[PATCH v3 1/2] drivers/hv: introduce vmbus_channel_set_cpu()

[PATCH v3 1/2] drivers/hv: introduce vmbus_channel_set_cpu()

[Hamza Mahfooz]

The core functionality in target_cpu_store() is also needed in a
subsequent patch for automatically changing the CPU when taking
a CPU offline. As such, factor out the body of target_cpu_store()
into new function vmbus_channel_set_cpu() that can also be used
elsewhere.

No functional change is intended.

Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Michael Kelley <mhklinux@outlook.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Hamza Mahfooz <hamzamahfooz@linux.microsoft.com>
---
v2: separate vmbus_channel_set_cpu() changes from
    cpu offlining changes.

v3: address comments from Michael.
---
 drivers/hv/vmbus_drv.c | 50 +++++++++++++++++++++++++-----------------
 include/linux/hyperv.h |  1 +
 2 files changed, 31 insertions(+), 20 deletions(-)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 2892b8da20a5..0ca0e85e6edd 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1611,16 +1611,16 @@ static ssize_t target_cpu_show(struct vmbus_channel *channel, char *buf)
 {
 	return sprintf(buf, "%u\n", channel->target_cpu);
 }
-static ssize_t target_cpu_store(struct vmbus_channel *channel,
-				const char *buf, size_t count)
+
+int vmbus_channel_set_cpu(struct vmbus_channel *channel, u32 target_cpu)
 {
-	u32 target_cpu, origin_cpu;
-	ssize_t ret = count;
+	u32 origin_cpu;
+	int ret = 0;
 
-	if (vmbus_proto_version < VERSION_WIN10_V4_1)
-		return -EIO;
+	lockdep_assert_cpus_held();
+	lockdep_assert_held(&vmbus_connection.channel_mutex);
 
-	if (sscanf(buf, "%uu", &target_cpu) != 1)
+	if (vmbus_proto_version < VERSION_WIN10_V4_1)
 		return -EIO;
 
 	/* Validate target_cpu for the cpumask_test_cpu() operation below. */
@@ -1630,22 +1630,17 @@ static ssize_t target_cpu_store(struct vmbus_channel *channel,
 	if (!cpumask_test_cpu(target_cpu, housekeeping_cpumask(HK_TYPE_MANAGED_IRQ)))
 		return -EINVAL;
 
-	/* No CPUs should come up or down during this. */
-	cpus_read_lock();
-
-	if (!cpu_online(target_cpu)) {
-		cpus_read_unlock();
+	if (!cpu_online(target_cpu))
 		return -EINVAL;
-	}
 
 	/*
-	 * Synchronizes target_cpu_store() and channel closure:
+	 * Synchronizes vmbus_channel_set_cpu() and channel closure:
 	 *
 	 * { Initially: state = CHANNEL_OPENED }
 	 *
 	 * CPU1				CPU2
 	 *
-	 * [target_cpu_store()]		[vmbus_disconnect_ring()]
+	 * [vmbus_channel_set_cpu()]	[vmbus_disconnect_ring()]
 	 *
 	 * LOCK channel_mutex		LOCK channel_mutex
 	 * LOAD r1 = state		LOAD r2 = state
@@ -1660,7 +1655,6 @@ static ssize_t target_cpu_store(struct vmbus_channel *channel,
 	 * Note.  The host processes the channel messages "sequentially", in
 	 * the order in which they are received on a per-partition basis.
 	 */
-	mutex_lock(&vmbus_connection.channel_mutex);
 
 	/*
 	 * Hyper-V will ignore MODIFYCHANNEL messages for "non-open" channels;
@@ -1668,17 +1662,17 @@ static ssize_t target_cpu_store(struct vmbus_channel *channel,
 	 */
 	if (channel->state != CHANNEL_OPENED_STATE) {
 		ret = -EIO;
-		goto cpu_store_unlock;
+		goto end;
 	}
 
 	origin_cpu = channel->target_cpu;
 	if (target_cpu == origin_cpu)
-		goto cpu_store_unlock;
+		goto end;
 
 	if (vmbus_send_modifychannel(channel,
 				     hv_cpu_number_to_vp_number(target_cpu))) {
 		ret = -EIO;
-		goto cpu_store_unlock;
+		goto end;
 	}
 
 	/*
@@ -1708,9 +1702,25 @@ static ssize_t target_cpu_store(struct vmbus_channel *channel,
 				origin_cpu, target_cpu);
 	}
 
-cpu_store_unlock:
+end:
+	return ret;
+}
+
+static ssize_t target_cpu_store(struct vmbus_channel *channel,
+				const char *buf, size_t count)
+{
+	ssize_t ret = count;
+	u32 target_cpu;
+
+	if (sscanf(buf, "%uu", &target_cpu) != 1)
+		return -EIO;
+
+	cpus_read_lock();
+	mutex_lock(&vmbus_connection.channel_mutex);
+	ret = vmbus_channel_set_cpu(channel, target_cpu);
 	mutex_unlock(&vmbus_connection.channel_mutex);
 	cpus_read_unlock();
+
 	return ret;
 }
 static VMBUS_CHAN_ATTR(cpu, 0644, target_cpu_show, target_cpu_store);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 02a226bcf0ed..25e9e982f1b0 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1670,6 +1670,7 @@ int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 				  const guid_t *shv_host_servie_id);
 int vmbus_send_modifychannel(struct vmbus_channel *channel, u32 target_vp);
 void vmbus_set_event(struct vmbus_channel *channel);
+int vmbus_channel_set_cpu(struct vmbus_channel *channel, u32 target_cpu);
 
 /* Get the start of the ring buffer. */
 static inline void *
-- 
2.47.1

[PATCH v3 2/2] drivers/hv: add CPU offlining support

[Hamza Mahfooz]

Currently, it is tedious to offline CPUs. Since, most CPUs will have
vmbus channels attached to them that a user would have to manually
rebind elsewhere. So, as made mention of in
commit d570aec0f2154 ("Drivers: hv: vmbus: Synchronize init_vp_index()
vs. CPU hotplug"), rebind channels associated with CPUs that a user is
trying to offline to a new "randomly" selected CPU.

Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Michael Kelley <mhklinux@outlook.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Hamza Mahfooz <hamzamahfooz@linux.microsoft.com>
---
v2: remove cpus_read_{un,}lock() from hv_pick_new_cpu() and add
    lockdep_assert_cpus_held().

v3: use for_each_cpu_wrap() in hv_pick_new_cpu().
---
 drivers/hv/hv.c | 63 +++++++++++++++++++++++++++++++++++++------------
 1 file changed, 48 insertions(+), 15 deletions(-)

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 36d9ba097ff5..f120b808258f 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -433,13 +433,46 @@ static bool hv_synic_event_pending(void)
 	return pending;
 }
 
+static int hv_pick_new_cpu(struct vmbus_channel *channel,
+			   unsigned int current_cpu)
+{
+	int ret = 0;
+	int cpu;
+
+	lockdep_assert_cpus_held();
+	lockdep_assert_held(&vmbus_connection.channel_mutex);
+
+	/*
+	 * We can't assume that the relevant interrupts will be sent before
+	 * the cpu is offlined on older versions of hyperv.
+	 */
+	if (vmbus_proto_version < VERSION_WIN10_V5_3)
+		return -EBUSY;
+
+	for_each_cpu_wrap(cpu, cpu_online_mask,
+			  get_random_u32_below(nr_cpu_ids)) {
+		if (cpu == current_cpu || cpu == VMBUS_CONNECT_CPU)
+			continue;
+
+		ret = vmbus_channel_set_cpu(channel, cpu);
+
+		if (!ret)
+			break;
+	}
+
+	if (ret)
+		ret = vmbus_channel_set_cpu(channel, VMBUS_CONNECT_CPU);
+
+	return ret;
+}
+
 /*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
 int hv_synic_cleanup(unsigned int cpu)
 {
 	struct vmbus_channel *channel, *sc;
-	bool channel_found = false;
+	int ret = 0;
 
 	if (vmbus_connection.conn_state != CONNECTED)
 		goto always_cleanup;
@@ -456,31 +489,31 @@ int hv_synic_cleanup(unsigned int cpu)
 
 	/*
 	 * 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
-	 * fail; this will effectively prevent CPU offlining.
-	 *
-	 * TODO: Re-bind the channels to different CPUs.
+	 * cleanup.
 	 */
 	mutex_lock(&vmbus_connection.channel_mutex);
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
 		if (channel->target_cpu == cpu) {
-			channel_found = true;
-			break;
+			ret = hv_pick_new_cpu(channel, cpu);
+
+			if (ret) {
+				mutex_unlock(&vmbus_connection.channel_mutex);
+				return ret;
+			}
 		}
 		list_for_each_entry(sc, &channel->sc_list, sc_list) {
 			if (sc->target_cpu == cpu) {
-				channel_found = true;
-				break;
+				ret = hv_pick_new_cpu(channel, cpu);
+
+				if (ret) {
+					mutex_unlock(&vmbus_connection.channel_mutex);
+					return ret;
+				}
 			}
 		}
-		if (channel_found)
-			break;
 	}
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
-	if (channel_found)
-		return -EBUSY;
-
 	/*
 	 * channel_found == false means that any channels that were previously
 	 * assigned to the CPU have been reassigned elsewhere with a call of
@@ -497,5 +530,5 @@ int hv_synic_cleanup(unsigned int cpu)
 
 	hv_synic_disable_regs(cpu);
 
-	return 0;
+	return ret;
 }
-- 
2.47.1

Re: [PATCH v3 1/2] drivers/hv: introduce vmbus_channel_set_cpu()

[kernel test robot]

Hi Hamza,

kernel test robot noticed the following build errors:

[auto build test ERROR on linus/master]
[also build test ERROR on v6.13-rc7 next-20250117]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Hamza-Mahfooz/drivers-hv-add-CPU-offlining-support/20250116-054519
base:   linus/master
patch link:    https://lore.kernel.org/r/20250115214306.154853-1-hamzamahfooz%40linux.microsoft.com
patch subject: [PATCH v3 1/2] drivers/hv: introduce vmbus_channel_set_cpu()
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250119/202501190802.DKAgQNvk-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501190802.DKAgQNvk-lkp@intel.com/

All errors (new ones prefixed by >>):

   Makefile:60: warning: overriding recipe for target 'emit_tests'
   ../lib.mk:182: warning: ignoring old recipe for target 'emit_tests'
   make[1]: *** No targets.  Stop.
>> Makefile:47: *** Cannot find a vmlinux for VMLINUX_BTF at any of "  ../../../../vmlinux /sys/kernel/btf/vmlinux /boot/vmlinux-5.9.0-2-amd64".  Stop.
   make[1]: *** No targets.  Stop.
   make[1]: *** No targets.  Stop.


vim +47 Makefile

3812b8c5c5d527 Masahiro Yamada 2019-02-22  46  
3812b8c5c5d527 Masahiro Yamada 2019-02-22 @47  # Do not use make's built-in rules and variables
3812b8c5c5d527 Masahiro Yamada 2019-02-22  48  # (this increases performance and avoids hard-to-debug behaviour)
3812b8c5c5d527 Masahiro Yamada 2019-02-22  49  MAKEFLAGS += -rR
3812b8c5c5d527 Masahiro Yamada 2019-02-22  50  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki