Skip to contentSkip to conversation

Asynchronous shutdown interface and example implementation

PATCH Superseded Tanjore Suresh 9 participants 12 messages Mar 28, 2022 – Mar 31, 2022

Subsystems (3)

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

cover Asynchronous shutdown interface and example implementation

Problem:

Some of our machines are configured with many NVMe devices and are validated for strict shutdown time requirements. Each NVMe device plugged into the system, typicaly takes about 4.5 secs to shutdown. A system with 16 such NVMe devices will takes approximately 80 secs to shutdown and go through reboot.

The current shutdown APIs as defined at bus level is defined to be synchronous. Therefore, more devices are in the system the greater the time it takes to shutdown. This shutdown time significantly contributes the machine reboot time.

Solution:

This patch set proposes an asynchronous shutdown interface at bus level, modifies the core driver, device shutdown routine to exploit the new interface while maintaining backward compatibility with synchronous implementation already existing (Patch 1 of 3) and exploits new interface to enable all PCI-E based devices to use asynchronous interface semantics if necessary (Patch 2 of 3). The implementation at PCI-E level also works in a backward compatible way, to allow exiting device implementation to work with current synchronous semantics. Only show cases an example implementation for NVMe device to exploit this asynchronous shutdown interface. (Patch 3 of 3).

Tanjore Suresh (3):
driver core: Support asynchronous driver shutdown
PCI: Support asynchronous shutdown
nvme: Add async shutdown support

 drivers/base/core.c        | 39 ++++++++++++++++++-
 drivers/nvme/host/core.c   | 28 +++++++++----
 drivers/nvme/host/nvme.h   |  8 ++++
 drivers/nvme/host/pci.c    | 80 ++++++++++++++++++++++++--------------
 drivers/pci/pci-driver.c   | 17 ++++++--
 include/linux/device/bus.h | 10 +++++
 include/linux/pci.h        |  2 +
 7 files changed, 144 insertions(+), 40 deletions(-)
Signature · 1 line
2.35.1.1021.g381101b075-goog
#1 lore raw

PATCH 1/3 driver core: Support asynchronous driver shutdown

This changes the bus driver interface with additional entry points to enable devices to implement asynchronous shutdown. The existing synchronous interface to shutdown is unmodified and retained for backward compatibility.

This changes the common device shutdown code to enable devices to participate in asynchronous shutdown implementation.

---
 drivers/base/core.c        | 39 +++++++++++++++++++++++++++++++++++++-
 include/linux/device/bus.h | 10 ++++++++++
 2 files changed, 48 insertions(+), 1 deletion(-)
drivers/base/core.c +38 -1
index 3d6430eb0c6a..359e7067e8b8 100644
@@ -4479,6 +4479,7 @@ EXPORT_SYMBOL_GPL(device_change_owner);
 void device_shutdown(void)
 {
 	struct device *dev, *parent;
+	LIST_HEAD(async_shutdown_list);
 
 	wait_for_device_probe();
 	device_block_probing();
@@ -4523,7 +4524,14 @@ void device_shutdown(void)
 				dev_info(dev, "shutdown_pre\n");
 			dev->class->shutdown_pre(dev);
 		}
-		if (dev->bus && dev->bus->shutdown) {
+
+		if (dev->bus && dev->bus->shutdown_pre) {
+			if (initcall_debug)
+				dev_info(dev, "shutdown_pre\n");
+			dev->bus->shutdown_pre(dev);
+			list_add(&dev->kobj.entry,
+				&async_shutdown_list);
+		} else if (dev->bus && dev->bus->shutdown) {
 			if (initcall_debug)
 				dev_info(dev, "shutdown\n");
 			dev->bus->shutdown(dev);
@@ -4543,6 +4551,35 @@ void device_shutdown(void)
 		spin_lock(&devices_kset->list_lock);
 	}
 	spin_unlock(&devices_kset->list_lock);
+
+	/*
+	 * Second pass spin for only devices, that have configured
+	 * Asynchronous shutdown.
+	 */
+	while (!list_empty(&async_shutdown_list)) {
+		dev = list_entry(async_shutdown_list.next, struct device,
+				kobj.entry);
+		parent = get_device(dev->parent);
+		get_device(dev);
+		/*
+		 * Make sure the device is off the  list
+		 */
+		list_del_init(&dev->kobj.entry);
+		if (parent)
+			device_lock(parent);
+		device_lock(dev);
+		if (dev->bus && dev->bus->shutdown_post) {
+			if (initcall_debug)
+				dev_info(dev,
+				"shutdown_post called\n");
+			dev->bus->shutdown_post(dev);
+		}
+		device_unlock(dev);
+		if (parent)
+			device_unlock(parent);
+		put_device(dev);
+		put_device(parent);
+	}
 }
 
