From d2ccde1c8e90d38cee87a1b0309ad2827f3fd30d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 02:45:28 +0000
Subject: [PATCH] add boot partition size
---
kernel/mm/zswap.c | 187 ++++++++++++++++++++++++++--------------------
1 files changed, 106 insertions(+), 81 deletions(-)
diff --git a/kernel/mm/zswap.c b/kernel/mm/zswap.c
index 420225d..b24f761 100644
--- a/kernel/mm/zswap.c
+++ b/kernel/mm/zswap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* zswap.c - zswap driver file
*
@@ -8,16 +9,6 @@
* than reading from the swap device, can also improve workload performance.
*
* Copyright (C) 2012 Seth Jennings <sjenning@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -27,7 +18,7 @@
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
-#include <linux/locallock.h>
+#include <linux/local_lock.h>
#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/frontswap.h>
@@ -42,6 +33,7 @@
#include <linux/swapops.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
+#include <linux/workqueue.h>
/*********************************
* statistics
@@ -75,14 +67,19 @@
/* Duplicate store was encountered (rare) */
static u64 zswap_duplicate_entry;
+/* Shrinker work queue */
+static struct workqueue_struct *shrink_wq;
+/* Pool limit was hit, we need to calm down */
+static bool zswap_pool_reached_full;
+
/*********************************
* tunables
**********************************/
#define ZSWAP_PARAM_UNSET ""
-/* Enable/disable zswap (disabled by default) */
-static bool zswap_enabled;
+/* Enable/disable zswap */
+static bool zswap_enabled = IS_ENABLED(CONFIG_ZSWAP_DEFAULT_ON);
static int zswap_enabled_param_set(const char *,
const struct kernel_param *);
static struct kernel_param_ops zswap_enabled_param_ops = {
@@ -92,8 +89,7 @@
module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644);
/* Crypto compressor to use */
-#define ZSWAP_COMPRESSOR_DEFAULT "lzo"
-static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
+static char *zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT;
static int zswap_compressor_param_set(const char *,
const struct kernel_param *);
static struct kernel_param_ops zswap_compressor_param_ops = {
@@ -105,8 +101,7 @@
&zswap_compressor, 0644);
/* Compressed storage zpool to use */
-#define ZSWAP_ZPOOL_DEFAULT "zbud"
-static char *zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
+static char *zswap_zpool_type = CONFIG_ZSWAP_ZPOOL_DEFAULT;
static int zswap_zpool_param_set(const char *, const struct kernel_param *);
static struct kernel_param_ops zswap_zpool_param_ops = {
.set = zswap_zpool_param_set,
@@ -118,6 +113,11 @@
/* The maximum percentage of memory that the compressed pool can occupy */
static unsigned int zswap_max_pool_percent = 20;
module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644);
+
+/* The threshold for accepting new pages after the max_pool_percent was hit */
+static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */
+module_param_named(accept_threshold_percent, zswap_accept_thr_percent,
+ uint, 0644);
/* Enable/disable handling same-value filled pages (enabled by default) */
static bool zswap_same_filled_pages_enabled = true;
@@ -133,7 +133,8 @@
struct crypto_comp * __percpu *tfm;
struct kref kref;
struct list_head list;
- struct work_struct work;
+ struct work_struct release_work;
+ struct work_struct shrink_work;
struct hlist_node node;
char tfm_name[CRYPTO_MAX_ALG_NAME];
};
@@ -220,8 +221,15 @@
static bool zswap_is_full(void)
{
- return totalram_pages * zswap_max_pool_percent / 100 <
- DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+ return totalram_pages() * zswap_max_pool_percent / 100 <
+ DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+}
+
+static bool zswap_can_accept(void)
+{
+ return totalram_pages() * zswap_accept_thr_percent / 100 *
+ zswap_max_pool_percent / 100 >
+ DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
}
static void zswap_update_total_size(void)
@@ -380,27 +388,37 @@
/*********************************
* per-cpu code
