The patch titled
Subject: zswap: fix writeback lock ordering for zsmalloc
has been added to the -mm mm-unstable branch. Its filename is
zswap-fix-writeback-lock-ordering-for-zsmalloc.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/zswap-fix-writeback-lock-ordering-for-zsmalloc.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: zswap: fix writeback lock ordering for zsmalloc
Date: Tue, 8 Nov 2022 11:32:03 -0800
Patch series "Implement writeback for zsmalloc", v3.
Unlike other zswap allocators such as zbud or z3fold, zsmalloc currently
lacks the writeback mechanism. This means that when the zswap pool is
full, it will simply reject further allocations, and the pages will be
written directly to swap.
This series of patches implements writeback for zsmalloc. When the zswap
pool becomes full, zsmalloc will attempt to evict all the compressed
objects in the least-recently used zspages.
This patch (of 3):
zswap's customary lock order is tree->lock before pool->lock, because the
tree->lock protects the entries' refcount, and the free callbacks in the
backends acquire their respective pool locks to dispatch the backing
object. zsmalloc's map callback takes the pool lock, so zswap must not
grab the tree->lock while a handle is mapped. This currently only happens
during writeback, which isn't implemented for zsmalloc. In preparation
for it, move the tree->lock section out of the mapped entry section
Link: https://lkml.kernel.org/r/20221108193207.3297327-1-nphamcs@xxxxxxxxx
Link: https://lkml.kernel.org/r/20221108193207.3297327-2-nphamcs@xxxxxxxxx
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Signed-off-by: Nhat Pham <nphamcs@xxxxxxxxx>
Cc: Dan Streetman <ddstreet@xxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Nitin Gupta <ngupta@xxxxxxxxxx>
Cc: Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx>
Cc: Seth Jennings <sjenning@xxxxxxxxxx>
Cc: Vitaly Wool <vitaly.wool@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/zswap.c | 37 ++++++++++++++++++++-----------------
1 file changed, 20 insertions(+), 17 deletions(-)
--- a/mm/zswap.c~zswap-fix-writeback-lock-ordering-for-zsmalloc
+++ a/mm/zswap.c
@@ -958,7 +958,7 @@ static int zswap_writeback_entry(struct
};
if (!zpool_can_sleep_mapped(pool)) {
- tmp = kmalloc(PAGE_SIZE, GFP_ATOMIC);
+ tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!tmp)
return -ENOMEM;
}
@@ -968,6 +968,7 @@ static int zswap_writeback_entry(struct
swpentry = zhdr->swpentry; /* here */
tree = zswap_trees[swp_type(swpentry)];
offset = swp_offset(swpentry);
+ zpool_unmap_handle(pool, handle);
/* find and ref zswap entry */
spin_lock(&tree->lock);
@@ -975,20 +976,12 @@ static int zswap_writeback_entry(struct
if (!entry) {
/* entry was invalidated */
spin_unlock(&tree->lock);
- zpool_unmap_handle(pool, handle);
kfree(tmp);
return 0;
}
spin_unlock(&tree->lock);
BUG_ON(offset != entry->offset);
- src = (u8 *)zhdr + sizeof(struct zswap_header);
- if (!zpool_can_sleep_mapped(pool)) {
- memcpy(tmp, src, entry->length);
- src = tmp;
- zpool_unmap_handle(pool, handle);
- }
-
/* try to allocate swap cache page */
switch (zswap_get_swap_cache_page(swpentry, &page)) {
case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
@@ -1006,6 +999,14 @@ static int zswap_writeback_entry(struct
acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
dlen = PAGE_SIZE;
+ zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
+ src = (u8 *)zhdr + sizeof(struct zswap_header);
+ if (!zpool_can_sleep_mapped(pool)) {
+ memcpy(tmp, src, entry->length);
+ src = tmp;
+ zpool_unmap_handle(pool, handle);
+ }
+
mutex_lock(acomp_ctx->mutex);
sg_init_one(&input, src, entry->length);
sg_init_table(&output, 1);
@@ -1015,6 +1016,11 @@ static int zswap_writeback_entry(struct
dlen = acomp_ctx->req->dlen;
mutex_unlock(acomp_ctx->mutex);
+ if (!zpool_can_sleep_mapped(pool))
+ kfree(tmp);
+ else
+ zpool_unmap_handle(pool, handle);
+
BUG_ON(ret);
BUG_ON(dlen != PAGE_SIZE);
@@ -1045,7 +1051,11 @@ static int zswap_writeback_entry(struct
zswap_entry_put(tree, entry);
spin_unlock(&tree->lock);
- goto end;
+ return ret;
+
+fail:
+ if (!zpool_can_sleep_mapped(pool))
+ kfree(tmp);
/*
* if we get here due to ZSWAP_SWAPCACHE_EXIST
@@ -1054,17 +1064,10 @@ static int zswap_writeback_entry(struct
* if we free the entry in the following put
* it is also okay to return !0
*/
-fail:
spin_lock(&tree->lock);
zswap_entry_put(tree, entry);
spin_unlock(&tree->lock);
-end:
- if (zpool_can_sleep_mapped(pool))
- zpool_unmap_handle(pool, handle);
- else
- kfree(tmp);
-
return ret;
}
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
fs-fix-leaked-psi-pressure-state.patch
mm-vmscan-make-rotations-a-secondary-factor-in-balancing-anon-vs-file.patch
mm-vmscan-split-khugepaged-stats-from-direct-reclaim-stats.patch
zswap-fix-writeback-lock-ordering-for-zsmalloc.patch
mm-vmscan-fix-extreme-overreclaim-and-swap-floods.patch
