Linux-HyperV Archive on lore.kernel.org
 help / color / Atom feed
* [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation
@ 2019-09-05 23:01 Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 1/9] Drivers: hv: vmbus: Break out synic enable and disable operations Dexuan Cui
                   ` (9 more replies)
  0 siblings, 10 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

This patchset (consisting of 9 patches) was part of the v4 patchset (consisting
of 12 patches):
    https://lkml.org/lkml/2019/9/2/894

The other 3 patches in v4 are posted in another patchset, which will go
through the tip.git tree.

All the 9 patches here are now rebased to the hyperv tree's hyperv-next branch:
https://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git/log/?h=hyperv-next
, and all the 9 patches have Michael Kelley's Signed-off-by's.

Please review.

Thanks!
Dexuan

Dexuan Cui (9):
  Drivers: hv: vmbus: Break out synic enable and disable operations
  Drivers: hv: vmbus: Suspend/resume the synic for hibernation
  Drivers: hv: vmbus: Add a helper function is_sub_channel()
  Drivers: hv: vmbus: Implement suspend/resume for VSC drivers for
    hibernation
  Drivers: hv: vmbus: Ignore the offers when resuming from hibernation
  Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation
  Drivers: hv: vmbus: Clean up hv_sock channels by force upon suspend
  Drivers: hv: vmbus: Suspend after cleaning up hv_sock and sub channels
  Drivers: hv: vmbus: Resume after fixing up old primary channels

 drivers/hv/channel_mgmt.c | 161 +++++++++++++++++++++++++---
 drivers/hv/connection.c   |   8 +-
 drivers/hv/hv.c           |  66 +++++++-----
 drivers/hv/hyperv_vmbus.h |  30 ++++++
 drivers/hv/vmbus_drv.c    | 265 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/hyperv.h    |  16 ++-
 6 files changed, 497 insertions(+), 49 deletions(-)

-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 1/9] Drivers: hv: vmbus: Break out synic enable and disable operations
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 3/9] Drivers: hv: vmbus: Add a helper function is_sub_channel() Dexuan Cui
                   ` (8 subsequent siblings)
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

Break out synic enable and disable operations into separate
hv_synic_disable_regs() and hv_synic_enable_regs() functions for use by a
later patch to support hibernation.

There is no functional change except the unnecessary check
"if (sctrl.enable != 1) return -EFAULT;" which is removed, because when
we're in hv_synic_cleanup(), we're absolutely sure sctrl.enable must be 1.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/hv.c           | 66 ++++++++++++++++++++++++++---------------------
 drivers/hv/hyperv_vmbus.h |  2 ++
 2 files changed, 39 insertions(+), 29 deletions(-)

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 6188fb7..fcc5279 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -154,7 +154,7 @@ void hv_synic_free(void)
  * retrieve the initialized message and event pages.  Otherwise, we create and
  * initialize the message and event pages.
  */
-int hv_synic_init(unsigned int cpu)
+void hv_synic_enable_regs(unsigned int cpu)
 {
 	struct hv_per_cpu_context *hv_cpu
 		= per_cpu_ptr(hv_context.cpu_context, cpu);
@@ -196,6 +196,11 @@ int hv_synic_init(unsigned int cpu)
 	sctrl.enable = 1;
 
 	hv_set_synic_state(sctrl.as_uint64);
+}
+
+int hv_synic_init(unsigned int cpu)
+{
+	hv_synic_enable_regs(cpu);
 
 	hv_stimer_init(cpu);
 
@@ -205,20 +210,45 @@ int hv_synic_init(unsigned int cpu)
 /*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
-int hv_synic_cleanup(unsigned int cpu)
+void hv_synic_disable_regs(unsigned int cpu)
 {
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_scontrol sctrl;
+
+	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+
+	shared_sint.masked = 1;
+
+	/* Need to correctly cleanup in the case of SMP!!! */
+	/* Disable the interrupt */
+	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+
+	hv_get_simp(simp.as_uint64);
+	simp.simp_enabled = 0;
+	simp.base_simp_gpa = 0;
+
+	hv_set_simp(simp.as_uint64);
+
+	hv_get_siefp(siefp.as_uint64);
+	siefp.siefp_enabled = 0;
+	siefp.base_siefp_gpa = 0;
+
+	hv_set_siefp(siefp.as_uint64);
+
+	/* Disable the global synic bit */
+	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.enable = 0;
+	hv_set_synic_state(sctrl.as_uint64);
+}
+
+int hv_synic_cleanup(unsigned int cpu)
+{
 	struct vmbus_channel *channel, *sc;
 	bool channel_found = false;
 	unsigned long flags;
 
-	hv_get_synic_state(sctrl.as_uint64);
-	if (sctrl.enable != 1)
-		return -EFAULT;
-
 	/*
 	 * Search for channels which are bound to the CPU we're about to
 	 * cleanup. In case we find one and vmbus is still connected we need to
@@ -249,29 +279,7 @@ int hv_synic_cleanup(unsigned int cpu)
 
 	hv_stimer_cleanup(cpu);
 
-	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
-
-	shared_sint.masked = 1;
-
-	/* Need to correctly cleanup in the case of SMP!!! */
-	/* Disable the interrupt */
-	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
-
-	hv_get_simp(simp.as_uint64);
-	simp.simp_enabled = 0;
-	simp.base_simp_gpa = 0;
-
-	hv_set_simp(simp.as_uint64);
-
-	hv_get_siefp(siefp.as_uint64);
-	siefp.siefp_enabled = 0;
-	siefp.base_siefp_gpa = 0;
-
-	hv_set_siefp(siefp.as_uint64);
-
-	/* Disable the global synic bit */
-	sctrl.enable = 0;
-	hv_set_synic_state(sctrl.as_uint64);
+	hv_synic_disable_regs(cpu);
 
 	return 0;
 }
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 362e70e..26ea161 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -171,8 +171,10 @@ extern int hv_post_message(union hv_connection_id connection_id,
 
 extern void hv_synic_free(void);
 
+extern void hv_synic_enable_regs(unsigned int cpu);
 extern int hv_synic_init(unsigned int cpu);
 
+extern void hv_synic_disable_regs(unsigned int cpu);
 extern int hv_synic_cleanup(unsigned int cpu);
 
 /* Interface */
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 2/9] Drivers: hv: vmbus: Suspend/resume the synic for hibernation
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 1/9] Drivers: hv: vmbus: Break out synic enable and disable operations Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 3/9] Drivers: hv: vmbus: Add a helper function is_sub_channel() Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 4/9] Drivers: hv: vmbus: Implement suspend/resume for VSC drivers " Dexuan Cui
                   ` (6 subsequent siblings)
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

This is needed when we resume the old kernel from the "current" kernel.

Note: when hv_synic_suspend() and hv_synic_resume() run, all the
non-boot CPUs have been offlined, and interrupts are disabled on CPU0.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/vmbus_drv.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index ebd35fc..2ef375c 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -30,6 +30,7 @@
 #include <linux/kdebug.h>
 #include <linux/efi.h>
 #include <linux/random.h>
+#include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 #include "hyperv_vmbus.h"
 
@@ -2086,6 +2087,47 @@ static void hv_crash_handler(struct pt_regs *regs)
 	hyperv_cleanup();
 };
 
+static int hv_synic_suspend(void)
+{
+	/*
+	 * When we reach here, all the non-boot CPUs have been offlined, and
+	 * the stimers on them have been unbound in hv_synic_cleanup() ->
+	 * hv_stimer_cleanup() -> clockevents_unbind_device().
+	 *
+	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled. Here
+	 * we do not unbind the stimer on CPU0 because: 1) it's unnecessary
+	 * because the interrupts remain disabled between syscore_suspend()
+	 * and syscore_resume(): see create_image() and resume_target_kernel();
+	 * 2) the stimer on CPU0 is automatically disabled later by
+	 * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
+	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown(); 3) a warning
+	 * would be triggered if we call clockevents_unbind_device(), which
+	 * may sleep, in an interrupts-disabled context. So, we intentionally
+	 * don't call hv_stimer_cleanup(0) here.
+	 */
+
+	hv_synic_disable_regs(0);
+
+	return 0;
+}
+
+static void hv_synic_resume(void)
+{
+	hv_synic_enable_regs(0);
+
+	/*
+	 * Note: we don't need to call hv_stimer_init(0), because the timer
+	 * on CPU0 is not unbound in hv_synic_suspend(), and the timer is
+	 * automatically re-enabled in timekeeping_resume().
+	 */
+}
+
+/* The callbacks run only on CPU0, with irqs_disabled. */
+static struct syscore_ops hv_synic_syscore_ops = {
+	.suspend = hv_synic_suspend,
+	.resume = hv_synic_resume,
+};
+
 static int __init hv_acpi_init(void)
 {
 	int ret, t;
@@ -2116,6 +2158,8 @@ static int __init hv_acpi_init(void)
 	hv_setup_kexec_handler(hv_kexec_handler);
 	hv_setup_crash_handler(hv_crash_handler);
 
+	register_syscore_ops(&hv_synic_syscore_ops);
+
 	return 0;
 
 cleanup:
@@ -2128,6 +2172,8 @@ static void __exit vmbus_exit(void)
 {
 	int cpu;
 
+	unregister_syscore_ops(&hv_synic_syscore_ops);
+
 	hv_remove_kexec_handler();
 	hv_remove_crash_handler();
 	vmbus_connection.conn_state = DISCONNECTED;
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 3/9] Drivers: hv: vmbus: Add a helper function is_sub_channel()
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 1/9] Drivers: hv: vmbus: Break out synic enable and disable operations Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 2/9] Drivers: hv: vmbus: Suspend/resume the synic for hibernation Dexuan Cui
                   ` (7 subsequent siblings)
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

The existing method of telling if a channel is sub-channel in
vmbus_process_offer() is cumbersome. This new simple helper function
is preferred in future.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 include/linux/hyperv.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6256cc3..2d39248 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -245,7 +245,10 @@ struct vmbus_channel_offer {
 		} pipe;
 	} u;
 	/*
-	 * The sub_channel_index is defined in win8.
+	 * The sub_channel_index is defined in Win8: a value of zero means a
+	 * primary channel and a value of non-zero means a sub-channel.
+	 *
+	 * Before Win8, the field is reserved, meaning it's always zero.
 	 */
 	u16 sub_channel_index;
 	u16 reserved3;
@@ -934,6 +937,11 @@ static inline bool is_hvsock_channel(const struct vmbus_channel *c)
 		  VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER);
 }
 
+static inline bool is_sub_channel(const struct vmbus_channel *c)
+{
+	return c->offermsg.offer.sub_channel_index != 0;
+}
+
 static inline void set_channel_affinity_state(struct vmbus_channel *c,
 					      enum hv_numa_policy policy)
 {
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 4/9] Drivers: hv: vmbus: Implement suspend/resume for VSC drivers for hibernation
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
                   ` (2 preceding siblings ...)
  2019-09-05 23:01 ` [PATCH v5 2/9] Drivers: hv: vmbus: Suspend/resume the synic for hibernation Dexuan Cui
@ 2019-09-05 23:01 ` " Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 5/9] Drivers: hv: vmbus: Ignore the offers when resuming from hibernation Dexuan Cui
                   ` (5 subsequent siblings)
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

The high-level VSC drivers will implement device-specific callbacks.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/vmbus_drv.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/hyperv.h |  3 +++
 2 files changed, 49 insertions(+)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 2ef375c..a30c70a 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -911,6 +911,43 @@ static void vmbus_shutdown(struct device *child_device)
 		drv->shutdown(dev);
 }
 
+/*
+ * vmbus_suspend - Suspend a vmbus device
+ */
+static int vmbus_suspend(struct device *child_device)
+{
+	struct hv_driver *drv;
+	struct hv_device *dev = device_to_hv_device(child_device);
+
+	/* The device may not be attached yet */
+	if (!child_device->driver)
+		return 0;
+
+	drv = drv_to_hv_drv(child_device->driver);
+	if (!drv->suspend)
+		return -EOPNOTSUPP;
+
+	return drv->suspend(dev);
+}
+
+/*
+ * vmbus_resume - Resume a vmbus device
+ */
+static int vmbus_resume(struct device *child_device)
+{
+	struct hv_driver *drv;
+	struct hv_device *dev = device_to_hv_device(child_device);
+
+	/* The device may not be attached yet */
+	if (!child_device->driver)
+		return 0;
+
+	drv = drv_to_hv_drv(child_device->driver);
+	if (!drv->resume)
+		return -EOPNOTSUPP;
+
+	return drv->resume(dev);
+}
 
 /*
  * vmbus_device_release - Final callback release of the vmbus child device
@@ -926,6 +963,14 @@ static void vmbus_device_release(struct device *device)
 	kfree(hv_dev);
 }
 