**********************************/
-static DEFINE_PER_CPU(u8 *, zswap_dstmem);
+struct zswap_comp {
+ /* Used for per-CPU dstmem and tfm */
+ local_lock_t lock;
+ u8 *dstmem;
+};
+
+static DEFINE_PER_CPU(struct zswap_comp, zswap_comp) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
static int zswap_dstmem_prepare(unsigned int cpu)
{
+ struct zswap_comp *zcomp;
u8 *dst;
dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
if (!dst)
return -ENOMEM;
- per_cpu(zswap_dstmem, cpu) = dst;
+ zcomp = per_cpu_ptr(&zswap_comp, cpu);
+ zcomp->dstmem = dst;
return 0;
}
static int zswap_dstmem_dead(unsigned int cpu)
{
- u8 *dst;
+ struct zswap_comp *zcomp;
- dst = per_cpu(zswap_dstmem, cpu);
- kfree(dst);
- per_cpu(zswap_dstmem, cpu) = NULL;
+ zcomp = per_cpu_ptr(&zswap_comp, cpu);
+ kfree(zcomp->dstmem);
+ zcomp->dstmem = NULL;
return 0;
}
@@ -511,6 +529,16 @@
return NULL;
}
+static void shrink_worker(struct work_struct *w)
+{
+ struct zswap_pool *pool = container_of(w, typeof(*pool),
+ shrink_work);
+
+ if (zpool_shrink(pool->zpool, 1, NULL))
+ zswap_reject_reclaim_fail++;
+ zswap_pool_put(pool);
+}
+
static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
{
struct zswap_pool *pool;
@@ -561,6 +589,7 @@
*/
kref_init(&pool->kref);
INIT_LIST_HEAD(&pool->list);
+ INIT_WORK(&pool->shrink_work, shrink_worker);
zswap_pool_debug("created", pool);
@@ -579,11 +608,12 @@
bool has_comp, has_zpool;
has_comp = crypto_has_comp(zswap_compressor, 0, 0);
- if (!has_comp && strcmp(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT)) {
+ if (!has_comp && strcmp(zswap_compressor,
+ CONFIG_ZSWAP_COMPRESSOR_DEFAULT)) {
pr_err("compressor %s not available, using default %s\n",
- zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT);
+ zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT);
param_free_charp(&zswap_compressor);
- zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
+ zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT;
has_comp = crypto_has_comp(zswap_compressor, 0, 0);
}
if (!has_comp) {
@@ -594,11 +624,12 @@
}
has_zpool = zpool_has_pool(zswap_zpool_type);
- if (!has_zpool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
+ if (!has_zpool && strcmp(zswap_zpool_type,
+ CONFIG_ZSWAP_ZPOOL_DEFAULT)) {
pr_err("zpool %s not available, using default %s\n",
- zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT);
+ zswap_zpool_type, CONFIG_ZSWAP_ZPOOL_DEFAULT);
param_free_charp(&zswap_zpool_type);
- zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
+ zswap_zpool_type = CONFIG_ZSWAP_ZPOOL_DEFAULT;
has_zpool = zpool_has_pool(zswap_zpool_type);
}
if (!has_zpool) {
@@ -634,7 +665,8 @@
static void __zswap_pool_release(struct work_struct *work)
{
- struct zswap_pool *pool = container_of(work, typeof(*pool), work);
+ struct zswap_pool *pool = container_of(work, typeof(*pool),
+ release_work);
synchronize_rcu();
@@ -657,8 +689,8 @@
list_del_rcu(&pool->list);
- INIT_WORK(&pool->work, __zswap_pool_release);
- schedule_work(&pool->work);
+ INIT_WORK(&pool->release_work, __zswap_pool_release);
+ schedule_work(&pool->release_work);
spin_unlock(&zswap_pools_lock);
}
@@ -866,7 +898,6 @@
/* extract swpentry from data */
zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
swpentry = zhdr->swpentry; /* here */
- zpool_unmap_handle(pool, handle);
tree = zswap_trees[swp_type(swpentry)];
offset = swp_offset(swpentry);
@@ -876,6 +907,7 @@
if (!entry) {
/* entry was invalidated */
spin_unlock(&tree->lock);
+ zpool_unmap_handle(pool, handle);
return 0;
}
spin_unlock(&tree->lock);
@@ -896,15 +928,14 @@
case ZSWAP_SWAPCACHE_NEW: /* page is locked */
/* decompress */
dlen = PAGE_SIZE;
- src = (u8 *)zpool_map_handle(entry->pool->zpool, entry->handle,
- ZPOOL_MM_RO) + sizeof(struct zswap_header);
+ src = (u8 *)zhdr + sizeof(struct zswap_header);
dst = kmap_atomic(page);
- tfm = *get_cpu_ptr(entry->pool->tfm);
+ local_lock(&zswap_comp.lock);
+ tfm = *this_cpu_ptr(entry->pool->tfm);
ret = crypto_comp_decompress(tfm, src, entry->length,
dst, &dlen);
