[PATCH AUTOSEL 6.6 04/14] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241

[PATCH AUTOSEL 6.6 04/14] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241

[Sasha Levin]

From: Srikar Srimath Tirumala <srikars@nvidia.com>

[ Upstream commit 310293a2b94197f3d75e65ab22672287a7938a00 ]

Current implementation of processor_thermal performs software throttling
in fixed steps of "20%" which can be too coarse for some platforms.
We observed some performance gain after reducing the throttle percentage.
Change the CPUFREQ thermal reduction percentage and maximum thermal steps
to be configurable. Also, update the default values of both for Nvidia
Tegra241 (Grace) SoC. The thermal reduction percentage is reduced to "5%"
and accordingly the maximum number of thermal steps are increased as they
are derived from the reduction percentage.

Signed-off-by: Srikar Srimath Tirumala <srikars@nvidia.com>
Co-developed-by: Sumit Gupta <sumitg@nvidia.com>
Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/acpi/arm64/Makefile          |  1 +
 drivers/acpi/arm64/thermal_cpufreq.c | 20 ++++++++++++
 drivers/acpi/internal.h              |  9 +++++
 drivers/acpi/processor_thermal.c     | 49 +++++++++++++++++++++++-----
 4 files changed, 70 insertions(+), 9 deletions(-)
 create mode 100644 drivers/acpi/arm64/thermal_cpufreq.c

diff --git a/drivers/acpi/arm64/Makefile b/drivers/acpi/arm64/Makefile
index 143debc1ba4a..726944648c9b 100644
--- a/drivers/acpi/arm64/Makefile
+++ b/drivers/acpi/arm64/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_ACPI_GTDT) 	+= gtdt.o
 obj-$(CONFIG_ACPI_APMT) 	+= apmt.o
 obj-$(CONFIG_ARM_AMBA)		+= amba.o
 obj-y				+= dma.o init.o
+obj-y				+= thermal_cpufreq.o
diff --git a/drivers/acpi/arm64/thermal_cpufreq.c b/drivers/acpi/arm64/thermal_cpufreq.c
new file mode 100644
index 000000000000..d524f2cd6044
--- /dev/null
+++ b/drivers/acpi/arm64/thermal_cpufreq.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/acpi.h>
+
+#include "../internal.h"
+
+#define SMCCC_SOC_ID_T241      0x036b0241
+
+int acpi_arch_thermal_cpufreq_pctg(void)
+{
+	s32 soc_id = arm_smccc_get_soc_id_version();
+
+	/*
+	 * Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) and
+	 * reduce the CPUFREQ Thermal reduction percentage to 5%.
+	 */
+	if (soc_id == SMCCC_SOC_ID_T241)
+		return 5;
+
+	return 0;
+}
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 866c7c4ed233..af1198e2b526 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -85,6 +85,15 @@ bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent);
 acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context);
 void acpi_scan_table_notify(void);
 
+#ifdef CONFIG_ARM64
+int acpi_arch_thermal_cpufreq_pctg(void);
+#else
+static inline int acpi_arch_thermal_cpufreq_pctg(void)
+{
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                      Device Node Initialization / Removal
    -------------------------------------------------------------------------- */
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index b7c6287eccca..1219adb11ab9 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -17,6 +17,8 @@
 #include <acpi/processor.h>
 #include <linux/uaccess.h>
 
+#include "internal.h"
+
 #ifdef CONFIG_CPU_FREQ
 
 /* If a passive cooling situation is detected, primarily CPUfreq is used, as it
@@ -26,12 +28,21 @@
  */
 
 #define CPUFREQ_THERMAL_MIN_STEP 0
-#define CPUFREQ_THERMAL_MAX_STEP 3
 
-static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
+static int cpufreq_thermal_max_step __read_mostly = 3;
+
+/*
+ * Minimum throttle percentage for processor_thermal cooling device.
+ * The processor_thermal driver uses it to calculate the percentage amount by
+ * which cpu frequency must be reduced for each cooling state. This is also used
+ * to calculate the maximum number of throttling steps or cooling states.
+ */
+static int cpufreq_thermal_reduction_pctg __read_mostly = 20;
 
-#define reduction_pctg(cpu) \
-	per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
+static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_step);
+
+#define reduction_step(cpu) \
+	per_cpu(cpufreq_thermal_reduction_step, phys_package_first_cpu(cpu))
 
 /*
  * Emulate "per package data" using per cpu data (which should really be
@@ -71,7 +82,7 @@ static int cpufreq_get_max_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return CPUFREQ_THERMAL_MAX_STEP;
+	return cpufreq_thermal_max_step;
 }
 
 static int cpufreq_get_cur_state(unsigned int cpu)
@@ -79,7 +90,7 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return reduction_pctg(cpu);
+	return reduction_step(cpu);
 }
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
@@ -92,7 +103,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	reduction_pctg(cpu) = state;
+	reduction_step(cpu) = state;
 
