Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1344705 > unrolled thread

[PATCH 1/8] Drivers: hv: vmbus: don't loose HVMSG_TIMER_EXPIRED messages

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCH 1/8] Drivers: hv: vmbus: don't loose HVMSG_TIMER_EXPIRED messages "K. Y. Srinivasan" <kys@microsoft.com> - 2016-02-26 22:40 +0100
    [PATCH 7/8] Drivers: hv: vmbus: Support handling messages on multiple CPUs "K. Y. Srinivasan" <kys@microsoft.com> - 2016-02-26 22:40 +0100
    [PATCH 8/8] Drivers: hv: vmbus: Support kexec on ws2012 r2 and above "K. Y. Srinivasan" <kys@microsoft.com> - 2016-02-26 22:50 +0100
    [PATCH 2/8] Drivers: hv: vmbus: avoid wait_for_completion() on crash "K. Y. Srinivasan" <kys@microsoft.com> - 2016-02-26 22:50 +0100

#1344705 — [PATCH 1/8] Drivers: hv: vmbus: don't loose HVMSG_TIMER_EXPIRED messages

From: Vitaly Kuznetsov <vkuznets@redhat.com>

We must handle HVMSG_TIMER_EXPIRED messages in the interrupt context
and we offload all the rest to vmbus_on_msg_dpc() tasklet. This functions
loops to see if there are new messages pending. In case we'll ever see
HVMSG_TIMER_EXPIRED message there we're going to lose it as we can't
handle it from there. Avoid looping in vmbus_on_msg_dpc(), we're OK
with handling one message per interrupt.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Radim Kr.má<rkrcmar@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/vmbus_drv.c |   68 +++++++++++++++++++++++------------------------
 1 files changed, 33 insertions(+), 35 deletions(-)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 063e5f5..30ea8ad 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -740,51 +740,49 @@ static void vmbus_on_msg_dpc(unsigned long data)
 	struct vmbus_channel_message_table_entry *entry;
 	struct onmessage_work_context *ctx;
 
-	while (1) {
-		if (msg->header.message_type == HVMSG_NONE)
-			/* no msg */
-			break;
+	if (msg->header.message_type == HVMSG_NONE)
+		/* no msg */
+		return;
 
-		hdr = (struct vmbus_channel_message_header *)msg->u.payload;
+	hdr = (struct vmbus_channel_message_header *)msg->u.payload;
 
-		if (hdr->msgtype >= CHANNELMSG_COUNT) {
-			WARN_ONCE(1, "unknown msgtype=%d\n", hdr->msgtype);
-			goto msg_handled;
-		}
+	if (hdr->msgtype >= CHANNELMSG_COUNT) {
+		WARN_ONCE(1, "unknown msgtype=%d\n", hdr->msgtype);
+		goto msg_handled;
+	}
 
-		entry = &channel_message_table[hdr->msgtype];
-		if (entry->handler_type	== VMHT_BLOCKING) {
-			ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
-			if (ctx == NULL)
-				continue;
+	entry = &channel_message_table[hdr->msgtype];
+	if (entry->handler_type	== VMHT_BLOCKING) {
+		ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
+		if (ctx == NULL)
+			return;
 
-			INIT_WORK(&ctx->work, vmbus_onmessage_work);
-			memcpy(&ctx->msg, msg, sizeof(*msg));
+		INIT_WORK(&ctx->work, vmbus_onmessage_work);
+		memcpy(&ctx->msg, msg, sizeof(*msg));
 
-			queue_work(vmbus_connection.work_queue, &ctx->work);
-		} else
-			entry->message_handler(hdr);
+		queue_work(vmbus_connection.work_queue, &ctx->work);
+	} else
+		entry->message_handler(hdr);
 
 msg_handled:
-		msg->header.message_type = HVMSG_NONE;
+	msg->header.message_type = HVMSG_NONE;
+
+	/*
+	 * Make sure the write to MessageType (ie set to
+	 * HVMSG_NONE) happens before we read the
+	 * MessagePending and EOMing. Otherwise, the EOMing
+	 * will not deliver any more messages since there is
+	 * no empty slot
+	 */
+	mb();
 
+	if (msg->header.message_flags.msg_pending) {
 		/*
-		 * Make sure the write to MessageType (ie set to
-		 * HVMSG_NONE) happens before we read the
-		 * MessagePending and EOMing. Otherwise, the EOMing
-		 * will not deliver any more messages since there is
-		 * no empty slot
+		 * This will cause message queue rescan to
+		 * possibly deliver another msg from the
+		 * hypervisor
 		 */
-		mb();
-
-		if (msg->header.message_flags.msg_pending) {
-			/*
-			 * This will cause message queue rescan to
-			 * possibly deliver another msg from the
-			 * hypervisor
-			 */
-			wrmsrl(HV_X64_MSR_EOM, 0);
-		}
+		wrmsrl(HV_X64_MSR_EOM, 0);
 	}
 }
 
-- 
1.7.4.1

[toc] | [next] | [standalone]

#1344717 — [PATCH 7/8] Drivers: hv: vmbus: Support handling messages on multiple CPUs

Starting with Windows 2012 R2, message inteerupts can be delivered
on any VCPU in the guest. Support this functionality.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/hv.c           |   10 ++++++++++
 drivers/hv/hyperv_vmbus.h |    4 +++-
 drivers/hv/vmbus_drv.c    |   10 ++++------
 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index ccb335f..a1c086b 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -204,6 +204,8 @@ int hv_init(void)
 	       sizeof(int) * NR_CPUS);
 	memset(hv_context.event_dpc, 0,
 	       sizeof(void *) * NR_CPUS);
+	memset(hv_context.msg_dpc, 0,
+	       sizeof(void *) * NR_CPUS);
 	memset(hv_context.clk_evt, 0,
 	       sizeof(void *) * NR_CPUS);
 
@@ -415,6 +417,13 @@ int hv_synic_alloc(void)
 		}
 		tasklet_init(hv_context.event_dpc[cpu], vmbus_on_event, cpu);
 
+		hv_context.msg_dpc[cpu] = kmalloc(size, GFP_ATOMIC);
+		if (hv_context.msg_dpc[cpu] == NULL) {
+			pr_err("Unable to allocate event dpc\n");
+			goto err;
+		}
+		tasklet_init(hv_context.msg_dpc[cpu], vmbus_on_msg_dpc, cpu);
+
 		hv_context.clk_evt[cpu] = kzalloc(ced_size, GFP_ATOMIC);
 		if (hv_context.clk_evt[cpu] == NULL) {
 			pr_err("Unable to allocate clock event device\n");
@@ -456,6 +465,7 @@ err:
 static void hv_synic_free_cpu(int cpu)
 {
 	kfree(hv_context.event_dpc[cpu]);
+	kfree(hv_context.msg_dpc[cpu]);
 	kfree(hv_context.clk_evt[cpu]);
 	if (hv_context.synic_event_page[cpu])
 		free_page((unsigned long)hv_context.synic_event_page[cpu]);
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index cada56a..a64b176 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -449,10 +449,11 @@ struct hv_context {
 	u32 vp_index[NR_CPUS];
 	/*
 	 * Starting with win8, we can take channel interrupts on any CPU;
-	 * we will manage the tasklet that handles events on a per CPU
+	 * we will manage the tasklet that handles events messages on a per CPU
 	 * basis.
 	 */
 	struct tasklet_struct *event_dpc[NR_CPUS];
+	struct tasklet_struct *msg_dpc[NR_CPUS];
 	/*
 	 * To optimize the mapping of relid to channel, maintain
 	 * per-cpu list of the channels based on their CPU affinity.
@@ -675,6 +676,7 @@ int vmbus_post_msg(void *buffer, size_t buflen);
 void vmbus_set_event(struct vmbus_channel *channel);
 
 void vmbus_on_event(unsigned long data);
+void vmbus_on_msg_dpc(unsigned long data);
 
 int hv_kvp_init(struct hv_util_service *);
 void hv_kvp_deinit(void);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 6cd12f1..64713ff 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -45,7 +45,6 @@
 
 static struct acpi_device  *hv_acpi_dev;
 
-static struct tasklet_struct msg_dpc;
 static struct completion probe_event;
 
 
@@ -712,7 +711,7 @@ static void hv_process_timer_expiration(struct hv_message *msg, int cpu)
 	vmbus_signal_eom(msg);
 }
 
-static void vmbus_on_msg_dpc(unsigned long data)
+void vmbus_on_msg_dpc(unsigned long data)
 {
 	int cpu = smp_processor_id();
 	void *page_addr = hv_context.synic_message_page[cpu];
@@ -800,7 +799,7 @@ static void vmbus_isr(void)
 		if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
 			hv_process_timer_expiration(msg, cpu);
 		else
-			tasklet_schedule(&msg_dpc);
+			tasklet_schedule(hv_context.msg_dpc[cpu]);
 	}
 }
 
