hwmon/coretemp: Handle large core ID value

Bugzilla: https://bugzilla.redhat.com/2159554

commit 7108b80
Author: Zhang Rui <rui.zhang@intel.com>
Date:   Fri Oct 14 17:01:45 2022 +0800

    hwmon/coretemp: Handle large core ID value

    The coretemp driver supports up to a hard-coded limit of 128 cores.

    Today, the driver can not support a core with an ID above that limit.
    Yet, the encoding of core ID's is arbitrary (BIOS APIC-ID) and so they
    may be sparse and they may be large.

    Update the driver to map arbitrary core ID numbers into appropriate
    array indexes so that 128 cores can be supported, no matter the encoding
    of core ID's.

    Signed-off-by: Zhang Rui <rui.zhang@intel.com>
    Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
    Acked-by: Len Brown <len.brown@intel.com>
    Acked-by: Guenter Roeck <linux@roeck-us.net>
    Cc: stable@vger.kernel.org
    Link: https://lkml.kernel.org/r/20221014090147.1836-3-rui.zhang@intel.com

Signed-off-by: David Arcari <darcari@redhat.com>

Author: darcari

drivers/hwmon/coretemp.c

@@ -46,9 +46,6 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
 #define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
 
-#define TO_CORE_ID(cpu)		(cpu_data(cpu).cpu_core_id)
-#define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
-
 #ifdef CONFIG_SMP
 #define for_each_sibling(i, cpu) \
 	for_each_cpu(i, topology_sibling_cpumask(cpu))
@@ -91,6 +88,8 @@ struct temp_data {
 struct platform_data {
 	struct device		*hwmon_dev;
 	u16			pkg_id;
+	u16			cpu_map[NUM_REAL_CORES];
+	struct ida		ida;
 	struct cpumask		cpumask;
 	struct temp_data	*core_data[MAX_CORE_DATA];
 	struct device_attribute name_attr;
@@ -441,7 +440,7 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag)
 							MSR_IA32_THERM_STATUS;
 	tdata->is_pkg_data = pkg_flag;
 	tdata->cpu = cpu;
-	tdata->cpu_core_id = TO_CORE_ID(cpu);
+	tdata->cpu_core_id = topology_core_id(cpu);
 	tdata->attr_size = MAX_CORE_ATTRS;
 	mutex_init(&tdata->update_lock);
 	return tdata;
@@ -454,22 +453,34 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
-	int err, attr_no;
+	int err, index, attr_no;
 
 	/*
 	 * Find attr number for sysfs:
 	 * We map the attr number to core id of the CPU
 	 * The attr number is always core id + 2
 	 * The Pkgtemp will always show up as temp1_*, if available
 	 */
-	attr_no = pkg_flag ? PKG_SYSFS_ATTR_NO : TO_ATTR_NO(cpu);
+	if (pkg_flag) {
+		attr_no = PKG_SYSFS_ATTR_NO;
+	} else {
+		index = ida_alloc(&pdata->ida, GFP_KERNEL);
+		if (index < 0)
+			return index;
+		pdata->cpu_map[index] = topology_core_id(cpu);
+		attr_no = index + BASE_SYSFS_ATTR_NO;
+	}
 
-	if (attr_no > MAX_CORE_DATA - 1)
-		return -ERANGE;
+	if (attr_no > MAX_CORE_DATA - 1) {
+		err = -ERANGE;
+		goto ida_free;
+	}
 
 	tdata = init_temp_data(cpu, pkg_flag);
-	if (!tdata)
-		return -ENOMEM;
+	if (!tdata) {
+		err = -ENOMEM;
+		goto ida_free;
+	}
 
 	/* Test if we can access the status register */
 	err = rdmsr_safe_on_cpu(cpu, tdata->status_reg, &eax, &edx);
@@ -505,6 +516,9 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 exit_free:
 	pdata->core_data[attr_no] = NULL;
 	kfree(tdata);
+ida_free:
+	if (!pkg_flag)
+		ida_free(&pdata->ida, index);
 	return err;
 }
 
@@ -528,6 +542,9 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx)
 
 	kfree(pdata->core_data[indx]);
 	pdata->core_data[indx] = NULL;
+
+	if (indx >= BASE_SYSFS_ATTR_NO)
+		ida_free(&pdata->ida, indx - BASE_SYSFS_ATTR_NO);
 }
 
 static int coretemp_probe(struct platform_device *pdev)
@@ -541,6 +558,7 @@ static int coretemp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	pdata->pkg_id = pdev->id;
+	ida_init(&pdata->ida);
 	platform_set_drvdata(pdev, pdata);
 
 	pdata->hwmon_dev = devm_hwmon_device_register_with_groups(dev, DRVNAME,
@@ -557,6 +575,7 @@ static int coretemp_remove(struct platform_device *pdev)
 		if (pdata->core_data[i])
 			coretemp_remove_core(pdata, i);
 
+	ida_destroy(&pdata->ida);
 	return 0;
 }
 
@@ -651,7 +670,7 @@ static int coretemp_cpu_offline(unsigned int cpu)
 	struct platform_device *pdev = coretemp_get_pdev(cpu);
 	struct platform_data *pd;
 	struct temp_data *tdata;
-	int indx, target;
+	int i, indx = -1, target;
 
 	/*
 	 * Don't execute this on suspend as the device remove locks
@@ -664,12 +683,19 @@ static int coretemp_cpu_offline(unsigned int cpu)
 	if (!pdev)
 		return 0;
 
-	/* The core id is too big, just return */
-	indx = TO_ATTR_NO(cpu);
-	if (indx > MAX_CORE_DATA - 1)
+	pd = platform_get_drvdata(pdev);
+
+	for (i = 0; i < NUM_REAL_CORES; i++) {
+		if (pd->cpu_map[i] == topology_core_id(cpu)) {
+			indx = i + BASE_SYSFS_ATTR_NO;
+			break;
+		}
+	}
+
+	/* Too many cores and this core is not populated, just return */
+	if (indx < 0)
 		return 0;
 
-	pd = platform_get_drvdata(pdev);
 	tdata = pd->core_data[indx];
 
 	cpumask_clear_cpu(cpu, &pd->cpumask);