 	/*
 	 * Update all the CPUs in the same package because they all
@@ -113,7 +124,8 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 		if (!policy)
 			return -EINVAL;
 
-		max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
+		max_freq = (policy->cpuinfo.max_freq *
+			    (100 - reduction_step(i) * cpufreq_thermal_reduction_pctg)) / 100;
 
 		cpufreq_cpu_put(policy);
 
@@ -126,10 +138,29 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	return 0;
 }
 
+static void acpi_thermal_cpufreq_config(void)
+{
+	int cpufreq_pctg = acpi_arch_thermal_cpufreq_pctg();
+
+	if (!cpufreq_pctg)
+		return;
+
+	cpufreq_thermal_reduction_pctg = cpufreq_pctg;
+
+	/*
+	 * Derive the MAX_STEP from minimum throttle percentage so that the reduction
+	 * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
+	 * the CPU performance doesn't become 0.
+	 */
+	cpufreq_thermal_max_step = (100 / cpufreq_pctg) - 2;
+}
+
 void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
 {
 	unsigned int cpu;
 
+	acpi_thermal_cpufreq_config();
+
 	for_each_cpu(cpu, policy->related_cpus) {
 		struct acpi_processor *pr = per_cpu(processors, cpu);
 		int ret;
@@ -190,7 +221,7 @@ static int acpi_processor_max_state(struct acpi_processor *pr)
 
 	/*
 	 * There exists four states according to
-	 * cpufreq_thermal_reduction_pctg. 0, 1, 2, 3
+	 * cpufreq_thermal_reduction_step. 0, 1, 2, 3
 	 */
 	max_state += cpufreq_get_max_state(pr->id);
 	if (pr->flags.throttling)
-- 
2.43.0

[PATCH AUTOSEL 6.6 05/14] ACPI: video: Add quirk for the Colorful X15 AT 23 Laptop

[Sasha Levin]

From: Yuluo Qiu <qyl27@outlook.com>

[ Upstream commit 143176a46bdd3bfbe9ba2462bf94458e80d65ebf ]

The Colorful X15 AT 23 ACPI video-bus device report spurious
ACPI_VIDEO_NOTIFY_CYCLE events resulting in spurious KEY_SWITCHVIDEOMODE
events being reported to userspace (and causing trouble there) when
an external screen plugged in.

Add a quirk setting the report_key_events mask to
REPORT_BRIGHTNESS_KEY_EVENTS so that the ACPI_VIDEO_NOTIFY_CYCLE
events will be ignored, while still reporting brightness up/down
hotkey-presses to userspace normally.

Signed-off-by: Yuluo Qiu <qyl27@outlook.com>
Co-developed-by: Celeste Liu <CoelacanthusHex@gmail.com>
Signed-off-by: Celeste Liu <CoelacanthusHex@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/acpi/acpi_video.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 35f071ad9532..34f3880f61a5 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -500,6 +500,15 @@ static const struct dmi_system_id video_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3350"),
 		},
 	},
+	{
+	 .callback = video_set_report_key_events,
+	 .driver_data = (void *)((uintptr_t)REPORT_BRIGHTNESS_KEY_EVENTS),
+	 .ident = "COLORFUL X15 AT 23",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "COLORFUL"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "X15 AT 23"),
+		},
+	},
 	/*
 	 * Some machines change the brightness themselves when a brightness
 	 * hotkey gets pressed, despite us telling them not to. In this case
-- 
2.43.0

[PATCH AUTOSEL 6.6 06/14] PNP: ACPI: fix fortify warning

[Sasha Levin]

From: Dmitry Antipov <dmantipov@yandex.ru>

[ Upstream commit ba3f5058db437d919f8468db50483dd9028ff688 ]

When compiling with gcc version 14.0.0 20231126 (experimental)
and CONFIG_FORTIFY_SOURCE=y, I've noticed the following:

In file included from ./include/linux/string.h:295,
                 from ./include/linux/bitmap.h:12,
                 from ./include/linux/cpumask.h:12,
                 from ./arch/x86/include/asm/paravirt.h:17,
                 from ./arch/x86/include/asm/cpuid.h:62,
                 from ./arch/x86/include/asm/processor.h:19,
                 from ./arch/x86/include/asm/cpufeature.h:5,
                 from ./arch/x86/include/asm/thread_info.h:53,
                 from ./include/linux/thread_info.h:60,
                 from ./arch/x86/include/asm/preempt.h:9,
                 from ./include/linux/preempt.h:79,
                 from ./include/linux/spinlock.h:56,
                 from ./include/linux/mmzone.h:8,
                 from ./include/linux/gfp.h:7,
                 from ./include/linux/slab.h:16,
                 from ./include/linux/resource_ext.h:11,
                 from ./include/linux/acpi.h:13,
                 from drivers/pnp/pnpacpi/rsparser.c:11:
In function 'fortify_memcpy_chk',
    inlined from 'pnpacpi_parse_allocated_vendor' at drivers/pnp/pnpacpi/rsparser.c:158:3,
    inlined from 'pnpacpi_allocated_resource' at drivers/pnp/pnpacpi/rsparser.c:249:3:
./include/linux/fortify-string.h:588:25: warning: call to '__read_overflow2_field'
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  588 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

