[tip:perf/x86] perf/x86/intel: Implement LRU monitoring ID allocation for CQM

[tip-bot for Matt Fleming]

Commit-ID:  35298e554c74b7849875e3676ba8eaf833c7b917
Gitweb:     http://git.kernel.org/tip/35298e554c74b7849875e3676ba8eaf833c7b917
Author:     Matt Fleming <matt.fleming@xxxxxxxxx>
AuthorDate: Fri, 23 Jan 2015 18:45:45 +0000
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 25 Feb 2015 13:53:33 +0100

perf/x86/intel: Implement LRU monitoring ID allocation for CQM

It's possible to run into issues with re-using unused monitoring IDs
because there may be stale cachelines associated with that ID from a
previous allocation. This can cause the LLC occupancy values to be
inaccurate.

To attempt to mitigate this problem we place the IDs on a least recently
used list, essentially a FIFO. The basic idea is that the longer the
time period between ID re-use the lower the probability that stale
cachelines exist in the cache.

Signed-off-by: Matt Fleming <matt.fleming@xxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kanaka Juvva <kanaka.d.juvva@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1422038748-21397-7-git-send-email-matt@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/kernel/cpu/perf_event_intel_cqm.c | 100 ++++++++++++++++++++++++++---
 1 file changed, 92 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 05b4cd2..b5d9d74 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -25,7 +25,7 @@ struct intel_cqm_state {
 static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
 
 /*
- * Protects cache_cgroups.
+ * Protects cache_cgroups and cqm_rmid_lru.
  */
 static DEFINE_MUTEX(cache_mutex);
 
@@ -64,36 +64,120 @@ static u64 __rmid_read(unsigned long rmid)
 	return val;
 }
 
-static unsigned long *cqm_rmid_bitmap;
+struct cqm_rmid_entry {
+	u64 rmid;
+	struct list_head list;
+};
+
+/*
+ * A least recently used list of RMIDs.
+ *
+ * Oldest entry at the head, newest (most recently used) entry at the
+ * tail. This list is never traversed, it's only used to keep track of
+ * the lru order. That is, we only pick entries of the head or insert
+ * them on the tail.
+ *
+ * All entries on the list are 'free', and their RMIDs are not currently
+ * in use. To mark an RMID as in use, remove its entry from the lru
+ * list.
+ *
+ * This list is protected by cache_mutex.
+ */
+static LIST_HEAD(cqm_rmid_lru);
+
+/*
+ * We use a simple array of pointers so that we can lookup a struct
+ * cqm_rmid_entry in O(1). This alleviates the callers of __get_rmid()
+ * and __put_rmid() from having to worry about dealing with struct
+ * cqm_rmid_entry - they just deal with rmids, i.e. integers.
+ *
+ * Once this array is initialized it is read-only. No locks are required
+ * to access it.
+ *
+ * All entries for all RMIDs can be looked up in the this array at all
+ * times.
+ */
+static struct cqm_rmid_entry **cqm_rmid_ptrs;
+
+static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+{
+	struct cqm_rmid_entry *entry;
+
+	entry = cqm_rmid_ptrs[rmid];
+	WARN_ON(entry->rmid != rmid);
+
+	return entry;
+}
 
 /*
  * Returns < 0 on fail.
+ *
+ * We expect to be called with cache_mutex held.
  */
 static int __get_rmid(void)
 {
-	return bitmap_find_free_region(cqm_rmid_bitmap, cqm_max_rmid, 0);
+	struct cqm_rmid_entry *entry;
+
+	lockdep_assert_held(&cache_mutex);
+
+	if (list_empty(&cqm_rmid_lru))
+		return -EAGAIN;
+
+	entry = list_first_entry(&cqm_rmid_lru, struct cqm_rmid_entry, list);
+	list_del(&entry->list);
+
+	return entry->rmid;
 }
 
 static void __put_rmid(int rmid)
 {
-	bitmap_release_region(cqm_rmid_bitmap, rmid, 0);
+	struct cqm_rmid_entry *entry;
+
+	lockdep_assert_held(&cache_mutex);
+
+	entry = __rmid_entry(rmid);
+
+	list_add_tail(&entry->list, &cqm_rmid_lru);
 }
 
 static int intel_cqm_setup_rmid_cache(void)
 {
-	cqm_rmid_bitmap = kmalloc(sizeof(long) * BITS_TO_LONGS(cqm_max_rmid), GFP_KERNEL);
-	if (!cqm_rmid_bitmap)
+	struct cqm_rmid_entry *entry;
+	int r;
+
+	cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
+				(cqm_max_rmid + 1), GFP_KERNEL);
+	if (!cqm_rmid_ptrs)
 		return -ENOMEM;
 
-	bitmap_zero(cqm_rmid_bitmap, cqm_max_rmid);
+	for (r = 0; r <= cqm_max_rmid; r++) {
+		struct cqm_rmid_entry *entry;
+
+		entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+		if (!entry)
+			goto fail;
+
+		INIT_LIST_HEAD(&entry->list);
+		entry->rmid = r;
+		cqm_rmid_ptrs[r] = entry;
+
+		list_add_tail(&entry->list, &cqm_rmid_lru);
+	}
 
 	/*
 	 * RMID 0 is special and is always allocated. It's used for all
 	 * tasks that are not monitored.
 	 */
-	bitmap_allocate_region(cqm_rmid_bitmap, 0, 0);
+	entry = __rmid_entry(0);
+	list_del(&entry->list);
 
 	return 0;
+fail:
+	while (r--)
+		kfree(cqm_rmid_ptrs[r]);
+
+	kfree(cqm_rmid_ptrs);
+	return -ENOMEM;
 }
 
 /*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/