platform/x86/amd/hsmp: Serialize per-socket metric table reads with a mutex

HSMP_GET_METRIC_TABLE makes the firmware refill a shared per-socket metric
DRAM region, which hsmp_metric_tbl_read() then copies out with
memcpy_fromio(). Two concurrent readers of the metrics_bin sysfs attribute
on the same socket can race: one can trigger a fresh fill while the other
is mid-copy and return a torn snapshot. (The hwmon path does not touch
this region; it only issues power messages via hsmp_send_message().)

Embed a struct mutex metric_read_lock in each hsmp_socket and hold it
across the fill-and-copy in hsmp_metric_tbl_read(). Add
hsmp_init_metric_read_locks() and hsmp_destroy_metric_read_locks(), which
take only struct hsmp_plat_device and iterate pdev->sock[] over
pdev->num_sockets so the caller cannot pass a count that disagrees with the
array.

Wire them into both front-ends' probe and teardown paths so the mutex is
always initialized before metrics_bin is exposed: the platform driver and
the ACPI driver both drive hsmp_metric_tbl_read() through the same 0444
metrics_bin attribute. Doing this in one patch avoids a bisection point
where an ACPI read would lock an uninitialized mutex.

Signed-off-by: Muralidhara M K <muralidhara.mk@amd.com>
Link: https://patch.msgid.link/20260723094656.3806028-4-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/acpi.c

@@ -639,6 +639,8 @@ static int hsmp_acpi_probe(struct platform_device *pdev)
 					       GFP_KERNEL);
 		if (!hsmp_pdev->sock)
 			return -ENOMEM;
+
+		hsmp_init_metric_read_locks(hsmp_pdev);
 	}
 
 	ret = init_acpi(&pdev->dev);
@@ -670,6 +672,7 @@ static void hsmp_acpi_remove(struct platform_device *pdev)
 	 */
 	if (hsmp_pdev->is_probed) {
 		hsmp_misc_deregister();
+		hsmp_destroy_metric_read_locks(hsmp_pdev);
 		hsmp_pdev->is_probed = false;
 	}
 }

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

@@ -10,9 +10,11 @@
 #include <asm/amd/hsmp.h>
 
 #include <linux/acpi.h>
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/io.h>
+#include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/semaphore.h>
 #include <linux/sysfs.h>
@@ -415,6 +417,14 @@ ssize_t hsmp_metric_tbl_read(struct hsmp_socket *sock, char *buf, size_t size)
 	msg.msg_id	= HSMP_GET_METRIC_TABLE;
 	msg.sock_ind	= sock->sock_ind;
 
+	/*
+	 * HSMP_GET_METRIC_TABLE makes firmware refill this socket's shared
+	 * metric DRAM region, which is then copied out below.  Hold the
+	 * per-socket lock across the fill-and-copy so concurrent readers of the
+	 * same socket cannot return a torn snapshot.
+	 */
+	guard(mutex)(&sock->metric_read_lock);
+
 	ret = hsmp_send_message(&msg);
 	if (ret)
 		return ret;
@@ -424,6 +434,24 @@ ssize_t hsmp_metric_tbl_read(struct hsmp_socket *sock, char *buf, size_t size)
 }
 EXPORT_SYMBOL_NS_GPL(hsmp_metric_tbl_read, "AMD_HSMP");
 
+void hsmp_init_metric_read_locks(struct hsmp_plat_device *pdev)
+{
+	u16 i;
+
+	for (i = 0; i < pdev->num_sockets; i++)
+		mutex_init(&pdev->sock[i].metric_read_lock);
+}
+EXPORT_SYMBOL_NS_GPL(hsmp_init_metric_read_locks, "AMD_HSMP");
+
+void hsmp_destroy_metric_read_locks(struct hsmp_plat_device *pdev)
+{
+	u16 i;
+
+	for (i = 0; i < pdev->num_sockets; i++)
+		mutex_destroy(&pdev->sock[i].metric_read_lock);
+}
+EXPORT_SYMBOL_NS_GPL(hsmp_destroy_metric_read_locks, "AMD_HSMP");
+
 void hsmp_unmap_metric_tbls(struct hsmp_plat_device *pdev)
 {
 	struct hsmp_socket *sock;

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

@@ -15,6 +15,7 @@
 #include <linux/hwmon.h>
 #include <linux/kconfig.h>
 #include <linux/miscdevice.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/rwsem.h>
 #include <linux/semaphore.h>
@@ -44,6 +45,8 @@ struct hsmp_socket {
 	void __iomem *metric_tbl_addr;
 	void __iomem *virt_base_addr;
 	struct semaphore hsmp_sem;
+	/* Serializes HSMP_GET_METRIC_TABLE fill-and-copy for this socket */
+	struct mutex metric_read_lock;
 	char name[HSMP_ATTR_GRP_NAME_SIZE];
 	struct device *dev;
 	u16 sock_ind;
@@ -65,6 +68,8 @@ void hsmp_misc_deregister(void);
 int hsmp_misc_register(struct device *dev);
 int hsmp_get_tbl_dram_base(u16 sock_ind);
 void hsmp_unmap_metric_tbls(struct hsmp_plat_device *pdev);
+void hsmp_init_metric_read_locks(struct hsmp_plat_device *pdev);
+void hsmp_destroy_metric_read_locks(struct hsmp_plat_device *pdev);
 ssize_t hsmp_metric_tbl_read(struct hsmp_socket *sock, char *buf, size_t size);
 struct hsmp_plat_device *get_hsmp_pdev(void);
 #if IS_ENABLED(CONFIG_HWMON)

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

@@ -212,6 +212,7 @@ static int init_platform_device(struct device *dev)
 static void hsmp_pltdrv_release(void *data)
 {
 	hsmp_unmap_metric_tbls(hsmp_pdev);
+	hsmp_destroy_metric_read_locks(hsmp_pdev);
 }
 
 static int hsmp_pltdrv_probe(struct platform_device *pdev)
@@ -224,6 +225,8 @@ static int hsmp_pltdrv_probe(struct platform_device *pdev)
 	if (!hsmp_pdev->sock)
 		return -ENOMEM;
 
+	hsmp_init_metric_read_locks(hsmp_pdev);
+
 	ret = devm_add_action_or_reset(&pdev->dev, hsmp_pltdrv_release, NULL);
 	if (ret)
 		return ret;