 /*
include/linux/device/bus.h +10 -0
index a039ab809753..e261819601e9 100644
@@ -49,6 +49,14 @@ struct fwnode_handle;
  *		will never get called until they do.
  * @remove:	Called when a device removed from this bus.
  * @shutdown:	Called at shut-down time to quiesce the device.
+ * @shutdown_pre:	Called at the shutdown-time to start the shutdown
+ *			process on the device. This entry point will be called
+ *			only when the bus driver has indicated it would like
+ *			to participate in asynchronous shutdown completion.
+ * @shutdown_post:	Called at shutdown-time  to complete the shutdown
+ *			process of the device. This entry point will be called
+ *			only when the bus drive has indicated it would like to
+ *			participate in the asynchronous shutdown completion.
  *
  * @online:	Called to put the device back online (after offlining it).
  * @offline:	Called to put the device offline for hot-removal. May fail.
@@ -93,6 +101,8 @@ struct bus_type {
 	void (*sync_state)(struct device *dev);
 	void (*remove)(struct device *dev);
 	void (*shutdown)(struct device *dev);
+	void (*shutdown_pre)(struct device *dev);
+	void (*shutdown_post)(struct device *dev);
 
 	int (*online)(struct device *dev);
 	int (*offline)(struct device *dev);
Signature · 1 line
2.35.1.1021.g381101b075-goog
#2 lore raw

PATCH 2/3 PCI: Support asynchronous shutdown

Enhances the base PCI driver to add support for asynchronous shutdown.

Assume a device takes n secs to shutdown. If a machine has been populated with M such devices, the total time spent in shutting down all the devices will be M * n secs, if the shutdown is done synchronously. For example, if NVMe PCI Controllers take 5 secs to shutdown and if there are 16 such NVMe controllers in a system, system will spend a total of 80 secs to shutdown all
NVMe devices in that system.

In order to speed up the shutdown time, asynchronous interface to shutdown has been implemented. This will significantly reduce the machine reboot time.

---
 drivers/pci/pci-driver.c | 17 ++++++++++++++---
 include/linux/pci.h      |  2 ++
 2 files changed, 16 insertions(+), 3 deletions(-)
drivers/pci/pci-driver.c +14 -3
index 4ceeb75fc899..0d0b46d71e88 100644
@@ -501,14 +501,16 @@ static void pci_device_remove(struct device *dev)
 	pci_dev_put(pci_dev);
 }
 
-static void pci_device_shutdown(struct device *dev)
+static void pci_device_shutdown_pre(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct pci_driver *drv = pci_dev->driver;
 
 	pm_runtime_resume(dev);
 
-	if (drv && drv->shutdown)
+	if (drv && drv->shutdown_pre)
+		drv->shutdown_pre(pci_dev);
+	else if (drv && drv->shutdown)
 		drv->shutdown(pci_dev);
 
 	/*
@@ -522,6 +524,14 @@ static void pci_device_shutdown(struct device *dev)
 		pci_clear_master(pci_dev);
 }
 
+static void pci_device_shutdown_post(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
+
+	if (drv && drv->shutdown_post)
+		drv->shutdown_post(pci_dev);
+}
 #ifdef CONFIG_PM
 
 /* Auxiliary functions used for system resume and run-time resume. */
@@ -1625,7 +1635,8 @@ struct bus_type pci_bus_type = {
 	.uevent		= pci_uevent,
 	.probe		= pci_device_probe,
 	.remove		= pci_device_remove,
-	.shutdown	= pci_device_shutdown,
+	.shutdown_pre	= pci_device_shutdown_pre,
+	.shutdown_post	= pci_device_shutdown_post,
 	.dev_groups	= pci_dev_groups,
 	.bus_groups	= pci_bus_groups,
 	.drv_groups	= pci_drv_groups,
include/linux/pci.h +2 -0
index b957eeb89c7a..19047fcb3c8a 100644
@@ -905,6 +905,8 @@ struct pci_driver {
 	int  (*suspend)(struct pci_dev *dev, pm_message_t state);	/* Device suspended */
 	int  (*resume)(struct pci_dev *dev);	/* Device woken up */
 	void (*shutdown)(struct pci_dev *dev);
+	void (*shutdown_pre)(struct pci_dev *dev);
+	void (*shutdown_post)(struct pci_dev *dev);
 	int  (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */
 	int  (*sriov_set_msix_vec_count)(struct pci_dev *vf, int msix_vec_count); /* On PF */
 	u32  (*sriov_get_vf_total_msix)(struct pci_dev *pf);
Signature · 1 line
2.35.1.1021.g381101b075-goog
#3 lore raw

PATCH 3/3 nvme: Add async shutdown support

This works with the asynchronous shutdown mechanism setup for the PCI drivers and participates to provide both pre and post shutdown routines at pci_driver structure level.

The shutdown_pre routine starts the shutdown and does not wait for the shutdown to complete. The shutdown_post routine waits for the shutdown to complete on individual controllers that this driver instance controls. This mechanism optimizes to speed up the shutdown in a system which host many controllers.

---
 drivers/nvme/host/core.c | 28 ++++++++++----
 drivers/nvme/host/nvme.h |  8 ++++
 drivers/nvme/host/pci.c  | 80 +++++++++++++++++++++++++---------------
 3 files changed, 80 insertions(+), 36 deletions(-)
drivers/nvme/host/core.c +21 -7
index 677fa4bf76d3..24b08789fd34 100644
@@ -2173,16 +2173,30 @@ EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
 
 int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
 {
-	unsigned long timeout = jiffies + (ctrl->shutdown_timeout * HZ);
-	u32 csts;
 	int ret;
 
+	ret = nvme_shutdown_ctrl_start(ctrl);
+	if (ret)
+		return ret;
+	return nvme_wait_for_shutdown_cmpl(ctrl);
+}
+EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);
+
+int nvme_shutdown_ctrl_start(struct nvme_ctrl *ctrl)
+{
+
 	ctrl->ctrl_config &= ~NVME_CC_SHN_MASK;
 	ctrl->ctrl_config |= NVME_CC_SHN_NORMAL;
 
-	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
-	if (ret)
-		return ret;
+	return ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
+}
+EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl_start);
+
+int nvme_wait_for_shutdown_cmpl(struct nvme_ctrl *ctrl)
+{
+	unsigned long deadline = jiffies + (ctrl->shutdown_timeout * HZ);
+	u32 csts;
+	int ret;
 
 	while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
 		if ((csts & NVME_CSTS_SHST_MASK) == NVME_CSTS_SHST_CMPLT)
@@ -2191,7 +2205,7 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
 		msleep(100);
 		if (fatal_signal_pending(current))
 			return -EINTR;
-		if (time_after(jiffies, timeout)) {
+		if (time_after(jiffies, deadline)) {
 			dev_err(ctrl->device,
 				"Device shutdown incomplete; abort shutdown\n");
 			return -ENODEV;
@@ -2200,7 +2214,7 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);
+EXPORT_SYMBOL_GPL(nvme_wait_for_shutdown_cmpl);
 
 static int nvme_configure_timestamp(struct nvme_ctrl *ctrl)
 {
drivers/nvme/host/nvme.h +8 -0
index f4b674a8ce20..87f5803ef577 100644
@@ -170,6 +170,12 @@ enum {
 	NVME_REQ_USERCMD		= (1 << 1),
 };
 
+enum shutdown_type {
+	DO_NOT_SHUTDOWN = 0,
+	SHUTDOWN_TYPE_SYNC = 1,
+	SHUTDOWN_TYPE_ASYNC = 2,
+};
+
 static inline struct nvme_request *nvme_req(struct request *req)
 {
 	return blk_mq_rq_to_pdu(req);
@@ -672,6 +678,8 @@ bool nvme_wait_reset(struct nvme_ctrl *ctrl);
 int nvme_disable_ctrl(struct nvme_ctrl *ctrl);
 int nvme_enable_ctrl(struct nvme_ctrl *ctrl);
 int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
+int nvme_shutdown_ctrl_start(struct nvme_ctrl *ctrl);
+int nvme_wait_for_shutdown_cmpl(struct nvme_ctrl *ctrl);
 int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		const struct nvme_ctrl_ops *ops, unsigned long quirks);
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
drivers/nvme/host/pci.c +51 -29

216 lines not on this page · raw message

Signature · 1 line
2.35.1.1021.g381101b075-goog
#4 lore raw

Re: [PATCH v1 1/3] driver core: Support asynchronous driver shutdown

In reply to Tanjore Suresh
Quoted 8 lines · Tanjore Suresh

This changes the bus driver interface with additional entry points to enable devices to implement asynchronous shutdown. The existing synchronous interface to shutdown is unmodified and retained for backward compatibility.

This changes the common device shutdown code to enable devices to participate in asynchronous shutdown implementation.

nice to see someone looking at improving the shutdown path

drivers/base/core.c EXPORT_SYMBOL_GPL(device_change_owner); · line 4479

Quoted 12 lines
---
 drivers/base/core.c        | 39 +++++++++++++++++++++++++++++++++++++-
 include/linux/device/bus.h | 10 ++++++++++
 2 files changed, 48 insertions(+), 1 deletion(-)
drivers/base/core.c +0 -0
index 3d6430eb0c6a..359e7067e8b8 100644
@@ -4479,6 +4479,7 @@ EXPORT_SYMBOL_GPL(device_change_owner);
 *snip*

This all seems a bit dangerous and I'm wondering what systems you've tested these changes with. I had a look at implementing something similar a few years ago and one case that always concerned me was embedded systems where the PCIe root complex also has a driver bound. Say you've got the following PCIe topology:

00:00.0 - root port
01:00.0 - nvme drive

With the current implementation of device_shutdown() we can guarantee that the child device (the nvme) is shut down before we start trying to shut down the parent device (the root complex) so there's no possibility of deadlocks and other dependency headaches. With this implementation of async shutdown we lose that guarantee and I'm not sure what the consequences are. Personally I was never able to convince myself it was safe, but maybe you're braver than I am :)

That all said, there's probably only a few kinds of device that will really want to implement async shutdown support so maybe you can restrict it to leaf devices and flip the ordering around to something like:

for_each_device(dev) {
if (can_async(dev) && has_no_children(dev))
start_async_shutdown(dev)
}
wait_for_all_async_shutdowns_to_finish()

// tear down the remaining system devices synchronously for_each_device(dev)
do_sync_shutdown(dev)

include/linux/device/bus.h struct bus_type { · line 105

Quoted 11 lines
drivers/base/core.c +0 -0
 /*
include/linux/device/bus.h +2 -0
index a039ab809753..e261819601e9 100644
@@ -93,6 +101,8 @@ struct bus_type {
        void (*sync_state)(struct device *dev);
        void (*remove)(struct device *dev);
        void (*shutdown)(struct device *dev);
+       void (*shutdown_pre)(struct device *dev);
+       void (*shutdown_post)(struct device *dev);

