linux-kernel - [RFC PATCH v4 5/9] x86: ibs: Enable IBS profiling for memory accesses

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251206101423.5004-6-bharata@amd.com>
Date: Sat, 6 Dec 2025 15:44:19 +0530
From: Bharata B Rao <bharata@....com>
To: <linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>
CC: <Jonathan.Cameron@...wei.com>, <dave.hansen@...el.com>,
	<gourry@...rry.net>, <mgorman@...hsingularity.net>, <mingo@...hat.com>,
	<peterz@...radead.org>, <raghavendra.kt@....com>, <riel@...riel.com>,
	<rientjes@...gle.com>, <sj@...nel.org>, <weixugc@...gle.com>,
	<willy@...radead.org>, <ying.huang@...ux.alibaba.com>, <ziy@...dia.com>,
	<dave@...olabs.net>, <nifan.cxl@...il.com>, <xuezhengchu@...wei.com>,
	<yiannis@...corp.com>, <akpm@...ux-foundation.org>, <david@...hat.com>,
	<byungchul@...com>, <kinseyho@...gle.com>, <joshua.hahnjy@...il.com>,
	<yuanchu@...gle.com>, <balbirs@...dia.com>, <alok.rathore@...sung.com>,
	<shivankg@....com>, Bharata B Rao <bharata@....com>
Subject: [RFC PATCH v4 5/9] x86: ibs: Enable IBS profiling for memory accesses

Enable IBS memory access data collection for user memory
accesses by programming the required MSRs. The profiling
is turned ON only for user mode execution and turned OFF
for kernel mode execution. Profiling is explicitly disabled
for NMI handler too.

TODOs:

- IBS sampling rate is kept fixed for now.
- Arch/vendor separation/isolation of the code needs relook.

Signed-off-by: Bharata B Rao <bharata@....com>
---
 arch/x86/include/asm/entry-common.h |  3 +++
 arch/x86/include/asm/hardirq.h      |  2 ++
 arch/x86/mm/ibs.c                   | 32 +++++++++++++++++++++++++++++
 include/linux/pghot.h               |  4 ++++
 4 files changed, 41 insertions(+)

diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index ce3eb6d5fdf9..0f381a63669e 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -4,6 +4,7 @@
 
 #include <linux/randomize_kstack.h>
 #include <linux/user-return-notifier.h>
+#include <linux/pghot.h>
 
 #include <asm/nospec-branch.h>
 #include <asm/io_bitmap.h>
@@ -13,6 +14,7 @@
 /* Check that the stack and regs on entry from user mode are sane. */
 static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs)
 {
+	hwmem_access_profiling_stop();
 	if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
 		/*
 		 * Make sure that the entry code gave us a sensible EFLAGS
@@ -106,6 +108,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 static __always_inline void arch_exit_to_user_mode(void)
 {
 	amd_clear_divider();
+	hwmem_access_profiling_start();
 }
 #define arch_exit_to_user_mode arch_exit_to_user_mode
 
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index f00c09ffe6a9..281dd76f5efb 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -91,4 +91,6 @@ static __always_inline bool kvm_get_cpu_l1tf_flush_l1d(void)
 static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { }
 #endif /* IS_ENABLED(CONFIG_KVM_INTEL) */
 
+#define arch_nmi_enter()	hwmem_access_profiling_stop()
+#define arch_nmi_exit()		hwmem_access_profiling_start()
 #endif /* _ASM_X86_HARDIRQ_H */
diff --git a/arch/x86/mm/ibs.c b/arch/x86/mm/ibs.c
index 946f3a82ca11..cf21052118c9 100644
--- a/arch/x86/mm/ibs.c
+++ b/arch/x86/mm/ibs.c
@@ -16,6 +16,7 @@ static u64 ibs_config __read_mostly;
 static u32 ibs_caps;
 
 #define IBS_NR_SAMPLES	150
+#define IBS_SAMPLE_PERIOD      10000
 
 /*
  * Basic access info captured for each memory access.
@@ -43,6 +44,36 @@ struct ibs_sample_pcpu __percpu *ibs_s;
 static struct work_struct ibs_work;
 static struct irq_work ibs_irq_work;
 
+void hwmem_access_profiling_stop(void)
+{
+	u64 ops_ctl;
+
+	if (!hwmem_access_profiling)
+		return;
+
+	rdmsrl(MSR_AMD64_IBSOPCTL, ops_ctl);
+	wrmsrl(MSR_AMD64_IBSOPCTL, ops_ctl & ~IBS_OP_ENABLE);
+}
+
+void hwmem_access_profiling_start(void)
+{
+	u64 config = 0;
+	unsigned int period = IBS_SAMPLE_PERIOD;
+
+	if (!hwmem_access_profiling)
+		return;
+
+	/* Disable IBS for kernel thread */
+	if (!current->mm)
+		goto out;
+
+	config = (period >> 4) & IBS_OP_MAX_CNT;
+	config |= (period & IBS_OP_MAX_CNT_EXT_MASK);
+	config |= ibs_config;
+out:
+	wrmsrl(MSR_AMD64_IBSOPCTL, config);
+}
+
 bool hwmem_access_profiler_inuse(void)
 {
 	return hwmem_access_profiling;
@@ -309,6 +340,7 @@ static int __init ibs_access_profiling_init(void)
 			  x86_amd_ibs_access_profile_startup,
 			  x86_amd_ibs_access_profile_teardown);
 
+	hwmem_access_profiling = true;
 	pr_info("IBS setup for memory access profiling\n");
 	return 0;
 }
diff --git a/include/linux/pghot.h b/include/linux/pghot.h
index 6410cb131d3d..00f450f79c86 100644
--- a/include/linux/pghot.h
+++ b/include/linux/pghot.h
@@ -4,8 +4,12 @@
 
 #ifdef CONFIG_HWMEM_PROFILER
 bool hwmem_access_profiler_inuse(void);
+void hwmem_access_profiling_start(void);
+void hwmem_access_profiling_stop(void);
 #else
 static inline bool hwmem_access_profiler_inuse(void) { return false; }
+static inline void hwmem_access_profiling_start(void) {}
+static inline void hwmem_access_profiling_stop(void) {}
 #endif
 
 /* Page hotness temperature sources */
-- 
2.34.1