According to the comments in include/linux/fortify-string.h, 'memcpy()',
'memmove()' and 'memset()' must not be used beyond individual struct
members to ensure that the compiler can enforce protection against
buffer overflows, and, IIUC, this also applies to partial copies from
the particular member ('vendor->byte_data' in this case). So it should
be better (and safer) to do both copies at once (and 'byte_data' of
'struct acpi_resource_vendor_typed' seems to be a good candidate for
'__counted_by(byte_length)' as well).

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pnp/pnpacpi/rsparser.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 4f05f610391b..c02ce0834c2c 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -151,13 +151,13 @@ static int vendor_resource_matches(struct pnp_dev *dev,
 static void pnpacpi_parse_allocated_vendor(struct pnp_dev *dev,
 				    struct acpi_resource_vendor_typed *vendor)
 {
-	if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, 16)) {
-		u64 start, length;
+	struct { u64 start, length; } range;
 
-		memcpy(&start, vendor->byte_data, sizeof(start));
-		memcpy(&length, vendor->byte_data + 8, sizeof(length));
-
-		pnp_add_mem_resource(dev, start, start + length - 1, 0);
+	if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid,
+				    sizeof(range))) {
+		memcpy(&range, vendor->byte_data, sizeof(range));
+		pnp_add_mem_resource(dev, range.start, range.start +
+				     range.length - 1, 0);
 	}
 }
 
-- 
2.43.0

[PATCH AUTOSEL 6.6 07/14] ACPI: extlog: fix NULL pointer dereference check

[Sasha Levin]

From: Prarit Bhargava <prarit@redhat.com>

[ Upstream commit 72d9b9747e78979510e9aafdd32eb99c7aa30dd1 ]

The gcc plugin -fanalyzer [1] tries to detect various
patterns of incorrect behaviour.  The tool reports:

drivers/acpi/acpi_extlog.c: In function ‘extlog_exit’:
drivers/acpi/acpi_extlog.c:307:12: warning: check of ‘extlog_l1_addr’ for NULL after already dereferencing it [-Wanalyzer-deref-before-check]
    |
    |  306 |         ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
    |      |         ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
    |      |                                                  |
    |      |                                                  (1) pointer ‘extlog_l1_addr’ is dereferenced here
    |  307 |         if (extlog_l1_addr)
    |      |            ~
    |      |            |
    |      |            (2) pointer ‘extlog_l1_addr’ is checked for NULL here but it was already dereferenced at (1)
    |

Fix the NULL pointer dereference check in extlog_exit().

Link: https://gcc.gnu.org/onlinedocs/gcc-10.1.0/gcc/Static-Analyzer-Options.html # [1]

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/acpi/acpi_extlog.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index e120a96e1eae..193147769146 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -303,9 +303,10 @@ static int __init extlog_init(void)
 static void __exit extlog_exit(void)
 {
 	mce_unregister_decode_chain(&extlog_mce_dec);
-	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
-	if (extlog_l1_addr)
+	if (extlog_l1_addr) {
+		((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
+	}
 	if (elog_addr)
 		acpi_os_unmap_iomem(elog_addr, elog_size);
 	release_mem_region(elog_base, elog_size);
-- 
2.43.0

[PATCH AUTOSEL 6.6 10/14] ACPI: NUMA: Fix the logic of getting the fake_pxm value

[Sasha Levin]

From: Yuntao Wang <ytcoode@gmail.com>

[ Upstream commit e3f577830ce216b0ca21d4750cbbd64cfc21efff ]

The for loop does not iterate over the last element of the node_to_pxm_map
array. This could lead to a conflict between the final fake_pxm value and
the existing pxm values. That is, the final fake_pxm value can not be
guaranteed to be an unused pxm value.

While at it, fix up white space in slit_valid().

