aboutsummaryrefslogtreecommitdiff
path: root/drivers/hv
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/hv')
-rw-r--r--drivers/hv/Kconfig3
-rw-r--r--drivers/hv/channel.c25
-rw-r--r--drivers/hv/channel_mgmt.c27
-rw-r--r--drivers/hv/hv_fcopy.c4
-rw-r--r--drivers/hv/hv_kvp.c4
-rw-r--r--drivers/hv/hv_snapshot.c4
-rw-r--r--drivers/hv/hv_util.c2
-rw-r--r--drivers/hv/hv_utils_transport.c12
-rw-r--r--drivers/hv/hv_utils_transport.h1
-rw-r--r--drivers/hv/ring_buffer.c94
-rw-r--r--drivers/hv/vmbus_drv.c6
11 files changed, 129 insertions, 53 deletions
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 0403b51d20ba..c29cd5387a35 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -7,6 +7,9 @@ config HYPERV
Select this option to run Linux as a Hyper-V client operating
system.
+config HYPERV_TSCPAGE
+ def_bool HYPERV && X86_64
+
config HYPERV_UTILS
tristate "Microsoft Hyper-V Utilities driver"
depends on HYPERV && CONNECTOR && NLS
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index bd0d1988feb2..321b8833fa6f 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -502,12 +502,15 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
wait_for_completion(&info->waitevent);
- if (channel->rescind) {
- ret = -ENODEV;
- goto post_msg_err;
- }
-
post_msg_err:
+ /*
+ * If the channel has been rescinded;
+ * we will be awakened by the rescind
+ * handler; set the error code to zero so we don't leak memory.
+ */
+ if (channel->rescind)
+ ret = 0;
+
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&info->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
@@ -530,15 +533,13 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
int ret;
/*
- * vmbus_on_event(), running in the tasklet, can race
+ * vmbus_on_event(), running in the per-channel tasklet, can race
* with vmbus_close_internal() in the case of SMP guest, e.g., when
* the former is accessing channel->inbound.ring_buffer, the latter
- * could be freeing the ring_buffer pages.
- *
- * To resolve the race, we can serialize them by disabling the
- * tasklet when the latter is running here.
+ * could be freeing the ring_buffer pages, so here we must stop it
+ * first.
*/
- hv_event_tasklet_disable(channel);
+ tasklet_disable(&channel->callback_event);
/*
* In case a device driver's probe() fails (e.g.,
@@ -605,8 +606,6 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
out:
- hv_event_tasklet_enable(channel);
-
return ret;
}
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index f33465d78a02..fbcb06352308 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -350,7 +350,8 @@ static struct vmbus_channel *alloc_channel(void)
static void free_channel(struct vmbus_channel *channel)
{
tasklet_kill(&channel->callback_event);
- kfree(channel);
+
+ kfree_rcu(channel, rcu);
}
static void percpu_channel_enq(void *arg)
@@ -359,14 +360,14 @@ static void percpu_channel_enq(void *arg)
struct hv_per_cpu_context *hv_cpu
= this_cpu_ptr(hv_context.cpu_context);
- list_add_tail(&channel->percpu_list, &hv_cpu->chan_list);
+ list_add_tail_rcu(&channel->percpu_list, &hv_cpu->chan_list);
}
static void percpu_channel_deq(void *arg)
{
struct vmbus_channel *channel = arg;
- list_del(&channel->percpu_list);
+ list_del_rcu(&channel->percpu_list);
}
@@ -381,19 +382,6 @@ static void vmbus_release_relid(u32 relid)
true);
}
-void hv_event_tasklet_disable(struct vmbus_channel *channel)
-{
- tasklet_disable(&channel->callback_event);
-}
-
-void hv_event_tasklet_enable(struct vmbus_channel *channel)
-{
- tasklet_enable(&channel->callback_event);
-
- /* In case there is any pending event */
- tasklet_schedule(&channel->callback_event);
-}
-
void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
{
unsigned long flags;
@@ -402,7 +390,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
BUG_ON(!channel->rescind);
BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
- hv_event_tasklet_disable(channel);
if (channel->target_cpu != get_cpu()) {
put_cpu();
smp_call_function_single(channel->target_cpu,
@@ -411,7 +398,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
percpu_channel_deq(channel);
put_cpu();
}
- hv_event_tasklet_enable(channel);
if (channel->primary_channel == NULL) {
list_del(&channel->listentry);
@@ -505,7 +491,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
init_vp_index(newchannel, dev_type);
- hv_event_tasklet_disable(newchannel);
if (newchannel->target_cpu != get_cpu()) {
put_cpu();
smp_call_function_single(newchannel->target_cpu,
@@ -515,7 +500,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
percpu_channel_enq(newchannel);
put_cpu();
}
- hv_event_tasklet_enable(newchannel);
/*
* This state is used to indicate a successful open
@@ -565,7 +549,6 @@ err_deq_chan:
list_del(&newchannel->listentry);
mutex_unlock(&vmbus_connection.channel_mutex);
- hv_event_tasklet_disable(newchannel);
if (newchannel->target_cpu != get_cpu()) {
put_cpu();
smp_call_function_single(newchannel->target_cpu,
@@ -574,7 +557,6 @@ err_deq_chan:
percpu_channel_deq(newchannel);
put_cpu();
}
- hv_event_tasklet_enable(newchannel);
vmbus_release_relid(newchannel->offermsg.child_relid);
@@ -814,6 +796,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
/* Allocate the channel object and save this offer. */
newchannel = alloc_channel();
if (!newchannel) {
+ vmbus_release_relid(offer->child_relid);
pr_err("Unable to allocate channel object\n");
return;
}
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 9aee6014339d..a5596a642ed0 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -71,7 +71,6 @@ static DECLARE_WORK(fcopy_send_work, fcopy_send_data);
static const char fcopy_devname[] = "vmbus/hv_fcopy";
static u8 *recv_buffer;
static struct hvutil_transport *hvt;
-static struct completion release_event;
/*
* This state maintains the version number registered by the daemon.
