* [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags
2024-04-03 11:40 [PATCH v6 0/6] Swap-out mTHP without splitting Ryan Roberts
@ 2024-04-03 11:40 ` Ryan Roberts
2024-04-03 22:12 ` Chris Li
2024-04-05 9:25 ` David Hildenbrand
2024-04-03 11:40 ` [PATCH v6 2/6] mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Ryan Roberts
` (4 subsequent siblings)
5 siblings, 2 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-03 11:40 UTC (permalink / raw)
To: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: Ryan Roberts, linux-mm, linux-kernel
As preparation for supporting small-sized THP in the swap-out path,
without first needing to split to order-0, Remove the CLUSTER_FLAG_HUGE,
which, when present, always implies PMD-sized THP, which is the same as
the cluster size.
The only use of the flag was to determine whether a swap entry refers to
a single page or a PMD-sized THP in swap_page_trans_huge_swapped().
Instead of relying on the flag, we now pass in nr_pages, which
originates from the folio's number of pages. This allows the logic to
work for folios of any order.
The one snag is that one of the swap_page_trans_huge_swapped() call
sites does not have the folio. But it was only being called there to
shortcut a call __try_to_reclaim_swap() in some cases.
__try_to_reclaim_swap() gets the folio and (via some other functions)
calls swap_page_trans_huge_swapped(). So I've removed the problematic
call site and believe the new logic should be functionally equivalent.
That said, removing the fast path means that we will take a reference
and trylock a large folio much more often, which we would like to avoid.
The next patch will solve this.
Removing CLUSTER_FLAG_HUGE also means we can remove split_swap_cluster()
which used to be called during folio splitting, since
split_swap_cluster()'s only job was to remove the flag.
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
include/linux/swap.h | 10 ----------
mm/huge_memory.c | 3 ---
mm/swapfile.c | 47 ++++++++------------------------------------
3 files changed, 8 insertions(+), 52 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a211a0383425..f6f78198f000 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -259,7 +259,6 @@ struct swap_cluster_info {
};
#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
-#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
/*
* We assign a cluster to each CPU, so each CPU can allocate swap entry from
@@ -590,15 +589,6 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
}
#endif /* CONFIG_SWAP */
-#ifdef CONFIG_THP_SWAP
-extern int split_swap_cluster(swp_entry_t entry);
-#else
-static inline int split_swap_cluster(swp_entry_t entry)
-{
- return 0;
-}
-#endif
-
#ifdef CONFIG_MEMCG
static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ea6d1f09a0b9..3ca9282a0dc9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2844,9 +2844,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
shmem_uncharge(folio->mapping->host, nr_dropped);
remap_page(folio, nr);
- if (folio_test_swapcache(folio))
- split_swap_cluster(folio->swap);
-
/*
* set page to its compound_head when split to non order-0 pages, so
* we can skip unlocking it below, since PG_locked is transferred to
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 5e6d2304a2a4..0d44ee2b4f9c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -343,18 +343,6 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
info->data = 0;
}
-static inline bool cluster_is_huge(struct swap_cluster_info *info)
-{
- if (IS_ENABLED(CONFIG_THP_SWAP))
- return info->flags & CLUSTER_FLAG_HUGE;
- return false;
-}
-
-static inline void cluster_clear_huge(struct swap_cluster_info *info)
-{
- info->flags &= ~CLUSTER_FLAG_HUGE;
-}
-
static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
unsigned long offset)
{
@@ -1027,7 +1015,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
offset = idx * SWAPFILE_CLUSTER;
ci = lock_cluster(si, offset);
alloc_cluster(si, idx);
- cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);
+ cluster_set_count(ci, SWAPFILE_CLUSTER);
memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
unlock_cluster(ci);
@@ -1365,7 +1353,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
ci = lock_cluster_or_swap_info(si, offset);
if (size == SWAPFILE_CLUSTER) {
- VM_BUG_ON(!cluster_is_huge(ci));
map = si->swap_map + offset;
for (i = 0; i < SWAPFILE_CLUSTER; i++) {
val = map[i];
@@ -1373,7 +1360,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
if (val == SWAP_HAS_CACHE)
free_entries++;
}
- cluster_clear_huge(ci);
if (free_entries == SWAPFILE_CLUSTER) {
unlock_cluster_or_swap_info(si, ci);
spin_lock(&si->lock);
@@ -1395,23 +1381,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
unlock_cluster_or_swap_info(si, ci);
}
-#ifdef CONFIG_THP_SWAP
-int split_swap_cluster(swp_entry_t entry)
-{
- struct swap_info_struct *si;
- struct swap_cluster_info *ci;
- unsigned long offset = swp_offset(entry);
-
- si = _swap_info_get(entry);
- if (!si)
- return -EBUSY;
- ci = lock_cluster(si, offset);
- cluster_clear_huge(ci);
- unlock_cluster(ci);
- return 0;
-}
-#endif
-
static int swp_entry_cmp(const void *ent1, const void *ent2)
{
const swp_entry_t *e1 = ent1, *e2 = ent2;
@@ -1519,22 +1488,23 @@ int swp_swapcount(swp_entry_t entry)
}
static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
- swp_entry_t entry)
+ swp_entry_t entry,
+ unsigned int nr_pages)
{
struct swap_cluster_info *ci;
unsigned char *map = si->swap_map;
unsigned long roffset = swp_offset(entry);
- unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER);
+ unsigned long offset = round_down(roffset, nr_pages);
int i;
bool ret = false;
ci = lock_cluster_or_swap_info(si, offset);
- if (!ci || !cluster_is_huge(ci)) {
+ if (!ci || nr_pages == 1) {
if (swap_count(map[roffset]))
ret = true;
goto unlock_out;
}
- for (i = 0; i < SWAPFILE_CLUSTER; i++) {
+ for (i = 0; i < nr_pages; i++) {
if (swap_count(map[offset + i])) {
ret = true;
break;
@@ -1556,7 +1526,7 @@ static bool folio_swapped(struct folio *folio)
if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio)))
return swap_swapcount(si, entry) != 0;
- return swap_page_trans_huge_swapped(si, entry);
+ return swap_page_trans_huge_swapped(si, entry, folio_nr_pages(folio));
}
/**
@@ -1622,8 +1592,7 @@ int free_swap_and_cache(swp_entry_t entry)
}
count = __swap_entry_free(p, entry);
- if (count == SWAP_HAS_CACHE &&
- !swap_page_trans_huge_swapped(p, entry))
+ if (count == SWAP_HAS_CACHE)
__try_to_reclaim_swap(p, swp_offset(entry),
TTRS_UNMAPPED | TTRS_FULL);
put_swap_device(p);
--
2.25.1
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags
2024-04-03 11:40 ` [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags Ryan Roberts
@ 2024-04-03 22:12 ` Chris Li
2024-04-04 7:06 ` Ryan Roberts
2024-04-05 9:25 ` David Hildenbrand
1 sibling, 1 reply; 30+ messages in thread
From: Chris Li @ 2024-04-03 22:12 UTC (permalink / raw)
To: Ryan Roberts
Cc: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Lance Yang, linux-mm, linux-kernel
Hi Ryan,
Sorry for the late reply. I want to review this series but don't have
the chance to do it sooner.
On Wed, Apr 3, 2024 at 4:40 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>
> As preparation for supporting small-sized THP in the swap-out path,
> without first needing to split to order-0, Remove the CLUSTER_FLAG_HUGE,
> which, when present, always implies PMD-sized THP, which is the same as
> the cluster size.
>
> The only use of the flag was to determine whether a swap entry refers to
> a single page or a PMD-sized THP in swap_page_trans_huge_swapped().
> Instead of relying on the flag, we now pass in nr_pages, which
> originates from the folio's number of pages. This allows the logic to
> work for folios of any order.
>
> The one snag is that one of the swap_page_trans_huge_swapped() call
> sites does not have the folio. But it was only being called there to
> shortcut a call __try_to_reclaim_swap() in some cases.
> __try_to_reclaim_swap() gets the folio and (via some other functions)
> calls swap_page_trans_huge_swapped(). So I've removed the problematic
> call site and believe the new logic should be functionally equivalent.
>
> That said, removing the fast path means that we will take a reference
> and trylock a large folio much more often, which we would like to avoid.
> The next patch will solve this.
>
> Removing CLUSTER_FLAG_HUGE also means we can remove split_swap_cluster()
> which used to be called during folio splitting, since
> split_swap_cluster()'s only job was to remove the flag.
Seems necessary to remove the assumption of large folio be PMD size.
Acked-by: Chris Li <chrisl@kernel.org>
>
> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
> include/linux/swap.h | 10 ----------
> mm/huge_memory.c | 3 ---
> mm/swapfile.c | 47 ++++++++------------------------------------
> 3 files changed, 8 insertions(+), 52 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index a211a0383425..f6f78198f000 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -259,7 +259,6 @@ struct swap_cluster_info {
> };
> #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
> #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
> -#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
>
> /*
> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
> @@ -590,15 +589,6 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
> }
> #endif /* CONFIG_SWAP */
>
> -#ifdef CONFIG_THP_SWAP
> -extern int split_swap_cluster(swp_entry_t entry);
> -#else
> -static inline int split_swap_cluster(swp_entry_t entry)
> -{
> - return 0;
> -}
> -#endif
> -
> #ifdef CONFIG_MEMCG
> static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
> {
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index ea6d1f09a0b9..3ca9282a0dc9 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2844,9 +2844,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> shmem_uncharge(folio->mapping->host, nr_dropped);
> remap_page(folio, nr);
>
> - if (folio_test_swapcache(folio))
> - split_swap_cluster(folio->swap);
> -
> /*
> * set page to its compound_head when split to non order-0 pages, so
> * we can skip unlocking it below, since PG_locked is transferred to
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 5e6d2304a2a4..0d44ee2b4f9c 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -343,18 +343,6 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
> info->data = 0;
> }
>
> -static inline bool cluster_is_huge(struct swap_cluster_info *info)
> -{
> - if (IS_ENABLED(CONFIG_THP_SWAP))
> - return info->flags & CLUSTER_FLAG_HUGE;
> - return false;
> -}
> -
> -static inline void cluster_clear_huge(struct swap_cluster_info *info)
> -{
> - info->flags &= ~CLUSTER_FLAG_HUGE;
> -}
> -
> static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
> unsigned long offset)
> {
> @@ -1027,7 +1015,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
> offset = idx * SWAPFILE_CLUSTER;
> ci = lock_cluster(si, offset);
> alloc_cluster(si, idx);
> - cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);
> + cluster_set_count(ci, SWAPFILE_CLUSTER);
>
> memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
> unlock_cluster(ci);
> @@ -1365,7 +1353,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>
> ci = lock_cluster_or_swap_info(si, offset);
> if (size == SWAPFILE_CLUSTER) {
> - VM_BUG_ON(!cluster_is_huge(ci));
> map = si->swap_map + offset;
> for (i = 0; i < SWAPFILE_CLUSTER; i++) {
> val = map[i];
> @@ -1373,7 +1360,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
> if (val == SWAP_HAS_CACHE)
> free_entries++;
> }
> - cluster_clear_huge(ci);
> if (free_entries == SWAPFILE_CLUSTER) {
> unlock_cluster_or_swap_info(si, ci);
> spin_lock(&si->lock);
> @@ -1395,23 +1381,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
> unlock_cluster_or_swap_info(si, ci);
> }
>
> -#ifdef CONFIG_THP_SWAP
> -int split_swap_cluster(swp_entry_t entry)
> -{
> - struct swap_info_struct *si;
> - struct swap_cluster_info *ci;
> - unsigned long offset = swp_offset(entry);
> -
> - si = _swap_info_get(entry);
> - if (!si)
> - return -EBUSY;
> - ci = lock_cluster(si, offset);
> - cluster_clear_huge(ci);
> - unlock_cluster(ci);
> - return 0;
> -}
> -#endif
> -
> static int swp_entry_cmp(const void *ent1, const void *ent2)
> {
> const swp_entry_t *e1 = ent1, *e2 = ent2;
> @@ -1519,22 +1488,23 @@ int swp_swapcount(swp_entry_t entry)
> }
>
> static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
> - swp_entry_t entry)
> + swp_entry_t entry,
> + unsigned int nr_pages)
> {
> struct swap_cluster_info *ci;
> unsigned char *map = si->swap_map;
> unsigned long roffset = swp_offset(entry);
> - unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER);
> + unsigned long offset = round_down(roffset, nr_pages);
It is obvious this code only works for powers two nr_pages. The
SWAPFILE_CLSTER is a power of two. If we switch to an API for
nr_pages, we might want to warn/ban passing in the non-power of two
nr_pages.
> int i;
> bool ret = false;
>
> ci = lock_cluster_or_swap_info(si, offset);
> - if (!ci || !cluster_is_huge(ci)) {
> + if (!ci || nr_pages == 1) {
> if (swap_count(map[roffset]))
> ret = true;
> goto unlock_out;
> }
> - for (i = 0; i < SWAPFILE_CLUSTER; i++) {
> + for (i = 0; i < nr_pages; i++) {
Here we assume the swap entry offset is contiguous. That is beyond
your patch's scope. If in the future we want to have non-contiguous
swap entries to swap out large pages, we will need to find out and
change all the places that have the assumption of contiguous swap
entries.
Chris
> if (swap_count(map[offset + i])) {
> ret = true;
> break;
> @@ -1556,7 +1526,7 @@ static bool folio_swapped(struct folio *folio)
> if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio)))
> return swap_swapcount(si, entry) != 0;
>
> - return swap_page_trans_huge_swapped(si, entry);
> + return swap_page_trans_huge_swapped(si, entry, folio_nr_pages(folio));
> }
>
> /**
> @@ -1622,8 +1592,7 @@ int free_swap_and_cache(swp_entry_t entry)
> }
>
> count = __swap_entry_free(p, entry);
> - if (count == SWAP_HAS_CACHE &&
> - !swap_page_trans_huge_swapped(p, entry))
> + if (count == SWAP_HAS_CACHE)
> __try_to_reclaim_swap(p, swp_offset(entry),
> TTRS_UNMAPPED | TTRS_FULL);
> put_swap_device(p);
> --
> 2.25.1
>
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags
2024-04-03 22:12 ` Chris Li
@ 2024-04-04 7:06 ` Ryan Roberts
2024-04-04 13:43 ` Chris Li
0 siblings, 1 reply; 30+ messages in thread
From: Ryan Roberts @ 2024-04-04 7:06 UTC (permalink / raw)
To: Chris Li
Cc: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Lance Yang, linux-mm, linux-kernel
On 03/04/2024 23:12, Chris Li wrote:
> Hi Ryan,
>
> Sorry for the late reply. I want to review this series but don't have
> the chance to do it sooner.
No problem. This series is now in mm-unstable, so if you want to request any
changes in the other patches, I'd prefer it sooner rather than later, if possible.
>
> On Wed, Apr 3, 2024 at 4:40 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>
>> As preparation for supporting small-sized THP in the swap-out path,
>> without first needing to split to order-0, Remove the CLUSTER_FLAG_HUGE,
>> which, when present, always implies PMD-sized THP, which is the same as
>> the cluster size.
>>
>> The only use of the flag was to determine whether a swap entry refers to
>> a single page or a PMD-sized THP in swap_page_trans_huge_swapped().
>> Instead of relying on the flag, we now pass in nr_pages, which
>> originates from the folio's number of pages. This allows the logic to
>> work for folios of any order.
>>
>> The one snag is that one of the swap_page_trans_huge_swapped() call
>> sites does not have the folio. But it was only being called there to
>> shortcut a call __try_to_reclaim_swap() in some cases.
>> __try_to_reclaim_swap() gets the folio and (via some other functions)
>> calls swap_page_trans_huge_swapped(). So I've removed the problematic
>> call site and believe the new logic should be functionally equivalent.
>>
>> That said, removing the fast path means that we will take a reference
>> and trylock a large folio much more often, which we would like to avoid.
>> The next patch will solve this.
>>
>> Removing CLUSTER_FLAG_HUGE also means we can remove split_swap_cluster()
>> which used to be called during folio splitting, since
>> split_swap_cluster()'s only job was to remove the flag.
>
> Seems necessary to remove the assumption of large folio be PMD size.
>
> Acked-by: Chris Li <chrisl@kernel.org>
Thanks!
>
>>
>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> ---
>> include/linux/swap.h | 10 ----------
>> mm/huge_memory.c | 3 ---
>> mm/swapfile.c | 47 ++++++++------------------------------------
>> 3 files changed, 8 insertions(+), 52 deletions(-)
>>
>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>> index a211a0383425..f6f78198f000 100644
>> --- a/include/linux/swap.h
>> +++ b/include/linux/swap.h
>> @@ -259,7 +259,6 @@ struct swap_cluster_info {
>> };
>> #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
>> #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
>> -#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
>>
>> /*
>> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
>> @@ -590,15 +589,6 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
>> }
>> #endif /* CONFIG_SWAP */
>>
>> -#ifdef CONFIG_THP_SWAP
>> -extern int split_swap_cluster(swp_entry_t entry);
>> -#else
>> -static inline int split_swap_cluster(swp_entry_t entry)
>> -{
>> - return 0;
>> -}
>> -#endif
>> -
>> #ifdef CONFIG_MEMCG
>> static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
>> {
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index ea6d1f09a0b9..3ca9282a0dc9 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -2844,9 +2844,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>> shmem_uncharge(folio->mapping->host, nr_dropped);
>> remap_page(folio, nr);
>>
>> - if (folio_test_swapcache(folio))
>> - split_swap_cluster(folio->swap);
>> -
>> /*
>> * set page to its compound_head when split to non order-0 pages, so
>> * we can skip unlocking it below, since PG_locked is transferred to
>> diff --git a/mm/swapfile.c b/mm/swapfile.c
>> index 5e6d2304a2a4..0d44ee2b4f9c 100644
>> --- a/mm/swapfile.c
>> +++ b/mm/swapfile.c
>> @@ -343,18 +343,6 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
>> info->data = 0;
>> }
>>
>> -static inline bool cluster_is_huge(struct swap_cluster_info *info)
>> -{
>> - if (IS_ENABLED(CONFIG_THP_SWAP))
>> - return info->flags & CLUSTER_FLAG_HUGE;
>> - return false;
>> -}
>> -
>> -static inline void cluster_clear_huge(struct swap_cluster_info *info)
>> -{
>> - info->flags &= ~CLUSTER_FLAG_HUGE;
>> -}
>> -
>> static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
>> unsigned long offset)
>> {
>> @@ -1027,7 +1015,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
>> offset = idx * SWAPFILE_CLUSTER;
>> ci = lock_cluster(si, offset);
>> alloc_cluster(si, idx);
>> - cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);
>> + cluster_set_count(ci, SWAPFILE_CLUSTER);
>>
>> memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
>> unlock_cluster(ci);
>> @@ -1365,7 +1353,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>>
>> ci = lock_cluster_or_swap_info(si, offset);
>> if (size == SWAPFILE_CLUSTER) {
>> - VM_BUG_ON(!cluster_is_huge(ci));
>> map = si->swap_map + offset;
>> for (i = 0; i < SWAPFILE_CLUSTER; i++) {
>> val = map[i];
>> @@ -1373,7 +1360,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>> if (val == SWAP_HAS_CACHE)
>> free_entries++;
>> }
>> - cluster_clear_huge(ci);
>> if (free_entries == SWAPFILE_CLUSTER) {
>> unlock_cluster_or_swap_info(si, ci);
>> spin_lock(&si->lock);
>> @@ -1395,23 +1381,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>> unlock_cluster_or_swap_info(si, ci);
>> }
>>
>> -#ifdef CONFIG_THP_SWAP
>> -int split_swap_cluster(swp_entry_t entry)
>> -{
>> - struct swap_info_struct *si;
>> - struct swap_cluster_info *ci;
>> - unsigned long offset = swp_offset(entry);
>> -
>> - si = _swap_info_get(entry);
>> - if (!si)
>> - return -EBUSY;
>> - ci = lock_cluster(si, offset);
>> - cluster_clear_huge(ci);
>> - unlock_cluster(ci);
>> - return 0;
>> -}
>> -#endif
>> -
>> static int swp_entry_cmp(const void *ent1, const void *ent2)
>> {
>> const swp_entry_t *e1 = ent1, *e2 = ent2;
>> @@ -1519,22 +1488,23 @@ int swp_swapcount(swp_entry_t entry)
>> }
>>
>> static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
>> - swp_entry_t entry)
>> + swp_entry_t entry,
>> + unsigned int nr_pages)
>> {
>> struct swap_cluster_info *ci;
>> unsigned char *map = si->swap_map;
>> unsigned long roffset = swp_offset(entry);
>> - unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER);
>> + unsigned long offset = round_down(roffset, nr_pages);
>
> It is obvious this code only works for powers two nr_pages. The
> SWAPFILE_CLSTER is a power of two. If we switch to an API for
> nr_pages, we might want to warn/ban passing in the non-power of two
> nr_pages.