- put_cpu_ptr(entry->pool->tfm);
+ local_unlock(&zswap_comp.lock);
kunmap_atomic(dst);
- zpool_unmap_handle(entry->pool->zpool, entry->handle);
BUG_ON(ret);
BUG_ON(dlen != PAGE_SIZE);
@@ -950,22 +981,7 @@
spin_unlock(&tree->lock);
end:
- return ret;
-}
-
-static int zswap_shrink(void)
-{
- struct zswap_pool *pool;
- int ret;
-
- pool = zswap_pool_last_get();
- if (!pool)
- return -ENOENT;
-
- ret = zpool_shrink(pool->zpool, 1, NULL);
-
- zswap_pool_put(pool);
-
+ zpool_unmap_handle(pool, handle);
return ret;
}
@@ -991,8 +1007,6 @@
memset_l(page, value, PAGE_SIZE / sizeof(unsigned long));
}
-/* protect zswap_dstmem from concurrency */
-static DEFINE_LOCAL_IRQ_LOCK(zswap_dstmem_lock);
/*********************************
* frontswap hooks
**********************************/
@@ -1009,6 +1023,7 @@
char *buf;
u8 *src, *dst;
struct zswap_header zhdr = { .swpentry = swp_entry(type, offset) };
+ gfp_t gfp;
/* THP isn't supported */
if (PageTransHuge(page)) {
@@ -1023,21 +1038,23 @@
/* reclaim space if needed */
if (zswap_is_full()) {
- zswap_pool_limit_hit++;
- if (zswap_shrink()) {
- zswap_reject_reclaim_fail++;
- ret = -ENOMEM;
- goto reject;
- }
+ struct zswap_pool *pool;
- /* A second zswap_is_full() check after
- * zswap_shrink() to make sure it's now
- * under the max_pool_percent
- */
- if (zswap_is_full()) {
+ zswap_pool_limit_hit++;
+ zswap_pool_reached_full = true;
+ pool = zswap_pool_last_get();
+ if (pool)
+ queue_work(shrink_wq, &pool->shrink_work);
+ ret = -ENOMEM;
+ goto reject;
+ }
+
+ if (zswap_pool_reached_full) {
+ if (!zswap_can_accept()) {
ret = -ENOMEM;
goto reject;
- }
+ } else
+ zswap_pool_reached_full = false;
}
/* allocate entry */
@@ -1069,7 +1086,8 @@
}
/* compress */
- dst = get_locked_var(zswap_dstmem_lock, zswap_dstmem);
+ local_lock(&zswap_comp.lock);
+ dst = *this_cpu_ptr(&zswap_comp.dstmem);
tfm = *this_cpu_ptr(entry->pool->tfm);
src = kmap_atomic(page);
ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
@@ -1081,9 +1099,10 @@
/* store */
hlen = zpool_evictable(entry->pool->zpool) ? sizeof(zhdr) : 0;
- ret = zpool_malloc(entry->pool->zpool, hlen + dlen,
- __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM,
- &handle);
+ gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+ if (zpool_malloc_support_movable(entry->pool->zpool))
+ gfp |= __GFP_HIGHMEM | __GFP_MOVABLE;
+ ret = zpool_malloc(entry->pool->zpool, hlen + dlen, gfp, &handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
goto put_dstmem;
@@ -1096,7 +1115,7 @@
memcpy(buf, &zhdr, hlen);
memcpy(buf + hlen, dst, dlen);
zpool_unmap_handle(entry->pool->zpool, handle);
- put_locked_var(zswap_dstmem_lock, zswap_dstmem);
+ local_unlock(&zswap_comp.lock);
/* populate entry */
entry->offset = offset;
@@ -1124,7 +1143,7 @@
return 0;
put_dstmem:
- put_locked_var(zswap_dstmem_lock, zswap_dstmem);
+ local_unlock(&zswap_comp.lock);
zswap_pool_put(entry->pool);
freepage:
zswap_entry_cache_free(entry);
@@ -1169,9 +1188,10 @@
if (zpool_evictable(entry->pool->zpool))
src += sizeof(struct zswap_header);
dst = kmap_atomic(page);
- tfm = *get_cpu_ptr(entry->pool->tfm);
+ local_lock(&zswap_comp.lock);
+ tfm = *this_cpu_ptr(entry->pool->tfm);
ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen);
- put_cpu_ptr(entry->pool->tfm);
+ local_unlock(&zswap_comp.lock);
kunmap_atomic(dst);
zpool_unmap_handle(entry->pool->zpool, entry->handle);
BUG_ON(ret);
@@ -1264,8 +1284,6 @@
return -ENODEV;
zswap_debugfs_root = debugfs_create_dir("zswap", NULL);
- if (!zswap_debugfs_root)
- return -ENOMEM;
debugfs_create_u64("pool_limit_hit", 0444,
zswap_debugfs_root, &zswap_pool_limit_hit);
@@ -1344,11 +1362,18 @@
zswap_enabled = false;
}
+ shrink_wq = create_workqueue("zswap-shrink");
+ if (!shrink_wq)
+ goto fallback_fail;
+
frontswap_register_ops(&zswap_frontswap_ops);
if (zswap_debugfs_init())
pr_warn("debugfs initialization failed\n");
return 0;
+fallback_fail:
+ if (pool)
+ zswap_pool_destroy(pool);
hp_fail:
cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
dstmem_fail:
--
Gitblit v1.6.2