Call them shutdown_async_start() / shutdown_async_end() or something IMO. These names are not at all helpful and they're easy to mix up their role with the class based shutdown_pre / _post

#5 lore raw

RE: [PATCH v1 1/3] driver core: Support asynchronous driver shutdown

Quoted 18 lines

From: Linux-nvme <[email protected]> On Behalf Of Oliver O'Halloran
Sent: Monday, March 28, 2022 8:20 PM
To: Tanjore Suresh
Cc: Greg Kroah-Hartman; Rafael J . Wysocki; Christoph Hellwig; Sagi Grimberg; Bjorn Helgaas; Linux Kernel Mailing List; [email protected]; linux- pci
Subject: Re: [PATCH v1 1/3] driver core: Support asynchronous driver shutdown

Quoted 6 lines · Tanjore Suresh

This changes the bus driver interface with additional entry points to enable devices to implement asynchronous shutdown. The existing synchronous interface to shutdown is unmodified and retained for backward compatibility.

Quoted 4 lines
Quoted 2 lines

This changes the common device shutdown code to enable devices to participate in asynchronous shutdown implementation.

nice to see someone looking at improving the shutdown path

Agreed!

I know this patch is mainly for PCI devices, however, NVMe over Fabrics devices can suffer even longer shutdowns. Last September, I reported that shutting down an NVMe-oF TCP connection while the network is down will result in a 1-minute deadlock. That's because the driver tries to perform a proper shutdown by sending commands to the remote target and the timeout for unanswered commands is 1-minute. If one needs to shut down several NVMe-oF connections, each connection will be shut down sequentially taking each 1 minute. Try running "nvme disconnect-all" while the network is down and you'll see what I mean. Of course, the KATO is supposed to detect when connectivity is lost, but if you have a long KATO (e.g. 2 minutes) you will most likely hit this condition.

Here's the patch I proposed in September, which shortens the timeout to 5 sec on a disconnect.

http://lists.infradead.org/pipermail/linux-nvme/2021-September/027867.html

Regards,
Martin Belanger

Quoted 61 lines

drivers/base/core.c EXPORT_SYMBOL_GPL(device_change_owner); · line 4479

Quoted 13 lines
---
 drivers/base/core.c        | 39 +++++++++++++++++++++++++++++++++++++-
 include/linux/device/bus.h | 10 ++++++++++
 2 files changed, 48 insertions(+), 1 deletion(-)
drivers/base/core.c index renamed from drivers/base/core.c +0 -0

3d6430eb0c6a..359e7067e8b8 100644

drivers/base/core.c +0 -0
@@ -4479,6 +4479,7 @@ EXPORT_SYMBOL_GPL(device_change_owner);
 *snip*

This all seems a bit dangerous and I'm wondering what systems you've tested these changes with. I had a look at implementing something similar a few years ago and one case that always concerned me was embedded systems where the PCIe root complex also has a driver bound.
Say you've got the following PCIe topology:

00:00.0 - root port
01:00.0 - nvme drive

With the current implementation of device_shutdown() we can guarantee that the child device (the nvme) is shut down before we start trying to shut down the parent device (the root complex) so there's no possibility of deadlocks and other dependency headaches. With this implementation of async shutdown we lose that guarantee and I'm not sure what the consequences are. Personally I was never able to convince myself it was safe, but maybe you're braver than I am :)

That all said, there's probably only a few kinds of device that will really want to implement async shutdown support so maybe you can restrict it to leaf devices and flip the ordering around to something
like:

for_each_device(dev) {
   if (can_async(dev) && has_no_children(dev))
      start_async_shutdown(dev)
}

wait_for_all_async_shutdowns_to_finish()

// tear down the remaining system devices synchronously for_each_device(dev)
do_sync_shutdown(dev)

include/linux/device/bus.h struct bus_type { · line 105

Quoted 11 lines
drivers/base/core.c +0 -0
 /*
include/linux/device/bus.h +2 -0
index a039ab809753..e261819601e9 100644
@@ -93,6 +101,8 @@ struct bus_type {
        void (*sync_state)(struct device *dev);
        void (*remove)(struct device *dev);
        void (*shutdown)(struct device *dev);
+       void (*shutdown_pre)(struct device *dev);
+       void (*shutdown_post)(struct device *dev);

