| 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: <qh2p3k5c2ulb5g2zmckhrm4o2eoruatb5lnumkrwrvmsxwcn3s@nh5vx4kjn5in>
Date: Wed, 7 Jan 2026 00:23:25 +0000
From: Yosry Ahmed <yosry.ahmed@...ux.dev>
To: Sergey Senozhatsky <senozhatsky@...omium.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Nhat Pham <nphamcs@...il.com>, Minchan Kim <minchan@...nel.org>,
Johannes Weiner <hannes@...xchg.org>, Brian Geffon <bgeffon@...gle.com>, linux-kernel@...r.kernel.org,
linux-mm@...ck.org
Subject: Re: [PATCH] zsmalloc: use actual object size to detect spans
On Tue, Jan 06, 2026 at 01:25:07PM +0900, Sergey Senozhatsky wrote:
> Using class->size to detect spanning objects is not entirely correct,
> because some size classes can hold a range of object sizes of up to
> class->size bytes in length, due to size-classes merge. Such classes
> use padding for cases when actually written objects are smaller than
> class->size. zs_obj_read_begin() can incorrectly hit the slow path
> and perform memcpy of such objects, basically copying padding bytes.
> Instead of class->size zs_obj_read_begin() should use the actual
> compressed object length (both zram and zswap know it) so that it can
> correctly handle situations when a written object is small enough to
> fit into the first physical page.
>
> Signed-off-by: Sergey Senozhatsky <senozhatsky@...omium.org>
> ---
> drivers/block/zram/zram_drv.c | 14 ++++++++------
> include/linux/zsmalloc.h | 4 ++--
> mm/zsmalloc.c | 16 ++++++++++++----
> mm/zswap.c | 5 +++--
> 4 files changed, 25 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
> index a6587bed6a03..76a54eabe889 100644
> --- a/drivers/block/zram/zram_drv.c
> +++ b/drivers/block/zram/zram_drv.c
> @@ -2065,11 +2065,11 @@ static int read_incompressible_page(struct zram *zram, struct page *page,
> void *src, *dst;
>
> handle = get_slot_handle(zram, index);
> - src = zs_obj_read_begin(zram->mem_pool, handle, NULL);
> + src = zs_obj_read_begin(zram->mem_pool, handle, PAGE_SIZE, NULL);
> dst = kmap_local_page(page);
> copy_page(dst, src);
> kunmap_local(dst);
> - zs_obj_read_end(zram->mem_pool, handle, src);
> + zs_obj_read_end(zram->mem_pool, handle, PAGE_SIZE, src);
>
> return 0;
> }
> @@ -2087,11 +2087,12 @@ static int read_compressed_page(struct zram *zram, struct page *page, u32 index)
> prio = get_slot_comp_priority(zram, index);
>
> zstrm = zcomp_stream_get(zram->comps[prio]);
> - src = zs_obj_read_begin(zram->mem_pool, handle, zstrm->local_copy);
> + src = zs_obj_read_begin(zram->mem_pool, handle, size,
> + zstrm->local_copy);
> dst = kmap_local_page(page);
> ret = zcomp_decompress(zram->comps[prio], zstrm, src, size, dst);
> kunmap_local(dst);
> - zs_obj_read_end(zram->mem_pool, handle, src);
> + zs_obj_read_end(zram->mem_pool, handle, size, src);
> zcomp_stream_put(zstrm);
>
> return ret;
> @@ -2114,9 +2115,10 @@ static int read_from_zspool_raw(struct zram *zram, struct page *page, u32 index)
> * takes place here, as we read raw compressed data.
