| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAF8kJuM1RKjTsZZjDRWW-Kz=i8kfq4zVD6K8r=z03oBJ1dgk8g@mail.gmail.com>
Date: Sat, 2 Mar 2024 13:32:33 -0800
From: Chris Li <chrisl@...nel.org>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Yosry Ahmed <yosryahmed@...gle.com>, Nhat Pham <nphamcs@...il.com>,
Johannes Weiner <hannes@...xchg.org>, "Matthew Wilcox (Oracle)" <willy@...radead.org>,
Chengming Zhou <zhouchengming@...edance.com>, Barry Song <v-songbaohua@...o.com>
Subject: Re: [PATCH v3] zswap: replace RB tree with xarray
I have finally set up my own kernel compile machine. My home test
machine is slower and has less cores(12).
The kernel compile test is based on Chengming's test script with minor
modification to do loops.
Run the kernel build testing 10 times for each version, averages:
(memory.max=2GB, zswap shrinker and writeback enabled, one 50GB swapfile.)
mm-9a0181a3710eb xarray v3
user 3526.829 3526.842
sys 532.754 524.310
real 198.748 198.206
So there is about 1.5% improvement on sys time according to my test.
Chris
On Sat, Mar 2, 2024 at 12:16 PM Chris Li <chrisl@...nel.org> wrote:
>
> Very deep RB tree requires rebalance at times. That
> contributes to the zswap fault latencies. Xarray does not
> need to perform tree rebalance. Replacing RB tree to xarray
> can have some small performance gain.
>
> One small difference is that xarray insert might fail with
> ENOMEM, while RB tree insert does not allocate additional
> memory.
>
> The zswap_entry size will reduce a bit due to removing the
> RB node, which has two pointers and a color field. Xarray
> store the pointer in the xarray tree rather than the
> zswap_entry. Every entry has one pointer from the xarray
> tree. Overall, switching to xarray should save some memory,
> if the swap entries are densely packed.
>
> Notice the zswap_rb_search and zswap_rb_insert always
> followed by zswap_rb_erase. Fold the entry erase into
> zswap_xa_search_and_erase and zswap_xa_insert. That saves
> one tree lookup as well.
>
> Remove zswap_invalidate_entry due to no need to call
> zswap_rb_erase any more. Use zswap_free_entry instead.
>
> The "struct zswap_tree" has been replaced by "struct xarray".
> The tree spin lock has transferred to the xarray lock.
>
> ---
>
>
> Signed-off-by: Chris Li <chrisl@...nel.org>
> ---
> Changes in v3:
> - Use xa_cmpxchg instead of zswap_xa_search_and_delete in zswap_writeback_entry.
> - Use xa_store in zswap_xa_insert directly. Reduce the scope of spinlock.
> - Fix xa_store error handling for same page fill case.
> - Link to v2: https://lore.kernel.org/r/20240229-zswap-xarray-v2-1-e50284dfcdb1@kernel.org
>
> Changes in v2:
> - Replace struct zswap_tree with struct xarray.
> - Remove zswap_tree spinlock, use xarray lock instead.
> - Fold zswap_rb_erase() into zswap_xa_search_and_delete() and zswap_xa_insert().
> - Delete zswap_invalidate_entry(), use zswap_free_entry() instead.
> - Link to v1: https://lore.kernel.org/r/20240117-zswap-xarray-v1-0-6daa86c08fae@kernel.org
> ---
> mm/zswap.c | 174 +++++++++++++++++++++++--------------------------------------
> 1 file changed, 64 insertions(+), 110 deletions(-)
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 011e068eb355..9d0bfe077ff1 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -20,7 +20,6 @@
> #include <linux/spinlock.h>
> #include <linux/types.h>
> #include <linux/atomic.h>
> -#include <linux/rbtree.h>
> #include <linux/swap.h>
> #include <linux/crypto.h>
> #include <linux/scatterlist.h>
> @@ -71,6 +70,8 @@ static u64 zswap_reject_compress_poor;
> static u64 zswap_reject_alloc_fail;
> /* Store failed because the entry metadata could not be allocated (rare) */
> static u64 zswap_reject_kmemcache_fail;
> +/* Store failed because xarray can't insert the entry*/
> +static u64 zswap_reject_xarray_fail;
>
> /* Shrinker work queue */
> static struct workqueue_struct *shrink_wq;
> @@ -196,7 +197,6 @@ static struct {
> * This structure contains the metadata for tracking a single compressed
> * page within zswap.
> *
> - * rbnode - links the entry into red-black tree for the appropriate swap type
> * swpentry - associated swap entry, the offset indexes into the red-black tree
> * length - the length in bytes of the compressed page data. Needed during
> * decompression. For a same value filled page length is 0, and both
> @@ -208,7 +208,6 @@ static struct {
> * lru - handle to the pool's lru used to evict pages.
> */
> struct zswap_entry {
> - struct rb_node rbnode;
> swp_entry_t swpentry;
> unsigned int length;
> struct zswap_pool *pool;
> @@ -220,12 +219,7 @@ struct zswap_entry {
> struct list_head lru;
> };
>
> -struct zswap_tree {
> - struct rb_root rbroot;
> - spinlock_t lock;
> -};
> -
> -static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
> +static struct xarray *zswap_trees[MAX_SWAPFILES];
> static unsigned int nr_zswap_trees[MAX_SWAPFILES];
>
> /* RCU-protected iteration */
> @@ -253,10 +247,10 @@ static bool zswap_has_pool;
> * helpers and fwd declarations
> **********************************/
>
> -static inline struct zswap_tree *swap_zswap_tree(swp_entry_t swp)
> +static inline struct xarray *swap_zswap_tree(swp_entry_t swp)
> {
> - return &zswap_trees[swp_type(swp)][swp_offset(swp)
> - >> SWAP_ADDRESS_SPACE_SHIFT];
> + return zswap_trees[swp_type(swp)] + (swp_offset(swp)
> + >> SWAP_ADDRESS_SPACE_SHIFT);
> }
>
> #define zswap_pool_debug(msg, p) \
> @@ -805,60 +799,37 @@ void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg)
> }
>
> /*********************************
> -* rbtree functions
> +* xarray functions
> **********************************/
> -static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset)
> +static struct zswap_entry *zswap_xa_search_and_erase(struct xarray *tree, pgoff_t offset)
> {
> - struct rb_node *node = root->rb_node;
> - struct zswap_entry *entry;
> - pgoff_t entry_offset;
> -
> - while (node) {
> - entry = rb_entry(node, struct zswap_entry, rbnode);
> - entry_offset = swp_offset(entry->swpentry);
> - if (entry_offset > offset)
> - node = node->rb_left;
> - else if (entry_offset < offset)
> - node = node->rb_right;
> - else
> - return entry;
> - }
> - return NULL;
> + return xa_erase(tree, offset);
> }
>
> /*
> * In the case that a entry with the same offset is found, a pointer to
> - * the existing entry is stored in dupentry and the function returns -EEXIST
> + * the existing entry is stored in old and erased from the tree.
> + * Function return error on insert.
> */
> -static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry,
> - struct zswap_entry **dupentry)
> +static int zswap_xa_insert(struct xarray *tree, struct zswap_entry *entry,
> + struct zswap_entry **old)
> {
> - struct rb_node **link = &root->rb_node, *parent = NULL;
> - struct zswap_entry *myentry;
> - pgoff_t myentry_offset, entry_offset = swp_offset(entry->swpentry);
> -
> - while (*link) {
> - parent = *link;
> - myentry = rb_entry(parent, struct zswap_entry, rbnode);
> - myentry_offset = swp_offset(myentry->swpentry);
> - if (myentry_offset > entry_offset)
> - link = &(*link)->rb_left;
> - else if (myentry_offset < entry_offset)
> - link = &(*link)->rb_right;
> - else {
> - *dupentry = myentry;
> - return -EEXIST;
> - }
> - }
> - rb_link_node(&entry->rbnode, parent, link);
> - rb_insert_color(&entry->rbnode, root);
> - return 0;
> -}
> + int err;
> + struct zswap_entry *e;
> + pgoff_t offset = swp_offset(entry->swpentry);
>
> -static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
> -{
> - rb_erase(&entry->rbnode, root);
> - RB_CLEAR_NODE(&entry->rbnode);
> + e = xa_store(tree, offset, entry, GFP_KERNEL);
> + err = xa_err(e);
> +
> + if (err) {
> + e = xa_erase(tree, offset);
> + if (err == -ENOMEM)
> + zswap_reject_alloc_fail++;
> + else
> + zswap_reject_xarray_fail++;
> + }
> + *old = e;
> + return err;
> }
>
> /*********************************
> @@ -872,7 +843,6 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid)
> entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid);
> if (!entry)
> return NULL;
> - RB_CLEAR_NODE(&entry->rbnode);
> return entry;
> }
>
> @@ -914,17 +884,6 @@ static void zswap_entry_free(struct zswap_entry *entry)
> zswap_update_total_size();
> }
>
> -/*
> - * The caller hold the tree lock and search the entry from the tree,
> - * so it must be on the tree, remove it from the tree and free it.