Call them shutdown_async_start() / shutdown_async_end() or something IMO. These names are not at all helpful and they're easy to mix up their role with the class based shutdown_pre / _post

#6 lore raw

Re: [PATCH v1 1/3] driver core: Support asynchronous driver shutdown

Quoted 11 lines · Martin

I know this patch is mainly for PCI devices, however, NVMe over Fabrics devices can suffer even longer shutdowns. Last September, I reported that shutting down an NVMe-oF TCP connection while the network is down will result in a 1-minute deadlock. That's because the driver tries to perform a proper shutdown by sending commands to the remote target and the timeout for unanswered commands is 1-minute. If one needs to shut down several NVMe-oF connections, each connection will be shut down sequentially taking each 1 minute. Try running "nvme disconnect-all" while the network is down and you'll see what I mean. Of course, the KATO is supposed to detect when connectivity is lost, but if you have a long KATO (e.g. 2 minutes) you will most likely hit this condition.

I've debugging something similar:

[44888.710527] nvme nvme0: Removing ctrl: NQN "xxx"
[44898.981684] nvme nvme0: failed to send request -32
[44960.982977] nvme nvme0: queue 0: timeout request 0x18 type 4
[44960.983099] nvme nvme0: Property Set error: 881, offset 0x14

Currently testing this patch:

+++ b/drivers/nvme/host/tcp.c
@@ -1103,9 +1103,12 @@ static int nvme_tcp_try_send(struct nvme_tcp_queue *queue)

        if (ret == -EAGAIN) {
                ret = 0;
        } else if (ret < 0) {
+               struct request *rq = blk_mq_rq_from_pdu(queue->request);
+
                dev_err(queue->ctrl->ctrl.device,
                        "failed to send request %d\n", ret);
-               if (ret != -EPIPE && ret != -ECONNRESET)
+               if ((ret != -EPIPE && ret != -ECONNRESET) ||
+                   rq->cmd_flags & REQ_FAILFAST_DRIVER)
                        nvme_tcp_fail_request(queue->request);
                nvme_tcp_done_send_req(queue);
        }
#7 lore raw

Re: [PATCH v1 1/3] driver core: Support asynchronous driver shutdown

In reply to Oliver O'Halloran
Quoted 42 lines · Oliver O'Halloran
Quoted 8 lines · Tanjore Suresh

This changes the bus driver interface with additional entry points to enable devices to implement asynchronous shutdown. The existing synchronous interface to shutdown is unmodified and retained for backward compatibility.

This changes the common device shutdown code to enable devices to participate in asynchronous shutdown implementation.

nice to see someone looking at improving the shutdown path

drivers/base/core.c EXPORT_SYMBOL_GPL(device_change_owner); · line 4479

Quoted 12 lines
---
  drivers/base/core.c        | 39 +++++++++++++++++++++++++++++++++++++-
  include/linux/device/bus.h | 10 ++++++++++
  2 files changed, 48 insertions(+), 1 deletion(-)
drivers/base/core.c +0 -0
index 3d6430eb0c6a..359e7067e8b8 100644
@@ -4479,6 +4479,7 @@ EXPORT_SYMBOL_GPL(device_change_owner);
 *snip*

This all seems a bit dangerous and I'm wondering what systems you've tested these changes with. I had a look at implementing something similar a few years ago and one case that always concerned me was embedded systems where the PCIe root complex also has a driver bound. Say you've got the following PCIe topology:

00:00.0 - root port
01:00.0 - nvme drive

With the current implementation of device_shutdown() we can guarantee that the child device (the nvme) is shut down before we start trying to shut down the parent device (the root complex) so there's no possibility of deadlocks and other dependency headaches. With this implementation of async shutdown we lose that guarantee and I'm not sure what the consequences are. Personally I was never able to convince myself it was safe, but maybe you're braver than I am :)

Quoted 4 lines

That all said, there's probably only a few kinds of device that will really want to implement async shutdown support so maybe you can restrict it to leaf devices and flip the ordering around to something like:

It seems like it might be helpful to split the async shutdowns into refcounted hierarchies and proceed with the next level up when all the refs are in.