Indeed. I could change the prototype to pass order instead of nr_pages, then
generate nr_pages (= 1 << order) inside the function. But given the function is
static and only called from a single callsite, I don't see it as hugely
important. I'd prefer to leave as is at this stage, unless you have strong
objection.
>
>> int i;
>> bool ret = false;
>>
>> ci = lock_cluster_or_swap_info(si, offset);
>> - if (!ci || !cluster_is_huge(ci)) {
>> + if (!ci || nr_pages == 1) {
>> if (swap_count(map[roffset]))
>> ret = true;
>> goto unlock_out;
>> }
>> - for (i = 0; i < SWAPFILE_CLUSTER; i++) {
>> + for (i = 0; i < nr_pages; i++) {
>
> Here we assume the swap entry offset is contiguous. That is beyond
> your patch's scope. If in the future we want to have non-contiguous
> swap entries to swap out large pages, we will need to find out and
> change all the places that have the assumption of contiguous swap
> entries.
Yes there are tonnes of places that make this assumption :)
>
> Chris
>
>> if (swap_count(map[offset + i])) {
>> ret = true;
>> break;
>> @@ -1556,7 +1526,7 @@ static bool folio_swapped(struct folio *folio)
>> if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio)))
>> return swap_swapcount(si, entry) != 0;
>>
>> - return swap_page_trans_huge_swapped(si, entry);
>> + return swap_page_trans_huge_swapped(si, entry, folio_nr_pages(folio));
>> }
>>
>> /**
>> @@ -1622,8 +1592,7 @@ int free_swap_and_cache(swp_entry_t entry)
>> }
>>
>> count = __swap_entry_free(p, entry);
>> - if (count == SWAP_HAS_CACHE &&
>> - !swap_page_trans_huge_swapped(p, entry))
>> + if (count == SWAP_HAS_CACHE)
>> __try_to_reclaim_swap(p, swp_offset(entry),
>> TTRS_UNMAPPED | TTRS_FULL);
>> put_swap_device(p);
>> --
>> 2.25.1
>>
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags
2024-04-04 7:06 ` Ryan Roberts
@ 2024-04-04 13:43 ` Chris Li
2024-04-08 11:56 ` Ryan Roberts
0 siblings, 1 reply; 30+ messages in thread
From: Chris Li @ 2024-04-04 13:43 UTC (permalink / raw)
To: Ryan Roberts
Cc: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Lance Yang, linux-mm, linux-kernel
On Thu, Apr 4, 2024 at 12:06 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>
> On 03/04/2024 23:12, Chris Li wrote:
> > Hi Ryan,
> >
> > Sorry for the late reply. I want to review this series but don't have
> > the chance to do it sooner.
>
> No problem. This series is now in mm-unstable, so if you want to request any
> changes in the other patches, I'd prefer it sooner rather than later, if possible.
>
> >
> > On Wed, Apr 3, 2024 at 4:40 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
> >>
> >> As preparation for supporting small-sized THP in the swap-out path,
> >> without first needing to split to order-0, Remove the CLUSTER_FLAG_HUGE,
> >> which, when present, always implies PMD-sized THP, which is the same as
> >> the cluster size.
> >>
> >> The only use of the flag was to determine whether a swap entry refers to
> >> a single page or a PMD-sized THP in swap_page_trans_huge_swapped().
> >> Instead of relying on the flag, we now pass in nr_pages, which
> >> originates from the folio's number of pages. This allows the logic to
> >> work for folios of any order.
> >>
> >> The one snag is that one of the swap_page_trans_huge_swapped() call
> >> sites does not have the folio. But it was only being called there to
> >> shortcut a call __try_to_reclaim_swap() in some cases.
> >> __try_to_reclaim_swap() gets the folio and (via some other functions)
> >> calls swap_page_trans_huge_swapped(). So I've removed the problematic
> >> call site and believe the new logic should be functionally equivalent.
> >>
> >> That said, removing the fast path means that we will take a reference
> >> and trylock a large folio much more often, which we would like to avoid.
> >> The next patch will solve this.
> >>
> >> Removing CLUSTER_FLAG_HUGE also means we can remove split_swap_cluster()
> >> which used to be called during folio splitting, since
> >> split_swap_cluster()'s only job was to remove the flag.
> >
> > Seems necessary to remove the assumption of large folio be PMD size.
> >
> > Acked-by: Chris Li <chrisl@kernel.org>
>
> Thanks!
>
> >
> >>
> >> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
> >> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> >> ---
> >> include/linux/swap.h | 10 ----------
> >> mm/huge_memory.c | 3 ---
> >> mm/swapfile.c | 47 ++++++++------------------------------------
> >> 3 files changed, 8 insertions(+), 52 deletions(-)
> >>
> >> diff --git a/include/linux/swap.h b/include/linux/swap.h
> >> index a211a0383425..f6f78198f000 100644
> >> --- a/include/linux/swap.h
> >> +++ b/include/linux/swap.h
> >> @@ -259,7 +259,6 @@ struct swap_cluster_info {
> >> };
> >> #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
> >> #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
> >> -#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
> >>
> >> /*
> >> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
> >> @@ -590,15 +589,6 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
> >> }
> >> #endif /* CONFIG_SWAP */
> >>
> >> -#ifdef CONFIG_THP_SWAP
> >> -extern int split_swap_cluster(swp_entry_t entry);
> >> -#else
> >> -static inline int split_swap_cluster(swp_entry_t entry)
> >> -{
> >> - return 0;
> >> -}
> >> -#endif
> >> -
> >> #ifdef CONFIG_MEMCG
> >> static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
> >> {
> >> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> >> index ea6d1f09a0b9..3ca9282a0dc9 100644
> >> --- a/mm/huge_memory.c
> >> +++ b/mm/huge_memory.c
> >> @@ -2844,9 +2844,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> >> shmem_uncharge(folio->mapping->host, nr_dropped);
> >> remap_page(folio, nr);
> >>
> >> - if (folio_test_swapcache(folio))
> >> - split_swap_cluster(folio->swap);
> >> -
> >> /*
> >> * set page to its compound_head when split to non order-0 pages, so
> >> * we can skip unlocking it below, since PG_locked is transferred to
> >> diff --git a/mm/swapfile.c b/mm/swapfile.c
> >> index 5e6d2304a2a4..0d44ee2b4f9c 100644
> >> --- a/mm/swapfile.c
> >> +++ b/mm/swapfile.c
> >> @@ -343,18 +343,6 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
> >> info->data = 0;
> >> }
> >>
> >> -static inline bool cluster_is_huge(struct swap_cluster_info *info)
> >> -{
> >> - if (IS_ENABLED(CONFIG_THP_SWAP))
> >> - return info->flags & CLUSTER_FLAG_HUGE;
> >> - return false;
> >> -}
> >> -
> >> -static inline void cluster_clear_huge(struct swap_cluster_info *info)
> >> -{
> >> - info->flags &= ~CLUSTER_FLAG_HUGE;
> >> -}
> >> -
> >> static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
> >> unsigned long offset)
> >> {
> >> @@ -1027,7 +1015,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
> >> offset = idx * SWAPFILE_CLUSTER;
> >> ci = lock_cluster(si, offset);
> >> alloc_cluster(si, idx);
> >> - cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);
> >> + cluster_set_count(ci, SWAPFILE_CLUSTER);
> >>
> >> memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
> >> unlock_cluster(ci);
> >> @@ -1365,7 +1353,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
> >>
> >> ci = lock_cluster_or_swap_info(si, offset);
> >> if (size == SWAPFILE_CLUSTER) {
> >> - VM_BUG_ON(!cluster_is_huge(ci));
> >> map = si->swap_map + offset;
> >> for (i = 0; i < SWAPFILE_CLUSTER; i++) {
> >> val = map[i];
> >> @@ -1373,7 +1360,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
> >> if (val == SWAP_HAS_CACHE)
> >> free_entries++;
> >> }
> >> - cluster_clear_huge(ci);
> >> if (free_entries == SWAPFILE_CLUSTER) {
> >> unlock_cluster_or_swap_info(si, ci);
> >> spin_lock(&si->lock);
> >> @@ -1395,23 +1381,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
> >> unlock_cluster_or_swap_info(si, ci);
> >> }
> >>
> >> -#ifdef CONFIG_THP_SWAP
> >> -int split_swap_cluster(swp_entry_t entry)
> >> -{
> >> - struct swap_info_struct *si;
> >> - struct swap_cluster_info *ci;
> >> - unsigned long offset = swp_offset(entry);
> >> -
> >> - si = _swap_info_get(entry);
> >> - if (!si)
> >> - return -EBUSY;
> >> - ci = lock_cluster(si, offset);
> >> - cluster_clear_huge(ci);
> >> - unlock_cluster(ci);
> >> - return 0;
> >> -}
> >> -#endif
> >> -
> >> static int swp_entry_cmp(const void *ent1, const void *ent2)
> >> {
> >> const swp_entry_t *e1 = ent1, *e2 = ent2;
> >> @@ -1519,22 +1488,23 @@ int swp_swapcount(swp_entry_t entry)
> >> }
> >>
> >> static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
> >> - swp_entry_t entry)
> >> + swp_entry_t entry,
> >> + unsigned int nr_pages)
> >> {
> >> struct swap_cluster_info *ci;
> >> unsigned char *map = si->swap_map;
> >> unsigned long roffset = swp_offset(entry);
> >> - unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER);
> >> + unsigned long offset = round_down(roffset, nr_pages);
> >
> > It is obvious this code only works for powers two nr_pages. The
> > SWAPFILE_CLSTER is a power of two. If we switch to an API for
> > nr_pages, we might want to warn/ban passing in the non-power of two
> > nr_pages.
>
> Indeed. I could change the prototype to pass order instead of nr_pages, then
> generate nr_pages (= 1 << order) inside the function. But given the function is
> static and only called from a single callsite, I don't see it as hugely
> important. I'd prefer to leave as is at this stage, unless you have strong
> objection.
That is fine with me.
>
> >
> >> int i;
> >> bool ret = false;
> >>
> >> ci = lock_cluster_or_swap_info(si, offset);
> >> - if (!ci || !cluster_is_huge(ci)) {
> >> + if (!ci || nr_pages == 1) {
> >> if (swap_count(map[roffset]))
> >> ret = true;
> >> goto unlock_out;
> >> }
> >> - for (i = 0; i < SWAPFILE_CLUSTER; i++) {
> >> + for (i = 0; i < nr_pages; i++) {
> >
> > Here we assume the swap entry offset is contiguous. That is beyond
> > your patch's scope. If in the future we want to have non-contiguous
> > swap entries to swap out large pages, we will need to find out and
> > change all the places that have the assumption of contiguous swap
> > entries.
>
> Yes there are tonnes of places that make this assumption :)
Yes, that is why I want to have some wrapper API to mark the existing
place that makes the assumption. Hopefully we can just change those
wrapper functions to implement the non-contiguous version of swap.
Thank you for the patch.
Chris
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags
2024-04-04 13:43 ` Chris Li
@ 2024-04-08 11:56 ` Ryan Roberts
0 siblings, 0 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-08 11:56 UTC (permalink / raw)
To: Chris Li
Cc: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Lance Yang, linux-mm, linux-kernel
On 04/04/2024 14:43, Chris Li wrote:
> On Thu, Apr 4, 2024 at 12:06 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>
>> On 03/04/2024 23:12, Chris Li wrote:
>>> Hi Ryan,
>>>
>>> Sorry for the late reply. I want to review this series but don't have
>>> the chance to do it sooner.
>>
>> No problem. This series is now in mm-unstable, so if you want to request any
>> changes in the other patches, I'd prefer it sooner rather than later, if possible.
>>
>>>
>>> On Wed, Apr 3, 2024 at 4:40 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>>>
>>>> As preparation for supporting small-sized THP in the swap-out path,
>>>> without first needing to split to order-0, Remove the CLUSTER_FLAG_HUGE,
>>>> which, when present, always implies PMD-sized THP, which is the same as
>>>> the cluster size.
>>>>
>>>> The only use of the flag was to determine whether a swap entry refers to
>>>> a single page or a PMD-sized THP in swap_page_trans_huge_swapped().
>>>> Instead of relying on the flag, we now pass in nr_pages, which
>>>> originates from the folio's number of pages. This allows the logic to
>>>> work for folios of any order.
>>>>
>>>> The one snag is that one of the swap_page_trans_huge_swapped() call
>>>> sites does not have the folio. But it was only being called there to
>>>> shortcut a call __try_to_reclaim_swap() in some cases.
>>>> __try_to_reclaim_swap() gets the folio and (via some other functions)
>>>> calls swap_page_trans_huge_swapped(). So I've removed the problematic
>>>> call site and believe the new logic should be functionally equivalent.
>>>>
>>>> That said, removing the fast path means that we will take a reference
>>>> and trylock a large folio much more often, which we would like to avoid.
>>>> The next patch will solve this.
>>>>
>>>> Removing CLUSTER_FLAG_HUGE also means we can remove split_swap_cluster()
>>>> which used to be called during folio splitting, since
>>>> split_swap_cluster()'s only job was to remove the flag.
>>>
>>> Seems necessary to remove the assumption of large folio be PMD size.
>>>
>>> Acked-by: Chris Li <chrisl@kernel.org>
>>
>> Thanks!
>>
>>>
>>>>
>>>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>>> ---
>>>> include/linux/swap.h | 10 ----------
>>>> mm/huge_memory.c | 3 ---
>>>> mm/swapfile.c | 47 ++++++++------------------------------------
>>>> 3 files changed, 8 insertions(+), 52 deletions(-)
>>>>
>>>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>>>> index a211a0383425..f6f78198f000 100644
>>>> --- a/include/linux/swap.h
>>>> +++ b/include/linux/swap.h
>>>> @@ -259,7 +259,6 @@ struct swap_cluster_info {
>>>> };
>>>> #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
>>>> #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
>>>> -#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
>>>>
>>>> /*
>>>> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
>>>> @@ -590,15 +589,6 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
>>>> }
>>>> #endif /* CONFIG_SWAP */
>>>>
>>>> -#ifdef CONFIG_THP_SWAP
>>>> -extern int split_swap_cluster(swp_entry_t entry);
>>>> -#else
>>>> -static inline int split_swap_cluster(swp_entry_t entry)
>>>> -{
>>>> - return 0;
>>>> -}
>>>> -#endif
>>>> -
>>>> #ifdef CONFIG_MEMCG
>>>> static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
>>>> {
>>>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>>>> index ea6d1f09a0b9..3ca9282a0dc9 100644
>>>> --- a/mm/huge_memory.c
>>>> +++ b/mm/huge_memory.c
>>>> @@ -2844,9 +2844,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>>>> shmem_uncharge(folio->mapping->host, nr_dropped);
>>>> remap_page(folio, nr);
>>>>
>>>> - if (folio_test_swapcache(folio))
>>>> - split_swap_cluster(folio->swap);
>>>> -
>>>> /*
>>>> * set page to its compound_head when split to non order-0 pages, so
>>>> * we can skip unlocking it below, since PG_locked is transferred to
>>>> diff --git a/mm/swapfile.c b/mm/swapfile.c
>>>> index 5e6d2304a2a4..0d44ee2b4f9c 100644
>>>> --- a/mm/swapfile.c
>>>> +++ b/mm/swapfile.c
>>>> @@ -343,18 +343,6 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
>>>> info->data = 0;
>>>> }
>>>>
>>>> -static inline bool cluster_is_huge(struct swap_cluster_info *info)
>>>> -{
>>>> - if (IS_ENABLED(CONFIG_THP_SWAP))
>>>> - return info->flags & CLUSTER_FLAG_HUGE;
>>>> - return false;
>>>> -}
>>>> -
>>>> -static inline void cluster_clear_huge(struct swap_cluster_info *info)
>>>> -{
>>>> - info->flags &= ~CLUSTER_FLAG_HUGE;
>>>> -}
>>>> -
>>>> static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
>>>> unsigned long offset)
>>>> {
>>>> @@ -1027,7 +1015,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
>>>> offset = idx * SWAPFILE_CLUSTER;
>>>> ci = lock_cluster(si, offset);
>>>> alloc_cluster(si, idx);
>>>> - cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);
>>>> + cluster_set_count(ci, SWAPFILE_CLUSTER);
>>>>
>>>> memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
>>>> unlock_cluster(ci);
>>>> @@ -1365,7 +1353,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>>>>
>>>> ci = lock_cluster_or_swap_info(si, offset);
>>>> if (size == SWAPFILE_CLUSTER) {
>>>> - VM_BUG_ON(!cluster_is_huge(ci));
>>>> map = si->swap_map + offset;
>>>> for (i = 0; i < SWAPFILE_CLUSTER; i++) {
>>>> val = map[i];
>>>> @@ -1373,7 +1360,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>>>> if (val == SWAP_HAS_CACHE)
>>>> free_entries++;
>>>> }
>>>> - cluster_clear_huge(ci);
>>>> if (free_entries == SWAPFILE_CLUSTER) {
>>>> unlock_cluster_or_swap_info(si, ci);
>>>> spin_lock(&si->lock);
>>>> @@ -1395,23 +1381,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>>>> unlock_cluster_or_swap_info(si, ci);
>>>> }
>>>>
>>>> -#ifdef CONFIG_THP_SWAP
>>>> -int split_swap_cluster(swp_entry_t entry)
>>>> -{
>>>> - struct swap_info_struct *si;
>>>> - struct swap_cluster_info *ci;
>>>> - unsigned long offset = swp_offset(entry);
>>>> -
>>>> - si = _swap_info_get(entry);
>>>> - if (!si)
>>>> - return -EBUSY;
>>>> - ci = lock_cluster(si, offset);
>>>> - cluster_clear_huge(ci);
>>>> - unlock_cluster(ci);
>>>> - return 0;
>>>> -}
>>>> -#endif
>>>> -
>>>> static int swp_entry_cmp(const void *ent1, const void *ent2)
>>>> {
>>>> const swp_entry_t *e1 = ent1, *e2 = ent2;
>>>> @@ -1519,22 +1488,23 @@ int swp_swapcount(swp_entry_t entry)
>>>> }
>>>>
>>>> static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
>>>> - swp_entry_t entry)
>>>> + swp_entry_t entry,
>>>> + unsigned int nr_pages)
>>>> {
>>>> struct swap_cluster_info *ci;
>>>> unsigned char *map = si->swap_map;
>>>> unsigned long roffset = swp_offset(entry);
>>>> - unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER);
>>>> + unsigned long offset = round_down(roffset, nr_pages);
>>>
>>> It is obvious this code only works for powers two nr_pages. The
>>> SWAPFILE_CLSTER is a power of two. If we switch to an API for
>>> nr_pages, we might want to warn/ban passing in the non-power of two
>>> nr_pages.
>>
>> Indeed. I could change the prototype to pass order instead of nr_pages, then
>> generate nr_pages (= 1 << order) inside the function. But given the function is
>> static and only called from a single callsite, I don't see it as hugely
>> important. I'd prefer to leave as is at this stage, unless you have strong
>> objection.
>
> That is fine with me.
Given David spotted a bug in a later patch, I'm re-spinning the series, so will
make this change to pass the order.
>
>>
>>>
>>>> int i;
>>>> bool ret = false;
>>>>
>>>> ci = lock_cluster_or_swap_info(si, offset);
>>>> - if (!ci || !cluster_is_huge(ci)) {
>>>> + if (!ci || nr_pages == 1) {
>>>> if (swap_count(map[roffset]))
>>>> ret = true;
>>>> goto unlock_out;
>>>> }
>>>> - for (i = 0; i < SWAPFILE_CLUSTER; i++) {
>>>> + for (i = 0; i < nr_pages; i++) {
>>>
>>> Here we assume the swap entry offset is contiguous. That is beyond
>>> your patch's scope. If in the future we want to have non-contiguous
>>> swap entries to swap out large pages, we will need to find out and
>>> change all the places that have the assumption of contiguous swap
>>> entries.
>>
>> Yes there are tonnes of places that make this assumption :)
>
> Yes, that is why I want to have some wrapper API to mark the existing
> place that makes the assumption. Hopefully we can just change those
> wrapper functions to implement the non-contiguous version of swap.
>
> Thank you for the patch.
>
> Chris
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags
2024-04-03 11:40 ` [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags Ryan Roberts
2024-04-03 22:12 ` Chris Li
@ 2024-04-05 9:25 ` David Hildenbrand
1 sibling, 0 replies; 30+ messages in thread
From: David Hildenbrand @ 2024-04-05 9:25 UTC (permalink / raw)
To: Ryan Roberts, Andrew Morton, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: linux-mm, linux-kernel
On 03.04.24 13:40, Ryan Roberts wrote:
> As preparation for supporting small-sized THP in the swap-out path,
> without first needing to split to order-0, Remove the CLUSTER_FLAG_HUGE,
> which, when present, always implies PMD-sized THP, which is the same as
> the cluster size.