+/*
+ * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
+ * SET_SYSTEM_SLEEP_PM_OPS: see the comment before vmbus_bus_pm.
+ */
+static const struct dev_pm_ops vmbus_pm = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_suspend, vmbus_resume)
+};
+
 /* The one and only one */
 static struct bus_type  hv_bus = {
 	.name =		"vmbus",
@@ -936,6 +981,7 @@ static void vmbus_device_release(struct device *device)
 	.uevent =		vmbus_uevent,
 	.dev_groups =		vmbus_dev_groups,
 	.drv_groups =		vmbus_drv_groups,
+	.pm =			&vmbus_pm,
 };
 
 struct onmessage_work_context {
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 2d39248..8a60e77 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1157,6 +1157,9 @@ struct hv_driver {
 	int (*remove)(struct hv_device *);
 	void (*shutdown)(struct hv_device *);
 
+	int (*suspend)(struct hv_device *);
+	int (*resume)(struct hv_device *);
+
 };
 
 /* Base device object */
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 5/9] Drivers: hv: vmbus: Ignore the offers when resuming from hibernation
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
                   ` (3 preceding siblings ...)
  2019-09-05 23:01 ` [PATCH v5 4/9] Drivers: hv: vmbus: Implement suspend/resume for VSC drivers " Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 6/9] Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation Dexuan Cui
                   ` (4 subsequent siblings)
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

When the VM resumes, the host re-sends the offers. We should not add the
offers to the global vmbus_connection.chn_list again.

This patch assumes the RELIDs of the channels don't change across
hibernation. Actually this is not always true, especially in the case of
NIC SR-IOV the VF vmbus device's RELID sometimes can change. A later patch
will address this issue by mapping the new offers to the old channels and
fixing up the old channels, if necessary.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/channel_mgmt.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index addcef5..44b92fa 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -848,18 +848,74 @@ void vmbus_initiate_unload(bool crash)
 }
 
 /*
+ * find_primary_channel_by_offer - Get the channel object given the new offer.
+ * This is only used in the resume path of hibernation.
+ */
+static struct vmbus_channel *
+find_primary_channel_by_offer(const struct vmbus_channel_offer_channel *offer)
+{
+	struct vmbus_channel *channel = NULL, *iter;
+	const guid_t *inst1, *inst2;
+
+	/* Ignore sub-channel offers. */
+	if (offer->offer.sub_channel_index != 0)
+		return NULL;
+
+	mutex_lock(&vmbus_connection.channel_mutex);
+
+	list_for_each_entry(iter, &vmbus_connection.chn_list, listentry) {
+		inst1 = &iter->offermsg.offer.if_instance;
+		inst2 = &offer->offer.if_instance;
+
+		if (guid_equal(inst1, inst2)) {
+			channel = iter;
+			break;
+		}
+	}
+
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
+	return channel;
+}
+
+/*
  * vmbus_onoffer - Handler for channel offers from vmbus in parent partition.
  *
  */
 static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 {
 	struct vmbus_channel_offer_channel *offer;
-	struct vmbus_channel *newchannel;
+	struct vmbus_channel *oldchannel, *newchannel;
+	size_t offer_sz;
 
 	offer = (struct vmbus_channel_offer_channel *)hdr;
 
 	trace_vmbus_onoffer(offer);
 
+	oldchannel = find_primary_channel_by_offer(offer);
+
+	if (oldchannel != NULL) {
+		atomic_dec(&vmbus_connection.offer_in_progress);
+
+		/*
+		 * We're resuming from hibernation: we expect the host to send
+		 * exactly the same offers that we had before the hibernation.
+		 */
+		offer_sz = sizeof(*offer);
+		if (memcmp(offer, &oldchannel->offermsg, offer_sz) == 0)
+			return;
+
+		pr_debug("Mismatched offer from the host (relid=%d)\n",
+			 offer->child_relid);
+
+		print_hex_dump_debug("Old vmbus offer: ", DUMP_PREFIX_OFFSET,
+				     16, 4, &oldchannel->offermsg, offer_sz,
+				     false);
+		print_hex_dump_debug("New vmbus offer: ", DUMP_PREFIX_OFFSET,
+				     16, 4, offer, offer_sz, false);
+		return;
+	}
+
 	/* Allocate the channel object and save this offer. */
 	newchannel = alloc_channel();
 	if (!newchannel) {
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 6/9] Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
                   ` (4 preceding siblings ...)
  2019-09-05 23:01 ` [PATCH v5 5/9] Drivers: hv: vmbus: Ignore the offers when resuming from hibernation Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 7/9] Drivers: hv: vmbus: Clean up hv_sock channels by force upon suspend Dexuan Cui
                   ` (3 subsequent siblings)
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

Before Linux enters hibernation, it sends the CHANNELMSG_UNLOAD message to
the host so all the offers are gone. After hibernation, Linux needs to
re-negotiate with the host using the same vmbus protocol version (which
was in use before hibernation), and ask the host to re-offer the vmbus
devices.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/connection.c   |  3 +--
 drivers/hv/hyperv_vmbus.h |  2 ++
 drivers/hv/vmbus_drv.c    | 59 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 62 insertions(+), 2 deletions(-)

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 09829e1..806319c 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -59,8 +59,7 @@ static __u32 vmbus_get_next_version(__u32 current_version)
 	}
 }
 
-static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
-					__u32 version)
+int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 {
 	int ret = 0;
 	unsigned int cur_cpu;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 26ea161..e657197 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -274,6 +274,8 @@ struct vmbus_msginfo {
 
 extern struct vmbus_connection vmbus_connection;
 
+int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version);
+
 static inline void vmbus_send_interrupt(u32 relid)
 {
 	sync_set_bit(relid, vmbus_connection.send_int_page);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index a30c70a..ce9974b 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2089,6 +2089,51 @@ static int vmbus_acpi_add(struct acpi_device *device)
 	return ret_val;
 }
 
+static int vmbus_bus_suspend(struct device *dev)
+{
+	vmbus_initiate_unload(false);
+
+	vmbus_connection.conn_state = DISCONNECTED;
+
+	return 0;
+}
+
+static int vmbus_bus_resume(struct device *dev)
+{
+	struct vmbus_channel_msginfo *msginfo;
+	size_t msgsize;
+	int ret;
+
+	/*
+	 * We only use the 'vmbus_proto_version', which was in use before
+	 * hibernation, to re-negotiate with the host.
+	 */
+	if (vmbus_proto_version == VERSION_INVAL ||
+	    vmbus_proto_version == 0) {
+		pr_err("Invalid proto version = 0x%x\n", vmbus_proto_version);
+		return -EINVAL;
+	}
+
+	msgsize = sizeof(*msginfo) +
+		  sizeof(struct vmbus_channel_initiate_contact);
+
+	msginfo = kzalloc(msgsize, GFP_KERNEL);
+
+	if (msginfo == NULL)
+		return -ENOMEM;
+
+	ret = vmbus_negotiate_version(msginfo, vmbus_proto_version);
+
+	kfree(msginfo);
+
+	if (ret != 0)
+		return ret;
+
+	vmbus_request_offers();
+
+	return 0;
+}
+
 static const struct acpi_device_id vmbus_acpi_device_ids[] = {
 	{"VMBUS", 0},
 	{"VMBus", 0},
@@ -2096,6 +2141,19 @@ static int vmbus_acpi_add(struct acpi_device *device)
 };
 MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids);
 