@@ -824,8 +823,6 @@ static int vmbus_bus_init(void)
 		return ret;
 	}
 
-	tasklet_init(&msg_dpc, vmbus_on_msg_dpc, 0);
-
 	ret = bus_register(&hv_bus);
 	if (ret)
 		goto err_cleanup;
@@ -1321,7 +1318,8 @@ static void __exit vmbus_exit(void)
 	hv_synic_clockevents_cleanup();
 	vmbus_disconnect();
 	hv_remove_vmbus_irq();
-	tasklet_kill(&msg_dpc);
+	for_each_online_cpu(cpu)
+		tasklet_kill(hv_context.msg_dpc[cpu]);
 	vmbus_free_channels();
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
 		unregister_die_notifier(&hyperv_die_block);
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1344724 — [PATCH 8/8] Drivers: hv: vmbus: Support kexec on ws2012 r2 and above

From: Alex Ng <alexng@microsoft.com>

WS2012 R2 and above hosts can support kexec in that thay can support
reconnecting to the host (as would be needed in the kexec path)
on any CPU. Enable this. Pre ws2012 r2 hosts don't have this ability
and consequently cannot support kexec.

Signed-off-by: Alex Ng <alexng@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/connection.c |   10 +++++++++-
 1 files changed, 9 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 3b6dc00..d02f137 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -88,8 +88,16 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	 * This has been the behavior pre-win8. This is not
 	 * perf issue and having all channel messages delivered on CPU 0
 	 * would be ok.
+	 * For post win8 hosts, we support receiving channel messagges on
+	 * all the CPUs. This is needed for kexec to work correctly where
+	 * the CPU attempting to connect may not be CPU 0.
 	 */
-	msg->target_vcpu = 0;
+	if (version >= VERSION_WIN8_1) {
+		msg->target_vcpu = hv_context.vp_index[get_cpu()];
+		put_cpu();
+	} else {
+		msg->target_vcpu = 0;
+	}
 
 	/*
 	 * Add to list before we send the request since we may
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1344728 — [PATCH 2/8] Drivers: hv: vmbus: avoid wait_for_completion() on crash

From: Vitaly Kuznetsov <vkuznets@redhat.com>

wait_for_completion() may sleep, it enables interrupts and this
is something we really want to avoid on crashes because interrupt
handlers can cause other crashes. Switch to the recently introduced
vmbus_wait_for_unload() doing busy wait instead.

Reported-by: Radim Krcmar <rkrcmar@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Radim Kr.má<rkrcmar@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel_mgmt.c |    4 ++--
 drivers/hv/connection.c   |    2 +-
 drivers/hv/hyperv_vmbus.h |    2 +-
 drivers/hv/vmbus_drv.c    |    4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index b40f429..f70e352 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -641,7 +641,7 @@ static void vmbus_unload_response(struct vmbus_channel_message_header *hdr)
 	complete(&vmbus_connection.unload_event);
 }
 
-void vmbus_initiate_unload(void)
+void vmbus_initiate_unload(bool crash)
 {
 	struct vmbus_channel_message_header hdr;
 
@@ -658,7 +658,7 @@ void vmbus_initiate_unload(void)
 	 * vmbus_initiate_unload() is also called on crash and the crash can be
 	 * happening in an interrupt context, where scheduling is impossible.
 	 */
-	if (!in_interrupt())
+	if (!crash)
 		wait_for_completion(&vmbus_connection.unload_event);
 	else
 		vmbus_wait_for_unload();
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index fa86b2c..3b6dc00 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -236,7 +236,7 @@ void vmbus_disconnect(void)
 	/*
 	 * First send the unload request to the host.
 	 */
-	vmbus_initiate_unload();
+	vmbus_initiate_unload(false);
 
 	if (vmbus_connection.work_queue) {
 		drain_workqueue(vmbus_connection.work_queue);
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index b9ea7f5..b0299da 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -663,7 +663,7 @@ void hv_vss_onchannelcallback(void *);
 int hv_fcopy_init(struct hv_util_service *);
 void hv_fcopy_deinit(void);
 void hv_fcopy_onchannelcallback(void *);
-void vmbus_initiate_unload(void);
+void vmbus_initiate_unload(bool crash);
 
 static inline void hv_poll_channel(struct vmbus_channel *channel,
 				   void (*cb)(void *))
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 30ea8ad..c8f1671 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1291,7 +1291,7 @@ static void hv_kexec_handler(void)
 	int cpu;
 
 	hv_synic_clockevents_cleanup();
-	vmbus_initiate_unload();
+	vmbus_initiate_unload(false);
 	for_each_online_cpu(cpu)
 		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
 	hv_cleanup();
@@ -1299,7 +1299,7 @@ static void hv_kexec_handler(void)
 
 static void hv_crash_handler(struct pt_regs *regs)
 {
-	vmbus_initiate_unload();
+	vmbus_initiate_unload(true);
 	/*
 	 * In crash handler we can't schedule synic cleanup for all CPUs,
 	 * doing the cleanup for current CPU only. This should be sufficient
-- 
1.7.4.1

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web