>
> The only use of the flag was to determine whether a swap entry refers to
> a single page or a PMD-sized THP in swap_page_trans_huge_swapped().
> Instead of relying on the flag, we now pass in nr_pages, which
> originates from the folio's number of pages. This allows the logic to
> work for folios of any order.
>
> The one snag is that one of the swap_page_trans_huge_swapped() call
> sites does not have the folio. But it was only being called there to
> shortcut a call __try_to_reclaim_swap() in some cases.
> __try_to_reclaim_swap() gets the folio and (via some other functions)
> calls swap_page_trans_huge_swapped(). So I've removed the problematic
> call site and believe the new logic should be functionally equivalent.
>
> That said, removing the fast path means that we will take a reference
> and trylock a large folio much more often, which we would like to avoid.
> The next patch will solve this.
>
> Removing CLUSTER_FLAG_HUGE also means we can remove split_swap_cluster()
> which used to be called during folio splitting, since
> split_swap_cluster()'s only job was to remove the flag.
>
> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
[started to review v5, then saw v6]
Acked-by: David Hildenbrand <david@redhat.com>
--
Cheers,
David / dhildenb
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH v6 2/6] mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache()
2024-04-03 11:40 [PATCH v6 0/6] Swap-out mTHP without splitting Ryan Roberts
2024-04-03 11:40 ` [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags Ryan Roberts
@ 2024-04-03 11:40 ` Ryan Roberts
[not found] ` <051052af-3b56-4290-98d3-fd5a1eb11ce1@redhat.com>
2024-04-03 11:40 ` [PATCH v6 3/6] mm: swap: Simplify struct percpu_cluster Ryan Roberts
` (3 subsequent siblings)
5 siblings, 1 reply; 30+ messages in thread
From: Ryan Roberts @ 2024-04-03 11:40 UTC (permalink / raw)
To: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: Ryan Roberts, linux-mm, linux-kernel
Now that we no longer have a convenient flag in the cluster to determine
if a folio is large, free_swap_and_cache() will take a reference and
lock a large folio much more often, which could lead to contention and
(e.g.) failure to split large folios, etc.
Let's solve that problem by batch freeing swap and cache with a new
function, free_swap_and_cache_nr(), to free a contiguous range of swap
entries together. This allows us to first drop a reference to each swap
slot before we try to release the cache folio. This means we only try to
release the folio once, only taking the reference and lock once - much
better than the previous 512 times for the 2M THP case.
Contiguous swap entries are gathered in zap_pte_range() and
madvise_free_pte_range() in a similar way to how present ptes are
already gathered in zap_pte_range().
While we are at it, let's simplify by converting the return type of both
functions to void. The return value was used only by zap_pte_range() to
print a bad pte, and was ignored by everyone else, so the extra
reporting wasn't exactly guaranteed. We will still get the warning with
most of the information from get_swap_device(). With the batch version,
we wouldn't know which pte was bad anyway so could print the wrong one.
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
include/linux/pgtable.h | 28 ++++++++++++++
include/linux/swap.h | 12 ++++--
mm/internal.h | 48 +++++++++++++++++++++++
mm/madvise.c | 12 ++++--
mm/memory.c | 13 ++++---
mm/swapfile.c | 86 ++++++++++++++++++++++++++++++++---------
6 files changed, 167 insertions(+), 32 deletions(-)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index a3fc8150b047..0278259f7078 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -708,6 +708,34 @@ static inline void pte_clear_not_present_full(struct mm_struct *mm,
}
#endif
+#ifndef clear_not_present_full_ptes
+/**
+ * clear_not_present_full_ptes - Clear consecutive not present PTEs.
+ * @mm: Address space the ptes represent.
+ * @addr: Address of the first pte.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries to clear.
+ * @full: Whether we are clearing a full mm.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over pte_clear_not_present_full().
+ *
+ * Context: The caller holds the page table lock. The PTEs are all not present.
+ * The PTEs are all in the same PMD.
+ */
+static inline void clear_not_present_full_ptes(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, unsigned int nr, int full)
+{
+ for (;;) {
+ pte_clear_not_present_full(mm, addr, ptep, full);
+ if (--nr == 0)
+ break;
+ ptep++;
+ addr += PAGE_SIZE;
+ }
+}
+#endif
+
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
unsigned long address,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f6f78198f000..5737236dc3ce 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -471,7 +471,7 @@ extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t);
extern void swapcache_free_entries(swp_entry_t *entries, int n);
-extern int free_swap_and_cache(swp_entry_t);
+extern void free_swap_and_cache_nr(swp_entry_t entry, int nr);
int swap_type_of(dev_t device, sector_t offset);
int find_first_swap(dev_t *device);
extern unsigned int count_swap_pages(int, int);
@@ -520,8 +520,9 @@ static inline void put_swap_device(struct swap_info_struct *si)
#define free_pages_and_swap_cache(pages, nr) \
release_pages((pages), (nr));
-/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */
-#define free_swap_and_cache(e) is_pfn_swap_entry(e)
+static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr)
+{
+}
static inline void free_swap_cache(struct folio *folio)
{
@@ -589,6 +590,11 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
}
#endif /* CONFIG_SWAP */
+static inline void free_swap_and_cache(swp_entry_t entry)
+{
+ free_swap_and_cache_nr(entry, 1);
+}
+
#ifdef CONFIG_MEMCG
static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
diff --git a/mm/internal.h b/mm/internal.h
index d567381b12cc..88705ab4c50a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -11,6 +11,8 @@
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
#include <linux/tracepoint-defs.h>
struct folio_batch;
@@ -189,6 +191,52 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
return min(ptep - start_ptep, max_nr);
}
+
+/**
+ * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
+ * @start_ptep: Page table pointer for the first entry.
+ * @max_nr: The maximum number of table entries to consider.
+ * @entry: Swap entry recovered from the first table entry.
+ *
+ * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs
+ * containing swap entries all with consecutive offsets and targeting the same
+ * swap type.
+ *
+ * max_nr must be at least one and must be limited by the caller so scanning
+ * cannot exceed a single page table.
+ *
+ * Return: the number of table entries in the batch.
+ */
+static inline int swap_pte_batch(pte_t *start_ptep, int max_nr,
+ swp_entry_t entry)
+{
+ const pte_t *end_ptep = start_ptep + max_nr;
+ unsigned long expected_offset = swp_offset(entry) + 1;
+ unsigned int expected_type = swp_type(entry);
+ pte_t *ptep = start_ptep + 1;
+
+ VM_WARN_ON(max_nr < 1);
+ VM_WARN_ON(non_swap_entry(entry));
+
+ while (ptep < end_ptep) {
+ pte_t pte = ptep_get(ptep);
+
+ if (pte_none(pte) || pte_present(pte))
+ break;
+
+ entry = pte_to_swp_entry(pte);
+
+ if (non_swap_entry(entry) ||
+ swp_type(entry) != expected_type ||
+ swp_offset(entry) != expected_offset)
+ break;
+
+ expected_offset++;
+ ptep++;
+ }
+
+ return ptep - start_ptep;
+}
#endif /* CONFIG_MMU */
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
diff --git a/mm/madvise.c b/mm/madvise.c
index 1f77a51baaac..070bedb4996e 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -628,6 +628,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
int nr_swap = 0;
unsigned long next;
+ int nr, max_nr;
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd))
@@ -640,7 +641,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
- for (; addr != end; pte++, addr += PAGE_SIZE) {
+ for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) {
+ nr = 1;
ptent = ptep_get(pte);
if (pte_none(ptent))
@@ -655,9 +657,11 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
entry = pte_to_swp_entry(ptent);
if (!non_swap_entry(entry)) {
- nr_swap--;
- free_swap_and_cache(entry);
- pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+ max_nr = (end - addr) / PAGE_SIZE;
+ nr = swap_pte_batch(pte, max_nr, entry);
+ nr_swap -= nr;
+ free_swap_and_cache_nr(entry, nr);
+ clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm);
} else if (is_hwpoison_entry(entry) ||
is_poisoned_swp_entry(entry)) {
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
diff --git a/mm/memory.c b/mm/memory.c
index 7dc6c3d9fa83..ef2968894718 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1637,12 +1637,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
folio_remove_rmap_pte(folio, page, vma);
folio_put(folio);
} else if (!non_swap_entry(entry)) {
- /* Genuine swap entry, hence a private anon page */
+ max_nr = (end - addr) / PAGE_SIZE;
+ nr = swap_pte_batch(pte, max_nr, entry);
+ /* Genuine swap entries, hence a private anon pages */
if (!should_zap_cows(details))
continue;
- rss[MM_SWAPENTS]--;
- if (unlikely(!free_swap_and_cache(entry)))
- print_bad_pte(vma, addr, ptent, NULL);
+ rss[MM_SWAPENTS] -= nr;
+ free_swap_and_cache_nr(entry, nr);
} else if (is_migration_entry(entry)) {
folio = pfn_swap_entry_folio(entry);
if (!should_zap_folio(details, folio))
@@ -1665,8 +1666,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
WARN_ON_ONCE(1);
}
- pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
- zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent);
+ clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm);
+ zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent);
} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
add_mm_rss_vec(mm, rss);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0d44ee2b4f9c..d059de6896c1 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -130,7 +130,11 @@ static inline unsigned char swap_count(unsigned char ent)
/* Reclaim the swap entry if swap is getting full*/
#define TTRS_FULL 0x4
-/* returns 1 if swap entry is freed */
+/*
+ * returns number of pages in the folio that backs the swap entry. If positive,
+ * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no
+ * folio was associated with the swap entry.
+ */
static int __try_to_reclaim_swap(struct swap_info_struct *si,
unsigned long offset, unsigned long flags)
{
@@ -155,6 +159,7 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
ret = folio_free_swap(folio);
folio_unlock(folio);
}
+ ret = ret ? folio_nr_pages(folio) : -folio_nr_pages(folio);
folio_put(folio);
return ret;
}
@@ -895,7 +900,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY);
spin_lock(&si->lock);
/* entry was freed successfully, try to use this again */
- if (swap_was_freed)
+ if (swap_was_freed > 0)
goto checks;
goto scan; /* check next one */
}
@@ -1572,32 +1577,75 @@ bool folio_free_swap(struct folio *folio)
return true;
}
-/*
- * Free the swap entry like above, but also try to
- * free the page cache entry if it is the last user.
- */
-int free_swap_and_cache(swp_entry_t entry)
+void free_swap_and_cache_nr(swp_entry_t entry, int nr)
{
- struct swap_info_struct *p;
+ unsigned long end = swp_offset(entry) + nr;
+ unsigned int type = swp_type(entry);
+ struct swap_info_struct *si;
+ bool any_only_cache = false;
+ unsigned long offset;
unsigned char count;
if (non_swap_entry(entry))
- return 1;
+ return;
- p = get_swap_device(entry);
- if (p) {
- if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) {
- put_swap_device(p);
- return 0;
+ si = get_swap_device(entry);
+ if (!si)
+ return;
+
+ if (WARN_ON(end > si->max))
+ goto out;
+
+ /*
+ * First free all entries in the range.
+ */
+ for (offset = swp_offset(entry); offset < end; offset++) {
+ if (!WARN_ON(data_race(!si->swap_map[offset]))) {
+ count = __swap_entry_free(si, swp_entry(type, offset));
+ if (count == SWAP_HAS_CACHE)
+ any_only_cache = true;
}
+ }
+
+ /*
+ * Short-circuit the below loop if none of the entries had their
+ * reference drop to zero.
+ */
+ if (!any_only_cache)
+ goto out;
- count = __swap_entry_free(p, entry);
- if (count == SWAP_HAS_CACHE)
- __try_to_reclaim_swap(p, swp_offset(entry),
+ /*
+ * Now go back over the range trying to reclaim the swap cache. This is
+ * more efficient for large folios because we will only try to reclaim
+ * the swap once per folio in the common case. If we do
+ * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the
+ * latter will get a reference and lock the folio for every individual
+ * page but will only succeed once the swap slot for every subpage is
+ * zero.
+ */
+ for (offset = swp_offset(entry); offset < end; offset += nr) {
+ nr = 1;
+ if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) {
+ /*
+ * Folios are always naturally aligned in swap so
+ * advance forward to the next boundary. Zero means no
+ * folio was found for the swap entry, so advance by 1
+ * in this case. Negative value means folio was found
+ * but could not be reclaimed. Here we can still advance
+ * to the next boundary.
+ */
+ nr = __try_to_reclaim_swap(si, offset,
TTRS_UNMAPPED | TTRS_FULL);
- put_swap_device(p);
+ if (nr == 0)
+ nr = 1;
+ else if (nr < 0)
+ nr = -nr;
+ nr = ALIGN(offset + 1, nr) - offset;
+ }
}
- return p != NULL;
+
+out:
+ put_swap_device(si);
}
#ifdef CONFIG_HIBERNATION
--
2.25.1
^ permalink raw reply [flat|nested] 30+ messages in thread* [PATCH v6 3/6] mm: swap: Simplify struct percpu_cluster
2024-04-03 11:40 [PATCH v6 0/6] Swap-out mTHP without splitting Ryan Roberts
2024-04-03 11:40 ` [PATCH v6 1/6] mm: swap: Remove CLUSTER_FLAG_HUGE from swap_cluster_info:flags Ryan Roberts
2024-04-03 11:40 ` [PATCH v6 2/6] mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Ryan Roberts
@ 2024-04-03 11:40 ` Ryan Roberts
2024-04-03 11:40 ` [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders Ryan Roberts
` (2 subsequent siblings)
5 siblings, 0 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-03 11:40 UTC (permalink / raw)
To: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: Ryan Roberts, linux-mm, linux-kernel
struct percpu_cluster stores the index of cpu's current cluster and the
offset of the next entry that will be allocated for the cpu. These two
pieces of information are redundant because the cluster index is just
(offset / SWAPFILE_CLUSTER). The only reason for explicitly keeping the
cluster index is because the structure used for it also has a flag to
indicate "no cluster". However this data structure also contains a spin
lock, which is never used in this context, as a side effect the code
copies the spinlock_t structure, which is questionable coding practice
in my view.
So let's clean this up and store only the next offset, and use a
sentinal value (SWAP_NEXT_INVALID) to indicate "no cluster".
SWAP_NEXT_INVALID is chosen to be 0, because 0 will never be seen
legitimately; The first page in the swap file is the swap header, which
is always marked bad to prevent it from being allocated as an entry.
This also prevents the cluster to which it belongs being marked free, so
it will never appear on the free list.
This change saves 16 bytes per cpu. And given we are shortly going to
extend this mechanism to be per-cpu-AND-per-order, we will end up saving
16 * 9 = 144 bytes per cpu, which adds up if you have 256 cpus in the
system.
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
include/linux/swap.h | 9 ++++++++-
mm/swapfile.c | 22 +++++++++++-----------
2 files changed, 19 insertions(+), 12 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5737236dc3ce..5e1e4f5bf0cb 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -260,13 +260,20 @@ struct swap_cluster_info {
#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+/*
+ * The first page in the swap file is the swap header, which is always marked
+ * bad to prevent it from being allocated as an entry. This also prevents the
+ * cluster to which it belongs being marked free. Therefore 0 is safe to use as
+ * a sentinel to indicate next is not valid in percpu_cluster.
+ */
+#define SWAP_NEXT_INVALID 0
+
/*
* We assign a cluster to each CPU, so each CPU can allocate swap entry from
* its own cluster and swapout sequentially. The purpose is to optimize swapout
* throughput.
*/
struct percpu_cluster {
- struct swap_cluster_info index; /* Current cluster index */
unsigned int next; /* Likely next allocation offset */
};
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d059de6896c1..c95986b9cb9c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -609,7 +609,7 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
return false;
percpu_cluster = this_cpu_ptr(si->percpu_cluster);
- cluster_set_null(&percpu_cluster->index);
+ percpu_cluster->next = SWAP_NEXT_INVALID;
return true;
}
@@ -622,14 +622,14 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
{
struct percpu_cluster *cluster;
struct swap_cluster_info *ci;
- unsigned long tmp, max;
+ unsigned int tmp, max;
new_cluster:
cluster = this_cpu_ptr(si->percpu_cluster);
- if (cluster_is_null(&cluster->index)) {
+ tmp = cluster->next;
+ if (tmp == SWAP_NEXT_INVALID) {
if (!cluster_list_empty(&si->free_clusters)) {
- cluster->index = si->free_clusters.head;
- cluster->next = cluster_next(&cluster->index) *
+ tmp = cluster_next(&si->free_clusters.head) *
SWAPFILE_CLUSTER;
} else if (!cluster_list_empty(&si->discard_clusters)) {
/*
@@ -649,9 +649,7 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
* Other CPUs can use our cluster if they can't find a free cluster,
* check if there is still free entry in the cluster
*/
- tmp = cluster->next;
- max = min_t(unsigned long, si->max,
- (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER);
+ max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER));
if (tmp < max) {
ci = lock_cluster(si, tmp);
while (tmp < max) {
@@ -662,12 +660,13 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
unlock_cluster(ci);
}
if (tmp >= max) {
- cluster_set_null(&cluster->index);
+ cluster->next = SWAP_NEXT_INVALID;
goto new_cluster;
}
- cluster->next = tmp + 1;
*offset = tmp;
*scan_base = tmp;
+ tmp += 1;
+ cluster->next = tmp < max ? tmp : SWAP_NEXT_INVALID;
return true;
}
@@ -3150,8 +3149,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
}
for_each_possible_cpu(cpu) {
struct percpu_cluster *cluster;
+
cluster = per_cpu_ptr(p->percpu_cluster, cpu);
- cluster_set_null(&cluster->index);
+ cluster->next = SWAP_NEXT_INVALID;
}
} else {
atomic_inc(&nr_rotate_swap);
--
2.25.1
^ permalink raw reply [flat|nested] 30+ messages in thread* [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-03 11:40 [PATCH v6 0/6] Swap-out mTHP without splitting Ryan Roberts
` (2 preceding siblings ...)
2024-04-03 11:40 ` [PATCH v6 3/6] mm: swap: Simplify struct percpu_cluster Ryan Roberts
@ 2024-04-03 11:40 ` Ryan Roberts
2024-04-05 10:38 ` David Hildenbrand
2024-04-07 7:38 ` Barry Song
2024-04-03 11:40 ` [PATCH v6 5/6] mm: vmscan: Avoid split during shrink_folio_list() Ryan Roberts
2024-04-03 11:40 ` [PATCH v6 6/6] mm: madvise: Avoid split during MADV_PAGEOUT and MADV_COLD Ryan Roberts
5 siblings, 2 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-03 11:40 UTC (permalink / raw)
To: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: Ryan Roberts, linux-mm, linux-kernel
Multi-size THP enables performance improvements by allocating large,
pte-mapped folios for anonymous memory. However I've observed that on an
arm64 system running a parallel workload (e.g. kernel compilation)
across many cores, under high memory pressure, the speed regresses. This
is due to bottlenecking on the increased number of TLBIs added due to
all the extra folio splitting when the large folios are swapped out.
Therefore, solve this regression by adding support for swapping out mTHP
without needing to split the folio, just like is already done for
PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
and when the swap backing store is a non-rotating block device. These
are the same constraints as for the existing PMD-sized THP swap-out
support.
Note that no attempt is made to swap-in (m)THP here - this is still done
page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
prerequisite for swapping-in mTHP.
The main change here is to improve the swap entry allocator so that it
can allocate any power-of-2 number of contiguous entries between [1, (1
<< PMD_ORDER)]. This is done by allocating a cluster for each distinct
order and allocating sequentially from it until the cluster is full.
This ensures that we don't need to search the map and we get no
fragmentation due to alignment padding for different orders in the
cluster. If there is no current cluster for a given order, we attempt to
allocate a free cluster from the list. If there are no free clusters, we
fail the allocation and the caller can fall back to splitting the folio
and allocates individual entries (as per existing PMD-sized THP
fallback).
The per-order current clusters are maintained per-cpu using the existing
infrastructure. This is done to avoid interleving pages from different
tasks, which would prevent IO being batched. This is already done for
the order-0 allocations so we follow the same pattern.
As is done for order-0 per-cpu clusters, the scanner now can steal
order-0 entries from any per-cpu-per-order reserved cluster. This
ensures that when the swap file is getting full, space doesn't get tied
up in the per-cpu reserves.
This change only modifies swap to be able to accept any order mTHP. It
doesn't change the callers to elide doing the actual split. That will be
done in separate changes.
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
include/linux/swap.h | 10 ++-
mm/swap_slots.c | 6 +-
mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
3 files changed, 109 insertions(+), 82 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5e1e4f5bf0cb..11c53692f65f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -268,13 +268,19 @@ struct swap_cluster_info {
*/
#define SWAP_NEXT_INVALID 0
+#ifdef CONFIG_THP_SWAP
+#define SWAP_NR_ORDERS (PMD_ORDER + 1)
+#else
+#define SWAP_NR_ORDERS 1
+#endif
+
/*
* We assign a cluster to each CPU, so each CPU can allocate swap entry from
* its own cluster and swapout sequentially. The purpose is to optimize swapout
* throughput.
*/
struct percpu_cluster {
- unsigned int next; /* Likely next allocation offset */
+ unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
};
struct swap_cluster_list {
@@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
bool folio_free_swap(struct folio *folio);
void put_swap_folio(struct folio *folio, swp_entry_t entry);
extern swp_entry_t get_swap_page_of_type(int);
-extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
+extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
extern void swap_shmem_alloc(swp_entry_t);
extern int swap_duplicate(swp_entry_t);
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 53abeaf1371d..13ab3b771409 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
cache->cur = 0;
if (swap_slot_cache_active)
cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
- cache->slots, 1);
+ cache->slots, 0);
return cache->nr;
}
@@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
if (folio_test_large(folio)) {
if (IS_ENABLED(CONFIG_THP_SWAP))
- get_swap_pages(1, &entry, folio_nr_pages(folio));
+ get_swap_pages(1, &entry, folio_order(folio));
goto out;
}
@@ -343,7 +343,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
goto out;
}
- get_swap_pages(1, &entry, 1);
+ get_swap_pages(1, &entry, 0);
out:
if (mem_cgroup_try_charge_swap(folio, entry)) {
put_swap_folio(folio, entry);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index c95986b9cb9c..3ee8957a46e6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -278,15 +278,15 @@ static void discard_swap_cluster(struct swap_info_struct *si,
#ifdef CONFIG_THP_SWAP
#define SWAPFILE_CLUSTER HPAGE_PMD_NR
-#define swap_entry_size(size) (size)
+#define swap_entry_order(order) (order)
#else
#define SWAPFILE_CLUSTER 256
/*
- * Define swap_entry_size() as constant to let compiler to optimize
+ * Define swap_entry_order() as constant to let compiler to optimize
* out some code if !CONFIG_THP_SWAP
*/
-#define swap_entry_size(size) 1
+#define swap_entry_order(order) 0
#endif
#define LATENCY_LIMIT 256
@@ -551,10 +551,12 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
/*
* The cluster corresponding to page_nr will be used. The cluster will be
- * removed from free cluster list and its usage counter will be increased.
+ * removed from free cluster list and its usage counter will be increased by
+ * count.
*/
-static void inc_cluster_info_page(struct swap_info_struct *p,
- struct swap_cluster_info *cluster_info, unsigned long page_nr)
+static void add_cluster_info_page(struct swap_info_struct *p,
+ struct swap_cluster_info *cluster_info, unsigned long page_nr,
+ unsigned long count)
{
unsigned long idx = page_nr / SWAPFILE_CLUSTER;
@@ -563,9 +565,19 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
if (cluster_is_free(&cluster_info[idx]))
alloc_cluster(p, idx);
- VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
+ VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
cluster_set_count(&cluster_info[idx],
- cluster_count(&cluster_info[idx]) + 1);
+ cluster_count(&cluster_info[idx]) + count);
+}
+
+/*
+ * The cluster corresponding to page_nr will be used. The cluster will be
+ * removed from free cluster list and its usage counter will be increased by 1.
+ */
+static void inc_cluster_info_page(struct swap_info_struct *p,
+ struct swap_cluster_info *cluster_info, unsigned long page_nr)
+{
+ add_cluster_info_page(p, cluster_info, page_nr, 1);
}
/*
@@ -595,7 +607,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p,
*/
static bool
scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
- unsigned long offset)
+ unsigned long offset, int order)
{
struct percpu_cluster *percpu_cluster;
bool conflict;
@@ -609,24 +621,39 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
return false;
percpu_cluster = this_cpu_ptr(si->percpu_cluster);
- percpu_cluster->next = SWAP_NEXT_INVALID;
+ percpu_cluster->next[order] = SWAP_NEXT_INVALID;
+ return true;
+}
+
+static inline bool swap_range_empty(char *swap_map, unsigned int start,
+ unsigned int nr_pages)
+{
+ unsigned int i;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (swap_map[start + i])
+ return false;
+ }
+
return true;
}
/*
- * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
- * might involve allocating a new cluster for current CPU too.
+ * Try to get swap entries with specified order from current cpu's swap entry
+ * pool (a cluster). This might involve allocating a new cluster for current CPU
+ * too.
*/
static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
- unsigned long *offset, unsigned long *scan_base)
+ unsigned long *offset, unsigned long *scan_base, int order)
{
+ unsigned int nr_pages = 1 << order;
struct percpu_cluster *cluster;
struct swap_cluster_info *ci;
unsigned int tmp, max;
new_cluster:
cluster = this_cpu_ptr(si->percpu_cluster);
- tmp = cluster->next;
+ tmp = cluster->next[order];
if (tmp == SWAP_NEXT_INVALID) {
if (!cluster_list_empty(&si->free_clusters)) {
tmp = cluster_next(&si->free_clusters.head) *
@@ -647,26 +674,27 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
/*
* Other CPUs can use our cluster if they can't find a free cluster,
- * check if there is still free entry in the cluster
+ * check if there is still free entry in the cluster, maintaining
+ * natural alignment.
*/
max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER));
if (tmp < max) {
ci = lock_cluster(si, tmp);
while (tmp < max) {
- if (!si->swap_map[tmp])
+ if (swap_range_empty(si->swap_map, tmp, nr_pages))
break;
- tmp++;
+ tmp += nr_pages;
}
unlock_cluster(ci);
}
if (tmp >= max) {
- cluster->next = SWAP_NEXT_INVALID;
+ cluster->next[order] = SWAP_NEXT_INVALID;
goto new_cluster;
}
*offset = tmp;
*scan_base = tmp;
- tmp += 1;
- cluster->next = tmp < max ? tmp : SWAP_NEXT_INVALID;
+ tmp += nr_pages;
+ cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID;
return true;
}
@@ -796,13 +824,14 @@ static bool swap_offset_available_and_locked(struct swap_info_struct *si,
static int scan_swap_map_slots(struct swap_info_struct *si,
unsigned char usage, int nr,
- swp_entry_t slots[])
+ swp_entry_t slots[], int order)
{
struct swap_cluster_info *ci;
unsigned long offset;
unsigned long scan_base;
unsigned long last_in_cluster = 0;
int latency_ration = LATENCY_LIMIT;
+ unsigned int nr_pages = 1 << order;
int n_ret = 0;
bool scanned_many = false;
@@ -817,6 +846,25 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
* And we let swap pages go all over an SSD partition. Hugh
*/
+ if (order > 0) {
+ /*
+ * Should not even be attempting large allocations when huge
+ * page swap is disabled. Warn and fail the allocation.
+ */
+ if (!IS_ENABLED(CONFIG_THP_SWAP) ||
+ nr_pages > SWAPFILE_CLUSTER) {
+ VM_WARN_ON_ONCE(1);
+ return 0;
+ }
+
+ /*
+ * Swapfile is not block device or not using clusters so unable
+ * to allocate large entries.
+ */
+ if (!(si->flags & SWP_BLKDEV) || !si->cluster_info)
+ return 0;
+ }
+
si->flags += SWP_SCANNING;
/*
* Use percpu scan base for SSD to reduce lock contention on
@@ -831,8 +879,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
/* SSD algorithm */
if (si->cluster_info) {
- if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+ if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) {
+ if (order > 0)
+ goto no_page;
goto scan;
+ }
} else if (unlikely(!si->cluster_nr--)) {
if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
si->cluster_nr = SWAPFILE_CLUSTER - 1;
@@ -874,13 +925,16 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
checks:
if (si->cluster_info) {
- while (scan_swap_map_ssd_cluster_conflict(si, offset)) {
+ while (scan_swap_map_ssd_cluster_conflict(si, offset, order)) {
/* take a break if we already got some slots */
if (n_ret)
goto done;
if (!scan_swap_map_try_ssd_cluster(si, &offset,
- &scan_base))
+ &scan_base, order)) {
+ if (order > 0)
+ goto no_page;
goto scan;
+ }
}
}
if (!(si->flags & SWP_WRITEOK))
@@ -911,11 +965,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
else
goto done;
}
- WRITE_ONCE(si->swap_map[offset], usage);
- inc_cluster_info_page(si, si->cluster_info, offset);
+ memset(si->swap_map + offset, usage, nr_pages);
+ add_cluster_info_page(si, si->cluster_info, offset, nr_pages);
unlock_cluster(ci);
- swap_range_alloc(si, offset, 1);
+ swap_range_alloc(si, offset, nr_pages);
slots[n_ret++] = swp_entry(si->type, offset);
/* got enough slots or reach max slots? */
@@ -936,8 +990,10 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
/* try to get more slots in cluster */
if (si->cluster_info) {
- if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+ if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order))
goto checks;
+ if (order > 0)
+ goto done;
} else if (si->cluster_nr && !si->swap_map[++offset]) {
/* non-ssd case, still more slots in cluster? */
--si->cluster_nr;
@@ -964,11 +1020,13 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
}
done:
- set_cluster_next(si, offset + 1);
+ if (order == 0)
+ set_cluster_next(si, offset + 1);
si->flags -= SWP_SCANNING;
return n_ret;
scan:
+ VM_WARN_ON(order > 0);
spin_unlock(&si->lock);
while (++offset <= READ_ONCE(si->highest_bit)) {
if (unlikely(--latency_ration < 0)) {
@@ -997,38 +1055,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
return n_ret;
}
-static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
-{
- unsigned long idx;
- struct swap_cluster_info *ci;
- unsigned long offset;
-
- /*
- * Should not even be attempting cluster allocations when huge
- * page swap is disabled. Warn and fail the allocation.
- */
- if (!IS_ENABLED(CONFIG_THP_SWAP)) {
- VM_WARN_ON_ONCE(1);
- return 0;
- }
-
- if (cluster_list_empty(&si->free_clusters))
- return 0;
-
- idx = cluster_list_first(&si->free_clusters);
- offset = idx * SWAPFILE_CLUSTER;
- ci = lock_cluster(si, offset);
- alloc_cluster(si, idx);
- cluster_set_count(ci, SWAPFILE_CLUSTER);
-
- memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
- unlock_cluster(ci);
- swap_range_alloc(si, offset, SWAPFILE_CLUSTER);
- *slot = swp_entry(si->type, offset);
-
- return 1;
-}
-
static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
{
unsigned long offset = idx * SWAPFILE_CLUSTER;
@@ -1042,17 +1068,15 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
swap_range_free(si, offset, SWAPFILE_CLUSTER);
}
-int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
+int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
{
- unsigned long size = swap_entry_size(entry_size);
+ int order = swap_entry_order(entry_order);
+ unsigned long size = 1 << order;
struct swap_info_struct *si, *next;
long avail_pgs;
int n_ret = 0;
int node;
- /* Only single cluster request supported */
- WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
-
spin_lock(&swap_avail_lock);
avail_pgs = atomic_long_read(&nr_swap_pages) / size;
@@ -1088,14 +1112,10 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
spin_unlock(&si->lock);
goto nextsi;
}
- if (size == SWAPFILE_CLUSTER) {
- if (si->flags & SWP_BLKDEV)
- n_ret = swap_alloc_cluster(si, swp_entries);
- } else
- n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
- n_goal, swp_entries);
+ n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
+ n_goal, swp_entries, order);
spin_unlock(&si->lock);
- if (n_ret || size == SWAPFILE_CLUSTER)
+ if (n_ret || size > 1)
goto check_out;
cond_resched();
@@ -1349,7 +1369,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
unsigned char *map;
unsigned int i, free_entries = 0;
unsigned char val;
- int size = swap_entry_size(folio_nr_pages(folio));
+ int size = 1 << swap_entry_order(folio_order(folio));
si = _swap_info_get(entry);
if (!si)
@@ -1659,7 +1679,7 @@ swp_entry_t get_swap_page_of_type(int type)
/* This is called for allocating swap entry, not cache */
spin_lock(&si->lock);
- if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry))
+ if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
atomic_long_dec(&nr_swap_pages);
spin_unlock(&si->lock);
fail:
@@ -3113,7 +3133,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
p->flags |= SWP_SYNCHRONOUS_IO;
if (p->bdev && bdev_nonrot(p->bdev)) {
- int cpu;
+ int cpu, i;
unsigned long ci, nr_cluster;
p->flags |= SWP_SOLIDSTATE;
@@ -3151,7 +3171,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
struct percpu_cluster *cluster;
cluster = per_cpu_ptr(p->percpu_cluster, cpu);
- cluster->next = SWAP_NEXT_INVALID;
+ for (i = 0; i < SWAP_NR_ORDERS; i++)
+ cluster->next[i] = SWAP_NEXT_INVALID;
}
} else {
atomic_inc(&nr_rotate_swap);
--
2.25.1
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-03 11:40 ` [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders Ryan Roberts
@ 2024-04-05 10:38 ` David Hildenbrand
2024-04-07 6:02 ` Huang, Ying
2024-04-07 7:38 ` Barry Song
1 sibling, 1 reply; 30+ messages in thread
From: David Hildenbrand @ 2024-04-05 10:38 UTC (permalink / raw)
To: Ryan Roberts, Andrew Morton, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: linux-mm, linux-kernel
On 03.04.24 13:40, Ryan Roberts wrote:
> Multi-size THP enables performance improvements by allocating large,
> pte-mapped folios for anonymous memory. However I've observed that on an
> arm64 system running a parallel workload (e.g. kernel compilation)
> across many cores, under high memory pressure, the speed regresses. This
> is due to bottlenecking on the increased number of TLBIs added due to
> all the extra folio splitting when the large folios are swapped out.
>
> Therefore, solve this regression by adding support for swapping out mTHP
> without needing to split the folio, just like is already done for
> PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
> and when the swap backing store is a non-rotating block device. These
> are the same constraints as for the existing PMD-sized THP swap-out
> support.
>
> Note that no attempt is made to swap-in (m)THP here - this is still done
> page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
> prerequisite for swapping-in mTHP.
>
> The main change here is to improve the swap entry allocator so that it
> can allocate any power-of-2 number of contiguous entries between [1, (1
> << PMD_ORDER)]. This is done by allocating a cluster for each distinct
> order and allocating sequentially from it until the cluster is full.
> This ensures that we don't need to search the map and we get no
> fragmentation due to alignment padding for different orders in the
> cluster. If there is no current cluster for a given order, we attempt to
> allocate a free cluster from the list. If there are no free clusters, we
> fail the allocation and the caller can fall back to splitting the folio
> and allocates individual entries (as per existing PMD-sized THP
> fallback).
>
> The per-order current clusters are maintained per-cpu using the existing
> infrastructure. This is done to avoid interleving pages from different
> tasks, which would prevent IO being batched. This is already done for
> the order-0 allocations so we follow the same pattern.
>
> As is done for order-0 per-cpu clusters, the scanner now can steal
> order-0 entries from any per-cpu-per-order reserved cluster. This
> ensures that when the swap file is getting full, space doesn't get tied
> up in the per-cpu reserves.
>
> This change only modifies swap to be able to accept any order mTHP. It
> doesn't change the callers to elide doing the actual split. That will be
> done in separate changes.
>
> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
> include/linux/swap.h | 10 ++-
> mm/swap_slots.c | 6 +-
> mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
> 3 files changed, 109 insertions(+), 82 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 5e1e4f5bf0cb..11c53692f65f 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -268,13 +268,19 @@ struct swap_cluster_info {
> */
> #define SWAP_NEXT_INVALID 0
>
> +#ifdef CONFIG_THP_SWAP
> +#define SWAP_NR_ORDERS (PMD_ORDER + 1)
> +#else
> +#define SWAP_NR_ORDERS 1
> +#endif
> +
> /*
> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
> * its own cluster and swapout sequentially. The purpose is to optimize swapout
> * throughput.
> */
> struct percpu_cluster {
> - unsigned int next; /* Likely next allocation offset */
> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
> };
>
> struct swap_cluster_list {
> @@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
> bool folio_free_swap(struct folio *folio);
> void put_swap_folio(struct folio *folio, swp_entry_t entry);
> extern swp_entry_t get_swap_page_of_type(int);
> -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
> +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
> extern int add_swap_count_continuation(swp_entry_t, gfp_t);
> extern void swap_shmem_alloc(swp_entry_t);
> extern int swap_duplicate(swp_entry_t);
> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
> index 53abeaf1371d..13ab3b771409 100644
> --- a/mm/swap_slots.c
> +++ b/mm/swap_slots.c
> @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
> cache->cur = 0;
> if (swap_slot_cache_active)
> cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
> - cache->slots, 1);
> + cache->slots, 0);
>
> return cache->nr;
> }
> @@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>
> if (folio_test_large(folio)) {
> if (IS_ENABLED(CONFIG_THP_SWAP))
> - get_swap_pages(1, &entry, folio_nr_pages(folio));
> + get_swap_pages(1, &entry, folio_order(folio));
The only comment I have is that this nr_pages -> order conversion adds a
bit of noise to this patch.
AFAIKS, it's primarily only required for "cluster->next[order]",
everything else doesn't really require the order.
I'd just have split that out into a separate patch, or simply converted
nr_pages -> order where required.
Nothing jumped at me, but I'm not an expert on that code, so I'm mostly
trusting the others ;)
--
Cheers,
David / dhildenb
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-05 10:38 ` David Hildenbrand
@ 2024-04-07 6:02 ` Huang, Ying
2024-04-08 9:24 ` Ryan Roberts
0 siblings, 1 reply; 30+ messages in thread
From: Huang, Ying @ 2024-04-07 6:02 UTC (permalink / raw)
To: David Hildenbrand
Cc: Ryan Roberts, Andrew Morton, Matthew Wilcox, Gao Xiang, Yu Zhao,
Yang Shi, Michal Hocko, Kefeng Wang, Barry Song, Chris Li,
Lance Yang, linux-mm, linux-kernel
David Hildenbrand <david@redhat.com> writes:
> On 03.04.24 13:40, Ryan Roberts wrote:
>> Multi-size THP enables performance improvements by allocating large,
>> pte-mapped folios for anonymous memory. However I've observed that on an
>> arm64 system running a parallel workload (e.g. kernel compilation)
>> across many cores, under high memory pressure, the speed regresses. This
>> is due to bottlenecking on the increased number of TLBIs added due to
>> all the extra folio splitting when the large folios are swapped out.
>> Therefore, solve this regression by adding support for swapping out
>> mTHP
>> without needing to split the folio, just like is already done for
>> PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
>> and when the swap backing store is a non-rotating block device. These
>> are the same constraints as for the existing PMD-sized THP swap-out
>> support.
>> Note that no attempt is made to swap-in (m)THP here - this is still
>> done
>> page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
>> prerequisite for swapping-in mTHP.
>> The main change here is to improve the swap entry allocator so that
>> it
>> can allocate any power-of-2 number of contiguous entries between [1, (1
>> << PMD_ORDER)]. This is done by allocating a cluster for each distinct
>> order and allocating sequentially from it until the cluster is full.
>> This ensures that we don't need to search the map and we get no
>> fragmentation due to alignment padding for different orders in the
>> cluster. If there is no current cluster for a given order, we attempt to
>> allocate a free cluster from the list. If there are no free clusters, we
>> fail the allocation and the caller can fall back to splitting the folio
>> and allocates individual entries (as per existing PMD-sized THP
>> fallback).
>> The per-order current clusters are maintained per-cpu using the
>> existing
>> infrastructure. This is done to avoid interleving pages from different
>> tasks, which would prevent IO being batched. This is already done for
>> the order-0 allocations so we follow the same pattern.
>> As is done for order-0 per-cpu clusters, the scanner now can steal
>> order-0 entries from any per-cpu-per-order reserved cluster. This
>> ensures that when the swap file is getting full, space doesn't get tied
>> up in the per-cpu reserves.
>> This change only modifies swap to be able to accept any order
>> mTHP. It
>> doesn't change the callers to elide doing the actual split. That will be
>> done in separate changes.
>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> ---
>> include/linux/swap.h | 10 ++-
>> mm/swap_slots.c | 6 +-
>> mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
>> 3 files changed, 109 insertions(+), 82 deletions(-)
>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>> index 5e1e4f5bf0cb..11c53692f65f 100644
>> --- a/include/linux/swap.h
>> +++ b/include/linux/swap.h
>> @@ -268,13 +268,19 @@ struct swap_cluster_info {
>> */
>> #define SWAP_NEXT_INVALID 0
>> +#ifdef CONFIG_THP_SWAP
>> +#define SWAP_NR_ORDERS (PMD_ORDER + 1)
>> +#else
>> +#define SWAP_NR_ORDERS 1
>> +#endif
>> +
>> /*
>> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
>> * its own cluster and swapout sequentially. The purpose is to optimize swapout
>> * throughput.
