platform/x86/amd/hsmp: Serialize the data plane against socket teardown

Before this change the HSMP data plane runs without any coordination with
driver teardown: open /dev/hsmp fds and hwmon sysfs reads call
hsmp_send_message() while probe and remove bring sockets up and down.
misc_deregister() does not drain already-open fds, so an in-flight message
can race a concurrent unbind and touch a freed socket array or an unmapped
mailbox.

Add the read side of hsmp_sock_rwsem to the data plane. Split the message
send into hsmp_send_message_locked(), which does the bounds check and MMIO
access and asserts the rwsem is held, and hsmp_send_message(), which wraps
it in guard(rwsem_read). Probe and remove hold the rwsem for write, so they
drain in-flight messages and keep new ones out while they tear a socket
down.

The probe-time senders run under the probe write lock and so must not take
the rwsem again: route hsmp_test(), hsmp_cache_proto_ver() and
hsmp_get_tbl_dram_base() through hsmp_send_message_locked() to avoid
recursive locking. A single rwsem therefore covers both the data plane and
the probe/remove handshake, with no separate probe lock:

 - acpi.c already holds it for write across probe for the socket-array and
   misc-registration handshake, so the mailbox handshake now nests under
   that same lock.

 - plat.c takes it for write around init_platform_device(). It is not held
   across devm_add_action_or_reset() so the release action, which also
   takes it for write, cannot deadlock if that registration fails.

Signed-off-by: Muralidhara M K <muralidhara.mk@amd.com>
Link: https://patch.msgid.link/20260723094656.3806028-7-muralidhara.mk@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>

drivers/platform/x86/amd/hsmp/hsmp.c

@@ -45,9 +45,12 @@
 static struct hsmp_plat_device hsmp_pdev;
 
 /*
- * Serializes AMD HSMP socket bring-up and teardown: ACPI probe and remove take
- * it for write so concurrent per-socket probes cannot race the is_probed
- * handshake or the one-time socket-array allocation.
+ * Gates the AMD HSMP data plane against socket bring-up and teardown.
+ *
+ * hsmp_send_message() takes it for read, so open /dev/hsmp fds and hwmon reads
+ * run concurrently. Probe and remove take it for write: probe brings sockets
+ * up (running the mailbox handshake via hsmp_send_message_locked()) and remove
+ * tears them down, both excluding and draining the data plane.
  */
 DECLARE_RWSEM(hsmp_sock_rwsem);
 EXPORT_SYMBOL_NS_GPL(hsmp_sock_rwsem, "AMD_HSMP");
@@ -211,12 +214,20 @@ static int validate_message(struct hsmp_message *msg)
 	return 0;
 }
 
-int hsmp_send_message(struct hsmp_message *msg)
+/*
+ * Core message send. The caller must hold hsmp_sock_rwsem: the data plane
+ * takes it for read so many messages run concurrently, while the probe-time
+ * senders run under the write lock taken by probe. Holding it here serializes
+ * every message against socket teardown, which also holds it for write.
+ */
+static int hsmp_send_message_locked(struct hsmp_message *msg)
 {
 	struct hsmp_socket *sock;
 	unsigned int sock_ind;
 	int ret;
 
+	lockdep_assert_held(&hsmp_sock_rwsem);
+
 	if (!msg)
 		return -EINVAL;
 	ret = validate_message(msg);
@@ -243,7 +254,8 @@ int hsmp_send_message(struct hsmp_message *msg)
 	 * non-NULL dev also guarantees virt_base_addr, the mailbox offsets and
 	 * the semaphore are visible.
 	 *
-	 * Pairs with smp_store_release(&sock->dev) in hsmp_parse_acpi_table().
+	 * Held under hsmp_sock_rwsem; pairs with smp_store_release(&sock->dev)
+	 * in hsmp_parse_acpi_table().
 	 */
 	if (!smp_load_acquire(&sock->dev))
 		return -ENODEV;
@@ -258,6 +270,19 @@ int hsmp_send_message(struct hsmp_message *msg)
 
 	return ret;
 }
+
+int hsmp_send_message(struct hsmp_message *msg)
+{
+	/*
+	 * Data-plane entry point: open /dev/hsmp fds and hwmon sysfs reads issue
+	 * messages from here. Take hsmp_sock_rwsem for read so messages run
+	 * concurrently with each other but are drained and kept out while
+	 * probe/remove hold it for write to tear a socket down.
+	 */
+	guard(rwsem_read)(&hsmp_sock_rwsem);
+
+	return hsmp_send_message_locked(msg);
+}
 EXPORT_SYMBOL_NS_GPL(hsmp_send_message, "AMD_HSMP");
 
 int hsmp_msg_get_nargs(u16 sock_ind, u32 msg_id, u32 *data, u8 num_args)
@@ -298,7 +323,7 @@ int hsmp_test(u16 sock_ind, u32 value)
 	msg.args[0]	= value;
 	msg.sock_ind	= sock_ind;
 
-	ret = hsmp_send_message(&msg);
+	ret = hsmp_send_message_locked(&msg);
 	if (ret)
 		return ret;
 
@@ -478,7 +503,7 @@ int hsmp_get_tbl_dram_base(u16 sock_ind)
 	msg.response_sz	= hsmp_msg_desc_table[HSMP_GET_METRIC_TABLE_DRAM_ADDR].response_sz;
 	msg.msg_id	= HSMP_GET_METRIC_TABLE_DRAM_ADDR;
 
-	ret = hsmp_send_message(&msg);
+	ret = hsmp_send_message_locked(&msg);
 	if (ret)
 		return ret;
 
@@ -521,7 +546,7 @@ int hsmp_cache_proto_ver(u16 sock_ind)
 	msg.sock_ind	= sock_ind;
 	msg.response_sz = hsmp_msg_desc_table[HSMP_GET_PROTO_VER].response_sz;
 
-	ret = hsmp_send_message(&msg);
+	ret = hsmp_send_message_locked(&msg);
 	if (!ret)
 		hsmp_pdev.proto_ver = msg.args[0];
 

drivers/platform/x86/amd/hsmp/hsmp.h

@@ -79,8 +79,8 @@ static inline int hsmp_create_sensor(struct device *dev, u16 sock_ind) { return
 int hsmp_msg_get_nargs(u16 sock_ind, u32 msg_id, u32 *data, u8 num_args);
 
 /*
- * Serializes HSMP socket bring-up and teardown. ACPI probe and remove take it
- * for write.
+ * Gates the HSMP data plane: hsmp_send_message() takes it for read; probe and
+ * remove take it for write to bring sockets up and tear them down.
  */
 extern struct rw_semaphore hsmp_sock_rwsem;
 #endif /* HSMP_H */

drivers/platform/x86/amd/hsmp/plat.c

@@ -13,12 +13,14 @@
 
 #include <linux/acpi.h>
 #include <linux/build_bug.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/dev_printk.h>
 #include <linux/kconfig.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
+#include <linux/rwsem.h>
 #include <linux/sysfs.h>
 
 #include <asm/amd/node.h>
@@ -204,15 +206,20 @@ static int init_platform_device(struct device *dev)
 /*
  * The socket array is devm-managed and freed by the driver core, but the
  * metric-table DRAM regions are mapped with plain ioremap() during probe and
- * are therefore not covered by devres.
+ * the per-socket mutexes need an explicit mutex_destroy(), neither of which
+ * devres covers.
  *
- * Drop those mappings from a devres action so both remove and probe failure
- * unmap them exactly once, before the socket array they refer to is freed.
+ * Take the data-plane rwsem for write to drain any in-flight
+ * hsmp_send_message(), unmap the metric tables, destroy the mutexes and drop
+ * the global socket pointer, all before devres frees the array. Registered as
+ * a devres action so it runs on both remove and probe failure.
  */
 static void hsmp_pltdrv_release(void *data)
 {
+	guard(rwsem_write)(&hsmp_sock_rwsem);
 	hsmp_unmap_metric_tbls(hsmp_pdev);
 	hsmp_destroy_metric_read_locks(hsmp_pdev);
+	hsmp_pdev->sock = NULL;
 }
 
 static int hsmp_pltdrv_probe(struct platform_device *pdev)
@@ -231,7 +238,16 @@ static int hsmp_pltdrv_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = init_platform_device(&pdev->dev);
+	/*
+	 * init_platform_device() runs the mailbox handshake via the probe-only
+	 * senders, which issue messages through hsmp_send_message_locked() and
+	 * so require hsmp_sock_rwsem held. Hold it for write, matching probe's
+	 * role as a socket bring-up path. The lock is not held across
+	 * devm_add_action_or_reset() above so the release action, which also
+	 * takes it for write, does not deadlock if that registration fails.
+	 */
+	scoped_guard(rwsem_write, &hsmp_sock_rwsem)
+		ret = init_platform_device(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to init HSMP mailbox\n");
 		return ret;