Signed-off-by: Yuntao Wang <ytcoode@gmail.com>
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/acpi/numa/srat.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 12f330b0eac0..b57de78fbf14 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -183,7 +183,7 @@ static int __init slit_valid(struct acpi_table_slit *slit)
 	int i, j;
 	int d = slit->locality_count;
 	for (i = 0; i < d; i++) {
-		for (j = 0; j < d; j++)  {
+		for (j = 0; j < d; j++) {
 			u8 val = slit->entry[d*i + j];
 			if (i == j) {
 				if (val != LOCAL_DISTANCE)
@@ -532,7 +532,7 @@ int __init acpi_numa_init(void)
 	 */
 
 	/* fake_pxm is the next unused PXM value after SRAT parsing */
-	for (i = 0, fake_pxm = -1; i < MAX_NUMNODES - 1; i++) {
+	for (i = 0, fake_pxm = -1; i < MAX_NUMNODES; i++) {
 		if (node_to_pxm_map[i] > fake_pxm)
 			fake_pxm = node_to_pxm_map[i];
 	}
-- 
2.43.0

[PATCH AUTOSEL 6.6 13/14] ACPI: APEI: set memory failure flags as MF_ACTION_REQUIRED on synchronous events

[Sasha Levin]

From: Shuai Xue <xueshuai@linux.alibaba.com>

[ Upstream commit a70297d2213253853e95f5b49651f924990c6d3b ]

There are two major types of uncorrected recoverable (UCR) errors :

 - Synchronous error: The error is detected and raised at the point of
   the consumption in the execution flow, e.g. when a CPU tries to
   access a poisoned cache line. The CPU will take a synchronous error
   exception such as Synchronous External Abort (SEA) on Arm64 and
   Machine Check Exception (MCE) on X86. OS requires to take action (for
   example, offline failure page/kill failure thread) to recover this
   uncorrectable error.

 - Asynchronous error: The error is detected out of processor execution
   context, e.g. when an error is detected by a background scrubber.
   Some data in the memory are corrupted. But the data have not been
   consumed. OS is optional to take action to recover this uncorrectable
   error.

When APEI firmware first is enabled, a platform may describe one error
source for the handling of synchronous errors (e.g. MCE or SEA notification
), or for handling asynchronous errors (e.g. SCI or External Interrupt
notification). In other words, we can distinguish synchronous errors by
APEI notification. For synchronous errors, kernel will kill the current
process which accessing the poisoned page by sending SIGBUS with
BUS_MCEERR_AR. In addition, for asynchronous errors, kernel will notify the
process who owns the poisoned page by sending SIGBUS with BUS_MCEERR_AO in
early kill mode. However, the GHES driver always sets mf_flags to 0 so that
all synchronous errors are handled as asynchronous errors in memory failure.

To this end, set memory failure flags as MF_ACTION_REQUIRED on synchronous
events.

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Tested-by: Ma Wupeng <mawupeng1@huawei.com>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Xiaofei Tan <tanxiaofei@huawei.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/acpi/apei/ghes.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 63ad0541db38..ab2a82cb1b0b 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -101,6 +101,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
 }
 
+/*
+ * A platform may describe one error source for the handling of synchronous
+ * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
+ * or External Interrupt). On x86, the HEST notifications are always
+ * asynchronous, so only SEA on ARM is delivered as a synchronous
+ * notification.
+ */
+static inline bool is_hest_sync_notify(struct ghes *ghes)
+{
+	u8 notify_type = ghes->generic->notify.type;
+
+	return notify_type == ACPI_HEST_NOTIFY_SEA;
+}
+
 /*
  * This driver isn't really modular, however for the time being,
  * continuing to use module_param is the easiest way to remain
@@ -489,7 +503,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 }
 
 static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
-				       int sev)
+				       int sev, bool sync)
 {
 	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
@@ -503,7 +517,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
 		flags = MF_SOFT_OFFLINE;
 	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
-		flags = 0;
+		flags = sync ? MF_ACTION_REQUIRED : 0;
 
 	if (flags != -1)
 		return ghes_do_memory_failure(mem_err->physical_addr, flags);
@@ -511,9 +525,11 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	return false;
 }
 
-static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
+static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
+				       int sev, bool sync)
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+	int flags = sync ? MF_ACTION_REQUIRED : 0;
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
@@ -538,7 +554,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s
 		 * and don't filter out 'corrected' error here.
 		 */
 		if (is_cache && has_pa) {
-			queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
+			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
 			p += err_info->length;
 			continue;
 		}
@@ -666,6 +682,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 	const guid_t *fru_id = &guid_null;
 	char *fru_text = "";
 	bool queued = false;
+	bool sync = is_hest_sync_notify(ghes);
 
 	sev = ghes_severity(estatus->error_severity);
 	apei_estatus_for_each_section(estatus, gdata) {
@@ -683,13 +700,13 @@ static bool ghes_do_proc(struct ghes *ghes,
 			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
-			queued = ghes_handle_memory_failure(gdata, sev);
+			queued = ghes_handle_memory_failure(gdata, sev, sync);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
-			queued = ghes_handle_arm_hw_error(gdata, sev);
+			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
-- 
2.43.0