>> */
>> struct percpu_cluster {
>> - unsigned int next; /* Likely next allocation offset */
>> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
>> };
>> struct swap_cluster_list {
>> @@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
>> bool folio_free_swap(struct folio *folio);
>> void put_swap_folio(struct folio *folio, swp_entry_t entry);
>> extern swp_entry_t get_swap_page_of_type(int);
>> -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
>> +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
>> extern int add_swap_count_continuation(swp_entry_t, gfp_t);
>> extern void swap_shmem_alloc(swp_entry_t);
>> extern int swap_duplicate(swp_entry_t);
>> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
>> index 53abeaf1371d..13ab3b771409 100644
>> --- a/mm/swap_slots.c
>> +++ b/mm/swap_slots.c
>> @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
>> cache->cur = 0;
>> if (swap_slot_cache_active)
>> cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
>> - cache->slots, 1);
>> + cache->slots, 0);
>> return cache->nr;
>> }
>> @@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>> if (folio_test_large(folio)) {
>> if (IS_ENABLED(CONFIG_THP_SWAP))
>> - get_swap_pages(1, &entry, folio_nr_pages(folio));
>> + get_swap_pages(1, &entry, folio_order(folio));
>
> The only comment I have is that this nr_pages -> order conversion adds
> a bit of noise to this patch.
>
> AFAIKS, it's primarily only required for "cluster->next[order]",
> everything else doesn't really require the order.
>
> I'd just have split that out into a separate patch, or simply
> converted nr_pages -> order where required.
>
> Nothing jumped at me, but I'm not an expert on that code, so I'm
> mostly trusting the others ;)
The nr_pages -> order conversion replaces ilog2(nr_pages) with
(1<<order). IIUC, "<<" is a little faster than "ilog2()". And, we
don't need to worry about whether nr_pages is a power of 2. Do you
think that this makes sense?
--
Best Regards,
Huang, Ying
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-07 6:02 ` Huang, Ying
@ 2024-04-08 9:24 ` Ryan Roberts
2024-04-08 9:33 ` David Hildenbrand
0 siblings, 1 reply; 30+ messages in thread
From: Ryan Roberts @ 2024-04-08 9:24 UTC (permalink / raw)
To: Huang, Ying, David Hildenbrand
Cc: Andrew Morton, Matthew Wilcox, Gao Xiang, Yu Zhao, Yang Shi,
Michal Hocko, Kefeng Wang, Barry Song, Chris Li, Lance Yang,
linux-mm, linux-kernel
On 07/04/2024 07:02, Huang, Ying wrote:
> David Hildenbrand <david@redhat.com> writes:
>
>> On 03.04.24 13:40, Ryan Roberts wrote:
>>> Multi-size THP enables performance improvements by allocating large,
>>> pte-mapped folios for anonymous memory. However I've observed that on an
>>> arm64 system running a parallel workload (e.g. kernel compilation)
>>> across many cores, under high memory pressure, the speed regresses. This
>>> is due to bottlenecking on the increased number of TLBIs added due to
>>> all the extra folio splitting when the large folios are swapped out.
>>> Therefore, solve this regression by adding support for swapping out
>>> mTHP
>>> without needing to split the folio, just like is already done for
>>> PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
>>> and when the swap backing store is a non-rotating block device. These
>>> are the same constraints as for the existing PMD-sized THP swap-out
>>> support.
>>> Note that no attempt is made to swap-in (m)THP here - this is still
>>> done
>>> page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
>>> prerequisite for swapping-in mTHP.
>>> The main change here is to improve the swap entry allocator so that
>>> it
>>> can allocate any power-of-2 number of contiguous entries between [1, (1
>>> << PMD_ORDER)]. This is done by allocating a cluster for each distinct
>>> order and allocating sequentially from it until the cluster is full.
>>> This ensures that we don't need to search the map and we get no
>>> fragmentation due to alignment padding for different orders in the
>>> cluster. If there is no current cluster for a given order, we attempt to
>>> allocate a free cluster from the list. If there are no free clusters, we
>>> fail the allocation and the caller can fall back to splitting the folio
>>> and allocates individual entries (as per existing PMD-sized THP
>>> fallback).
>>> The per-order current clusters are maintained per-cpu using the
>>> existing
>>> infrastructure. This is done to avoid interleving pages from different
>>> tasks, which would prevent IO being batched. This is already done for
>>> the order-0 allocations so we follow the same pattern.
>>> As is done for order-0 per-cpu clusters, the scanner now can steal
>>> order-0 entries from any per-cpu-per-order reserved cluster. This
>>> ensures that when the swap file is getting full, space doesn't get tied
>>> up in the per-cpu reserves.
>>> This change only modifies swap to be able to accept any order
>>> mTHP. It
>>> doesn't change the callers to elide doing the actual split. That will be
>>> done in separate changes.
>>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>> ---
>>> include/linux/swap.h | 10 ++-
>>> mm/swap_slots.c | 6 +-
>>> mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
>>> 3 files changed, 109 insertions(+), 82 deletions(-)
>>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>>> index 5e1e4f5bf0cb..11c53692f65f 100644
>>> --- a/include/linux/swap.h
>>> +++ b/include/linux/swap.h
>>> @@ -268,13 +268,19 @@ struct swap_cluster_info {
>>> */
>>> #define SWAP_NEXT_INVALID 0
>>> +#ifdef CONFIG_THP_SWAP
>>> +#define SWAP_NR_ORDERS (PMD_ORDER + 1)
>>> +#else
>>> +#define SWAP_NR_ORDERS 1
>>> +#endif
>>> +
>>> /*
>>> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
>>> * its own cluster and swapout sequentially. The purpose is to optimize swapout
>>> * throughput.
>>> */
>>> struct percpu_cluster {
>>> - unsigned int next; /* Likely next allocation offset */
>>> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
>>> };
>>> struct swap_cluster_list {
>>> @@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
>>> bool folio_free_swap(struct folio *folio);
>>> void put_swap_folio(struct folio *folio, swp_entry_t entry);
>>> extern swp_entry_t get_swap_page_of_type(int);
>>> -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
>>> +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
>>> extern int add_swap_count_continuation(swp_entry_t, gfp_t);
>>> extern void swap_shmem_alloc(swp_entry_t);
>>> extern int swap_duplicate(swp_entry_t);
>>> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
>>> index 53abeaf1371d..13ab3b771409 100644
>>> --- a/mm/swap_slots.c
>>> +++ b/mm/swap_slots.c
>>> @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
>>> cache->cur = 0;
>>> if (swap_slot_cache_active)
>>> cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
>>> - cache->slots, 1);
>>> + cache->slots, 0);
>>> return cache->nr;
>>> }
>>> @@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>>> if (folio_test_large(folio)) {
>>> if (IS_ENABLED(CONFIG_THP_SWAP))
>>> - get_swap_pages(1, &entry, folio_nr_pages(folio));
>>> + get_swap_pages(1, &entry, folio_order(folio));
>>
>> The only comment I have is that this nr_pages -> order conversion adds
>> a bit of noise to this patch.
>>
>> AFAIKS, it's primarily only required for "cluster->next[order]",
>> everything else doesn't really require the order.
>>
>> I'd just have split that out into a separate patch, or simply
>> converted nr_pages -> order where required.
>>
>> Nothing jumped at me, but I'm not an expert on that code, so I'm
>> mostly trusting the others ;)
>
> The nr_pages -> order conversion replaces ilog2(nr_pages) with
> (1<<order). IIUC, "<<" is a little faster than "ilog2()". And, we
> don't need to worry about whether nr_pages is a power of 2. Do you
> think that this makes sense?
I think that David's point was that I should just split out that change to its
own patch to aid readability? I'm happy to do that if no one objects.
>
> --
> Best Regards,
> Huang, Ying
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-08 9:24 ` Ryan Roberts
@ 2024-04-08 9:33 ` David Hildenbrand
2024-04-08 9:35 ` Ryan Roberts
0 siblings, 1 reply; 30+ messages in thread
From: David Hildenbrand @ 2024-04-08 9:33 UTC (permalink / raw)
To: Ryan Roberts, Huang, Ying
Cc: Andrew Morton, Matthew Wilcox, Gao Xiang, Yu Zhao, Yang Shi,
Michal Hocko, Kefeng Wang, Barry Song, Chris Li, Lance Yang,
linux-mm, linux-kernel
On 08.04.24 11:24, Ryan Roberts wrote:
> On 07/04/2024 07:02, Huang, Ying wrote:
>> David Hildenbrand <david@redhat.com> writes:
>>
>>> On 03.04.24 13:40, Ryan Roberts wrote:
>>>> Multi-size THP enables performance improvements by allocating large,
>>>> pte-mapped folios for anonymous memory. However I've observed that on an
>>>> arm64 system running a parallel workload (e.g. kernel compilation)
>>>> across many cores, under high memory pressure, the speed regresses. This
>>>> is due to bottlenecking on the increased number of TLBIs added due to
>>>> all the extra folio splitting when the large folios are swapped out.
>>>> Therefore, solve this regression by adding support for swapping out
>>>> mTHP
>>>> without needing to split the folio, just like is already done for
>>>> PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
>>>> and when the swap backing store is a non-rotating block device. These
>>>> are the same constraints as for the existing PMD-sized THP swap-out
>>>> support.
>>>> Note that no attempt is made to swap-in (m)THP here - this is still
>>>> done
>>>> page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
>>>> prerequisite for swapping-in mTHP.
>>>> The main change here is to improve the swap entry allocator so that
>>>> it
>>>> can allocate any power-of-2 number of contiguous entries between [1, (1
>>>> << PMD_ORDER)]. This is done by allocating a cluster for each distinct
>>>> order and allocating sequentially from it until the cluster is full.
>>>> This ensures that we don't need to search the map and we get no
>>>> fragmentation due to alignment padding for different orders in the
>>>> cluster. If there is no current cluster for a given order, we attempt to
>>>> allocate a free cluster from the list. If there are no free clusters, we
>>>> fail the allocation and the caller can fall back to splitting the folio
>>>> and allocates individual entries (as per existing PMD-sized THP
>>>> fallback).
>>>> The per-order current clusters are maintained per-cpu using the
>>>> existing
>>>> infrastructure. This is done to avoid interleving pages from different
>>>> tasks, which would prevent IO being batched. This is already done for
>>>> the order-0 allocations so we follow the same pattern.
>>>> As is done for order-0 per-cpu clusters, the scanner now can steal
>>>> order-0 entries from any per-cpu-per-order reserved cluster. This
>>>> ensures that when the swap file is getting full, space doesn't get tied
>>>> up in the per-cpu reserves.
>>>> This change only modifies swap to be able to accept any order
>>>> mTHP. It
>>>> doesn't change the callers to elide doing the actual split. That will be
>>>> done in separate changes.
>>>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>>> ---
>>>> include/linux/swap.h | 10 ++-
>>>> mm/swap_slots.c | 6 +-
>>>> mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
>>>> 3 files changed, 109 insertions(+), 82 deletions(-)
>>>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>>>> index 5e1e4f5bf0cb..11c53692f65f 100644
>>>> --- a/include/linux/swap.h
>>>> +++ b/include/linux/swap.h
>>>> @@ -268,13 +268,19 @@ struct swap_cluster_info {
>>>> */
>>>> #define SWAP_NEXT_INVALID 0
>>>> +#ifdef CONFIG_THP_SWAP
>>>> +#define SWAP_NR_ORDERS (PMD_ORDER + 1)
>>>> +#else
>>>> +#define SWAP_NR_ORDERS 1
>>>> +#endif
>>>> +
>>>> /*
>>>> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
>>>> * its own cluster and swapout sequentially. The purpose is to optimize swapout
>>>> * throughput.
>>>> */
>>>> struct percpu_cluster {
>>>> - unsigned int next; /* Likely next allocation offset */
>>>> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
>>>> };
>>>> struct swap_cluster_list {
>>>> @@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
>>>> bool folio_free_swap(struct folio *folio);
>>>> void put_swap_folio(struct folio *folio, swp_entry_t entry);
>>>> extern swp_entry_t get_swap_page_of_type(int);
>>>> -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
>>>> +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
>>>> extern int add_swap_count_continuation(swp_entry_t, gfp_t);
>>>> extern void swap_shmem_alloc(swp_entry_t);
>>>> extern int swap_duplicate(swp_entry_t);
>>>> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
>>>> index 53abeaf1371d..13ab3b771409 100644
>>>> --- a/mm/swap_slots.c
>>>> +++ b/mm/swap_slots.c
>>>> @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
>>>> cache->cur = 0;
>>>> if (swap_slot_cache_active)
>>>> cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
>>>> - cache->slots, 1);
>>>> + cache->slots, 0);
>>>> return cache->nr;
>>>> }
>>>> @@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>>>> if (folio_test_large(folio)) {
>>>> if (IS_ENABLED(CONFIG_THP_SWAP))
>>>> - get_swap_pages(1, &entry, folio_nr_pages(folio));
>>>> + get_swap_pages(1, &entry, folio_order(folio));
>>>
>>> The only comment I have is that this nr_pages -> order conversion adds
>>> a bit of noise to this patch.
>>>
>>> AFAIKS, it's primarily only required for "cluster->next[order]",
>>> everything else doesn't really require the order.
>>>
>>> I'd just have split that out into a separate patch, or simply
>>> converted nr_pages -> order where required.
>>>
>>> Nothing jumped at me, but I'm not an expert on that code, so I'm
>>> mostly trusting the others ;)
>>
>> The nr_pages -> order conversion replaces ilog2(nr_pages) with
>> (1<<order). IIUC, "<<" is a little faster than "ilog2()". And, we
>> don't need to worry about whether nr_pages is a power of 2. Do you
>> think that this makes sense?
>
> I think that David's point was that I should just split out that change to its
> own patch to aid readability? I'm happy to do that if no one objects.
Yes. Or avoiding it and not caring about a ilog vs. 1<<order
micro-optimization ;)
--
Cheers,
David / dhildenb
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-08 9:33 ` David Hildenbrand
@ 2024-04-08 9:35 ` Ryan Roberts
0 siblings, 0 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-08 9:35 UTC (permalink / raw)
To: David Hildenbrand, Huang, Ying
Cc: Andrew Morton, Matthew Wilcox, Gao Xiang, Yu Zhao, Yang Shi,
Michal Hocko, Kefeng Wang, Barry Song, Chris Li, Lance Yang,
linux-mm, linux-kernel
On 08/04/2024 10:33, David Hildenbrand wrote:
> On 08.04.24 11:24, Ryan Roberts wrote:
>> On 07/04/2024 07:02, Huang, Ying wrote:
>>> David Hildenbrand <david@redhat.com> writes:
>>>
>>>> On 03.04.24 13:40, Ryan Roberts wrote:
>>>>> Multi-size THP enables performance improvements by allocating large,
>>>>> pte-mapped folios for anonymous memory. However I've observed that on an
>>>>> arm64 system running a parallel workload (e.g. kernel compilation)
>>>>> across many cores, under high memory pressure, the speed regresses. This
>>>>> is due to bottlenecking on the increased number of TLBIs added due to
>>>>> all the extra folio splitting when the large folios are swapped out.
>>>>> Therefore, solve this regression by adding support for swapping out
>>>>> mTHP
>>>>> without needing to split the folio, just like is already done for
>>>>> PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
>>>>> and when the swap backing store is a non-rotating block device. These
>>>>> are the same constraints as for the existing PMD-sized THP swap-out
>>>>> support.
>>>>> Note that no attempt is made to swap-in (m)THP here - this is still
>>>>> done
>>>>> page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
>>>>> prerequisite for swapping-in mTHP.
>>>>> The main change here is to improve the swap entry allocator so that
>>>>> it
>>>>> can allocate any power-of-2 number of contiguous entries between [1, (1
>>>>> << PMD_ORDER)]. This is done by allocating a cluster for each distinct
>>>>> order and allocating sequentially from it until the cluster is full.
>>>>> This ensures that we don't need to search the map and we get no
>>>>> fragmentation due to alignment padding for different orders in the
>>>>> cluster. If there is no current cluster for a given order, we attempt to
>>>>> allocate a free cluster from the list. If there are no free clusters, we
>>>>> fail the allocation and the caller can fall back to splitting the folio
>>>>> and allocates individual entries (as per existing PMD-sized THP
>>>>> fallback).
>>>>> The per-order current clusters are maintained per-cpu using the
>>>>> existing
>>>>> infrastructure. This is done to avoid interleving pages from different
>>>>> tasks, which would prevent IO being batched. This is already done for
>>>>> the order-0 allocations so we follow the same pattern.
>>>>> As is done for order-0 per-cpu clusters, the scanner now can steal
>>>>> order-0 entries from any per-cpu-per-order reserved cluster. This
>>>>> ensures that when the swap file is getting full, space doesn't get tied
>>>>> up in the per-cpu reserves.
>>>>> This change only modifies swap to be able to accept any order
>>>>> mTHP. It
>>>>> doesn't change the callers to elide doing the actual split. That will be
>>>>> done in separate changes.
>>>>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>>>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>>>> ---
>>>>> include/linux/swap.h | 10 ++-
>>>>> mm/swap_slots.c | 6 +-
>>>>> mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
>>>>> 3 files changed, 109 insertions(+), 82 deletions(-)
>>>>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>>>>> index 5e1e4f5bf0cb..11c53692f65f 100644
>>>>> --- a/include/linux/swap.h
>>>>> +++ b/include/linux/swap.h
>>>>> @@ -268,13 +268,19 @@ struct swap_cluster_info {
>>>>> */
>>>>> #define SWAP_NEXT_INVALID 0
>>>>> +#ifdef CONFIG_THP_SWAP
>>>>> +#define SWAP_NR_ORDERS (PMD_ORDER + 1)
>>>>> +#else
>>>>> +#define SWAP_NR_ORDERS 1
>>>>> +#endif
>>>>> +
>>>>> /*
>>>>> * We assign a cluster to each CPU, so each CPU can allocate swap entry
>>>>> from
>>>>> * its own cluster and swapout sequentially. The purpose is to optimize
>>>>> swapout
>>>>> * throughput.
>>>>> */
>>>>> struct percpu_cluster {
>>>>> - unsigned int next; /* Likely next allocation offset */
>>>>> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
>>>>> };
>>>>> struct swap_cluster_list {
>>>>> @@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
>>>>> bool folio_free_swap(struct folio *folio);
>>>>> void put_swap_folio(struct folio *folio, swp_entry_t entry);
>>>>> extern swp_entry_t get_swap_page_of_type(int);
>>>>> -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
>>>>> +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
>>>>> extern int add_swap_count_continuation(swp_entry_t, gfp_t);
>>>>> extern void swap_shmem_alloc(swp_entry_t);
>>>>> extern int swap_duplicate(swp_entry_t);
>>>>> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
>>>>> index 53abeaf1371d..13ab3b771409 100644
>>>>> --- a/mm/swap_slots.c
>>>>> +++ b/mm/swap_slots.c
>>>>> @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct
>>>>> swap_slots_cache *cache)
>>>>> cache->cur = 0;
>>>>> if (swap_slot_cache_active)
>>>>> cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
>>>>> - cache->slots, 1);
>>>>> + cache->slots, 0);
>>>>> return cache->nr;
>>>>> }
>>>>> @@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>>>>> if (folio_test_large(folio)) {
>>>>> if (IS_ENABLED(CONFIG_THP_SWAP))
>>>>> - get_swap_pages(1, &entry, folio_nr_pages(folio));
>>>>> + get_swap_pages(1, &entry, folio_order(folio));
>>>>
>>>> The only comment I have is that this nr_pages -> order conversion adds
>>>> a bit of noise to this patch.
>>>>
>>>> AFAIKS, it's primarily only required for "cluster->next[order]",
>>>> everything else doesn't really require the order.
>>>>
>>>> I'd just have split that out into a separate patch, or simply
>>>> converted nr_pages -> order where required.
>>>>
>>>> Nothing jumped at me, but I'm not an expert on that code, so I'm
>>>> mostly trusting the others ;)
>>>
>>> The nr_pages -> order conversion replaces ilog2(nr_pages) with
>>> (1<<order). IIUC, "<<" is a little faster than "ilog2()". And, we
>>> don't need to worry about whether nr_pages is a power of 2. Do you
>>> think that this makes sense?
>>
>> I think that David's point was that I should just split out that change to its
>> own patch to aid readability? I'm happy to do that if no one objects.
>
> Yes. Or avoiding it and not caring about a ilog vs. 1<<order micro-optimization ;)
My motivation wasn't really the ilog vs shift, but rather improving the
self-documenting nature of the API; if it takes an order its clear that
power-of-2 is required.
I'll split out the patch.
>
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-03 11:40 ` [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders Ryan Roberts
2024-04-05 10:38 ` David Hildenbrand
@ 2024-04-07 7:38 ` Barry Song
2024-04-08 9:28 ` Ryan Roberts
1 sibling, 1 reply; 30+ messages in thread
From: Barry Song @ 2024-04-07 7:38 UTC (permalink / raw)
To: Ryan Roberts
Cc: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Chris Li, Lance Yang, linux-mm, linux-kernel
On Thu, Apr 4, 2024 at 12:40 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>
> Multi-size THP enables performance improvements by allocating large,
> pte-mapped folios for anonymous memory. However I've observed that on an
> arm64 system running a parallel workload (e.g. kernel compilation)
> across many cores, under high memory pressure, the speed regresses. This
> is due to bottlenecking on the increased number of TLBIs added due to
> all the extra folio splitting when the large folios are swapped out.
>
> Therefore, solve this regression by adding support for swapping out mTHP
> without needing to split the folio, just like is already done for
> PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
> and when the swap backing store is a non-rotating block device. These
> are the same constraints as for the existing PMD-sized THP swap-out
> support.
>
> Note that no attempt is made to swap-in (m)THP here - this is still done
> page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
> prerequisite for swapping-in mTHP.
>
> The main change here is to improve the swap entry allocator so that it
> can allocate any power-of-2 number of contiguous entries between [1, (1
> << PMD_ORDER)]. This is done by allocating a cluster for each distinct
> order and allocating sequentially from it until the cluster is full.
> This ensures that we don't need to search the map and we get no
> fragmentation due to alignment padding for different orders in the
> cluster. If there is no current cluster for a given order, we attempt to
> allocate a free cluster from the list. If there are no free clusters, we
> fail the allocation and the caller can fall back to splitting the folio
> and allocates individual entries (as per existing PMD-sized THP
> fallback).
>
> The per-order current clusters are maintained per-cpu using the existing
> infrastructure. This is done to avoid interleving pages from different
> tasks, which would prevent IO being batched. This is already done for
> the order-0 allocations so we follow the same pattern.
>
> As is done for order-0 per-cpu clusters, the scanner now can steal
> order-0 entries from any per-cpu-per-order reserved cluster. This
> ensures that when the swap file is getting full, space doesn't get tied
> up in the per-cpu reserves.
>
> This change only modifies swap to be able to accept any order mTHP. It
> doesn't change the callers to elide doing the actual split. That will be
> done in separate changes.
An idea suddenly struck me: we might not need to split the folio into
order 0. Instead,
if we attempt to obtain swap entries at a certain order but fail, we
could try at half the
order. If successful, we could utilize Zi Yan's approach to split the
large folios into two
smaller ones(still large folios) but not nr_pages small folios.
Please disregard this comment for now since we don't have any data regarding
THP_SWPOUT_FALLBACK of mTHP.
>
> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
> include/linux/swap.h | 10 ++-
> mm/swap_slots.c | 6 +-
> mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
> 3 files changed, 109 insertions(+), 82 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 5e1e4f5bf0cb..11c53692f65f 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -268,13 +268,19 @@ struct swap_cluster_info {
> */
> #define SWAP_NEXT_INVALID 0
>
> +#ifdef CONFIG_THP_SWAP
> +#define SWAP_NR_ORDERS (PMD_ORDER + 1)
> +#else
> +#define SWAP_NR_ORDERS 1
> +#endif
> +
> /*
> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
> * its own cluster and swapout sequentially. The purpose is to optimize swapout
> * throughput.
> */
> struct percpu_cluster {
> - unsigned int next; /* Likely next allocation offset */
> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
> };
>
> struct swap_cluster_list {
> @@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
> bool folio_free_swap(struct folio *folio);
> void put_swap_folio(struct folio *folio, swp_entry_t entry);
> extern swp_entry_t get_swap_page_of_type(int);
> -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
> +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
> extern int add_swap_count_continuation(swp_entry_t, gfp_t);
> extern void swap_shmem_alloc(swp_entry_t);
> extern int swap_duplicate(swp_entry_t);
> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
> index 53abeaf1371d..13ab3b771409 100644
> --- a/mm/swap_slots.c
> +++ b/mm/swap_slots.c
> @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
> cache->cur = 0;
> if (swap_slot_cache_active)
> cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
> - cache->slots, 1);
> + cache->slots, 0);
>
> return cache->nr;
> }
> @@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>
> if (folio_test_large(folio)) {
> if (IS_ENABLED(CONFIG_THP_SWAP))
> - get_swap_pages(1, &entry, folio_nr_pages(folio));
> + get_swap_pages(1, &entry, folio_order(folio));
> goto out;
> }
>
> @@ -343,7 +343,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
> goto out;
> }
>
> - get_swap_pages(1, &entry, 1);
> + get_swap_pages(1, &entry, 0);
> out:
> if (mem_cgroup_try_charge_swap(folio, entry)) {
> put_swap_folio(folio, entry);
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index c95986b9cb9c..3ee8957a46e6 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -278,15 +278,15 @@ static void discard_swap_cluster(struct swap_info_struct *si,
> #ifdef CONFIG_THP_SWAP
> #define SWAPFILE_CLUSTER HPAGE_PMD_NR
>
> -#define swap_entry_size(size) (size)
> +#define swap_entry_order(order) (order)
> #else
> #define SWAPFILE_CLUSTER 256
>
> /*
> - * Define swap_entry_size() as constant to let compiler to optimize
> + * Define swap_entry_order() as constant to let compiler to optimize
> * out some code if !CONFIG_THP_SWAP
> */
> -#define swap_entry_size(size) 1
> +#define swap_entry_order(order) 0
> #endif
> #define LATENCY_LIMIT 256
>
> @@ -551,10 +551,12 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
>
> /*
> * The cluster corresponding to page_nr will be used. The cluster will be
> - * removed from free cluster list and its usage counter will be increased.
> + * removed from free cluster list and its usage counter will be increased by
> + * count.
> */
> -static void inc_cluster_info_page(struct swap_info_struct *p,
> - struct swap_cluster_info *cluster_info, unsigned long page_nr)
> +static void add_cluster_info_page(struct swap_info_struct *p,
> + struct swap_cluster_info *cluster_info, unsigned long page_nr,
> + unsigned long count)
> {
> unsigned long idx = page_nr / SWAPFILE_CLUSTER;
>
> @@ -563,9 +565,19 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
> if (cluster_is_free(&cluster_info[idx]))
> alloc_cluster(p, idx);
>
> - VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
> + VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
> cluster_set_count(&cluster_info[idx],
> - cluster_count(&cluster_info[idx]) + 1);
> + cluster_count(&cluster_info[idx]) + count);
> +}
> +
> +/*
> + * The cluster corresponding to page_nr will be used. The cluster will be
> + * removed from free cluster list and its usage counter will be increased by 1.
> + */
> +static void inc_cluster_info_page(struct swap_info_struct *p,
> + struct swap_cluster_info *cluster_info, unsigned long page_nr)
> +{
> + add_cluster_info_page(p, cluster_info, page_nr, 1);
> }
>
> /*
> @@ -595,7 +607,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p,
> */
> static bool
> scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
> - unsigned long offset)
> + unsigned long offset, int order)
> {
> struct percpu_cluster *percpu_cluster;
> bool conflict;
> @@ -609,24 +621,39 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
> return false;
>
> percpu_cluster = this_cpu_ptr(si->percpu_cluster);
> - percpu_cluster->next = SWAP_NEXT_INVALID;
> + percpu_cluster->next[order] = SWAP_NEXT_INVALID;
> + return true;
> +}
> +
> +static inline bool swap_range_empty(char *swap_map, unsigned int start,
> + unsigned int nr_pages)
> +{
> + unsigned int i;
> +
> + for (i = 0; i < nr_pages; i++) {
> + if (swap_map[start + i])
> + return false;
> + }
> +
> return true;
> }
>
> /*
> - * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
> - * might involve allocating a new cluster for current CPU too.
> + * Try to get swap entries with specified order from current cpu's swap entry
> + * pool (a cluster). This might involve allocating a new cluster for current CPU
> + * too.
> */
> static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
> - unsigned long *offset, unsigned long *scan_base)
> + unsigned long *offset, unsigned long *scan_base, int order)
> {
> + unsigned int nr_pages = 1 << order;
> struct percpu_cluster *cluster;
> struct swap_cluster_info *ci;
> unsigned int tmp, max;
>
> new_cluster:
> cluster = this_cpu_ptr(si->percpu_cluster);
> - tmp = cluster->next;
> + tmp = cluster->next[order];
> if (tmp == SWAP_NEXT_INVALID) {
> if (!cluster_list_empty(&si->free_clusters)) {
> tmp = cluster_next(&si->free_clusters.head) *
> @@ -647,26 +674,27 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
>
> /*
> * Other CPUs can use our cluster if they can't find a free cluster,
> - * check if there is still free entry in the cluster
> + * check if there is still free entry in the cluster, maintaining
> + * natural alignment.
> */
> max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER));
> if (tmp < max) {
> ci = lock_cluster(si, tmp);
> while (tmp < max) {
> - if (!si->swap_map[tmp])
> + if (swap_range_empty(si->swap_map, tmp, nr_pages))
> break;
> - tmp++;
> + tmp += nr_pages;
> }
> unlock_cluster(ci);
> }
> if (tmp >= max) {
> - cluster->next = SWAP_NEXT_INVALID;
> + cluster->next[order] = SWAP_NEXT_INVALID;
> goto new_cluster;
> }
> *offset = tmp;
> *scan_base = tmp;
> - tmp += 1;
> - cluster->next = tmp < max ? tmp : SWAP_NEXT_INVALID;
> + tmp += nr_pages;
> + cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID;
> return true;
> }
>
> @@ -796,13 +824,14 @@ static bool swap_offset_available_and_locked(struct swap_info_struct *si,
>
> static int scan_swap_map_slots(struct swap_info_struct *si,
> unsigned char usage, int nr,
> - swp_entry_t slots[])
> + swp_entry_t slots[], int order)
> {
> struct swap_cluster_info *ci;
> unsigned long offset;
> unsigned long scan_base;
> unsigned long last_in_cluster = 0;
> int latency_ration = LATENCY_LIMIT;
> + unsigned int nr_pages = 1 << order;
> int n_ret = 0;
> bool scanned_many = false;
>
> @@ -817,6 +846,25 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
> * And we let swap pages go all over an SSD partition. Hugh
> */
>
> + if (order > 0) {
> + /*
> + * Should not even be attempting large allocations when huge
> + * page swap is disabled. Warn and fail the allocation.
> + */
> + if (!IS_ENABLED(CONFIG_THP_SWAP) ||
> + nr_pages > SWAPFILE_CLUSTER) {
> + VM_WARN_ON_ONCE(1);
> + return 0;
> + }
> +
> + /*
> + * Swapfile is not block device or not using clusters so unable
> + * to allocate large entries.
> + */
> + if (!(si->flags & SWP_BLKDEV) || !si->cluster_info)
> + return 0;
> + }
> +
> si->flags += SWP_SCANNING;
> /*
> * Use percpu scan base for SSD to reduce lock contention on
> @@ -831,8 +879,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>
> /* SSD algorithm */
> if (si->cluster_info) {
> - if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
> + if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) {
> + if (order > 0)
> + goto no_page;
> goto scan;
> + }
> } else if (unlikely(!si->cluster_nr--)) {
> if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
> si->cluster_nr = SWAPFILE_CLUSTER - 1;
> @@ -874,13 +925,16 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>
> checks:
> if (si->cluster_info) {
> - while (scan_swap_map_ssd_cluster_conflict(si, offset)) {
> + while (scan_swap_map_ssd_cluster_conflict(si, offset, order)) {
> /* take a break if we already got some slots */
> if (n_ret)
> goto done;
> if (!scan_swap_map_try_ssd_cluster(si, &offset,
> - &scan_base))
> + &scan_base, order)) {
> + if (order > 0)
> + goto no_page;
> goto scan;
> + }
> }
> }
> if (!(si->flags & SWP_WRITEOK))
> @@ -911,11 +965,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
> else
> goto done;
> }
> - WRITE_ONCE(si->swap_map[offset], usage);
> - inc_cluster_info_page(si, si->cluster_info, offset);
> + memset(si->swap_map + offset, usage, nr_pages);
> + add_cluster_info_page(si, si->cluster_info, offset, nr_pages);
> unlock_cluster(ci);
>
> - swap_range_alloc(si, offset, 1);
> + swap_range_alloc(si, offset, nr_pages);
> slots[n_ret++] = swp_entry(si->type, offset);
>
> /* got enough slots or reach max slots? */
> @@ -936,8 +990,10 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>
> /* try to get more slots in cluster */
> if (si->cluster_info) {
> - if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
> + if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order))
> goto checks;
> + if (order > 0)
> + goto done;
> } else if (si->cluster_nr && !si->swap_map[++offset]) {
> /* non-ssd case, still more slots in cluster? */
> --si->cluster_nr;
> @@ -964,11 +1020,13 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
> }
>
> done:
> - set_cluster_next(si, offset + 1);
> + if (order == 0)
> + set_cluster_next(si, offset + 1);
> si->flags -= SWP_SCANNING;
> return n_ret;
>
> scan:
> + VM_WARN_ON(order > 0);
> spin_unlock(&si->lock);
> while (++offset <= READ_ONCE(si->highest_bit)) {
> if (unlikely(--latency_ration < 0)) {
> @@ -997,38 +1055,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
> return n_ret;
> }
>
> -static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
> -{
> - unsigned long idx;
> - struct swap_cluster_info *ci;
> - unsigned long offset;
> -
> - /*
> - * Should not even be attempting cluster allocations when huge
> - * page swap is disabled. Warn and fail the allocation.
> - */
> - if (!IS_ENABLED(CONFIG_THP_SWAP)) {
> - VM_WARN_ON_ONCE(1);
> - return 0;
> - }
> -
> - if (cluster_list_empty(&si->free_clusters))
> - return 0;
> -
> - idx = cluster_list_first(&si->free_clusters);
> - offset = idx * SWAPFILE_CLUSTER;
> - ci = lock_cluster(si, offset);
> - alloc_cluster(si, idx);
> - cluster_set_count(ci, SWAPFILE_CLUSTER);
> -
> - memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
> - unlock_cluster(ci);
> - swap_range_alloc(si, offset, SWAPFILE_CLUSTER);
> - *slot = swp_entry(si->type, offset);
> -
> - return 1;
> -}
> -
> static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
> {
> unsigned long offset = idx * SWAPFILE_CLUSTER;
> @@ -1042,17 +1068,15 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
> swap_range_free(si, offset, SWAPFILE_CLUSTER);
> }
>
> -int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
> +int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
> {
> - unsigned long size = swap_entry_size(entry_size);
> + int order = swap_entry_order(entry_order);
> + unsigned long size = 1 << order;
> struct swap_info_struct *si, *next;
> long avail_pgs;
> int n_ret = 0;
> int node;
>
> - /* Only single cluster request supported */
> - WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
> -
> spin_lock(&swap_avail_lock);
>
> avail_pgs = atomic_long_read(&nr_swap_pages) / size;
> @@ -1088,14 +1112,10 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
> spin_unlock(&si->lock);
> goto nextsi;
> }
> - if (size == SWAPFILE_CLUSTER) {
> - if (si->flags & SWP_BLKDEV)
> - n_ret = swap_alloc_cluster(si, swp_entries);
> - } else
> - n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
> - n_goal, swp_entries);
> + n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
> + n_goal, swp_entries, order);
> spin_unlock(&si->lock);
> - if (n_ret || size == SWAPFILE_CLUSTER)
> + if (n_ret || size > 1)
> goto check_out;
> cond_resched();
>
> @@ -1349,7 +1369,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
> unsigned char *map;
> unsigned int i, free_entries = 0;
> unsigned char val;
> - int size = swap_entry_size(folio_nr_pages(folio));
> + int size = 1 << swap_entry_order(folio_order(folio));
>
> si = _swap_info_get(entry);
> if (!si)
> @@ -1659,7 +1679,7 @@ swp_entry_t get_swap_page_of_type(int type)
>
> /* This is called for allocating swap entry, not cache */
> spin_lock(&si->lock);
> - if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry))
> + if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
> atomic_long_dec(&nr_swap_pages);
> spin_unlock(&si->lock);
> fail:
> @@ -3113,7 +3133,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
> p->flags |= SWP_SYNCHRONOUS_IO;
>
> if (p->bdev && bdev_nonrot(p->bdev)) {
> - int cpu;
> + int cpu, i;
> unsigned long ci, nr_cluster;
>
> p->flags |= SWP_SOLIDSTATE;
> @@ -3151,7 +3171,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
> struct percpu_cluster *cluster;
>
> cluster = per_cpu_ptr(p->percpu_cluster, cpu);
> - cluster->next = SWAP_NEXT_INVALID;
> + for (i = 0; i < SWAP_NR_ORDERS; i++)
> + cluster->next[i] = SWAP_NEXT_INVALID;
> }
> } else {
> atomic_inc(&nr_rotate_swap);
> --
> 2.25.1
>
Thanks
Barry
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders
2024-04-07 7:38 ` Barry Song
@ 2024-04-08 9:28 ` Ryan Roberts
0 siblings, 0 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-08 9:28 UTC (permalink / raw)
To: Barry Song
Cc: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Chris Li, Lance Yang, linux-mm, linux-kernel
On 07/04/2024 08:38, Barry Song wrote:
> On Thu, Apr 4, 2024 at 12:40 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>
>> Multi-size THP enables performance improvements by allocating large,
>> pte-mapped folios for anonymous memory. However I've observed that on an
>> arm64 system running a parallel workload (e.g. kernel compilation)
>> across many cores, under high memory pressure, the speed regresses. This
>> is due to bottlenecking on the increased number of TLBIs added due to
>> all the extra folio splitting when the large folios are swapped out.
>>
>> Therefore, solve this regression by adding support for swapping out mTHP
>> without needing to split the folio, just like is already done for
>> PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
>> and when the swap backing store is a non-rotating block device. These
>> are the same constraints as for the existing PMD-sized THP swap-out
>> support.
>>
>> Note that no attempt is made to swap-in (m)THP here - this is still done
>> page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
>> prerequisite for swapping-in mTHP.
>>
>> The main change here is to improve the swap entry allocator so that it
>> can allocate any power-of-2 number of contiguous entries between [1, (1
>> << PMD_ORDER)]. This is done by allocating a cluster for each distinct
>> order and allocating sequentially from it until the cluster is full.
>> This ensures that we don't need to search the map and we get no
>> fragmentation due to alignment padding for different orders in the
>> cluster. If there is no current cluster for a given order, we attempt to
>> allocate a free cluster from the list. If there are no free clusters, we
>> fail the allocation and the caller can fall back to splitting the folio
>> and allocates individual entries (as per existing PMD-sized THP
>> fallback).
>>
>> The per-order current clusters are maintained per-cpu using the existing
>> infrastructure. This is done to avoid interleving pages from different
>> tasks, which would prevent IO being batched. This is already done for
>> the order-0 allocations so we follow the same pattern.
>>
>> As is done for order-0 per-cpu clusters, the scanner now can steal
>> order-0 entries from any per-cpu-per-order reserved cluster. This
>> ensures that when the swap file is getting full, space doesn't get tied
>> up in the per-cpu reserves.
>>
>> This change only modifies swap to be able to accept any order mTHP. It
>> doesn't change the callers to elide doing the actual split. That will be
>> done in separate changes.
>
> An idea suddenly struck me: we might not need to split the folio into
> order 0. Instead,
> if we attempt to obtain swap entries at a certain order but fail, we
> could try at half the
> order. If successful, we could utilize Zi Yan's approach to split the
> large folios into two
> smaller ones(still large folios) but not nr_pages small folios.
Yes, agree that there is certainly room for optimization here. Although deciding
on what order to target might not always be obvious; I guess we would want to
take into consideration the user-space enabled set of orders?
IIUC, Chris Li is working on an indirection layer that would permit storing
large folios non-contiguously in swap, so that might ultimately provide a better
solution than splitting.
>
> Please disregard this comment for now since we don't have any data regarding
> THP_SWPOUT_FALLBACK of mTHP.
Yes, let's see what the data tells us.
>
>>
>> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> ---
>> include/linux/swap.h | 10 ++-
>> mm/swap_slots.c | 6 +-
>> mm/swapfile.c | 175 ++++++++++++++++++++++++-------------------
>> 3 files changed, 109 insertions(+), 82 deletions(-)
>>
>> diff --git a/include/linux/swap.h b/include/linux/swap.h
>> index 5e1e4f5bf0cb..11c53692f65f 100644
>> --- a/include/linux/swap.h
>> +++ b/include/linux/swap.h
>> @@ -268,13 +268,19 @@ struct swap_cluster_info {
>> */
>> #define SWAP_NEXT_INVALID 0
>>
>> +#ifdef CONFIG_THP_SWAP
>> +#define SWAP_NR_ORDERS (PMD_ORDER + 1)
>> +#else
>> +#define SWAP_NR_ORDERS 1
>> +#endif
>> +
>> /*
>> * We assign a cluster to each CPU, so each CPU can allocate swap entry from
>> * its own cluster and swapout sequentially. The purpose is to optimize swapout
>> * throughput.