> */
> zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
> - src = zs_obj_read_begin(zram->mem_pool, handle, zstrm->local_copy);
> + src = zs_obj_read_begin(zram->mem_pool, handle, size,
> + zstrm->local_copy);
> memcpy_to_page(page, 0, src, size);
> - zs_obj_read_end(zram->mem_pool, handle, src);
> + zs_obj_read_end(zram->mem_pool, handle, size, src);
> zcomp_stream_put(zstrm);
>
> return 0;
> diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
> index f3ccff2d966c..5565c3171007 100644
> --- a/include/linux/zsmalloc.h
> +++ b/include/linux/zsmalloc.h
> @@ -40,9 +40,9 @@ unsigned int zs_lookup_class_index(struct zs_pool *pool, unsigned int size);
> void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats);
>
> void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
> - void *local_copy);
> + size_t mem_len, void *local_copy);
> void zs_obj_read_end(struct zs_pool *pool, unsigned long handle,
> - void *handle_mem);
> + size_t mem_len, void *handle_mem);
> void zs_obj_write(struct zs_pool *pool, unsigned long handle,
> void *handle_mem, size_t mem_len);
>
> diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
> index 84da164dcbc5..ab7767d9d87d 100644
> --- a/mm/zsmalloc.c
> +++ b/mm/zsmalloc.c
> @@ -1065,7 +1065,7 @@ unsigned long zs_get_total_pages(struct zs_pool *pool)
> EXPORT_SYMBOL_GPL(zs_get_total_pages);
>
> void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
> - void *local_copy)
> + size_t mem_len, void *local_copy)
> {
> struct zspage *zspage;
> struct zpdesc *zpdesc;
> @@ -1087,7 +1087,11 @@ void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
> class = zspage_class(pool, zspage);
> off = offset_in_page(class->size * obj_idx);
>
> - if (off + class->size <= PAGE_SIZE) {
> + /* Normal classes have inlined handle */
> + if (!ZsHugePage(zspage))
> + mem_len += ZS_HANDLE_SIZE;
Instead of modifying mem_len, can we modify 'off' like zs_obj_write()
and zs_obj_read_end()? I think this can actually be done as a prequel to
this patch. Arguably, it makes more sense as we avoid unnecessarily
copying the handle (completely untested):
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 5bf832f9c05c..48c288da43b8 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1087,6 +1087,9 @@ void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
class = zspage_class(pool, zspage);
off = offset_in_page(class->size * obj_idx);
+ if (!ZsHugePage(zspage))
+ off += ZS_HANDLE_SIZE;
+
if (off + class->size <= PAGE_SIZE) {
/* this object is contained entirely within a page */
addr = kmap_local_zpdesc(zpdesc);
@@ -1107,9 +1110,6 @@ void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
0, sizes[1]);
}
- if (!ZsHugePage(zspage))
- addr += ZS_HANDLE_SIZE;
-
return addr;
}
EXPORT_SYMBOL_GPL(zs_obj_read_begin);
@@ -1129,9 +1129,10 @@ void zs_obj_read_end(struct zs_pool *pool, unsigned long handle,
class = zspage_class(pool, zspage);
off = offset_in_page(class->size * obj_idx);
+ if (!ZsHugePage(zspage))
+ off += ZS_HANDLE_SIZE;
+
if (off + class->size <= PAGE_SIZE) {
- if (!ZsHugePage(zspage))
- off += ZS_HANDLE_SIZE;
handle_mem -= off;
kunmap_local(handle_mem);
}
---
Does this work?
> +
> + if (off + mem_len <= PAGE_SIZE) {
> /* this object is contained entirely within a page */
> addr = kmap_local_zpdesc(zpdesc);
> addr += off;
In the else case below (spanning object), should we also use mem_len
instead of class->size to determine the copy size?
> @@ -1115,7 +1119,7 @@ void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
> EXPORT_SYMBOL_GPL(zs_obj_read_begin);
>
> void zs_obj_read_end(struct zs_pool *pool, unsigned long handle,
> - void *handle_mem)
> + size_t mem_len, void *handle_mem)
> {
> struct zspage *zspage;
> struct zpdesc *zpdesc;
> @@ -1129,7 +1133,11 @@ void zs_obj_read_end(struct zs_pool *pool, unsigned long handle,
> class = zspage_class(pool, zspage);
> off = offset_in_page(class->size * obj_idx);
>
> - if (off + class->size <= PAGE_SIZE) {
> + /* Normal classes have inlined handle */
> + if (!ZsHugePage(zspage))
> + mem_len += ZS_HANDLE_SIZE;
> +
> + if (off + mem_len <= PAGE_SIZE) {
> if (!ZsHugePage(zspage))
> off += ZS_HANDLE_SIZE;
With the proposed prequel patch, I think we won't need to handle
ZS_HANDLE_SIZE twice here. WDYT? Did I miss sth?
> handle_mem -= off;
> diff --git a/mm/zswap.c b/mm/zswap.c
> index de8858ff1521..a3811b05ab57 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -937,7 +937,8 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
> u8 *src, *obj;
>
> acomp_ctx = acomp_ctx_get_cpu_lock(pool);
> - obj = zs_obj_read_begin(pool->zs_pool, entry->handle, acomp_ctx->buffer);
> + obj = zs_obj_read_begin(pool->zs_pool, entry->handle, entry->length,
> + acomp_ctx->buffer);
>
> /* zswap entries of length PAGE_SIZE are not compressed. */
> if (entry->length == PAGE_SIZE) {
> @@ -966,7 +967,7 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
> dlen = acomp_ctx->req->dlen;
>
> read_done:
> - zs_obj_read_end(pool->zs_pool, entry->handle, obj);
> + zs_obj_read_end(pool->zs_pool, entry->handle, entry->length, obj);
> acomp_ctx_put_unlock(acomp_ctx);
>
> if (!decomp_ret && dlen == PAGE_SIZE)
> --
> 2.52.0.351.gbe84eed79e-goog
>
Powered by blists - more mailing lists