> - */
> -static void zswap_invalidate_entry(struct zswap_tree *tree,
> - struct zswap_entry *entry)
> -{
> - zswap_rb_erase(&tree->rbroot, entry);
> - zswap_entry_free(entry);
> -}
> -
> /*********************************
> * compressed storage functions
> **********************************/
> @@ -1113,7 +1072,9 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
> static int zswap_writeback_entry(struct zswap_entry *entry,
> swp_entry_t swpentry)
> {
> - struct zswap_tree *tree;
> + struct xarray *tree;
> + pgoff_t offset = swp_offset(swpentry);
> + struct zswap_entry *e;
> struct folio *folio;
> struct mempolicy *mpol;
> bool folio_was_allocated;
> @@ -1150,19 +1111,14 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
> * be dereferenced.
> */
> tree = swap_zswap_tree(swpentry);
> - spin_lock(&tree->lock);
> - if (zswap_rb_search(&tree->rbroot, swp_offset(swpentry)) != entry) {
> - spin_unlock(&tree->lock);
> + e = xa_cmpxchg(tree, offset, entry, NULL, GFP_KERNEL);
> + if (e != entry) {
> delete_from_swap_cache(folio);
> folio_unlock(folio);
> folio_put(folio);
> return -ENOMEM;
> }
>
> - /* Safe to deref entry after the entry is verified above. */
> - zswap_rb_erase(&tree->rbroot, entry);
> - spin_unlock(&tree->lock);
> -
> zswap_decompress(entry, &folio->page);
>
> count_vm_event(ZSWPWB);
> @@ -1471,10 +1427,11 @@ bool zswap_store(struct folio *folio)
> {
> swp_entry_t swp = folio->swap;
> pgoff_t offset = swp_offset(swp);
> - struct zswap_tree *tree = swap_zswap_tree(swp);
> - struct zswap_entry *entry, *dupentry;
> + struct xarray *tree = swap_zswap_tree(swp);
> + struct zswap_entry *entry, *old;
> struct obj_cgroup *objcg = NULL;
> struct mem_cgroup *memcg = NULL;
> + int err;
>
> VM_WARN_ON_ONCE(!folio_test_locked(folio));
> VM_WARN_ON_ONCE(!folio_test_swapcache(folio));
> @@ -1526,6 +1483,7 @@ bool zswap_store(struct folio *folio)
> kunmap_local(src);
> entry->length = 0;
> entry->value = value;
> + entry->pool = NULL;
> atomic_inc(&zswap_same_filled_pages);
> goto insert_entry;
> }
> @@ -1562,21 +1520,21 @@ bool zswap_store(struct folio *folio)
> }
>
> /* map */
> - spin_lock(&tree->lock);
> /*
> * The folio may have been dirtied again, invalidate the
> * possibly stale entry before inserting the new entry.
> */
> - if (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) {
> - zswap_invalidate_entry(tree, dupentry);
> - WARN_ON(zswap_rb_insert(&tree->rbroot, entry, &dupentry));
> - }
> + err = zswap_xa_insert(tree, entry, &old);
> + if (old)
> + zswap_entry_free(old);
> + if (err)
> + goto insert_failed;
> +
> if (entry->length) {
> INIT_LIST_HEAD(&entry->lru);
> zswap_lru_add(&zswap.list_lru, entry);
> atomic_inc(&zswap.nr_stored);
> }
> - spin_unlock(&tree->lock);
>
> /* update stats */
> atomic_inc(&zswap_stored_pages);
> @@ -1585,6 +1543,12 @@ bool zswap_store(struct folio *folio)
>
> return true;
>
> +insert_failed:
> + if (!entry->length) {
> + atomic_dec(&zswap_same_filled_pages);
> + goto freepage;
> + }
> + zpool_free(zswap_find_zpool(entry), entry->handle);
> put_pool:
> zswap_pool_put(entry->pool);
> freepage:
> @@ -1598,11 +1562,9 @@ bool zswap_store(struct folio *folio)
> * possibly stale entry which was previously stored at this offset.
> * Otherwise, writeback could overwrite the new data in the swapfile.