>> */
>> struct percpu_cluster {
>> - unsigned int next; /* Likely next allocation offset */
>> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
>> };
>>
>> struct swap_cluster_list {
>> @@ -471,7 +477,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
>> bool folio_free_swap(struct folio *folio);
>> void put_swap_folio(struct folio *folio, swp_entry_t entry);
>> extern swp_entry_t get_swap_page_of_type(int);
>> -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
>> +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
>> extern int add_swap_count_continuation(swp_entry_t, gfp_t);
>> extern void swap_shmem_alloc(swp_entry_t);
>> extern int swap_duplicate(swp_entry_t);
>> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
>> index 53abeaf1371d..13ab3b771409 100644
>> --- a/mm/swap_slots.c
>> +++ b/mm/swap_slots.c
>> @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
>> cache->cur = 0;
>> if (swap_slot_cache_active)
>> cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE,
>> - cache->slots, 1);
>> + cache->slots, 0);
>>
>> return cache->nr;
>> }
>> @@ -311,7 +311,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>>
>> if (folio_test_large(folio)) {
>> if (IS_ENABLED(CONFIG_THP_SWAP))
>> - get_swap_pages(1, &entry, folio_nr_pages(folio));
>> + get_swap_pages(1, &entry, folio_order(folio));
>> goto out;
>> }
>>
>> @@ -343,7 +343,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>> goto out;
>> }
>>
>> - get_swap_pages(1, &entry, 1);
>> + get_swap_pages(1, &entry, 0);
>> out:
>> if (mem_cgroup_try_charge_swap(folio, entry)) {
>> put_swap_folio(folio, entry);
>> diff --git a/mm/swapfile.c b/mm/swapfile.c
>> index c95986b9cb9c..3ee8957a46e6 100644
>> --- a/mm/swapfile.c
>> +++ b/mm/swapfile.c
>> @@ -278,15 +278,15 @@ static void discard_swap_cluster(struct swap_info_struct *si,
>> #ifdef CONFIG_THP_SWAP
>> #define SWAPFILE_CLUSTER HPAGE_PMD_NR
>>
>> -#define swap_entry_size(size) (size)
>> +#define swap_entry_order(order) (order)
>> #else
>> #define SWAPFILE_CLUSTER 256
>>
>> /*
>> - * Define swap_entry_size() as constant to let compiler to optimize
>> + * Define swap_entry_order() as constant to let compiler to optimize
>> * out some code if !CONFIG_THP_SWAP
>> */
>> -#define swap_entry_size(size) 1
>> +#define swap_entry_order(order) 0
>> #endif
>> #define LATENCY_LIMIT 256
>>
>> @@ -551,10 +551,12 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
>>
>> /*
>> * The cluster corresponding to page_nr will be used. The cluster will be
>> - * removed from free cluster list and its usage counter will be increased.
>> + * removed from free cluster list and its usage counter will be increased by
>> + * count.
>> */
>> -static void inc_cluster_info_page(struct swap_info_struct *p,
>> - struct swap_cluster_info *cluster_info, unsigned long page_nr)
>> +static void add_cluster_info_page(struct swap_info_struct *p,
>> + struct swap_cluster_info *cluster_info, unsigned long page_nr,
>> + unsigned long count)
>> {
>> unsigned long idx = page_nr / SWAPFILE_CLUSTER;
>>
>> @@ -563,9 +565,19 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
>> if (cluster_is_free(&cluster_info[idx]))
>> alloc_cluster(p, idx);
>>
>> - VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
>> + VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
>> cluster_set_count(&cluster_info[idx],
>> - cluster_count(&cluster_info[idx]) + 1);
>> + cluster_count(&cluster_info[idx]) + count);
>> +}
>> +
>> +/*
>> + * The cluster corresponding to page_nr will be used. The cluster will be
>> + * removed from free cluster list and its usage counter will be increased by 1.
>> + */
>> +static void inc_cluster_info_page(struct swap_info_struct *p,
>> + struct swap_cluster_info *cluster_info, unsigned long page_nr)
>> +{
>> + add_cluster_info_page(p, cluster_info, page_nr, 1);
>> }
>>
>> /*
>> @@ -595,7 +607,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p,
>> */
>> static bool
>> scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
>> - unsigned long offset)
>> + unsigned long offset, int order)
>> {
>> struct percpu_cluster *percpu_cluster;
>> bool conflict;
>> @@ -609,24 +621,39 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
>> return false;
>>
>> percpu_cluster = this_cpu_ptr(si->percpu_cluster);
>> - percpu_cluster->next = SWAP_NEXT_INVALID;
>> + percpu_cluster->next[order] = SWAP_NEXT_INVALID;
>> + return true;
>> +}
>> +
>> +static inline bool swap_range_empty(char *swap_map, unsigned int start,
>> + unsigned int nr_pages)
>> +{
>> + unsigned int i;
>> +
>> + for (i = 0; i < nr_pages; i++) {
>> + if (swap_map[start + i])
>> + return false;
>> + }
>> +
>> return true;
>> }
>>
>> /*
>> - * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
>> - * might involve allocating a new cluster for current CPU too.
>> + * Try to get swap entries with specified order from current cpu's swap entry
>> + * pool (a cluster). This might involve allocating a new cluster for current CPU
>> + * too.
>> */
>> static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
>> - unsigned long *offset, unsigned long *scan_base)
>> + unsigned long *offset, unsigned long *scan_base, int order)
>> {
>> + unsigned int nr_pages = 1 << order;
>> struct percpu_cluster *cluster;
>> struct swap_cluster_info *ci;
>> unsigned int tmp, max;
>>
>> new_cluster:
>> cluster = this_cpu_ptr(si->percpu_cluster);
>> - tmp = cluster->next;
>> + tmp = cluster->next[order];
>> if (tmp == SWAP_NEXT_INVALID) {
>> if (!cluster_list_empty(&si->free_clusters)) {
>> tmp = cluster_next(&si->free_clusters.head) *
>> @@ -647,26 +674,27 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
>>
>> /*
>> * Other CPUs can use our cluster if they can't find a free cluster,
>> - * check if there is still free entry in the cluster
>> + * check if there is still free entry in the cluster, maintaining
>> + * natural alignment.
>> */
>> max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER));
>> if (tmp < max) {
>> ci = lock_cluster(si, tmp);
>> while (tmp < max) {
>> - if (!si->swap_map[tmp])
>> + if (swap_range_empty(si->swap_map, tmp, nr_pages))
>> break;
>> - tmp++;
>> + tmp += nr_pages;
>> }
>> unlock_cluster(ci);
>> }
>> if (tmp >= max) {
>> - cluster->next = SWAP_NEXT_INVALID;
>> + cluster->next[order] = SWAP_NEXT_INVALID;
>> goto new_cluster;
>> }
>> *offset = tmp;
>> *scan_base = tmp;
>> - tmp += 1;
>> - cluster->next = tmp < max ? tmp : SWAP_NEXT_INVALID;
>> + tmp += nr_pages;
>> + cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID;
>> return true;
>> }
>>
>> @@ -796,13 +824,14 @@ static bool swap_offset_available_and_locked(struct swap_info_struct *si,
>>
>> static int scan_swap_map_slots(struct swap_info_struct *si,
>> unsigned char usage, int nr,
>> - swp_entry_t slots[])
>> + swp_entry_t slots[], int order)
>> {
>> struct swap_cluster_info *ci;
>> unsigned long offset;
>> unsigned long scan_base;
>> unsigned long last_in_cluster = 0;
>> int latency_ration = LATENCY_LIMIT;
>> + unsigned int nr_pages = 1 << order;
>> int n_ret = 0;
>> bool scanned_many = false;
>>
>> @@ -817,6 +846,25 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>> * And we let swap pages go all over an SSD partition. Hugh
>> */
>>
>> + if (order > 0) {
>> + /*
>> + * Should not even be attempting large allocations when huge
>> + * page swap is disabled. Warn and fail the allocation.
>> + */
>> + if (!IS_ENABLED(CONFIG_THP_SWAP) ||
>> + nr_pages > SWAPFILE_CLUSTER) {
>> + VM_WARN_ON_ONCE(1);
>> + return 0;
>> + }
>> +
>> + /*
>> + * Swapfile is not block device or not using clusters so unable
>> + * to allocate large entries.
>> + */
>> + if (!(si->flags & SWP_BLKDEV) || !si->cluster_info)
>> + return 0;
>> + }
>> +
>> si->flags += SWP_SCANNING;
>> /*
>> * Use percpu scan base for SSD to reduce lock contention on
>> @@ -831,8 +879,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>>
>> /* SSD algorithm */
>> if (si->cluster_info) {
>> - if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
>> + if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) {
>> + if (order > 0)
>> + goto no_page;
>> goto scan;
>> + }
>> } else if (unlikely(!si->cluster_nr--)) {
>> if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
>> si->cluster_nr = SWAPFILE_CLUSTER - 1;
>> @@ -874,13 +925,16 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>>
>> checks:
>> if (si->cluster_info) {
>> - while (scan_swap_map_ssd_cluster_conflict(si, offset)) {
>> + while (scan_swap_map_ssd_cluster_conflict(si, offset, order)) {
>> /* take a break if we already got some slots */
>> if (n_ret)
>> goto done;
>> if (!scan_swap_map_try_ssd_cluster(si, &offset,
>> - &scan_base))
>> + &scan_base, order)) {
>> + if (order > 0)
>> + goto no_page;
>> goto scan;
>> + }
>> }
>> }
>> if (!(si->flags & SWP_WRITEOK))
>> @@ -911,11 +965,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>> else
>> goto done;
>> }
>> - WRITE_ONCE(si->swap_map[offset], usage);
>> - inc_cluster_info_page(si, si->cluster_info, offset);
>> + memset(si->swap_map + offset, usage, nr_pages);
>> + add_cluster_info_page(si, si->cluster_info, offset, nr_pages);
>> unlock_cluster(ci);
>>
>> - swap_range_alloc(si, offset, 1);
>> + swap_range_alloc(si, offset, nr_pages);
>> slots[n_ret++] = swp_entry(si->type, offset);
>>
>> /* got enough slots or reach max slots? */
>> @@ -936,8 +990,10 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>>
>> /* try to get more slots in cluster */
>> if (si->cluster_info) {
>> - if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
>> + if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order))
>> goto checks;
>> + if (order > 0)
>> + goto done;
>> } else if (si->cluster_nr && !si->swap_map[++offset]) {
>> /* non-ssd case, still more slots in cluster? */
>> --si->cluster_nr;
>> @@ -964,11 +1020,13 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>> }
>>
>> done:
>> - set_cluster_next(si, offset + 1);
>> + if (order == 0)
>> + set_cluster_next(si, offset + 1);
>> si->flags -= SWP_SCANNING;
>> return n_ret;
>>
>> scan:
>> + VM_WARN_ON(order > 0);
>> spin_unlock(&si->lock);
>> while (++offset <= READ_ONCE(si->highest_bit)) {
>> if (unlikely(--latency_ration < 0)) {
>> @@ -997,38 +1055,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
>> return n_ret;
>> }
>>
>> -static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
>> -{
>> - unsigned long idx;
>> - struct swap_cluster_info *ci;
>> - unsigned long offset;
>> -
>> - /*
>> - * Should not even be attempting cluster allocations when huge
>> - * page swap is disabled. Warn and fail the allocation.
>> - */
>> - if (!IS_ENABLED(CONFIG_THP_SWAP)) {
>> - VM_WARN_ON_ONCE(1);
>> - return 0;
>> - }
>> -
>> - if (cluster_list_empty(&si->free_clusters))
>> - return 0;
>> -
>> - idx = cluster_list_first(&si->free_clusters);
>> - offset = idx * SWAPFILE_CLUSTER;
>> - ci = lock_cluster(si, offset);
>> - alloc_cluster(si, idx);
>> - cluster_set_count(ci, SWAPFILE_CLUSTER);
>> -
>> - memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
>> - unlock_cluster(ci);
>> - swap_range_alloc(si, offset, SWAPFILE_CLUSTER);
>> - *slot = swp_entry(si->type, offset);
>> -
>> - return 1;
>> -}
>> -
>> static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
>> {
>> unsigned long offset = idx * SWAPFILE_CLUSTER;
>> @@ -1042,17 +1068,15 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
>> swap_range_free(si, offset, SWAPFILE_CLUSTER);
>> }
>>
>> -int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
>> +int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
>> {
>> - unsigned long size = swap_entry_size(entry_size);
>> + int order = swap_entry_order(entry_order);
>> + unsigned long size = 1 << order;
>> struct swap_info_struct *si, *next;
>> long avail_pgs;
>> int n_ret = 0;
>> int node;
>>
>> - /* Only single cluster request supported */
>> - WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
>> -
>> spin_lock(&swap_avail_lock);
>>
>> avail_pgs = atomic_long_read(&nr_swap_pages) / size;
>> @@ -1088,14 +1112,10 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
>> spin_unlock(&si->lock);
>> goto nextsi;
>> }
>> - if (size == SWAPFILE_CLUSTER) {
>> - if (si->flags & SWP_BLKDEV)
>> - n_ret = swap_alloc_cluster(si, swp_entries);
>> - } else
>> - n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
>> - n_goal, swp_entries);
>> + n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
>> + n_goal, swp_entries, order);
>> spin_unlock(&si->lock);
>> - if (n_ret || size == SWAPFILE_CLUSTER)
>> + if (n_ret || size > 1)
>> goto check_out;
>> cond_resched();
>>
>> @@ -1349,7 +1369,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
>> unsigned char *map;
>> unsigned int i, free_entries = 0;
>> unsigned char val;
>> - int size = swap_entry_size(folio_nr_pages(folio));
>> + int size = 1 << swap_entry_order(folio_order(folio));
>>
>> si = _swap_info_get(entry);
>> if (!si)
>> @@ -1659,7 +1679,7 @@ swp_entry_t get_swap_page_of_type(int type)
>>
>> /* This is called for allocating swap entry, not cache */
>> spin_lock(&si->lock);
>> - if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry))
>> + if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
>> atomic_long_dec(&nr_swap_pages);
>> spin_unlock(&si->lock);
>> fail:
>> @@ -3113,7 +3133,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>> p->flags |= SWP_SYNCHRONOUS_IO;
>>
>> if (p->bdev && bdev_nonrot(p->bdev)) {
>> - int cpu;
>> + int cpu, i;
>> unsigned long ci, nr_cluster;
>>
>> p->flags |= SWP_SOLIDSTATE;
>> @@ -3151,7 +3171,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>> struct percpu_cluster *cluster;
>>
>> cluster = per_cpu_ptr(p->percpu_cluster, cpu);
>> - cluster->next = SWAP_NEXT_INVALID;
>> + for (i = 0; i < SWAP_NR_ORDERS; i++)
>> + cluster->next[i] = SWAP_NEXT_INVALID;
>> }
>> } else {
>> atomic_inc(&nr_rotate_swap);
>> --
>> 2.25.1
>>
>
> Thanks
> Barry
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH v6 5/6] mm: vmscan: Avoid split during shrink_folio_list()
2024-04-03 11:40 [PATCH v6 0/6] Swap-out mTHP without splitting Ryan Roberts
` (3 preceding siblings ...)
2024-04-03 11:40 ` [PATCH v6 4/6] mm: swap: Allow storage of all mTHP orders Ryan Roberts
@ 2024-04-03 11:40 ` Ryan Roberts
2024-04-05 10:42 ` David Hildenbrand
2024-04-03 11:40 ` [PATCH v6 6/6] mm: madvise: Avoid split during MADV_PAGEOUT and MADV_COLD Ryan Roberts
5 siblings, 1 reply; 30+ messages in thread
From: Ryan Roberts @ 2024-04-03 11:40 UTC (permalink / raw)
To: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: Ryan Roberts, linux-mm, linux-kernel, Barry Song
Now that swap supports storing all mTHP sizes, avoid splitting large
folios before swap-out. This benefits performance of the swap-out path
by eliding split_folio_to_list(), which is expensive, and also sets us
up for swapping in large folios in a future series.
If the folio is partially mapped, we continue to split it since we want
to avoid the extra IO overhead and storage of writing out pages
uneccessarily.
THP_SWPOUT and THP_SWPOUT_FALLBACK counters should continue to count
events only for PMD-mappable folios to avoid user confusion. THP_SWPOUT
already has the appropriate guard. Add a guard for THP_SWPOUT_FALLBACK.
It may be appropriate to add per-size counters in future.
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Barry Song <v-songbaohua@oppo.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
mm/vmscan.c | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 00adaf1cb2c3..ffc4553c8615 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1223,11 +1223,12 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
if (!can_split_folio(folio, NULL))
goto activate_locked;
/*
- * Split folios without a PMD map right
- * away. Chances are some or all of the
- * tail pages can be freed without IO.
+ * Split partially mapped folios right
+ * away. We can free the unmapped pages
+ * without IO.
*/
- if (!folio_entire_mapcount(folio) &&
+ if (data_race(!list_empty(
+ &folio->_deferred_list)) &&
split_folio_to_list(folio,
folio_list))
goto activate_locked;
@@ -1240,8 +1241,12 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
folio_list))
goto activate_locked;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1);
- count_vm_event(THP_SWPOUT_FALLBACK);
+ if (nr_pages >= HPAGE_PMD_NR) {
+ count_memcg_folio_events(folio,
+ THP_SWPOUT_FALLBACK, 1);
+ count_vm_event(
+ THP_SWPOUT_FALLBACK);
+ }
#endif
if (!add_to_swap(folio))
goto activate_locked_split;
--
2.25.1
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 5/6] mm: vmscan: Avoid split during shrink_folio_list()
2024-04-03 11:40 ` [PATCH v6 5/6] mm: vmscan: Avoid split during shrink_folio_list() Ryan Roberts
@ 2024-04-05 10:42 ` David Hildenbrand
2024-04-08 9:31 ` Ryan Roberts
0 siblings, 1 reply; 30+ messages in thread
From: David Hildenbrand @ 2024-04-05 10:42 UTC (permalink / raw)
To: Ryan Roberts, Andrew Morton, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: linux-mm, linux-kernel, Barry Song
On 03.04.24 13:40, Ryan Roberts wrote:
> Now that swap supports storing all mTHP sizes, avoid splitting large
> folios before swap-out. This benefits performance of the swap-out path
> by eliding split_folio_to_list(), which is expensive, and also sets us
> up for swapping in large folios in a future series.
>
> If the folio is partially mapped, we continue to split it since we want
> to avoid the extra IO overhead and storage of writing out pages
> uneccessarily.
>
> THP_SWPOUT and THP_SWPOUT_FALLBACK counters should continue to count
> events only for PMD-mappable folios to avoid user confusion. THP_SWPOUT
> already has the appropriate guard. Add a guard for THP_SWPOUT_FALLBACK.
> It may be appropriate to add per-size counters in future.
>
> Reviewed-by: David Hildenbrand <david@redhat.com>
> Reviewed-by: Barry Song <v-songbaohua@oppo.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
> mm/vmscan.c | 17 +++++++++++------
> 1 file changed, 11 insertions(+), 6 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 00adaf1cb2c3..ffc4553c8615 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1223,11 +1223,12 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
> if (!can_split_folio(folio, NULL))
> goto activate_locked;
> /*
> - * Split folios without a PMD map right
> - * away. Chances are some or all of the
> - * tail pages can be freed without IO.
> + * Split partially mapped folios right
> + * away. We can free the unmapped pages
> + * without IO.
> */
> - if (!folio_entire_mapcount(folio) &&
> + if (data_race(!list_empty(
> + &folio->_deferred_list)) &&
Please violate the 80 chars rule where reasonable.
"
Statements longer than 80 columns should be broken into sensible chunks,
unless exceeding 80 columns significantly increases readability and does
not hide information.
"
Likely some of that code here should be refactored into readable
sub-functions.
codingstyle also mentions
"The answer to that is that if you need more than 3 levels of
indentation, you're screwed anyway, and should fix your program."
--
Cheers,
David / dhildenb
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v6 5/6] mm: vmscan: Avoid split during shrink_folio_list()
2024-04-05 10:42 ` David Hildenbrand
@ 2024-04-08 9:31 ` Ryan Roberts
0 siblings, 0 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-08 9:31 UTC (permalink / raw)
To: David Hildenbrand, Andrew Morton, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: linux-mm, linux-kernel, Barry Song
On 05/04/2024 11:42, David Hildenbrand wrote:
> On 03.04.24 13:40, Ryan Roberts wrote:
>> Now that swap supports storing all mTHP sizes, avoid splitting large
>> folios before swap-out. This benefits performance of the swap-out path
>> by eliding split_folio_to_list(), which is expensive, and also sets us
>> up for swapping in large folios in a future series.
>>
>> If the folio is partially mapped, we continue to split it since we want
>> to avoid the extra IO overhead and storage of writing out pages
>> uneccessarily.
>>
>> THP_SWPOUT and THP_SWPOUT_FALLBACK counters should continue to count
>> events only for PMD-mappable folios to avoid user confusion. THP_SWPOUT
>> already has the appropriate guard. Add a guard for THP_SWPOUT_FALLBACK.
>> It may be appropriate to add per-size counters in future.
>>
>> Reviewed-by: David Hildenbrand <david@redhat.com>
>> Reviewed-by: Barry Song <v-songbaohua@oppo.com>
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> ---
>> mm/vmscan.c | 17 +++++++++++------
>> 1 file changed, 11 insertions(+), 6 deletions(-)
>>
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index 00adaf1cb2c3..ffc4553c8615 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -1223,11 +1223,12 @@ static unsigned int shrink_folio_list(struct list_head
>> *folio_list,
>> if (!can_split_folio(folio, NULL))
>> goto activate_locked;
>> /*
>> - * Split folios without a PMD map right
>> - * away. Chances are some or all of the
>> - * tail pages can be freed without IO.
>> + * Split partially mapped folios right
>> + * away. We can free the unmapped pages
>> + * without IO.
>> */
>> - if (!folio_entire_mapcount(folio) &&
>> + if (data_race(!list_empty(
>> + &folio->_deferred_list)) &&
>
> Please violate the 80 chars rule where reasonable.
>
> "
> Statements longer than 80 columns should be broken into sensible chunks, unless
> exceeding 80 columns significantly increases readability and does not hide
> information.
> "
>
>
> Likely some of that code here should be refactored into readable sub-functions.
>
> codingstyle also mentions
>
> "The answer to that is that if you need more than 3 levels of indentation,
> you're screwed anyway, and should fix your program."
>
Boo! :)
Yeah, no problem, I'll sort this.
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH v6 6/6] mm: madvise: Avoid split during MADV_PAGEOUT and MADV_COLD
2024-04-03 11:40 [PATCH v6 0/6] Swap-out mTHP without splitting Ryan Roberts
` (4 preceding siblings ...)
2024-04-03 11:40 ` [PATCH v6 5/6] mm: vmscan: Avoid split during shrink_folio_list() Ryan Roberts
@ 2024-04-03 11:40 ` Ryan Roberts
2024-04-03 17:17 ` Ryan Roberts
5 siblings, 1 reply; 30+ messages in thread
From: Ryan Roberts @ 2024-04-03 11:40 UTC (permalink / raw)
To: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: Ryan Roberts, linux-mm, linux-kernel, Barry Song
Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large
folio that is fully and contiguously mapped in the pageout/cold vm
range. This change means that large folios will be maintained all the
way to swap storage. This both improves performance during swap-out, by
eliding the cost of splitting the folio, and sets us up nicely for
maintaining the large folio when it is swapped back in (to be covered in
a separate series).
Folios that are not fully mapped in the target range are still split,
but note that behavior is changed so that if the split fails for any
reason (folio locked, shared, etc) we now leave it as is and move to the
next pte in the range and continue work on the proceeding folios.
Previously any failure of this sort would cause the entire operation to
give up and no folios mapped at higher addresses were paged out or made
cold. Given large folios are becoming more common, this old behavior
would have likely lead to wasted opportunities.
While we are at it, change the code that clears young from the ptes to
use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper
function. This is more efficent than get_and_clear/modify/set,
especially for contpte mappings on arm64, where the old approach would
require unfolding/refolding and the new approach can be done in place.
Reviewed-by: Barry Song <v-songbaohua@oppo.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
include/linux/pgtable.h | 30 ++++++++++++++
mm/internal.h | 12 +++++-
mm/madvise.c | 88 ++++++++++++++++++++++++-----------------
mm/memory.c | 4 +-
4 files changed, 93 insertions(+), 41 deletions(-)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 0278259f7078..0f4b2faa1d71 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -361,6 +361,36 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
}
#endif
+#ifndef mkold_ptes
+/**
+ * mkold_ptes - Mark PTEs that map consecutive pages of the same folio as old.
+ * @vma: VMA the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries to mark old.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over ptep_test_and_clear_young().
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ. For example,
+ * some PTEs might be write-protected.
+ *
+ * Context: The caller holds the page table lock. The PTEs map consecutive
+ * pages that belong to the same folio. The PTEs are all in the same PMD.
+ */
+static inline void mkold_ptes(struct vm_area_struct *vma, unsigned long addr,
+ pte_t *ptep, unsigned int nr)
+{
+ for (;;) {
+ ptep_test_and_clear_young(vma, addr, ptep);
+ if (--nr == 0)
+ break;
+ ptep++;
+ addr += PAGE_SIZE;
+ }
+}
+#endif
+
#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
diff --git a/mm/internal.h b/mm/internal.h
index 88705ab4c50a..003bc189736b 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -130,6 +130,8 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
* @flags: Flags to modify the PTE batch semantics.
* @any_writable: Optional pointer to indicate whether any entry except the
* first one is writable.
+ * @any_young: Optional pointer to indicate whether any entry except the
+ * first one is young.
*
* Detect a PTE batch: consecutive (present) PTEs that map consecutive
* pages of the same large folio.
@@ -145,16 +147,18 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
*/
static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
- bool *any_writable)
+ bool *any_writable, bool *any_young)
{
unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
const pte_t *end_ptep = start_ptep + max_nr;
pte_t expected_pte, *ptep;
- bool writable;
+ bool writable, young;
int nr;
if (any_writable)
*any_writable = false;
+ if (any_young)
+ *any_young = false;
VM_WARN_ON_FOLIO(!pte_present(pte), folio);
VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
@@ -168,6 +172,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
pte = ptep_get(ptep);
if (any_writable)
writable = !!pte_write(pte);
+ if (any_young)
+ young = !!pte_young(pte);
pte = __pte_batch_clear_ignored(pte, flags);
if (!pte_same(pte, expected_pte))
@@ -183,6 +189,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
if (any_writable)
*any_writable |= writable;
+ if (any_young)
+ *any_young |= young;
nr = pte_batch_hint(ptep, pte);
expected_pte = pte_advance_pfn(expected_pte, nr);
diff --git a/mm/madvise.c b/mm/madvise.c
index 070bedb4996e..c1377f3b5ca1 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -336,6 +336,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
LIST_HEAD(folio_list);
bool pageout_anon_only_filter;
unsigned int batch_count = 0;
+ int nr;
if (fatal_signal_pending(current))
return -EINTR;
@@ -423,7 +424,8 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
- for (; addr < end; pte++, addr += PAGE_SIZE) {
+ for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) {
+ nr = 1;
ptent = ptep_get(pte);
if (++batch_count == SWAP_CLUSTER_MAX) {
@@ -447,55 +449,67 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
continue;
/*
- * Creating a THP page is expensive so split it only if we
- * are sure it's worth. Split it if we are only owner.
+ * If we encounter a large folio, only split it if it is not
+ * fully mapped within the range we are operating on. Otherwise
+ * leave it as is so that it can be swapped out whole. If we
+ * fail to split a folio, leave it in place and advance to the
+ * next pte in the range.
*/
if (folio_test_large(folio)) {
- int err;
-
- if (folio_likely_mapped_shared(folio))
- break;
- if (pageout_anon_only_filter && !folio_test_anon(folio))
- break;
- if (!folio_trylock(folio))
- break;
- folio_get(folio);
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(start_pte, ptl);
- start_pte = NULL;
- err = split_folio(folio);
- folio_unlock(folio);
- folio_put(folio);
- if (err)
- break;
- start_pte = pte =
- pte_offset_map_lock(mm, pmd, addr, &ptl);
- if (!start_pte)
- break;
- arch_enter_lazy_mmu_mode();
- pte--;
- addr -= PAGE_SIZE;
- continue;
+ const fpb_t fpb_flags = FPB_IGNORE_DIRTY |
+ FPB_IGNORE_SOFT_DIRTY;
+ int max_nr = (end - addr) / PAGE_SIZE;
+ bool any_young;
+
+ nr = folio_pte_batch(folio, addr, pte, ptent, max_nr,
+ fpb_flags, NULL, &any_young);
+ if (any_young)
+ ptent = pte_mkyoung(ptent);
+
+ if (nr < folio_nr_pages(folio)) {
+ int err;
+
+ if (folio_likely_mapped_shared(folio))
+ continue;
+ if (pageout_anon_only_filter && !folio_test_anon(folio))
+ continue;
+ if (!folio_trylock(folio))
+ continue;
+ folio_get(folio);
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ start_pte = NULL;
+ err = split_folio(folio);
+ folio_unlock(folio);
+ folio_put(folio);
+ start_pte = pte =
+ pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!start_pte)
+ break;
+ if (err)
+ continue;
+ arch_enter_lazy_mmu_mode();
+ nr = 0;
+ continue;
+ }
}
/*
* Do not interfere with other mappings of this folio and
- * non-LRU folio.
+ * non-LRU folio. If we have a large folio at this point, we
+ * know it is fully mapped so if its mapcount is the same as its
+ * number of pages, it must be exclusive.
*/
- if (!folio_test_lru(folio) || folio_mapcount(folio) != 1)
+ if (!folio_test_lru(folio) ||
+ folio_mapcount(folio) != folio_nr_pages(folio))
continue;
if (pageout_anon_only_filter && !folio_test_anon(folio))
continue;
- VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
-
if (!pageout && pte_young(ptent)) {
- ptent = ptep_get_and_clear_full(mm, addr, pte,
- tlb->fullmm);
- ptent = pte_mkold(ptent);
- set_pte_at(mm, addr, pte, ptent);
- tlb_remove_tlb_entry(tlb, pte, addr);
+ mkold_ptes(vma, addr, pte, nr);
+ tlb_remove_tlb_entries(tlb, pte, nr, addr);
}
/*
diff --git a/mm/memory.c b/mm/memory.c
index ef2968894718..912cd738ec03 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -989,7 +989,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
flags |= FPB_IGNORE_SOFT_DIRTY;
nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags,
- &any_writable);
+ &any_writable, NULL);
folio_ref_add(folio, nr);
if (folio_test_anon(folio)) {
if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page,
@@ -1559,7 +1559,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
*/
if (unlikely(folio_test_large(folio) && max_nr != 1)) {
nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags,
- NULL);
+ NULL, NULL);
zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr,
addr, details, rss, force_flush,
--
2.25.1
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v6 6/6] mm: madvise: Avoid split during MADV_PAGEOUT and MADV_COLD
2024-04-03 11:40 ` [PATCH v6 6/6] mm: madvise: Avoid split during MADV_PAGEOUT and MADV_COLD Ryan Roberts
@ 2024-04-03 17:17 ` Ryan Roberts
0 siblings, 0 replies; 30+ messages in thread
From: Ryan Roberts @ 2024-04-03 17:17 UTC (permalink / raw)
To: Andrew Morton, David Hildenbrand, Matthew Wilcox, Huang Ying,
Gao Xiang, Yu Zhao, Yang Shi, Michal Hocko, Kefeng Wang,
Barry Song, Chris Li, Lance Yang
Cc: linux-mm, linux-kernel, Barry Song
On 03/04/2024 12:40, Ryan Roberts wrote:
> Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large
> folio that is fully and contiguously mapped in the pageout/cold vm
> range. This change means that large folios will be maintained all the
> way to swap storage. This both improves performance during swap-out, by
> eliding the cost of splitting the folio, and sets us up nicely for
> maintaining the large folio when it is swapped back in (to be covered in
> a separate series).
>
> Folios that are not fully mapped in the target range are still split,
> but note that behavior is changed so that if the split fails for any
> reason (folio locked, shared, etc) we now leave it as is and move to the
> next pte in the range and continue work on the proceeding folios.
> Previously any failure of this sort would cause the entire operation to
> give up and no folios mapped at higher addresses were paged out or made
> cold. Given large folios are becoming more common, this old behavior
> would have likely lead to wasted opportunities.
>
> While we are at it, change the code that clears young from the ptes to
> use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper
> function. This is more efficent than get_and_clear/modify/set,
> especially for contpte mappings on arm64, where the old approach would
> require unfolding/refolding and the new approach can be done in place.
>
> Reviewed-by: Barry Song <v-songbaohua@oppo.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
> include/linux/pgtable.h | 30 ++++++++++++++
> mm/internal.h | 12 +++++-
> mm/madvise.c | 88 ++++++++++++++++++++++++-----------------
> mm/memory.c | 4 +-
> 4 files changed, 93 insertions(+), 41 deletions(-)
>
> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> index 0278259f7078..0f4b2faa1d71 100644
> --- a/include/linux/pgtable.h
> +++ b/include/linux/pgtable.h
> @@ -361,6 +361,36 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
> }
> #endif
>
> +#ifndef mkold_ptes
> +/**
> + * mkold_ptes - Mark PTEs that map consecutive pages of the same folio as old.
> + * @vma: VMA the pages are mapped into.
> + * @addr: Address the first page is mapped at.
> + * @ptep: Page table pointer for the first entry.
> + * @nr: Number of entries to mark old.
> + *
> + * May be overridden by the architecture; otherwise, implemented as a simple
> + * loop over ptep_test_and_clear_young().
> + *
> + * Note that PTE bits in the PTE range besides the PFN can differ. For example,
> + * some PTEs might be write-protected.
> + *
> + * Context: The caller holds the page table lock. The PTEs map consecutive
> + * pages that belong to the same folio. The PTEs are all in the same PMD.
> + */
> +static inline void mkold_ptes(struct vm_area_struct *vma, unsigned long addr,
> + pte_t *ptep, unsigned int nr)
> +{
> + for (;;) {
> + ptep_test_and_clear_young(vma, addr, ptep);
> + if (--nr == 0)
> + break;
> + ptep++;
> + addr += PAGE_SIZE;
> + }
> +}
> +#endif
> +
> #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
> #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
> static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
> diff --git a/mm/internal.h b/mm/internal.h
> index 88705ab4c50a..003bc189736b 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -130,6 +130,8 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
> * @flags: Flags to modify the PTE batch semantics.
> * @any_writable: Optional pointer to indicate whether any entry except the
> * first one is writable.
> + * @any_young: Optional pointer to indicate whether any entry except the
> + * first one is young.
> *
> * Detect a PTE batch: consecutive (present) PTEs that map consecutive
> * pages of the same large folio.
> @@ -145,16 +147,18 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
> */
> static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
> pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
> - bool *any_writable)
> + bool *any_writable, bool *any_young)
> {
> unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
> const pte_t *end_ptep = start_ptep + max_nr;
> pte_t expected_pte, *ptep;
> - bool writable;
> + bool writable, young;
> int nr;
>
> if (any_writable)
> *any_writable = false;
> + if (any_young)
> + *any_young = false;
>
> VM_WARN_ON_FOLIO(!pte_present(pte), folio);
> VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
> @@ -168,6 +172,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
> pte = ptep_get(ptep);
> if (any_writable)
> writable = !!pte_write(pte);
> + if (any_young)
> + young = !!pte_young(pte);
> pte = __pte_batch_clear_ignored(pte, flags);
>
> if (!pte_same(pte, expected_pte))
> @@ -183,6 +189,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
>
> if (any_writable)
> *any_writable |= writable;
> + if (any_young)
> + *any_young |= young;
>
> nr = pte_batch_hint(ptep, pte);
> expected_pte = pte_advance_pfn(expected_pte, nr);
> diff --git a/mm/madvise.c b/mm/madvise.c
> index 070bedb4996e..c1377f3b5ca1 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -336,6 +336,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> LIST_HEAD(folio_list);
> bool pageout_anon_only_filter;
> unsigned int batch_count = 0;
> + int nr;
>
> if (fatal_signal_pending(current))
> return -EINTR;
> @@ -423,7 +424,8 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> return 0;
> flush_tlb_batched_pending(mm);
> arch_enter_lazy_mmu_mode();
> - for (; addr < end; pte++, addr += PAGE_SIZE) {
> + for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) {
> + nr = 1;
> ptent = ptep_get(pte);
>
> if (++batch_count == SWAP_CLUSTER_MAX) {
> @@ -447,55 +449,67 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> continue;
>
> /*
> - * Creating a THP page is expensive so split it only if we
> - * are sure it's worth. Split it if we are only owner.
> + * If we encounter a large folio, only split it if it is not
> + * fully mapped within the range we are operating on. Otherwise
> + * leave it as is so that it can be swapped out whole. If we
> + * fail to split a folio, leave it in place and advance to the
> + * next pte in the range.
> */
> if (folio_test_large(folio)) {
> - int err;
> -
> - if (folio_likely_mapped_shared(folio))
> - break;
> - if (pageout_anon_only_filter && !folio_test_anon(folio))
> - break;
> - if (!folio_trylock(folio))
> - break;
> - folio_get(folio);
> - arch_leave_lazy_mmu_mode();
> - pte_unmap_unlock(start_pte, ptl);
> - start_pte = NULL;
> - err = split_folio(folio);
> - folio_unlock(folio);
> - folio_put(folio);
> - if (err)
> - break;
> - start_pte = pte =
> - pte_offset_map_lock(mm, pmd, addr, &ptl);
> - if (!start_pte)
> - break;
> - arch_enter_lazy_mmu_mode();
> - pte--;
> - addr -= PAGE_SIZE;
> - continue;
> + const fpb_t fpb_flags = FPB_IGNORE_DIRTY |
> + FPB_IGNORE_SOFT_DIRTY;
> + int max_nr = (end - addr) / PAGE_SIZE;
> + bool any_young;
> +
> + nr = folio_pte_batch(folio, addr, pte, ptent, max_nr,
> + fpb_flags, NULL, &any_young);
> + if (any_young)
> + ptent = pte_mkyoung(ptent);
> +
> + if (nr < folio_nr_pages(folio)) {
> + int err;
> +
> + if (folio_likely_mapped_shared(folio))
> + continue;
> + if (pageout_anon_only_filter && !folio_test_anon(folio))
> + continue;
> + if (!folio_trylock(folio))
> + continue;
> + folio_get(folio);
> + arch_leave_lazy_mmu_mode();
> + pte_unmap_unlock(start_pte, ptl);
> + start_pte = NULL;
> + err = split_folio(folio);
> + folio_unlock(folio);
> + folio_put(folio);
> + start_pte = pte =
> + pte_offset_map_lock(mm, pmd, addr, &ptl);
> + if (!start_pte)
> + break;
> + if (err)
> + continue;
> + arch_enter_lazy_mmu_mode();
Damn, this is still broken; arch_enter_lazy_mmu_mode() needs to be before the
continue. (thanks to Lance Yang; I noticed this while reviewing his MADV_FREE
series).
Andrew, is it possible to fix this up as you add it to mm-unstable, or do you
want me to send a v7?
The change would be:
diff --git a/mm/madvise.c b/mm/madvise.c
index c1377f3b5ca1..bf26cf2b7715 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -486,10 +486,9 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!start_pte)
break;
- if (err)
- continue;
arch_enter_lazy_mmu_mode();
- nr = 0;
+ if (!err)
+ nr = 0;
continue;
}
}
> + nr = 0;
> + continue;
> + }
> }
>
> /*
> * Do not interfere with other mappings of this folio and
> - * non-LRU folio.
> + * non-LRU folio. If we have a large folio at this point, we
> + * know it is fully mapped so if its mapcount is the same as its
> + * number of pages, it must be exclusive.
> */
> - if (!folio_test_lru(folio) || folio_mapcount(folio) != 1)
> + if (!folio_test_lru(folio) ||
> + folio_mapcount(folio) != folio_nr_pages(folio))
> continue;
>
> if (pageout_anon_only_filter && !folio_test_anon(folio))
> continue;
>
> - VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
> -
> if (!pageout && pte_young(ptent)) {
> - ptent = ptep_get_and_clear_full(mm, addr, pte,
> - tlb->fullmm);
> - ptent = pte_mkold(ptent);
> - set_pte_at(mm, addr, pte, ptent);
> - tlb_remove_tlb_entry(tlb, pte, addr);
> + mkold_ptes(vma, addr, pte, nr);
> + tlb_remove_tlb_entries(tlb, pte, nr, addr);
> }
>
> /*
> diff --git a/mm/memory.c b/mm/memory.c
> index ef2968894718..912cd738ec03 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -989,7 +989,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
> flags |= FPB_IGNORE_SOFT_DIRTY;
>
> nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags,
> - &any_writable);
> + &any_writable, NULL);
> folio_ref_add(folio, nr);
> if (folio_test_anon(folio)) {
> if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page,
> @@ -1559,7 +1559,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
> */
> if (unlikely(folio_test_large(folio) && max_nr != 1)) {
> nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags,
> - NULL);
> + NULL, NULL);
>
> zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr,
> addr, details, rss, force_flush,
^ permalink raw reply [flat|nested] 30+ messages in thread