This is a note to let you know that I've just added the patch titled
thermal: intel: hfi: Disable an HFI instance when all its CPUs go offline
to the 6.7-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
thermal-intel-hfi-disable-an-hfi-instance-when-all-i.patch
and it can be found in the queue-6.7 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit b4b1a43d74d6acd1d9924bf0fb72c6c5a87c2a47
Author: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
Date: Tue Jan 2 20:14:58 2024 -0800
thermal: intel: hfi: Disable an HFI instance when all its CPUs go offline
[ Upstream commit 1c53081d773c2cb4461636559b0d55b46559ceec ]
In preparation to support hibernation, add functionality to disable an HFI
instance during CPU offline. The last CPU of an instance that goes offline
will disable such instance.
The Intel Software Development Manual states that the operating system must
wait for the hardware to set MSR_IA32_PACKAGE_THERM_STATUS[26] after
disabling an HFI instance to ensure that it will no longer write on the HFI
memory. Some processors, however, do not ever set such bit. Wait a minimum
of 2ms to give time hardware to complete any pending memory writes.
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Stable-dep-of: 97566d09fd02 ("thermal: intel: hfi: Add syscore callbacks for system-wide PM")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index 820613e293cd..bb25c75acd45 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -24,6 +24,7 @@
#include <linux/bitops.h>
#include <linux/cpufeature.h>
#include <linux/cpumask.h>
+#include <linux/delay.h>
#include <linux/gfp.h>
#include <linux/io.h>
#include <linux/kernel.h>
@@ -367,6 +368,32 @@ static void hfi_set_hw_table(struct hfi_instance *hfi_instance)
wrmsrl(MSR_IA32_HW_FEEDBACK_PTR, msr_val);
}
+/* Caller must hold hfi_instance_lock. */
+static void hfi_disable(void)
+{
+ u64 msr_val;
+ int i;
+
+ rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+ msr_val &= ~HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT;
+ wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+
+ /*
+ * Wait for hardware to acknowledge the disabling of HFI. Some
+ * processors may not do it. Wait for ~2ms. This is a reasonable
+ * time for hardware to complete any pending actions on the HFI
+ * memory.
+ */
+ for (i = 0; i < 2000; i++) {
+ rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
+ if (msr_val & PACKAGE_THERM_STATUS_HFI_UPDATED)
+ break;
+
+ udelay(1);
+ cpu_relax();
+ }
+}
+
/**
* intel_hfi_online() - Enable HFI on @cpu
* @cpu: CPU in which the HFI will be enabled
@@ -421,6 +448,10 @@ void intel_hfi_online(unsigned int cpu)
/*
* Hardware is programmed with the physical address of the first page
* frame of the table. Hence, the allocated memory must be page-aligned.
+ *
+ * Some processors do not forget the initial address of the HFI table
+ * even after having been reprogrammed. Keep using the same pages. Do
+ * not free them.
*/
hfi_instance->hw_table = alloc_pages_exact(hfi_features.nr_table_pages,
GFP_KERNEL | __GFP_ZERO);
@@ -485,6 +516,10 @@ void intel_hfi_offline(unsigned int cpu)
mutex_lock(&hfi_instance_lock);
cpumask_clear_cpu(cpu, hfi_instance->cpus);
+
+ if (!cpumask_weight(hfi_instance->cpus))
+ hfi_disable();
+
mutex_unlock(&hfi_instance_lock);
}