> */
> - spin_lock(&tree->lock);
> - entry = zswap_rb_search(&tree->rbroot, offset);
> + entry = zswap_xa_search_and_erase(tree, offset);
> if (entry)
> - zswap_invalidate_entry(tree, entry);
> - spin_unlock(&tree->lock);
> + zswap_entry_free(entry);
> return false;
>
> shrink:
> @@ -1615,20 +1577,15 @@ bool zswap_load(struct folio *folio)
> swp_entry_t swp = folio->swap;
> pgoff_t offset = swp_offset(swp);
> struct page *page = &folio->page;
> - struct zswap_tree *tree = swap_zswap_tree(swp);
> + struct xarray *tree = swap_zswap_tree(swp);
> struct zswap_entry *entry;
> u8 *dst;
>
> VM_WARN_ON_ONCE(!folio_test_locked(folio));
>
> - spin_lock(&tree->lock);
> - entry = zswap_rb_search(&tree->rbroot, offset);
> - if (!entry) {
> - spin_unlock(&tree->lock);
> + entry = zswap_xa_search_and_erase(tree, offset);
> + if (!entry)
> return false;
> - }
> - zswap_rb_erase(&tree->rbroot, entry);
> - spin_unlock(&tree->lock);
>
> if (entry->length)
> zswap_decompress(entry, page);
> @@ -1652,19 +1609,17 @@ bool zswap_load(struct folio *folio)
> void zswap_invalidate(swp_entry_t swp)
> {
> pgoff_t offset = swp_offset(swp);
> - struct zswap_tree *tree = swap_zswap_tree(swp);
> + struct xarray *tree = swap_zswap_tree(swp);
> struct zswap_entry *entry;
>
> - spin_lock(&tree->lock);
> - entry = zswap_rb_search(&tree->rbroot, offset);
> + entry = zswap_xa_search_and_erase(tree, offset);
> if (entry)
> - zswap_invalidate_entry(tree, entry);
> - spin_unlock(&tree->lock);
> + zswap_entry_free(entry);
> }
>
> int zswap_swapon(int type, unsigned long nr_pages)
> {
> - struct zswap_tree *trees, *tree;
> + struct xarray *trees, *tree;
> unsigned int nr, i;
>
> nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
> @@ -1674,11 +1629,8 @@ int zswap_swapon(int type, unsigned long nr_pages)
> return -ENOMEM;
> }
>
> - for (i = 0; i < nr; i++) {
> - tree = trees + i;
> - tree->rbroot = RB_ROOT;
> - spin_lock_init(&tree->lock);
> - }
> + for (i = 0; i < nr; i++)
> + xa_init(trees + i);
>
> nr_zswap_trees[type] = nr;
> zswap_trees[type] = trees;
> @@ -1687,7 +1639,7 @@ int zswap_swapon(int type, unsigned long nr_pages)
>
> void zswap_swapoff(int type)
> {
> - struct zswap_tree *trees = zswap_trees[type];
> + struct xarray *trees = zswap_trees[type];
> unsigned int i;
>
> if (!trees)
> @@ -1695,7 +1647,7 @@ void zswap_swapoff(int type)
>
> /* try_to_unuse() invalidated all the entries already */
> for (i = 0; i < nr_zswap_trees[type]; i++)
> - WARN_ON_ONCE(!RB_EMPTY_ROOT(&trees[i].rbroot));
> + WARN_ON_ONCE(!xa_empty(trees + i));
>
> kvfree(trees);
> nr_zswap_trees[type] = 0;
> @@ -1727,6 +1679,8 @@ static int zswap_debugfs_init(void)
> zswap_debugfs_root, &zswap_reject_kmemcache_fail);
> debugfs_create_u64("reject_compress_fail", 0444,
> zswap_debugfs_root, &zswap_reject_compress_fail);
> + debugfs_create_u64("reject_xarray_fail", 0444,
> + zswap_debugfs_root, &zswap_reject_xarray_fail);
> debugfs_create_u64("reject_compress_poor", 0444,
> zswap_debugfs_root, &zswap_reject_compress_poor);
> debugfs_create_u64("written_back_pages", 0444,
>
> ---
> base-commit: 9a0181a3710eba1f5c6d19eadcca888be3d54e4f
> change-id: 20240104-zswap-xarray-716260e541e3
>
> Best regards,
> --
> Chris Li <chrisl@...nel.org>
>
>
Powered by blists - more mailing lists