[PATCH mm-unstable v1 1/2] mm: multi-gen LRU: clean up sysfs code

[PATCH mm-unstable v1 1/2] mm: multi-gen LRU: clean up sysfs code

[T.J. Alumbaugh]

This patch cleans up the sysfs code. Specifically,
  1. use sysfs_emit(),
  2. use __ATTR_RW(), and
  3. constify multi-gen LRU struct attribute_group.

Signed-off-by: T.J. Alumbaugh <talumbau@google.com>
---
 include/linux/mmzone.h |  2 +-
 mm/vmscan.c            | 22 +++++++++-------------
 2 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9fb1b03b83b2..bf8786d45b31 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1369,7 +1369,7 @@ typedef struct pglist_data {
 
 #ifdef CONFIG_LRU_GEN
 	/* kswap mm walk data */
-	struct lru_gen_mm_walk	mm_walk;
+	struct lru_gen_mm_walk mm_walk;
 	/* lru_gen_folio list */
 	struct lru_gen_memcg memcg_lru;
 #endif
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d4b9fd1ae0ed..09c064accdb1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5658,14 +5658,14 @@ static void lru_gen_change_state(bool enabled)
  *                          sysfs interface
  ******************************************************************************/
 
-static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
+	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
 }
 
 /* see Documentation/admin-guide/mm/multigen_lru.rst for details */
-static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
-			     const char *buf, size_t len)
+static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr,
+				const char *buf, size_t len)
 {
 	unsigned int msecs;
 
@@ -5677,11 +5677,9 @@ static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
 	return len;
 }
 
-static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR(
-	min_ttl_ms, 0644, show_min_ttl, store_min_ttl
-);
+static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms);
 
-static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	unsigned int caps = 0;
 
@@ -5698,7 +5696,7 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c
 }
 
 /* see Documentation/admin-guide/mm/multigen_lru.rst for details */
-static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr,
+static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
 			     const char *buf, size_t len)
 {
 	int i;
@@ -5725,9 +5723,7 @@ static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr,
 	return len;
 }
 
-static struct kobj_attribute lru_gen_enabled_attr = __ATTR(
-	enabled, 0644, show_enabled, store_enabled
-);
+static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled);
 
 static struct attribute *lru_gen_attrs[] = {
 	&lru_gen_min_ttl_attr.attr,
@@ -5735,7 +5731,7 @@ static struct attribute *lru_gen_attrs[] = {
 	NULL
 };
 
-static struct attribute_group lru_gen_attr_group = {
+static const struct attribute_group lru_gen_attr_group = {
 	.name = "lru_gen",
 	.attrs = lru_gen_attrs,
 };
-- 
2.39.1.581.gbfd45094c4-goog

[PATCH mm-unstable v1 2/2] mm: multi-gen LRU: improve design doc

[T.J. Alumbaugh]

This patch improves the design doc. Specifically,
  1. add a section for the per-memcg mm_struct list, and
  2. add a section for the PID controller.

Signed-off-by: T.J. Alumbaugh <talumbau@google.com>
---
 Documentation/mm/multigen_lru.rst | 44 +++++++++++++++++++++++++++----
 mm/vmscan.c                       |  2 +-
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/Documentation/mm/multigen_lru.rst b/Documentation/mm/multigen_lru.rst
index 5f1f6ecbb79b..52ed5092022f 100644
--- a/Documentation/mm/multigen_lru.rst
+++ b/Documentation/mm/multigen_lru.rst
@@ -103,7 +103,8 @@ moving across tiers only involves atomic operations on
 ``folio->flags`` and therefore has a negligible cost. A feedback loop
 modeled after the PID controller monitors refaults over all the tiers
 from anon and file types and decides which tiers from which types to
-evict or protect.
+evict or protect. The desired effect is to balance refault percentages
+between anon and file types proportional to the swappiness level.
 
 There are two conceptually independent procedures: the aging and the
 eviction. They form a closed-loop system, i.e., the page reclaim.
@@ -156,6 +157,27 @@ This time-based approach has the following advantages:
    and memory sizes.
 2. It is more reliable because it is directly wired to the OOM killer.
 
+``mm_struct`` list
+------------------
+An ``mm_struct`` list is maintained for each memcg, and an
+``mm_struct`` follows its owner task to the new memcg when this task
+is migrated.
+
+A page table walker iterates ``lruvec_memcg()->mm_list`` and calls
+``walk_page_range()`` with each ``mm_struct`` on this list to scan
+PTEs. When multiple page table walkers iterate the same list, each of
+them gets a unique ``mm_struct``, and therefore they can run in
+parallel.
+
+Page table walkers ignore any misplaced pages, e.g., if an
+``mm_struct`` was migrated, pages left in the previous memcg will be
+ignored when the current memcg is under reclaim. Similarly, page table
+walkers will ignore pages from nodes other than the one under reclaim.
+
+This infrastructure also tracks the usage of ``mm_struct`` between
+context switches so that page table walkers can skip processes that
+have been sleeping since the last iteration.
+
 Rmap/PT walk feedback
 ---------------------
 Searching the rmap for PTEs mapping each page on an LRU list (to test
@@ -170,7 +192,7 @@ promotes hot pages. If the scan was done cacheline efficiently, it
 adds the PMD entry pointing to the PTE table to the Bloom filter. This
 forms a feedback loop between the eviction and the aging.
 
-Bloom Filters
+Bloom filters
 -------------
 Bloom filters are a space and memory efficient data structure for set
 membership test, i.e., test if an element is not in the set or may be
@@ -186,6 +208,18 @@ is false positive, the cost is an additional scan of a range of PTEs,
 which may yield hot pages anyway. Parameters of the filter itself can
 control the false positive rate in the limit.
 
+PID controller
+--------------
+A feedback loop modeled after the Proportional-Integral-Derivative
+(PID) controller monitors refaults over anon and file types and
+decides which type to evict when both types are available from the
+same generation.
+
+The PID controller uses generations rather than the wall clock as the
+time domain because a CPU can scan pages at different rates under
+varying memory pressure. It calculates a moving average for each new
+generation to avoid being permanently locked in a suboptimal state.
+
 Memcg LRU
 ---------
 An memcg LRU is a per-node LRU of memcgs. It is also an LRU of LRUs,
@@ -223,9 +257,9 @@ parts:
 
 * Generations
 * Rmap walks
-* Page table walks
-* Bloom filters
-* PID controller
+* Page table walks via ``mm_struct`` list
+* Bloom filters for rmap/PT walk feedback
+* PID controller for refault feedback
 
 The aging and the eviction form a producer-consumer model;
 specifically, the latter drives the former by the sliding window over
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 09c064accdb1..43e69dc8b4bd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3604,7 +3604,7 @@ static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq)
 }
 
 /******************************************************************************
- *                          refault feedback loop
+ *                          PID controller
  ******************************************************************************/
 
 /*
-- 
2.39.1.581.gbfd45094c4-goog

Re: [PATCH mm-unstable v1 1/2] mm: multi-gen LRU: clean up sysfs code

[Wei Xu]

Reviewed-by: Wei Xu <weixugc@google.com>

On Mon, Feb 13, 2023 at 7:54 PM T.J. Alumbaugh <talumbau@google.com> wrote:
>
> This patch cleans up the sysfs code. Specifically,

Nit: Remove "This patch" per the "submitting patches" guide.

>   1. use sysfs_emit(),
>   2. use __ATTR_RW(), and
>   3. constify multi-gen LRU struct attribute_group.
>
> Signed-off-by: T.J. Alumbaugh <talumbau@google.com>
> ---
>  include/linux/mmzone.h |  2 +-
>  mm/vmscan.c            | 22 +++++++++-------------
>  2 files changed, 10 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 9fb1b03b83b2..bf8786d45b31 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -1369,7 +1369,7 @@ typedef struct pglist_data {
>
>  #ifdef CONFIG_LRU_GEN
>         /* kswap mm walk data */
> -       struct lru_gen_mm_walk  mm_walk;
> +       struct lru_gen_mm_walk mm_walk;
>         /* lru_gen_folio list */
>         struct lru_gen_memcg memcg_lru;
>  #endif
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index d4b9fd1ae0ed..09c064accdb1 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -5658,14 +5658,14 @@ static void lru_gen_change_state(bool enabled)
>   *                          sysfs interface
>   ******************************************************************************/
>
> -static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
> +static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
>  {
> -       return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
> +       return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
>  }
>
>  /* see Documentation/admin-guide/mm/multigen_lru.rst for details */
> -static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
> -                            const char *buf, size_t len)
> +static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr,
> +                               const char *buf, size_t len)
>  {
>         unsigned int msecs;
>
> @@ -5677,11 +5677,9 @@ static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
>         return len;
>  }
>
> -static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR(
> -       min_ttl_ms, 0644, show_min_ttl, store_min_ttl
> -);
> +static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms);
>
> -static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
> +static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
>  {
>         unsigned int caps = 0;
>
> @@ -5698,7 +5696,7 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c
>  }
>
>  /* see Documentation/admin-guide/mm/multigen_lru.rst for details */
> -static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr,
> +static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
>                              const char *buf, size_t len)
>  {
>         int i;
> @@ -5725,9 +5723,7 @@ static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr,
>         return len;
>  }
>
> -static struct kobj_attribute lru_gen_enabled_attr = __ATTR(
> -       enabled, 0644, show_enabled, store_enabled
> -);
> +static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled);
>
>  static struct attribute *lru_gen_attrs[] = {
>         &lru_gen_min_ttl_attr.attr,
> @@ -5735,7 +5731,7 @@ static struct attribute *lru_gen_attrs[] = {
>         NULL
>  };
>
> -static struct attribute_group lru_gen_attr_group = {
> +static const struct attribute_group lru_gen_attr_group = {
>         .name = "lru_gen",
>         .attrs = lru_gen_attrs,
>  };
> --
> 2.39.1.581.gbfd45094c4-goog
>
>