Ex:
00:00.0 - RP
01:00.0 - NVMe A
02:00.0 - Bridge USP

    03:00.0 - Bridge DSP
      04:00.0 - NVMe B
    03:00.1 - Bridge DSP
      05:00.0 - NVMe C

NVMe A could start shutting down at the beginning of the hierarchy traversal. Then async shutdown of bus 3 wouldn't start until all children of bus 3 are shutdown.

You could probably do this by having the async_shutdown_list in the pci_bus.

Quoted 27 lines
for_each_device(dev) {
    if (can_async(dev) && has_no_children(dev))
       start_async_shutdown(dev)
}

wait_for_all_async_shutdowns_to_finish()

// tear down the remaining system devices synchronously for_each_device(dev)
do_sync_shutdown(dev)

include/linux/device/bus.h struct bus_type { · line 105

Quoted 11 lines
drivers/base/core.c +0 -0
  /*
include/linux/device/bus.h +2 -0
index a039ab809753..e261819601e9 100644
@@ -93,6 +101,8 @@ struct bus_type {
         void (*sync_state)(struct device *dev);
         void (*remove)(struct device *dev);
         void (*shutdown)(struct device *dev);
+       void (*shutdown_pre)(struct device *dev);
+       void (*shutdown_post)(struct device *dev);

Call them shutdown_async_start() / shutdown_async_end() or something IMO. These names are not at all helpful and they're easy to mix up their role with the class based shutdown_pre / _post

#8 lore raw
In reply to Tanjore Suresh
Quoted 31 lines · Tanjore Suresh

Problem:

Some of our machines are configured with many NVMe devices and are validated for strict shutdown time requirements. Each NVMe device plugged into the system, typicaly takes about 4.5 secs to shutdown. A system with 16 such NVMe devices will takes approximately 80 secs to shutdown and go through reboot.

The current shutdown APIs as defined at bus level is defined to be synchronous. Therefore, more devices are in the system the greater the time it takes to shutdown. This shutdown time significantly contributes the machine reboot time.

Solution:

This patch set proposes an asynchronous shutdown interface at bus level, modifies the core driver, device shutdown routine to exploit the new interface while maintaining backward compatibility with synchronous implementation already existing (Patch 1 of 3) and exploits new interface to enable all PCI-E based devices to use asynchronous interface semantics if necessary (Patch 2 of 3). The implementation at PCI-E level also works in a backward compatible way, to allow exiting device implementation to work with current synchronous semantics. Only show cases an example implementation for NVMe device to exploit this asynchronous shutdown interface. (Patch 3 of 3).

Tanjore Suresh (3):
driver core: Support asynchronous driver shutdown
PCI: Support asynchronous shutdown
nvme: Add async shutdown support

Quoted 12 lines
 drivers/base/core.c        | 39 ++++++++++++++++++-
 drivers/nvme/host/core.c   | 28 +++++++++----
 drivers/nvme/host/nvme.h   |  8 ++++
 drivers/nvme/host/pci.c    | 80 ++++++++++++++++++++++++--------------
 drivers/pci/pci-driver.c   | 17 ++++++--
 include/linux/device/bus.h | 10 +++++
 include/linux/pci.h        |  2 +
 7 files changed, 144 insertions(+), 40 deletions(-)
Signature · 1 line
2.35.1.1021.g381101b075-goog

Hi,

This is the friendly patch-bot of Greg Kroah-Hartman. You have sent him a patch that has triggered this response. He used to manually respond to these common problems, but in order to save his sanity (he kept writing the same thing over and over, yet to different people), I was created. Hopefully you will not take offence and will fix the problem in your patch and resubmit it so that it can be accepted into the Linux kernel tree.