*/
@@ -331,7 +330,6 @@ static void fcopy_on_reset(void)
if (cancel_delayed_work_sync(&fcopy_timeout_work))
fcopy_respond_to_host(HV_E_FAIL);
- complete(&release_event);
}
int hv_fcopy_init(struct hv_util_service *srv)
@@ -339,7 +337,6 @@ int hv_fcopy_init(struct hv_util_service *srv)
recv_buffer = srv->recv_buffer;
fcopy_transaction.recv_channel = srv->channel;
- init_completion(&release_event);
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
@@ -361,5 +358,4 @@ void hv_fcopy_deinit(void)
fcopy_transaction.state = HVUTIL_DEVICE_DYING;
cancel_delayed_work_sync(&fcopy_timeout_work);
hvutil_transport_destroy(hvt);
- wait_for_completion(&release_event);
}
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index de263712e247..a1adfe2cfb34 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -101,7 +101,6 @@ static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
static const char kvp_devname[] = "vmbus/hv_kvp";
static u8 *recv_buffer;
static struct hvutil_transport *hvt;
-static struct completion release_event;
/*
* Register the kernel component with the user-level daemon.
* As part of this registration, pass the LIC version number.
@@ -714,7 +713,6 @@ static void kvp_on_reset(void)
if (cancel_delayed_work_sync(&kvp_timeout_work))
kvp_respond_to_host(NULL, HV_E_FAIL);
kvp_transaction.state = HVUTIL_DEVICE_INIT;
- complete(&release_event);
}
int
@@ -723,7 +721,6 @@ hv_kvp_init(struct hv_util_service *srv)
recv_buffer = srv->recv_buffer;
kvp_transaction.recv_channel = srv->channel;
- init_completion(&release_event);
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
@@ -747,5 +744,4 @@ void hv_kvp_deinit(void)
cancel_delayed_work_sync(&kvp_timeout_work);
cancel_work_sync(&kvp_sendkey_work);
hvutil_transport_destroy(hvt);
- wait_for_completion(&release_event);
}
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index bcc03f0748d6..e659d1b94a57 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -79,7 +79,6 @@ static int dm_reg_value;
static const char vss_devname[] = "vmbus/hv_vss";
static __u8 *recv_buffer;
static struct hvutil_transport *hvt;
-static struct completion release_event;
static void vss_timeout_func(struct work_struct *dummy);
static void vss_handle_request(struct work_struct *dummy);
@@ -361,13 +360,11 @@ static void vss_on_reset(void)
if (cancel_delayed_work_sync(&vss_timeout_work))
vss_respond_to_host(HV_E_FAIL);
vss_transaction.state = HVUTIL_DEVICE_INIT;
- complete(&release_event);
}
int
hv_vss_init(struct hv_util_service *srv)
{
- init_completion(&release_event);
if (vmbus_proto_version < VERSION_WIN8_1) {
pr_warn("Integration service 'Backup (volume snapshot)'"
" not supported on this host version.\n");
@@ -400,5 +397,4 @@ void hv_vss_deinit(void)
cancel_delayed_work_sync(&vss_timeout_work);
cancel_work_sync(&vss_handle_request_work);
hvutil_transport_destroy(hvt);
- wait_for_completion(&release_event);
}
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 3042eaa13062..186b10083c55 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -590,6 +590,8 @@ static int hv_timesync_init(struct hv_util_service *srv)
if (!hyperv_cs)
return -ENODEV;
+ spin_lock_init(&host_ts.lock);
+
INIT_WORK(&wrk.work, hv_set_host_time);
/*
diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c
index c235a9515267..4402a71e23f7 100644
--- a/drivers/hv/hv_utils_transport.c
+++ b/drivers/hv/hv_utils_transport.c
@@ -182,10 +182,11 @@ static int hvt_op_release(struct inode *inode, struct file *file)
* connects back.
