From: Ravi Jonnalagadda <ravis.opensrc@gmail.com>
To: sj@kernel.org, akinobu.mita@gmail.com, damon@lists.linux.dev,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
linux-doc@vger.kernel.org
Cc: akpm@linux-foundation.org, corbet@lwn.net, bijan311@gmail.com,
ajayjoshi@micron.com, honggyu.kim@sk.com, yunjeong.mun@sk.com,
ravis.opensrc@gmail.com
Subject: [RFC PATCH 1/6] mm/damon: add struct damon_perf_event{,_attr} and per-ctx perf_events list
Date: Fri, 29 May 2026 09:56:35 -0700 [thread overview]
Message-ID: <20260529165640.820-2-ravis.opensrc@gmail.com> (raw)
In-Reply-To: <20260529165640.820-1-ravis.opensrc@gmail.com>
Introduce the substrate types for using perf events as DAMON access
check sources. struct damon_perf_event_attr carries the raw PMU attr
configurable from userspace; struct damon_perf_event is the per-event
entry on a new damon_ctx::perf_events list.
Declare damon_perf_init() and damon_perf_cleanup() in
mm/damon/ops-common.h. When CONFIG_PERF_EVENTS=n they fold to a no-op
returning -ENOSYS.
Suggested-by: Akinobu Mita <akinobu.mita@gmail.com>
Link: https://lore.kernel.org/20260423004211.7037-1-akinobu.mita@gmail.com
Signed-off-by: Ravi Jonnalagadda <ravis.opensrc@gmail.com>
---
include/linux/damon.h | 80 +++++++++++++++++++++++++++++++++++++++++
mm/damon/ops-common.h | 39 ++++++++++++++++++++
mm/damon/sysfs-common.h | 6 ++++
3 files changed, 125 insertions(+)
diff --git a/include/linux/damon.h b/include/linux/damon.h
index c0375035a3a7b..11f1c1071b9ba 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -123,6 +123,7 @@ struct damon_target {
* @size: The size of the accessed address range.
* @cpu: The id of the CPU that made the access.
* @tid: The task id of the task that made the access.
+ * @tgid: Thread group id of the task that made the access.
* @is_write: Whether the access is write.
*
* Any DAMON API callers that notified access events can report the information
@@ -135,6 +136,7 @@ struct damon_access_report {
unsigned long size;
unsigned int cpu;
pid_t tid;
+ pid_t tgid;
bool is_write;
/* private: */
unsigned long report_jiffies; /* when this report is made */
@@ -501,6 +503,7 @@ struct damos_filter {
};
struct damon_ctx;
+struct damon_target_lookup;
struct damos;
/**
@@ -966,6 +969,67 @@ struct damon_sample_control {
struct list_head sample_filters;
};
+/**
+ * struct damon_perf_event_attr - raw PMU event attr for access check.
+ *
+ * @type: raw PMU event type.
+ * @config: raw PMU event config.
+ * @config1: raw PMU event config1.
+ * @config2: raw PMU event config2.
+ * @sample_phys_addr: whether to set PERF_SAMPLE_PHYS_ADDR in sample_type.
+ * @sample_weight_struct: whether to set PERF_SAMPLE_WEIGHT_STRUCT in
+ * sample_type. PMUs that do not advertise
+ * weight (e.g. AMD IBS Op) reject events with
+ * this flag set, so it must be opt-in.
+ * @exclude_kernel: exclude kernel-mode samples.
+ * @exclude_hv: exclude hypervisor samples.
+ * @freq: when true use @sample_freq, otherwise @sample_period.
+ * @sample_freq: target sample rate when @freq is true.
+ * @sample_period: period (samples-between-overflows) when @freq is false.
+ * @wakeup_events: perf_event_attr.wakeup_events.
+ * @precise_ip: precise sampling skid bound (PEBS-style PMUs).
+ */
+struct damon_perf_event_attr {
+ u32 type;
+ u64 config;
+ u64 config1;
+ u64 config2;
+ bool sample_phys_addr;
+ bool sample_weight_struct;
+ bool exclude_kernel;
+ bool exclude_hv;
+ bool freq;
+ u64 sample_freq;
+ u64 sample_period;
+ u32 wakeup_events;
+ u32 precise_ip;
+};
+
+/**
+ * struct damon_perf_event - perf event for access check.
+ *
+ * @attr: Per-event PMU attribute (configured via sysfs).
+ * @priv: Monitoring operations-specific data.
+ * @list: List head for &damon_ctx->perf_events siblings.
+ * @hlist_node: Tracks this event among cpuhp multi-instance entries.
+ * @init_complete: Set after the synchronous online sweep finishes; gates
+ * @any_cpu_failed writes from late hotplug callbacks.
+ * @any_cpu_failed: Set by the cpuhp online callback if perf_event creation
+ * fails on any CPU during the synchronous initial install.
+ * @ctx: Back-pointer to the owning damon_ctx; the cpu_online callback
+ * reads ctx->perf_events_active to decide whether to enable a
+ * late-onlining CPU's event immediately after create.
+ */
+struct damon_perf_event {
+ struct damon_perf_event_attr attr;
+ void *priv;
+ struct list_head list;
+ struct hlist_node hlist_node;
+ bool init_complete;
+ bool any_cpu_failed;
+ struct damon_ctx *ctx;
+};
+
/**
* struct damon_ctx - Represents a context for each monitoring. This is the
* main interface that allows users to set the attributes and get the results
@@ -991,6 +1055,11 @@ struct damon_sample_control {
* @addr_unit: Scale factor for core to ops address conversion.
* @min_region_sz: Minimum region size.
* @pause: Pause kdamond main loop.
+ * @perf_events: Head of perf events (&damon_perf_event) list.
+ * @perf_events_active: Set while kdamond_fn has the perf events armed.
+ * Cleared in the kdamond_fn done path before the events are
+ * disabled; serves as the gate for damon_commit_perf_events()
+ * and the kdamond_fn drain dispatch.
*/
struct damon_ctx {
struct damon_attrs attrs;
@@ -1046,6 +1115,9 @@ struct damon_ctx {
unsigned long min_region_sz;
bool pause;
+ struct list_head perf_events;
+ bool perf_events_active;
+
/* private: */
/* Head of monitoring targets (&damon_target) list. */
struct list_head adaptive_targets;
@@ -1054,6 +1126,14 @@ struct damon_ctx {
/* Per-ctx PRNG state for damon_rand(); kdamond is the sole consumer. */
struct rnd_state rnd_state;
+
+ /* Reusable drain-loop snapshot buffer (avoids per-tick kmalloc). */
+ struct {
+ struct damon_target_lookup *lookups;
+ unsigned int nr_lookups;
+ struct damon_region **region_buf;
+ unsigned int region_buf_cap;
+ } drain_snapshot;
};
/* Get a random number in [@l, @r) using @ctx's lockless PRNG. */
diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h
index 5efa5b5970def..35da400a67ec1 100644
--- a/mm/damon/ops-common.h
+++ b/mm/damon/ops-common.h
@@ -23,3 +23,42 @@ bool damos_folio_filter_match(struct damos_filter *filter, struct folio *folio);
unsigned long damon_migrate_pages(struct list_head *folio_list, int target_nid);
bool damos_ops_has_filter(struct damos *s);
+
+#ifdef CONFIG_PERF_EVENTS
+
+/*
+ * Per-event opaque allocated by damon_perf_init(). The NMI overflow
+ * handler does NOT touch this struct; submission goes through the
+ * shared per-CPU SPSC ring via damon_report_access().
+ */
+struct damon_perf {
+ struct perf_event * __percpu *event;
+};
+
+int damon_perf_init(struct damon_ctx *ctx, struct damon_perf_event *event);
+void damon_perf_cleanup(struct damon_ctx *ctx, struct damon_perf_event *event);
+void damon_perf_event_arm(struct damon_perf_event *event);
+void damon_perf_event_disarm(struct damon_perf_event *event);
+
+#else /* !CONFIG_PERF_EVENTS */
+
+static inline int damon_perf_init(struct damon_ctx *ctx,
+ struct damon_perf_event *event)
+{
+ return -ENOSYS;
+}
+
+static inline void damon_perf_cleanup(struct damon_ctx *ctx,
+ struct damon_perf_event *event)
+{
+}
+
+static inline void damon_perf_event_arm(struct damon_perf_event *event)
+{
+}
+
+static inline void damon_perf_event_disarm(struct damon_perf_event *event)
+{
+}
+
+#endif /* CONFIG_PERF_EVENTS */
diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h
index 25a6c28abdea8..67c7545fd57d0 100644
--- a/mm/damon/sysfs-common.h
+++ b/mm/damon/sysfs-common.h
@@ -66,10 +66,13 @@ int damon_sysfs_memcg_path_to_id(char *memcg_path, u64 *id);
* sample directory
*/
+struct damon_sysfs_perf_events;
+
struct damon_sysfs_sample {
struct kobject kobj;
struct damon_sysfs_primitives *primitives;
struct damon_sysfs_sample_filters *filters;
+ struct damon_sysfs_perf_events *perf_events;
};
struct damon_sysfs_sample *damon_sysfs_sample_alloc(void);
@@ -82,3 +85,6 @@ extern const struct kobj_type damon_sysfs_sample_ktype;
int damon_sysfs_set_sample_control(
struct damon_sample_control *control,
struct damon_sysfs_sample *sysfs_sample);
+
+int damon_sysfs_add_perf_events(struct damon_ctx *ctx,
+ struct damon_sysfs_sample *sysfs_sample);
--
2.43.0
next prev parent reply other threads:[~2026-05-29 16:57 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-29 16:56 [RFC PATCH 0/6] mm/damon: hardware-sampled access reports Ravi Jonnalagadda
2026-05-29 16:56 ` Ravi Jonnalagadda [this message]
2026-05-29 16:56 ` [RFC PATCH 2/6] mm/damon/sysfs-sample: expose perf_events configuration via sysfs Ravi Jonnalagadda
2026-05-29 16:56 ` [RFC PATCH 3/6] mm/damon/sysfs: install perf_events on apply Ravi Jonnalagadda
2026-05-29 16:56 ` [RFC PATCH 4/6] mm/damon/core: per-CPU SPSC ring drain and damon_perf_event lifecycle Ravi Jonnalagadda
2026-05-29 16:56 ` [RFC PATCH 5/6] mm/damon/vaddr: implement perf-event access check Ravi Jonnalagadda
2026-05-29 16:56 ` [RFC PATCH 6/6] mm/damon: add damos_node_eligible_mem_bp tracepoint Ravi Jonnalagadda
2026-05-30 0:04 ` [RFC PATCH 0/6] mm/damon: hardware-sampled access reports SeongJae Park
2026-05-30 3:01 ` Akinobu Mita
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=20260529165640.820-2-ravis.opensrc@gmail.com \
--to=ravis.opensrc@gmail.com \
--cc=ajayjoshi@micron.com \
--cc=akinobu.mita@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=bijan311@gmail.com \
--cc=corbet@lwn.net \
--cc=damon@lists.linux.dev \
--cc=honggyu.kim@sk.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=sj@kernel.org \
--cc=yunjeong.mun@sk.com \
/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