From: Aaron Rainbolt <arainbolt@kfocus.org>
To: linux-acpi@vger.kernel.org, rafael@kernel.org
Cc: mario.limonciello@amd.com, lenb@kernel.org,
linux-kernel@vger.kernel.org, mmikowski@kfocus.org
Subject: [PATCH] acpi: Allow ignoring _OSC CPPC v2 bit via kernel parameter
Date: Mon, 17 Jun 2024 21:54:17 -0500 [thread overview]
Message-ID: <ZnD22b3Br1ng7alf@kf-XE> (raw)
acpi: Allow ignoring _OSC CPPC v2 bit via kernel parameter
The _OSC is supposed to contain a bit indicating whether the hardware
supports CPPC v2 or not. This bit is not always set, causing CPPC v2 to
be considered absent. This results in severe single-core performance
issues with the EEVDF scheduler.
To work around this, provide a new kernel parameter,
"processor.ignore_osc_cppc_bit", which may be used to ignore the _OSC
CPPC v2 bit and act as if the bit was enabled. This allows CPPC to be
properly detected even if not "enabled" by _OSC, allowing users with
problematic hardware to obtain decent single-core performance.
Tested-by: Michael Mikowski <mmikowski@kfocus.org>
Signed-off-by: Aaron Rainbolt <arainbolt@kfocus.org>
---
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 1d857978f5f4..53406dd6cb87 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -671,7 +671,7 @@ static inline void arch_init_invariance_cppc(void) { }
*
* Return: 0 for success or negative value for err.
*/
-int acpi_cppc_processor_probe(struct acpi_processor *pr)
+int acpi_cppc_processor_probe(struct acpi_processor *pr, bool ignore_osc_cppc_bit)
{
struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
union acpi_object *out_obj, *cpc_obj;
@@ -686,7 +686,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
if (!osc_sb_cppc2_support_acked) {
pr_debug("CPPC v2 _OSC not acked\n");
- if (!cpc_supported_by_cpu()) {
+ if (!ignore_osc_cppc_bit && !cpc_supported_by_cpu()) {
pr_debug("CPPC is not supported by the CPU\n");
return -ENODEV;
}
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 67db60eda370..a183bca6c1c5 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -33,6 +33,11 @@ MODULE_AUTHOR("Paul Diefenbaugh");
MODULE_DESCRIPTION("ACPI Processor Driver");
MODULE_LICENSE("GPL");
+static bool ignore_osc_cppc_bit = false;
+module_param(ignore_osc_cppc_bit, bool, 0);
+MODULE_PARM_DESC(ignore_osc_cppc_bit,
+ "Ignore _OSC CPPC bit, assume CPPC v2 is present");
+
static int acpi_processor_start(struct device *dev);
static int acpi_processor_stop(struct device *dev);
@@ -170,7 +175,7 @@ static int __acpi_processor_start(struct acpi_device *device)
if (pr->flags.need_hotplug_init)
return 0;
- result = acpi_cppc_processor_probe(pr);
+ result = acpi_cppc_processor_probe(pr, ignore_osc_cppc_bit);
if (result && !IS_ENABLED(CONFIG_ACPI_CPU_FREQ_PSS))
dev_dbg(&device->dev, "CPPC data invalid or not present\n");
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 3f34ebb27525..79fd61b3f537 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -358,10 +358,10 @@ int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id);
int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
#ifdef CONFIG_ACPI_CPPC_LIB
-extern int acpi_cppc_processor_probe(struct acpi_processor *pr);
+extern int acpi_cppc_processor_probe(struct acpi_processor *pr, bool ignore_osc_cppc_bit);
extern void acpi_cppc_processor_exit(struct acpi_processor *pr);
#else
-static inline int acpi_cppc_processor_probe(struct acpi_processor *pr)
+static inline int acpi_cppc_processor_probe(struct acpi_processor *pr, bool ignore_osc_cppc_bit)
{
return 0;
}
next reply other threads:[~2024-06-18 2:54 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-18 2:54 Aaron Rainbolt [this message]
2024-06-18 17:09 ` [PATCH] acpi: Allow ignoring _OSC CPPC v2 bit via kernel parameter Mario Limonciello
2024-06-18 18:30 ` Aaron Rainbolt
2024-06-18 18:35 ` Mario Limonciello
2024-06-18 18:52 ` Aaron Rainbolt
2024-06-18 18:58 ` Mario Limonciello
2024-06-18 19:25 ` Aaron Rainbolt
2024-06-18 19:27 ` Mario Limonciello
2024-06-18 20:25 ` [PATCH V2 RFC] " Aaron Rainbolt
2024-06-18 20:58 ` Aaron Rainbolt
2024-06-18 21:24 ` Mario Limonciello
2024-06-18 21:47 ` Aaron Rainbolt
2024-06-19 4:33 ` [PATCH V3] " Aaron Rainbolt
2024-06-19 5:08 ` Mario Limonciello
2024-06-19 17:09 ` Rafael J. Wysocki
2024-06-19 17:30 ` Rafael J. Wysocki
2024-06-19 17:44 ` Aaron Rainbolt
2024-06-19 17:56 ` Aaron Rainbolt
2024-06-19 21:39 ` Aaron Rainbolt
2024-06-19 22:19 ` Aaron Rainbolt
2024-06-20 1:05 ` Aaron Rainbolt
2024-06-20 15:40 ` Rafael J. Wysocki
2024-06-19 17:34 ` Aaron Rainbolt
2024-06-19 17:37 ` Rafael J. Wysocki
2024-06-18 18:31 ` [PATCH] " kernel test robot
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ZnD22b3Br1ng7alf@kf-XE \
--to=arainbolt@kfocus.org \
--cc=lenb@kernel.org \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mario.limonciello@amd.com \
--cc=mmikowski@kfocus.org \
--cc=rafael@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox