h>
+#include <asm/futex.h>
 
 #include "vhost.h"
 
@@ -43,6 +44,8 @@
 MODULE_PARM_DESC(max_iotlb_entries,
 	"Maximum number of iotlb entries. (default: 2048)");
 
+static DEFINE_MUTEX(vhost_log_lock);
+
 enum {
 	VHOST_MEMORY_F_LOG = 0x1,
 };
@@ -1692,28 +1695,31 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
 
-/* TODO: This is really inefficient.  We need something like get_user()
- * (instruction directly accesses the data, with an exception table entry
- * returning -EFAULT). See Documentation/x86/exception-tables.txt.
- */
-static int set_bit_to_user(int nr, void __user *addr)
+static int set_bit_to_user(int nr, u32 __user *addr)
 {
-	unsigned long log = (unsigned long)addr;
-	struct page *page;
-	void *base;
-	int bit = nr + (log % PAGE_SIZE) * 8;
+	u32 old;
 	int r;
 
-	r = get_user_pages_fast(log, 1, 1, &page);
-	if (r < 0)
-		return r;
-	BUG_ON(r != 1);
-	base = kmap_atomic(page);
-	set_bit(bit, base);
-	kunmap_atomic(base);
-	set_page_dirty_lock(page);
-	put_page(page);
+	r = arch_futex_atomic_op_inuser(FUTEX_OP_OR, 1 << nr, &old, addr);
+	if (r) {
+		/* Fallback through get_user()/put_user(), this may
+		 * lead false positive that userspace may see more
+		 * dirty pages. A mutex is used to synchronize log
+		 * access between vhost threads.
+		 */
+		mutex_lock(&vhost_log_lock);
+		r = get_user(old, addr);
+		if (r)
+			goto err;
+		r = put_user(old | 1 << nr, addr);
+		if (r)
+			goto err;
+		mutex_unlock(&vhost_log_lock);
+	}
 	return 0;
+err:
+	mutex_unlock(&vhost_log_lock);
+	return r;
 }
 
 static int log_write(void __user *log_base,
@@ -1725,13 +1731,13 @@ static int log_write(void __user *log_base,
 	if (!write_length)
 		return 0;
 	write_length += write_address % VHOST_PAGE_SIZE;
+	log_base = (void __user *)((u64)log_base & ~0x3ULL);
+	write_page += ((u64)log_base & 0x3ULL) * 8;
 	for (;;) {
-		u64 base = (u64)(unsigned long)log_base;
-		u64 log = base + write_page / 8;
-		int bit = write_page % 8;
-		if ((u64)(unsigned long)log != log)
-			return -EFAULT;
-		r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
+		u32 __user *log = (u32 __user *)log_base + write_page / 32;
+		int bit = write_page % 32;
+
+		r = set_bit_to_user(bit, log);
 		if (r < 0)
 			return r;
 		if (write_length <= VHOST_PAGE_SIZE)
-- 
1.8.3.1


             reply	other threads:[~2019-05-13  5:27 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-13  5:27 Jason Wang [this message]
2019-05-13 16:42 ` David Miller
2019-05-14  3:42   ` Jason Wang
2019-05-14 22:16 ` Michael S. Tsirkin
2019-05-15  2:55   ` Jason Wang

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=1557725265-63525-1-git-send-email-jasowang@redhat.com \
    --to=jasowang@redhat.com \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=aarcange@redhat.com \
    --cc=dvhart@infradead.org \
    --cc=hch@infradead.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=virtualization@lists.linux-foundation.org \
    --subject='Re: [PATCH net] vhost: don'\''t use kmap() to log dirty pages' \
    /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

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).