lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200406001514.19876-7-parri.andrea@gmail.com>
Date:   Mon,  6 Apr 2020 02:15:09 +0200
From:   "Andrea Parri (Microsoft)" <parri.andrea@...il.com>
To:     linux-kernel@...r.kernel.org
Cc:     "K . Y . Srinivasan" <kys@...rosoft.com>,
        Haiyang Zhang <haiyangz@...rosoft.com>,
        Stephen Hemminger <sthemmin@...rosoft.com>,
        Wei Liu <wei.liu@...nel.org>, linux-hyperv@...r.kernel.org,
        Michael Kelley <mikelley@...rosoft.com>,
        Dexuan Cui <decui@...rosoft.com>,
        Boqun Feng <boqun.feng@...il.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        "Andrea Parri (Microsoft)" <parri.andrea@...il.com>
Subject: [PATCH 06/11] Drivers: hv: vmbus: Use a spin lock for synchronizing channel scheduling vs. channel removal

Since vmbus_chan_sched() dereferences the ring buffer pointer, we have
to make sure that the ring buffer data structures don't get freed while
such dereferencing is happening.  Current code does this by sending an
IPI to the CPU that is allowed to access that ring buffer from interrupt
level, cf., vmbus_reset_channel_cb().  But with the new functionality
to allow changing the CPU that a channel will interrupt, we can't be
sure what CPU will be running the vmbus_chan_sched() function for a
particular channel, so the current IPI mechanism is infeasible.

Instead synchronize vmbus_chan_sched() and vmbus_reset_channel_cb() by
using the (newly introduced) per-channel spin lock "sched_lock".  Move
the test for onchannel_callback being NULL before the "switch" control
statement in vmbus_chan_sched(), in order to not access the ring buffer
if the vmbus_reset_channel_cb() has been completed on the channel.

Suggested-by: Michael Kelley <mikelley@...rosoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@...il.com>
---
 drivers/hv/channel.c      | 24 +++++++-----------------
 drivers/hv/channel_mgmt.c |  1 +
 drivers/hv/vmbus_drv.c    | 30 +++++++++++++++++-------------
 include/linux/hyperv.h    |  6 ++++++
 4 files changed, 31 insertions(+), 30 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 256ee90c74460..132e476f87b2e 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -594,15 +594,10 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 }
 EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
 
-static void reset_channel_cb(void *arg)
-{
-	struct vmbus_channel *channel = arg;
-
-	channel->onchannel_callback = NULL;
-}
-
 void vmbus_reset_channel_cb(struct vmbus_channel *channel)
 {
+	unsigned long flags;
+
 	/*
 	 * vmbus_on_event(), running in the per-channel tasklet, can race
 	 * with vmbus_close_internal() in the case of SMP guest, e.g., when
@@ -618,17 +613,12 @@ void vmbus_reset_channel_cb(struct vmbus_channel *channel)
 	 */
 	tasklet_disable(&channel->callback_event);
 
-	channel->sc_creation_callback = NULL;
+	/* See the inline comments in vmbus_chan_sched(). */
+	spin_lock_irqsave(&channel->sched_lock, flags);
+	channel->onchannel_callback = NULL;
+	spin_unlock_irqrestore(&channel->sched_lock, flags);
 
-	/* Stop the callback asap */
-	if (channel->target_cpu != get_cpu()) {
-		put_cpu();
-		smp_call_function_single(channel->target_cpu, reset_channel_cb,
-					 channel, true);
-	} else {
-		reset_channel_cb(channel);
-		put_cpu();
-	}
+	channel->sc_creation_callback = NULL;
 
 	/* Re-enable tasklet for use on re-open */
 	tasklet_enable(&channel->callback_event);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 8c179f6866ef7..46ea978e4222a 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -315,6 +315,7 @@ static struct vmbus_channel *alloc_channel(void)
 	if (!channel)
 		return NULL;
 
+	spin_lock_init(&channel->sched_lock);
 	spin_lock_init(&channel->lock);
 	init_completion(&channel->rescind_event);
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 0e5a98ebe23b1..18bd1c0e09a83 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1174,18 +1174,6 @@ static void vmbus_force_channel_rescinded(struct vmbus_channel *channel)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-/*
- * Direct callback for channels using other deferred processing
- */
-static void vmbus_channel_isr(struct vmbus_channel *channel)
-{
-	void (*callback_fn)(void *);
-
-	callback_fn = READ_ONCE(channel->onchannel_callback);
-	if (likely(callback_fn != NULL))
-		(*callback_fn)(channel->channel_callback_context);
-}
-
 /*
  * Schedule all channels with events pending
  */
@@ -1216,6 +1204,7 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 		return;
 
 	for_each_set_bit(relid, recv_int_page, maxbits) {
+		void (*callback_fn)(void *context);
 		struct vmbus_channel *channel;
 
 		if (!sync_test_and_clear_bit(relid, recv_int_page))
@@ -1241,13 +1230,26 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 		if (channel->rescind)
 			goto sched_unlock_rcu;
 
+		/*
+		 * Make sure that the ring buffer data structure doesn't get
+		 * freed while we dereference the ring buffer pointer.  Test
+		 * for the channel's onchannel_callback being NULL within a
+		 * sched_lock critical section.  See also the inline comments
+		 * in vmbus_reset_channel_cb().
+		 */
+		spin_lock(&channel->sched_lock);
+
+		callback_fn = channel->onchannel_callback;
+		if (unlikely(callback_fn == NULL))
+			goto sched_unlock;
+
 		trace_vmbus_chan_sched(channel);
 
 		++channel->interrupts;
 
 		switch (channel->callback_mode) {
 		case HV_CALL_ISR:
-			vmbus_channel_isr(channel);
+			(*callback_fn)(channel->channel_callback_context);
 			break;
 
 		case HV_CALL_BATCHED:
@@ -1257,6 +1259,8 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 			tasklet_schedule(&channel->callback_event);
 		}
 
+sched_unlock:
+		spin_unlock(&channel->sched_lock);
 sched_unlock_rcu:
 		rcu_read_unlock();
 	}
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6c794fd5c903e..ce32ab186192f 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -771,6 +771,12 @@ struct vmbus_channel {
 	void (*onchannel_callback)(void *context);
 	void *channel_callback_context;
 
+	/*
+	 * Synchronize channel scheduling and channel removal; see the inline
+	 * comments in vmbus_chan_sched() and vmbus_reset_channel_cb().
+	 */
+	spinlock_t sched_lock;
+
 	/*
 	 * A channel can be marked for one of three modes of reading:
 	 *   BATCHED - callback called from taslket and should read
-- 
2.24.0

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