*/
hvt_reset(hvt);
- mutex_unlock(&hvt->lock);
if (mode_old == HVUTIL_TRANSPORT_DESTROY)
- hvt_transport_free(hvt);
+ complete(&hvt->release);
+
+ mutex_unlock(&hvt->lock);
return 0;
}
@@ -304,6 +305,7 @@ struct hvutil_transport *hvutil_transport_init(const char *name,
init_waitqueue_head(&hvt->outmsg_q);
mutex_init(&hvt->lock);
+ init_completion(&hvt->release);
spin_lock(&hvt_list_lock);
list_add(&hvt->list, &hvt_list);
@@ -351,6 +353,8 @@ void hvutil_transport_destroy(struct hvutil_transport *hvt)
if (hvt->cn_id.idx > 0 && hvt->cn_id.val > 0)
cn_del_callback(&hvt->cn_id);
- if (mode_old != HVUTIL_TRANSPORT_CHARDEV)
- hvt_transport_free(hvt);
+ if (mode_old == HVUTIL_TRANSPORT_CHARDEV)
+ wait_for_completion(&hvt->release);
+
+ hvt_transport_free(hvt);
}
diff --git a/drivers/hv/hv_utils_transport.h b/drivers/hv/hv_utils_transport.h
index d98f5225c3e6..79afb626e166 100644
--- a/drivers/hv/hv_utils_transport.h
+++ b/drivers/hv/hv_utils_transport.h
@@ -41,6 +41,7 @@ struct hvutil_transport {
int outmsg_len; /* its length */
wait_queue_head_t outmsg_q; /* poll/read wait queue */
struct mutex lock; /* protects struct members */
+ struct completion release; /* synchronize with fd release */
};
struct hvutil_transport *hvutil_transport_init(const char *name,
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 87799e81af97..c3f1a9e33cef 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -32,6 +32,8 @@
#include "hyperv_vmbus.h"
+#define VMBUS_PKT_TRAILER 8
+
/*
* When we write to the ring buffer, check if the host needs to
* be signaled. Here is the details of this protocol:
@@ -336,6 +338,12 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
return 0;
}
+static inline void
+init_cached_read_index(struct hv_ring_buffer_info *rbi)
+{
+ rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
int hv_ringbuffer_read(struct vmbus_channel *channel,
void *buffer, u32 buflen, u32 *buffer_actual_len,
u64 *requestid, bool raw)
@@ -366,7 +374,8 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
return ret;
}
- init_cached_read_index(channel);
+ init_cached_read_index(inring_info);
+
next_read_location = hv_get_next_read_location(inring_info);
next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
sizeof(desc),
@@ -410,3 +419,86 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
return ret;
}
+
+/*
+ * Determine number of bytes available in ring buffer after
+ * the current iterator (priv_read_index) location.
+ *
+ * This is similar to hv_get_bytes_to_read but with private
+ * read index instead.
+ */
+static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
+{
+ u32 priv_read_loc = rbi->priv_read_index;
+ u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index);
+
+ if (write_loc >= priv_read_loc)
+ return write_loc - priv_read_loc;
+ else
+ return (rbi->ring_datasize - priv_read_loc) + write_loc;
+}
+
+/*
+ * Get first vmbus packet from ring buffer after read_index
+ *
+ * If ring buffer is empty, returns NULL and no other action needed.
+ */
+struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
+{
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+ /* set state for later hv_signal_on_read() */
+ init_cached_read_index(rbi);
+
+ if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+ return NULL;
+
+ return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_first);
+
+/*
+ * Get next vmbus packet from ring buffer.
+ *
+ * Advances the current location (priv_read_index) and checks for more
+ * data. If the end of the ring buffer is reached, then return NULL.
+ */
+struct vmpacket_descriptor *
+__hv_pkt_iter_next(struct vmbus_channel *channel,
+ const struct vmpacket_descriptor *desc)
+{
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+ u32 packetlen = desc->len8 << 3;
+ u32 dsize = rbi->ring_datasize;
+
+ /* bump offset to next potential packet */
+ rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
+ if (rbi->priv_read_index >= dsize)
+ rbi->priv_read_index -= dsize;
+
+ /* more data? */
+ if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+ return NULL;
+ else
+ return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
+
+/*
+ * Update host ring buffer after iterating over packets.
+ */
+void hv_pkt_iter_close(struct vmbus_channel *channel)
+{
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+ /*
+ * Make sure all reads are done before we update the read index since
+ * the writer may start writing to the read area once the read index
+ * is updated.
+ */
+ virt_rmb();
+ rbi->ring_buffer->read_index = rbi->priv_read_index;
+
+ hv_signal_on_read(channel);
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_close);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index da6b59ba5940..8370b9dc6037 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -939,8 +939,10 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
if (relid == 0)
continue;
+ rcu_read_lock();
+
/* Find channel based on relid */
- list_for_each_entry(channel, &hv_cpu->chan_list, percpu_list) {
+ list_for_each_entry_rcu(channel, &hv_cpu->chan_list, percpu_list) {
if (channel->offermsg.child_relid != relid)
continue;
@@ -956,6 +958,8 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
tasklet_schedule(&channel->callback_event);
}
}
+
+ rcu_read_unlock();
}
}
Powered by cgit, Gruvboxed by Blaster4385.