+/*
+ * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
+ * SET_SYSTEM_SLEEP_PM_OPS, otherwise NIC SR-IOV can not work, because the
+ * "pci_dev_pm_ops" uses the "noirq" callbacks: in the resume path, the
+ * pci "noirq" restore callback runs before "non-noirq" callbacks (see
+ * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() ->
+ * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's
+ * resume callback must also run via the "noirq" callbacks.
+ */
+static const struct dev_pm_ops vmbus_bus_pm = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_bus_suspend, vmbus_bus_resume)
+};
+
 static struct acpi_driver vmbus_acpi_driver = {
 	.name = "vmbus",
 	.ids = vmbus_acpi_device_ids,
@@ -2103,6 +2161,7 @@ static int vmbus_acpi_add(struct acpi_device *device)
 		.add = vmbus_acpi_add,
 		.remove = vmbus_acpi_remove,
 	},
+	.drv.pm = &vmbus_bus_pm,
 };
 
 static void hv_kexec_handler(void)
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 7/9] Drivers: hv: vmbus: Clean up hv_sock channels by force upon suspend
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
                   ` (5 preceding siblings ...)
  2019-09-05 23:01 ` [PATCH v5 6/9] Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 8/9] Drivers: hv: vmbus: Suspend after cleaning up hv_sock and sub channels Dexuan Cui
                   ` (2 subsequent siblings)
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for
hibernation. There is no better method to clean up the channels since
some of the channels may still be referenced by the userspace apps when
hibernation is triggered: in this case, with this patch, the "rescind"
fields of the channels are set, and the apps will thoroughly destroy
the channels after hibernation.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/vmbus_drv.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index ce9974b..45b976e 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -24,6 +24,7 @@
 #include <linux/sched/task_stack.h>
 
 #include <asm/mshyperv.h>
+#include <linux/delay.h>
 #include <linux/notifier.h>
 #include <linux/ptrace.h>
 #include <linux/screen_info.h>
@@ -1069,6 +1070,41 @@ void vmbus_on_msg_dpc(unsigned long data)
 	vmbus_signal_eom(msg, message_type);
 }
 
+/*
+ * Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for
+ * hibernation, because hv_sock connections can not persist across hibernation.
+ */
+static void vmbus_force_channel_rescinded(struct vmbus_channel *channel)
+{
+	struct onmessage_work_context *ctx;
+	struct vmbus_channel_rescind_offer *rescind;
+
+	WARN_ON(!is_hvsock_channel(channel));
+
+	/*
+	 * sizeof(*ctx) is small and the allocation should really not fail,
+	 * otherwise the state of the hv_sock connections ends up in limbo.
+	 */
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL | __GFP_NOFAIL);
+
+	/*
+	 * So far, these are not really used by Linux. Just set them to the
+	 * reasonable values conforming to the definitions of the fields.
+	 */
+	ctx->msg.header.message_type = 1;
+	ctx->msg.header.payload_size = sizeof(*rescind);
+
+	/* These values are actually used by Linux. */
+	rescind = (struct vmbus_channel_rescind_offer *)ctx->msg.u.payload;
+	rescind->header.msgtype = CHANNELMSG_RESCIND_CHANNELOFFER;
+	rescind->child_relid = channel->offermsg.child_relid;
+
+	INIT_WORK(&ctx->work, vmbus_onmessage_work);
+
+	queue_work_on(vmbus_connection.connect_cpu,
+		      vmbus_connection.work_queue,
+		      &ctx->work);
+}
 
 /*
  * Direct callback for channels using other deferred processing
@@ -2091,6 +2127,25 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 static int vmbus_bus_suspend(struct device *dev)
 {
+	struct vmbus_channel *channel;
+
+	while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
+		/*
+		 * We wait here until the completion of any channel
+		 * offers that are currently in progress.
+		 */
+		msleep(1);
+	}
+
+	mutex_lock(&vmbus_connection.channel_mutex);
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (!is_hvsock_channel(channel))
+			continue;
+
+		vmbus_force_channel_rescinded(channel);
+	}
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
 	vmbus_initiate_unload(false);
 
 	vmbus_connection.conn_state = DISCONNECTED;
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 8/9] Drivers: hv: vmbus: Suspend after cleaning up hv_sock and sub channels
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
                   ` (6 preceding siblings ...)
  2019-09-05 23:01 ` [PATCH v5 7/9] Drivers: hv: vmbus: Clean up hv_sock channels by force upon suspend Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-05 23:01 ` [PATCH v5 9/9] Drivers: hv: vmbus: Resume after fixing up old primary channels Dexuan Cui
  2019-09-06 20:03 ` [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Sasha Levin
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

Before suspend, Linux must make sure all the hv_sock channels have been
properly cleaned up, because a hv_sock connection can not persist across
hibernation, and the user-space app must be properly notified of the
state change of the connection.

Before suspend, Linux also must make sure all the sub-channels have been
destroyed, i.e. the related channel structs of the sub-channels must be
properly removed, otherwise they would cause a conflict when the
sub-channels are recreated upon resume.

Add a counter to track such channels, and vmbus_bus_suspend() should wait
for the counter to drop to zero.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/channel_mgmt.c | 26 ++++++++++++++++++++++++++
 drivers/hv/connection.c   |  3 +++
 drivers/hv/hyperv_vmbus.h | 12 ++++++++++++
 drivers/hv/vmbus_drv.c    | 44 +++++++++++++++++++++++++++++++++++++++++++-
 4 files changed, 84 insertions(+), 1 deletion(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 44b92fa..5518d03 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -545,6 +545,10 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 
 	mutex_lock(&vmbus_connection.channel_mutex);
 
+	/* Remember the channels that should be cleaned up upon suspend. */
+	if (is_hvsock_channel(newchannel) || is_sub_channel(newchannel))
+		atomic_inc(&vmbus_connection.nr_chan_close_on_suspend);
+
 	/*
 	 * Now that we have acquired the channel_mutex,
 	 * we can release the potentially racing rescind thread.
@@ -944,6 +948,16 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 	vmbus_process_offer(newchannel);
 }
 