You are receiving this message because of the following common error(s) as indicated below:

- This looks like a new version of a previously submitted patch, but you did not list below the --- line any changes from the previous version. Please read the section entitled "The canonical patch format" in the kernel file, Documentation/SubmittingPatches for what needs to be done here to properly describe this.

If you wish to discuss this problem further, or you have questions about how to resolve this issue, please feel free to respond to this email and Greg will reply once he has dug out from the pending patches received from other developers.

thanks,

greg k-h's patch email bot

maintainer
#9 lore raw
In reply to Tanjore Suresh
Quoted 15 lines · Tanjore Suresh

Problem:

Some of our machines are configured with many NVMe devices and are validated for strict shutdown time requirements. Each NVMe device plugged into the system, typicaly takes about 4.5 secs to shutdown. A system with 16 such NVMe devices will takes approximately 80 secs to shutdown and go through reboot.

The current shutdown APIs as defined at bus level is defined to be synchronous. Therefore, more devices are in the system the greater the time it takes to shutdown. This shutdown time significantly contributes the machine reboot time.

Solution:

Quoted 10 lines

This patch set proposes an asynchronous shutdown interface at bus level, modifies the core driver, device shutdown routine to exploit the new interface while maintaining backward compatibility with synchronous implementation already existing (Patch 1 of 3) and exploits new interface to enable all PCI-E based devices to use asynchronous interface semantics if necessary (Patch 2 of 3). The implementation at PCI-E level also works in a backward compatible way, to allow exiting device implementation to work with current synchronous semantics. Only show cases an example implementation for NVMe device to exploit this asynchronous shutdown interface. (Patch 3 of 3).

Thanks, I agree we should improve shutdown times. I tried a while ago, but lost track to follow up at the time. Here's the reference, fwiw, though it may be out of date :):

http://lists.infradead.org/pipermail/linux-nvme/2014-May/000826.html

The above solution is similiar to how probe waits on an async domain. Maybe pci can schedule the async shutdown instead of relying on low-level drivers so that everyone implicitly benefits instead of just nvme? I'll double-check if that's reasonable, but I'll look through this series too.

#10 lore raw
Quoted 10 lines · Keith Busch

Thanks, I agree we should improve shutdown times. I tried a while ago, but lost track to follow up at the time. Here's the reference, fwiw, though it may be out of date :):

http://lists.infradead.org/pipermail/linux-nvme/2014-May/000826.html

The above solution is similiar to how probe waits on an async domain. Maybe pci can schedule the async shutdown instead of relying on low-level drivers so that everyone implicitly benefits instead of just nvme? I'll double-check if that's reasonable, but I'll look through this series too.

Using the async API seems much more reasonable than adding new callbacks.

However I'd argue that it shouldn't be necessary to amend any drivers, this should all be doable in the driver core: Basically a device needs to wait for its children and device links consumers to shutdown, apart from that everything should be able to run asynchronously.

Thanks,

Lukas

#11 lore raw
Quoted 13 lines · Lukas Wunner
Quoted 10 lines · Keith Busch

Thanks, I agree we should improve shutdown times. I tried a while ago, but lost track to follow up at the time. Here's the reference, fwiw, though it may be out of date :):

http://lists.infradead.org/pipermail/linux-nvme/2014-May/000826.html

The above solution is similiar to how probe waits on an async domain. Maybe pci can schedule the async shutdown instead of relying on low-level drivers so that everyone implicitly benefits instead of just nvme? I'll double-check if that's reasonable, but I'll look through this series too.

Quoted 6 lines

Using the async API seems much more reasonable than adding new callbacks.

However I'd argue that it shouldn't be necessary to amend any drivers, this should all be doable in the driver core: Basically a device needs to wait for its children and device links consumers to shutdown, apart from that everything should be able to run asynchronously.

Well, this is done already in the system-wide and hibernation paths. It should be possible to implement asynchronous shutdown analogously.