From: Mario Limonciello <mario.limonciello@amd.com>
To: "Borislav Petkov" <bp@alien8.de>,
"Hans de Goede" <hdegoede@redhat.com>,
"Ilpo Järvinen" <ilpo.jarvinen@linux.intel.com>
Cc: <x86@kernel.org>, "Gautham R . Shenoy" <gautham.shenoy@amd.com>,
"Mario Limonciello" <mario.limonciello@amd.com>,
Perry Yuan <perry.yuan@amd.com>, <linux-kernel@vger.kernel.org>,
<linux-doc@vger.kernel.org>, <linux-pm@vger.kernel.org>,
<platform-driver-x86@vger.kernel.org>,
"Shyam Sundar S K" <Shyam-sundar.S-k@amd.com>
Subject: [PATCH v4 10/13] x86/process: Clear hardware feedback history for AMD processors
Date: Mon, 21 Oct 2024 13:02:49 -0500 [thread overview]
Message-ID: <20241021180252.3531-11-mario.limonciello@amd.com> (raw)
In-Reply-To: <20241021180252.3531-1-mario.limonciello@amd.com>
From: Perry Yuan <perry.yuan@amd.com>
Incorporate a mechanism within the context switching code to reset
the hardware history for AMD processors. Specifically, when a task
is switched in, the class ID was read and reset the hardware workload
classification history of CPU firmware and then it start to trigger
workload classification for the next running thread.
Signed-off-by: Perry Yuan <perry.yuan@amd.com>
Co-developed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
arch/x86/include/asm/hreset.h | 6 ++++++
arch/x86/kernel/cpu/common.c | 15 +++++++++++++++
arch/x86/kernel/process_32.c | 3 +++
arch/x86/kernel/process_64.c | 3 +++
4 files changed, 27 insertions(+)
create mode 100644 arch/x86/include/asm/hreset.h
diff --git a/arch/x86/include/asm/hreset.h b/arch/x86/include/asm/hreset.h
new file mode 100644
index 0000000000000..ae1f72602bbd0
--- /dev/null
+++ b/arch/x86/include/asm/hreset.h
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_HRESET_H
+
+void reset_hardware_history_hetero(void);
+
+#endif /* _ASM_X86_HRESET_H */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 07a34d7235057..658c8fb4e25df 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -57,6 +57,7 @@
#include <asm/mce.h>
#include <asm/msr.h>
#include <asm/cacheinfo.h>
+#include <asm/hreset.h>
#include <asm/memtype.h>
#include <asm/microcode.h>
#include <asm/intel-family.h>
@@ -403,6 +404,7 @@ static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_C
X86_CR4_FSGSBASE | X86_CR4_CET | X86_CR4_FRED;
static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
static unsigned long cr4_pinned_bits __ro_after_init;
+static DEFINE_STATIC_KEY_FALSE_RO(hardware_history_features);
void native_write_cr0(unsigned long val)
{
@@ -481,6 +483,12 @@ void cr4_init(void)
this_cpu_write(cpu_tlbstate.cr4, cr4);
}
+static void __init setup_hreset(struct cpuinfo_x86 *c)
+{
+ if (cpu_feature_enabled(X86_FEATURE_AMD_WORKLOAD_CLASS))
+ static_key_enable_cpuslocked(&hardware_history_features.key);
+}
+
/*
* Once CPU feature detection is finished (and boot params have been
* parsed), record any of the sensitive CR bits that are set, and
@@ -1844,6 +1852,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
setup_smep(c);
setup_smap(c);
setup_umip(c);
+ setup_hreset(c);
/* Enable FSGSBASE instructions if available. */
if (cpu_has(c, X86_FEATURE_FSGSBASE)) {
@@ -2410,3 +2419,9 @@ void __init arch_cpu_finalize_init(void)
*/
mem_encrypt_init();
}
+
+__always_inline void reset_hardware_history_hetero(void)
+{
+ if (static_branch_unlikely(&hardware_history_features))
+ wrmsrl(AMD_WORKLOAD_HRST, 0x1);
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0917c7f25720b..6a3a1339f7a77 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -52,6 +52,7 @@
#include <asm/switch_to.h>
#include <asm/vm86.h>
#include <asm/resctrl.h>
+#include <asm/hreset.h>
#include <asm/proto.h>
#include "process.h"
@@ -213,6 +214,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/* Load the Intel cache allocation PQR MSR. */
resctrl_sched_in(next_p);
+ reset_hardware_history_hetero();
+
return prev_p;
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 226472332a70d..ea7f765c6262a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -54,6 +54,7 @@
#include <asm/xen/hypervisor.h>
#include <asm/vdso.h>
#include <asm/resctrl.h>
+#include <asm/hreset.h>
#include <asm/unistd.h>
#include <asm/fsgsbase.h>
#include <asm/fred.h>
@@ -709,6 +710,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/* Load the Intel cache allocation PQR MSR. */
resctrl_sched_in(next_p);
+ reset_hardware_history_hetero();
+
return prev_p;
}
--
2.43.0
next prev parent reply other threads:[~2024-10-21 18:03 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-21 18:02 [PATCH v4 00/13] Add support for AMD hardware feedback interface Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 01/13] Documentation: x86: Add AMD Hardware Feedback Interface documentation Mario Limonciello
2024-10-22 0:45 ` Bagas Sanjaya
2024-10-21 18:02 ` [PATCH v4 02/13] MAINTAINERS: Add maintainer entry for AMD Hardware Feedback Driver Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 03/13] x86/cpufeatures: add X86_FEATURE_WORKLOAD_CLASS feature bit Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 04/13] x86/msr-index: define AMD heterogeneous CPU related MSR Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 05/13] platform/x86: hfi: Introduce AMD Hardware Feedback Interface Driver Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 06/13] platform/x86: hfi: parse CPU core ranking data from shared memory Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 07/13] platform/x86: hfi: init per-cpu scores for each class Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 08/13] platform/x86: hfi: add online and offline callback support Mario Limonciello
2024-10-22 5:59 ` Gautham R. Shenoy
2024-10-21 18:02 ` [PATCH v4 09/13] platform/x86: hfi: add power management callback Mario Limonciello
2024-10-22 6:01 ` Gautham R. Shenoy
2024-10-21 18:02 ` Mario Limonciello [this message]
2024-10-22 6:28 ` [PATCH v4 10/13] x86/process: Clear hardware feedback history for AMD processors Gautham R. Shenoy
2024-10-22 20:02 ` Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 11/13] cpufreq/amd-pstate: Disable preferred cores on designs with workload classification Mario Limonciello
2024-10-22 6:35 ` Gautham R. Shenoy
2024-10-21 18:02 ` [PATCH v4 12/13] platform/x86/amd: hfi: Set ITMT priority from ranking data Mario Limonciello
2024-10-21 18:02 ` [PATCH v4 13/13] platform/x86/amd: hfi: Add debugfs support Mario Limonciello
2024-10-22 6:42 ` Gautham R. Shenoy
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=20241021180252.3531-11-mario.limonciello@amd.com \
--to=mario.limonciello@amd.com \
--cc=Shyam-sundar.S-k@amd.com \
--cc=bp@alien8.de \
--cc=gautham.shenoy@amd.com \
--cc=hdegoede@redhat.com \
--cc=ilpo.jarvinen@linux.intel.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=perry.yuan@amd.com \
--cc=platform-driver-x86@vger.kernel.org \
--cc=x86@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
all inboxes | Powered by JetHome®