+static void check_ready_for_suspend_event(void)
+{
+	/*
+	 * If all the sub-channels or hv_sock channels have been cleaned up,
+	 * then it's safe to suspend.
+	 */
+	if (atomic_dec_and_test(&vmbus_connection.nr_chan_close_on_suspend))
+		complete(&vmbus_connection.ready_for_suspend_event);
+}
+
 /*
  * vmbus_onoffer_rescind - Rescind offer handler.
  *
@@ -954,6 +968,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 	struct vmbus_channel_rescind_offer *rescind;
 	struct vmbus_channel *channel;
 	struct device *dev;
+	bool clean_up_chan_for_suspend;
 
 	rescind = (struct vmbus_channel_rescind_offer *)hdr;
 
@@ -993,6 +1008,8 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		return;
 	}
 
+	clean_up_chan_for_suspend = is_hvsock_channel(channel) ||
+				    is_sub_channel(channel);
 	/*
 	 * Before setting channel->rescind in vmbus_rescind_cleanup(), we
 	 * should make sure the channel callback is not running any more.
@@ -1018,6 +1035,10 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 	if (channel->device_obj) {
 		if (channel->chn_rescind_callback) {
 			channel->chn_rescind_callback(channel);
+
+			if (clean_up_chan_for_suspend)
+				check_ready_for_suspend_event();
+
 			return;
 		}
 		/*
@@ -1050,6 +1071,11 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		}
 		mutex_unlock(&vmbus_connection.channel_mutex);
 	}
+
+	/* The "channel" may have been freed. Do not access it any longer. */
+
+	if (clean_up_chan_for_suspend)
+		check_ready_for_suspend_event();
 }
 
 void vmbus_hvsock_device_unregister(struct vmbus_channel *channel)
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 806319c..99851ea 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -26,6 +26,9 @@
 struct vmbus_connection vmbus_connection = {
 	.conn_state		= DISCONNECTED,
 	.next_gpadl_handle	= ATOMIC_INIT(0xE1E10),
+
+	.ready_for_suspend_event= COMPLETION_INITIALIZER(
+				  vmbus_connection.ready_for_suspend_event),
 };
 EXPORT_SYMBOL_GPL(vmbus_connection);
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index e657197..974b747 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -260,6 +260,18 @@ struct vmbus_connection {
 	struct workqueue_struct *work_queue;
 	struct workqueue_struct *handle_primary_chan_wq;
 	struct workqueue_struct *handle_sub_chan_wq;
+
+	/*
+	 * The number of sub-channels and hv_sock channels that should be
+	 * cleaned up upon suspend: sub-channels will be re-created upon
+	 * resume, and hv_sock channels should not survive suspend.
+	 */
+	atomic_t nr_chan_close_on_suspend;
+	/*
+	 * vmbus_bus_suspend() waits for "nr_chan_close_on_suspend" to
+	 * drop to zero.
+	 */
+	struct completion ready_for_suspend_event;
 };
 
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 45b976e..32ec951 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2127,7 +2127,8 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 static int vmbus_bus_suspend(struct device *dev)
 {
-	struct vmbus_channel *channel;
+	struct vmbus_channel *channel, *sc;
+	unsigned long flags;
 
 	while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
 		/*
@@ -2146,6 +2147,44 @@ static int vmbus_bus_suspend(struct device *dev)
 	}
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
+	/*
+	 * Wait until all the sub-channels and hv_sock channels have been
+	 * cleaned up. Sub-channels should be destroyed upon suspend, otherwise
+	 * they would conflict with the new sub-channels that will be created
+	 * in the resume path. hv_sock channels should also be destroyed, but
+	 * a hv_sock channel of an established hv_sock connection can not be
+	 * really destroyed since it may still be referenced by the userspace
+	 * application, so we just force the hv_sock channel to be rescinded
+	 * by vmbus_force_channel_rescinded(), and the userspace application
+	 * will thoroughly destroy the channel after hibernation.
+	 *
+	 * Note: the counter nr_chan_close_on_suspend may never go above 0 if
+	 * the VM has no sub-channel and hv_sock channel, e.g. a 1-vCPU VM.
+	 */
+	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
+		wait_for_completion(&vmbus_connection.ready_for_suspend_event);
+
+	mutex_lock(&vmbus_connection.channel_mutex);
+
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (is_hvsock_channel(channel)) {
+			if (!channel->rescind) {
+				pr_err("hv_sock channel not rescinded!\n");
+				WARN_ON_ONCE(1);
+			}
+			continue;
+		}
+
+		spin_lock_irqsave(&channel->lock, flags);
+		list_for_each_entry(sc, &channel->sc_list, sc_list) {
+			pr_err("Sub-channel not deleted!\n");
+			WARN_ON_ONCE(1);
+		}
+		spin_unlock_irqrestore(&channel->lock, flags);
+	}
+
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
 	vmbus_initiate_unload(false);
 
 	vmbus_connection.conn_state = DISCONNECTED;
@@ -2186,6 +2225,9 @@ static int vmbus_bus_resume(struct device *dev)
 
 	vmbus_request_offers();
 
+	/* Reset the event for the next suspend. */
+	reinit_completion(&vmbus_connection.ready_for_suspend_event);
+
 	return 0;
 }
 
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v5 9/9] Drivers: hv: vmbus: Resume after fixing up old primary channels
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
                   ` (7 preceding siblings ...)
  2019-09-05 23:01 ` [PATCH v5 8/9] Drivers: hv: vmbus: Suspend after cleaning up hv_sock and sub channels Dexuan Cui
@ 2019-09-05 23:01 ` Dexuan Cui
  2019-09-06 20:03 ` [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Sasha Levin
  9 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-05 23:01 UTC (permalink / raw)
  To: linux-hyperv, Stephen Hemminger, Sasha Levin, sashal,
	Haiyang Zhang, KY Srinivasan, Michael Kelley, tglx
  Cc: gregkh, linux-kernel, Dexuan Cui

When the host re-offers the primary channels upon resume, the host only
guarantees the Instance GUID  doesn't change, so vmbus_bus_suspend()
should invalidate channel->offermsg.child_relid and figure out the
number of primary channels that need to be fixed up upon resume.

Upon resume, vmbus_onoffer() finds the old channel structs, and maps
the new offers to the old channels, and fixes up the old structs,
and finally the resume callbacks of the VSC drivers will re-open
the channels.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/hv/channel_mgmt.c | 85 ++++++++++++++++++++++++++++++++++++-----------
 drivers/hv/connection.c   |  2 ++
 drivers/hv/hyperv_vmbus.h | 14 ++++++++
 drivers/hv/vmbus_drv.c    | 17 ++++++++++
 include/linux/hyperv.h    |  3 ++
 5 files changed, 101 insertions(+), 20 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 5518d03..8eb1675 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -407,7 +407,15 @@ void hv_process_channel_removal(struct vmbus_channel *channel)
 		cpumask_clear_cpu(channel->target_cpu,
 				  &primary_channel->alloced_cpus_in_node);
 
-	vmbus_release_relid(channel->offermsg.child_relid);
+	/*
+	 * Upon suspend, an in-use hv_sock channel is marked as "rescinded" and
+	 * the relid is invalidated; after hibernation, when the user-space app
+	 * destroys the channel, the relid is INVALID_RELID, and in this case
+	 * it's unnecessary and unsafe to release the old relid, since the same
+	 * relid can refer to a completely different channel now.
+	 */
+	if (channel->offermsg.child_relid != INVALID_RELID)
+		vmbus_release_relid(channel->offermsg.child_relid);
 
 	free_channel(channel);
 }
@@ -851,6 +859,36 @@ void vmbus_initiate_unload(bool crash)
 		vmbus_wait_for_unload();
 }
 
+static void check_ready_for_resume_event(void)
+{
+	/*
+	 * If all the old primary channels have been fixed up, then it's safe
+	 * to resume.
+	 */
+	if (atomic_dec_and_test(&vmbus_connection.nr_chan_fixup_on_resume))
+		complete(&vmbus_connection.ready_for_resume_event);
+}
+
+static void vmbus_setup_channel_state(struct vmbus_channel *channel,
+				      struct vmbus_channel_offer_channel *offer)
+{
+	/*
+	 * Setup state for signalling the host.
+	 */
+	channel->sig_event = VMBUS_EVENT_CONNECTION_ID;
+
+	if (vmbus_proto_version != VERSION_WS2008) {
+		channel->is_dedicated_interrupt =
+				(offer->is_dedicated_interrupt != 0);
+		channel->sig_event = offer->connection_id;
+	}
+
+	memcpy(&channel->offermsg, offer,
+	       sizeof(struct vmbus_channel_offer_channel));
+	channel->monitor_grp = (u8)offer->monitorid / 32;
+	channel->monitor_bit = (u8)offer->monitorid % 32;
+}
+
 /*
  * find_primary_channel_by_offer - Get the channel object given the new offer.
  * This is only used in the resume path of hibernation.
@@ -902,14 +940,29 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 		atomic_dec(&vmbus_connection.offer_in_progress);
 
 		/*
-		 * We're resuming from hibernation: we expect the host to send
-		 * exactly the same offers that we had before the hibernation.
+		 * We're resuming from hibernation: all the sub-channel and
+		 * hv_sock channels we had before the hibernation should have
+		 * been cleaned up, and now we must be seeing a re-offered
+		 * primary channel that we had before the hibernation.
 		 */
+
+		WARN_ON(oldchannel->offermsg.child_relid != INVALID_RELID);
+		/* Fix up the relid. */
+		oldchannel->offermsg.child_relid = offer->child_relid;
+
 		offer_sz = sizeof(*offer);
-		if (memcmp(offer, &oldchannel->offermsg, offer_sz) == 0)
+		if (memcmp(offer, &oldchannel->offermsg, offer_sz) == 0) {
+			check_ready_for_resume_event();
 			return;
+		}
 
-		pr_debug("Mismatched offer from the host (relid=%d)\n",
+		/*
+		 * This is not an error, since the host can also change the
+		 * other field(s) of the offer, e.g. on WS RS5 (Build 17763),
+		 * the offer->connection_id of the Mellanox VF vmbus device
+		 * can change when the host reoffers the device upon resume.
+		 */
+		pr_debug("vmbus offer changed: relid=%d\n",
 			 offer->child_relid);
 
 		print_hex_dump_debug("Old vmbus offer: ", DUMP_PREFIX_OFFSET,
@@ -917,6 +970,12 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 				     false);
 		print_hex_dump_debug("New vmbus offer: ", DUMP_PREFIX_OFFSET,
 				     16, 4, offer, offer_sz, false);
+
+		/* Fix up the old channel. */
+		vmbus_setup_channel_state(oldchannel, offer);
+
+		check_ready_for_resume_event();
+
 		return;
 	}
 
@@ -929,21 +988,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 		return;
 	}
 
-	/*
-	 * Setup state for signalling the host.
-	 */
-	newchannel->sig_event = VMBUS_EVENT_CONNECTION_ID;
-
-	if (vmbus_proto_version != VERSION_WS2008) {
-		newchannel->is_dedicated_interrupt =
-				(offer->is_dedicated_interrupt != 0);
-		newchannel->sig_event = offer->connection_id;
-	}
-
-	memcpy(&newchannel->offermsg, offer,
-	       sizeof(struct vmbus_channel_offer_channel));
-	newchannel->monitor_grp = (u8)offer->monitorid / 32;
-	newchannel->monitor_bit = (u8)offer->monitorid % 32;
+	vmbus_setup_channel_state(newchannel, offer);
 
 	vmbus_process_offer(newchannel);
 }
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 99851ea..6e4c015 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -29,6 +29,8 @@ struct vmbus_connection vmbus_connection = {
 
 	.ready_for_suspend_event= COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_suspend_event),
+	.ready_for_resume_event	= COMPLETION_INITIALIZER(
+				  vmbus_connection.ready_for_resume_event),
 };
 EXPORT_SYMBOL_GPL(vmbus_connection);
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 974b747..f7a5f56 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -272,6 +272,20 @@ struct vmbus_connection {
 	 * drop to zero.
 	 */
 	struct completion ready_for_suspend_event;
+
+	/*
+	 * The number of primary channels that should be "fixed up"
+	 * upon resume: these channels are re-offered upon resume, and some
+	 * fields of the channel offers (i.e. child_relid and connection_id)
+	 * can change, so the old offermsg must be fixed up, before the resume
+	 * callbacks of the VSC drivers start to further touch the channels.
+	 */
+	atomic_t nr_chan_fixup_on_resume;
+	/*
+	 * vmbus_bus_resume() waits for "nr_chan_fixup_on_resume" to
+	 * drop to zero.
+	 */
+	struct completion ready_for_resume_event;
 };
 
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 32ec951..391f0b2 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2164,9 +2164,17 @@ static int vmbus_bus_suspend(struct device *dev)
 	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
 		wait_for_completion(&vmbus_connection.ready_for_suspend_event);
 
+	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0);
+
 	mutex_lock(&vmbus_connection.channel_mutex);
 
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		/*
+		 * Invalidate the field. Upon resume, vmbus_onoffer() will fix
+		 * up the field, and the other fields (if necessary).
+		 */
+		channel->offermsg.child_relid = INVALID_RELID;
+
 		if (is_hvsock_channel(channel)) {
 			if (!channel->rescind) {
 				pr_err("hv_sock channel not rescinded!\n");
@@ -2181,6 +2189,8 @@ static int vmbus_bus_suspend(struct device *dev)
 			WARN_ON_ONCE(1);
 		}
 		spin_unlock_irqrestore(&channel->lock, flags);
+
+		atomic_inc(&vmbus_connection.nr_chan_fixup_on_resume);
 	}
 
 	mutex_unlock(&vmbus_connection.channel_mutex);
@@ -2189,6 +2199,9 @@ static int vmbus_bus_suspend(struct device *dev)
 
 	vmbus_connection.conn_state = DISCONNECTED;
 
+	/* Reset the event for the next resume. */
+	reinit_completion(&vmbus_connection.ready_for_resume_event);
+
 	return 0;
 }
 
@@ -2223,8 +2236,12 @@ static int vmbus_bus_resume(struct device *dev)
 	if (ret != 0)
 		return ret;
 
+	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) == 0);
+
 	vmbus_request_offers();
 
+	wait_for_completion(&vmbus_connection.ready_for_resume_event);
+
 	/* Reset the event for the next suspend. */
 	reinit_completion(&vmbus_connection.ready_for_suspend_event);
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 8a60e77..a3aa9e9 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -426,6 +426,9 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_COUNT
 };
 
+/* Hyper-V supports about 2048 channels, and the RELIDs start with 1. */
+#define INVALID_RELID	U32_MAX
+
 struct vmbus_channel_message_header {
 	enum vmbus_channel_message_type msgtype;
 	u32 padding;
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation
  2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
                   ` (8 preceding siblings ...)
  2019-09-05 23:01 ` [PATCH v5 9/9] Drivers: hv: vmbus: Resume after fixing up old primary channels Dexuan Cui
@ 2019-09-06 20:03 ` Sasha Levin
  2019-09-06 22:45   ` Dexuan Cui
  9 siblings, 1 reply; 14+ messages in thread
From: Sasha Levin @ 2019-09-06 20:03 UTC (permalink / raw)
  To: Dexuan Cui
  Cc: linux-hyperv, Stephen Hemminger, Sasha Levin, Haiyang Zhang,
	KY Srinivasan, Michael Kelley, tglx, gregkh, linux-kernel

On Thu, Sep 05, 2019 at 11:01:14PM +0000, Dexuan Cui wrote:
>This patchset (consisting of 9 patches) was part of the v4 patchset (consisting
>of 12 patches):
>    https://lkml.org/lkml/2019/9/2/894
>
>The other 3 patches in v4 are posted in another patchset, which will go
>through the tip.git tree.
>
>All the 9 patches here are now rebased to the hyperv tree's hyperv-next branch:
>https://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git/log/?h=hyperv-next
>, and all the 9 patches have Michael Kelley's Signed-off-by's.
>
>Please review.

Given that these two series depend on each other, I'd much prefer for
them to go through one tree.

But, I may be wrong, and I'm going to see if a scenario such as this
make sense. I've queued this one to the hyperv-next, but I'll wait for
the x86 folks to send their pull request to Linus first before I do it
for these patches.

Usually cases such as these are the exception, but for Hyper-V it seems
to be the norm, so I'm curious to see how this will unfold.

--
Thanks,
Sasha

^ permalink raw reply	[flat|nested] 14+ messages in thread

* RE: [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation
  2019-09-06 20:03 ` [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Sasha Levin
@ 2019-09-06 22:45   ` Dexuan Cui
  2019-09-08 12:13     ` Sasha Levin
  0 siblings, 1 reply; 14+ messages in thread
From: Dexuan Cui @ 2019-09-06 22:45 UTC (permalink / raw)
  To: Sasha Levin
  Cc: linux-hyperv, Stephen Hemminger, Sasha Levin, Haiyang Zhang,
	KY Srinivasan, Michael Kelley, tglx, gregkh, linux-kernel

> From: Sasha Levin <sashal@kernel.org>
> Sent: Friday, September 6, 2019 1:03 PM
> On Thu, Sep 05, 2019 at 11:01:14PM +0000, Dexuan Cui wrote:
> >This patchset (consisting of 9 patches) was part of the v4 patchset (consisting
> >of 12 patches):
> >
> >The other 3 patches in v4 are posted in another patchset, which will go
> >through the tip.git tree.
> >
> >All the 9 patches here are now rebased to the hyperv tree's hyperv-next
> branch, and all the 9 patches have Michael Kelley's Signed-off-by's.
> >
> >Please review.
> 
> Given that these two series depend on each other, I'd much prefer for
> them to go through one tree.

Hi Sasha,
Yeah, that would be ideal. The problem here is: the other patchset conflicts
with the existing patches in the tip.git tree's timers/core branch, so IMO 
the 3 patches have to go through the tip tree:

[PATCH v5 1/3] x86/hyper-v: Suspend/resume the hypercall page for hibernation
[PATCH v5 2/3] x86/hyper-v: Implement hv_is_hibernation_supported()
[PATCH v5 3/3] clocksource/drivers: Suspend/resume Hyper-V clocksource for hibernation

> But, I may be wrong, and I'm going to see if a scenario such as this
> make sense. I've queued this one to the hyperv-next, but I'll wait for
> the x86 folks to send their pull request to Linus first before I do it
> for these patches.

Actually IMHO you don't need to wait, because there is not a build
dependency, so either patchset can go into the Linus's tree first.

The 2 patchsets are just the first step to make hibernation work for Linux VM
running on Hyper-V. Next I'm going to post some high-level VSC patches for
hv_balloon, hv_utils, hv_netvsc, hid_hyperv, hv_storvsc, hyperv_keyboard, 
hyperv_fb,etc. All of these should go through the hyperv tree, since they're
pure hyper-v changes, and they depend on this 9-patch patchset. I'll make
a note in every patch so the subsystem maintainers will be aware and ack it.

Among the VSC patches, the hv_balloon patch does depend on the 2nd patch:
    [PATCH v5 2/3] x86/hyper-v: Implement hv_is_hibernation_supported().
I think I'll wait for the aforementioned 2 patchsets to be in first, before posting
the hv_balloon patch.

> Usually cases such as these are the exception, but for Hyper-V it seems
> to be the norm, so I'm curious to see how this will unfold.
> 
> Thanks,
> Sasha

Thanks for taking care all the patches!

Thanks,
-- Dexuan

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation
  2019-09-06 22:45   ` Dexuan Cui
@ 2019-09-08 12:13     ` Sasha Levin
  2019-09-08 16:32       ` Dexuan Cui
  0 siblings, 1 reply; 14+ messages in thread
From: Sasha Levin @ 2019-09-08 12:13 UTC (permalink / raw)
  To: Dexuan Cui
  Cc: linux-hyperv, Stephen Hemminger, Sasha Levin, Haiyang Zhang,
	KY Srinivasan, Michael Kelley, tglx, gregkh, linux-kernel

On Fri, Sep 06, 2019 at 10:45:31PM +0000, Dexuan Cui wrote:
>> From: Sasha Levin <sashal@kernel.org>
>> Sent: Friday, September 6, 2019 1:03 PM
>> On Thu, Sep 05, 2019 at 11:01:14PM +0000, Dexuan Cui wrote:
>> >This patchset (consisting of 9 patches) was part of the v4 patchset (consisting
>> >of 12 patches):
>> >
>> >The other 3 patches in v4 are posted in another patchset, which will go
>> >through the tip.git tree.
>> >
>> >All the 9 patches here are now rebased to the hyperv tree's hyperv-next
>> branch, and all the 9 patches have Michael Kelley's Signed-off-by's.
>> >
>> >Please review.
>>
>> Given that these two series depend on each other, I'd much prefer for
>> them to go through one tree.
>
>Hi Sasha,
>Yeah, that would be ideal. The problem here is: the other patchset conflicts
>with the existing patches in the tip.git tree's timers/core branch, so IMO
>the 3 patches have to go through the tip tree:
>
>[PATCH v5 1/3] x86/hyper-v: Suspend/resume the hypercall page for hibernation
>[PATCH v5 2/3] x86/hyper-v: Implement hv_is_hibernation_supported()
>[PATCH v5 3/3] clocksource/drivers: Suspend/resume Hyper-V clocksource for hibernation
>
>> But, I may be wrong, and I'm going to see if a scenario such as this
>> make sense. I've queued this one to the hyperv-next, but I'll wait for
>> the x86 folks to send their pull request to Linus first before I do it
>> for these patches.
>
>Actually IMHO you don't need to wait, because there is not a build
>dependency, so either patchset can go into the Linus's tree first.

It'll build, sure. But did anyone actually test one without the other?
What happens if Thomas doesn't send his batch at all during the merge
window?

--
Thanks,
Sasha

^ permalink raw reply	[flat|nested] 14+ messages in thread

* RE: [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation
  2019-09-08 12:13     ` Sasha Levin
@ 2019-09-08 16:32       ` Dexuan Cui
  0 siblings, 0 replies; 14+ messages in thread
From: Dexuan Cui @ 2019-09-08 16:32 UTC (permalink / raw)
  To: Sasha Levin
  Cc: linux-hyperv, Stephen Hemminger, Sasha Levin, Haiyang Zhang,
	KY Srinivasan, Michael Kelley, tglx, gregkh, linux-kernel

> From: Sasha Levin <sashal@kernel.org>
> Sent: Sunday, September 8, 2019 5:13 AM
> On Fri, Sep 06, 2019 at 10:45:31PM +0000, Dexuan Cui wrote:
> >> From: Sasha Levin <sashal@kernel.org>
> >> Sent: Friday, September 6, 2019 1:03 PM
> >> On Thu, Sep 05, 2019 at 11:01:14PM +0000, Dexuan Cui wrote:
> >> >This patchset (consisting of 9 patches) was part of the v4 patchset
> (consisting
> >> >of 12 patches):
> >> >
> >> >The other 3 patches in v4 are posted in another patchset, which will go
> >> >through the tip.git tree.
> >> >
> >> >All the 9 patches here are now rebased to the hyperv tree's hyperv-next
> >> branch, and all the 9 patches have Michael Kelley's Signed-off-by's.
> >> >
> >> >Please review.
> >>
> >> Given that these two series depend on each other, I'd much prefer for
> >> them to go through one tree.
> >
> >Hi Sasha,
> >Yeah, that would be ideal. The problem here is: the other patchset conflicts
> >with the existing patches in the tip.git tree's timers/core branch, so IMO
> >the 3 patches have to go through the tip tree:
> >
> >[PATCH v5 1/3] x86/hyper-v: Suspend/resume the hypercall page for
> hibernation
> >[PATCH v5 2/3] x86/hyper-v: Implement hv_is_hibernation_supported()
> >[PATCH v5 3/3] clocksource/drivers: Suspend/resume Hyper-V clocksource for
> hibernation
> >
> >> But, I may be wrong, and I'm going to see if a scenario such as this
> >> make sense. I've queued this one to the hyperv-next, but I'll wait for
> >> the x86 folks to send their pull request to Linus first before I do it
> >> for these patches.
> >
> >Actually IMHO you don't need to wait, because there is not a build
> >dependency, so either patchset can go into the Linus's tree first.
> 
> It'll build, sure. But did anyone actually test one without the other?

Nobody tested this.

The fact is: even if we have the 2 patchsets, hibernation still can not work
for Linux VM on Hyper-V, because we also need the high level driver
changes to hv_netvsc, hv_storvsc, etc. I'm going to send out these
patches soon.

> What happens if Thomas doesn't send his batch at all during the merge
> window?
> Sasha

We need all the patches together to make hibernation work.
I just meant that the 2 patchsets don't have to go into Linus's tree in
a special order, as there is no build issue. 

Thanks,
-- Dexuan

^ permalink raw reply	[flat|nested] 14+ messages in thread

end of thread, back to index

Thread overview: 14+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-09-05 23:01 [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 1/9] Drivers: hv: vmbus: Break out synic enable and disable operations Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 3/9] Drivers: hv: vmbus: Add a helper function is_sub_channel() Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 2/9] Drivers: hv: vmbus: Suspend/resume the synic for hibernation Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 4/9] Drivers: hv: vmbus: Implement suspend/resume for VSC drivers " Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 5/9] Drivers: hv: vmbus: Ignore the offers when resuming from hibernation Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 6/9] Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 7/9] Drivers: hv: vmbus: Clean up hv_sock channels by force upon suspend Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 8/9] Drivers: hv: vmbus: Suspend after cleaning up hv_sock and sub channels Dexuan Cui
2019-09-05 23:01 ` [PATCH v5 9/9] Drivers: hv: vmbus: Resume after fixing up old primary channels Dexuan Cui
2019-09-06 20:03 ` [PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation Sasha Levin
2019-09-06 22:45   ` Dexuan Cui
2019-09-08 12:13     ` Sasha Levin
2019-09-08 16:32       ` Dexuan Cui

Linux-HyperV Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-hyperv/0 linux-hyperv/git/0.git

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

Example config snippet for mirrors

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


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