Commit a582e5f5 authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux

Pull thermal management fixes from Zhang Rui:
 "These are fixes collected over the last week, they fixes several
  problems caused by the x86_pkg_temp_thermal introduced in 3.11-rc1.

  Specifics:

   - the x86_pkg_temp_thermal driver causes crash on systems with no
     package MSR support as there is a bug in the logic to check
     presence of DTHERM and PTS feature together.  Added a change so
     that when there is no PTS support, module doesn't get loaded.

   - fix krealloc() misuse in pkg_temp_thermal_device_add().

     If krealloc() returns NULL, it doesn't free the original.  Thus if
     we want to exit because of the krealloc() failure, we must make
     sure the original one is freed.

   - The error code path of the x86 package temperature thermal driver's
     initialization routine makes an unbalanced call to
     get_online_cpus(), which causes subsequent CPU offline operations,
     and consequently system suspend, to permanently block in
     cpu_hotplug_begin() on systems where get_core_online() returns an
     error code.

     Remove the extra get_online_cpus() to fix the problem"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux:
  Thermal: Fix lockup of cpu_down()
  Thermal: x86_pkg_temp: Limit number of pkg temp zones
  Thermal: x86_pkg_temp: fix krealloc() misuse in in pkg_temp_thermal_device_add()
  Thermal: x86 package temp thermal crash
parents b7371e31 ace120dc
......@@ -54,6 +54,8 @@ MODULE_PARM_DESC(notify_delay_ms,
* is some wrong values returned by cpuid for number of thresholds.
*/
#define MAX_NUMBER_OF_TRIPS 2
/* Limit number of package temp zones */
#define MAX_PKG_TEMP_ZONE_IDS 256
struct phy_dev_entry {
struct list_head list;
......@@ -394,12 +396,16 @@ static int pkg_temp_thermal_device_add(unsigned int cpu)
char buffer[30];
int thres_count;
u32 eax, ebx, ecx, edx;
u8 *temp;
cpuid(6, &eax, &ebx, &ecx, &edx);
thres_count = ebx & 0x07;
if (!thres_count)
return -ENODEV;
if (topology_physical_package_id(cpu) > MAX_PKG_TEMP_ZONE_IDS)
return -ENODEV;
thres_count = clamp_val(thres_count, 0, MAX_NUMBER_OF_TRIPS);
err = get_tj_max(cpu, &tj_max);
......@@ -417,13 +423,14 @@ static int pkg_temp_thermal_device_add(unsigned int cpu)
spin_lock(&pkg_work_lock);
if (topology_physical_package_id(cpu) > max_phy_id)
max_phy_id = topology_physical_package_id(cpu);
pkg_work_scheduled = krealloc(pkg_work_scheduled,
(max_phy_id+1) * sizeof(u8), GFP_ATOMIC);
if (!pkg_work_scheduled) {
temp = krealloc(pkg_work_scheduled,
(max_phy_id+1) * sizeof(u8), GFP_ATOMIC);
if (!temp) {
spin_unlock(&pkg_work_lock);
err = -ENOMEM;
goto err_ret_free;
}
pkg_work_scheduled = temp;
pkg_work_scheduled[topology_physical_package_id(cpu)] = 0;
spin_unlock(&pkg_work_lock);
......@@ -511,7 +518,7 @@ static int get_core_online(unsigned int cpu)
/* Check if there is already an instance for this package */
if (!phdev) {
if (!cpu_has(c, X86_FEATURE_DTHERM) &&
if (!cpu_has(c, X86_FEATURE_DTHERM) ||
!cpu_has(c, X86_FEATURE_PTS))
return -ENODEV;
if (pkg_temp_thermal_device_add(cpu))
......@@ -562,7 +569,7 @@ static struct notifier_block pkg_temp_thermal_notifier __refdata = {
};
static const struct x86_cpu_id __initconst pkg_temp_thermal_ids[] = {
{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_DTHERM },
{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_PTS },
{}
};
MODULE_DEVICE_TABLE(x86cpu, pkg_temp_thermal_ids);
......@@ -592,7 +599,6 @@ static int __init pkg_temp_thermal_init(void)
return 0;
err_ret:
get_online_cpus();
for_each_online_cpu(i)
put_core_offline(i);
put_online_cpus();
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment