| 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: <20241103032111.333282-10-kanchana.p.sridhar@intel.com>
Date: Sat, 2 Nov 2024 20:21:07 -0700
From: Kanchana P Sridhar <kanchana.p.sridhar@...el.com>
To: linux-kernel@...r.kernel.org,
linux-mm@...ck.org,
hannes@...xchg.org,
yosryahmed@...gle.com,
nphamcs@...il.com,
chengming.zhou@...ux.dev,
usamaarif642@...il.com,
ryan.roberts@....com,
ying.huang@...el.com,
21cnbao@...il.com,
akpm@...ux-foundation.org,
linux-crypto@...r.kernel.org,
herbert@...dor.apana.org.au,
davem@...emloft.net,
clabbe@...libre.com,
ardb@...nel.org,
ebiggers@...gle.com,
surenb@...gle.com,
kristen.c.accardi@...el.com,
zanussi@...nel.org
Cc: wajdi.k.feghali@...el.com,
vinodh.gopal@...el.com,
kanchana.p.sridhar@...el.com
Subject: [PATCH v2 09/13] mm: zswap: Modify struct crypto_acomp_ctx to be configurable in nr of acomp_reqs.
Modified the definition of "struct crypto_acomp_ctx" to represent a
configurable number of acomp_reqs and the required number of buffers.
Accordingly, refactored the code that allocates/deallocates the acomp_ctx
resources, so that it can be called to create a regular acomp_ctx with
exactly one acomp_req/buffer, for use in the the existing non-batching
zswap_store(), as well as to create a separate "batching acomp_ctx" with
multiple acomp_reqs/buffers for IAA compress batching.
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@...el.com>
---
mm/zswap.c | 145 +++++++++++++++++++++++++++++++++++++----------------
1 file changed, 102 insertions(+), 43 deletions(-)
diff --git a/mm/zswap.c b/mm/zswap.c
index 3e899fa61445..f062c6dfcad4 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -143,9 +143,10 @@ bool zswap_never_enabled(void)
struct crypto_acomp_ctx {
struct crypto_acomp *acomp;
- struct acomp_req *req;
+ struct acomp_req **reqs;
+ u8 **buffers;
+ unsigned int nr_reqs;
struct crypto_wait wait;
- u8 *buffer;
struct mutex mutex;
bool is_sleepable;
};
@@ -241,6 +242,11 @@ static inline struct xarray *swap_zswap_tree(swp_entry_t swp)
pr_debug("%s pool %s/%s\n", msg, (p)->tfm_name, \
zpool_get_type((p)->zpool))
+static int zswap_create_acomp_ctx(unsigned int cpu,
+ struct crypto_acomp_ctx *acomp_ctx,
+ char *tfm_name,
+ unsigned int nr_reqs);
+
/*********************************
* pool functions
**********************************/
@@ -813,69 +819,122 @@ static void zswap_entry_free(struct zswap_entry *entry)
/*********************************
* compressed storage functions
**********************************/
-static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
+static int zswap_create_acomp_ctx(unsigned int cpu,
+ struct crypto_acomp_ctx *acomp_ctx,
+ char *tfm_name,
+ unsigned int nr_reqs)
{
- struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
- struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
struct crypto_acomp *acomp;
- struct acomp_req *req;
- int ret;
+ int ret = -ENOMEM;
+ int i, j;
+ acomp_ctx->nr_reqs = 0;
mutex_init(&acomp_ctx->mutex);
- acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
- if (!acomp_ctx->buffer)
- return -ENOMEM;
-
- acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
+ acomp = crypto_alloc_acomp_node(tfm_name, 0, 0, cpu_to_node(cpu));
if (IS_ERR(acomp)) {
pr_err("could not alloc crypto acomp %s : %ld\n",
- pool->tfm_name, PTR_ERR(acomp));
- ret = PTR_ERR(acomp);
- goto acomp_fail;
+ tfm_name, PTR_ERR(acomp));
+ return PTR_ERR(acomp);
}
+
acomp_ctx->acomp = acomp;
acomp_ctx->is_sleepable = acomp_is_async(acomp);
- req = acomp_request_alloc(acomp_ctx->acomp);
- if (!req) {
- pr_err("could not alloc crypto acomp_request %s\n",
- pool->tfm_name);
- ret = -ENOMEM;
- goto req_fail;
+ acomp_ctx->buffers = kmalloc_node(nr_reqs * sizeof(u8 *),
+ GFP_KERNEL, cpu_to_node(cpu));
+ for (i = 0; i < nr_reqs; ++i) {
+ acomp_ctx->buffers[i] = kmalloc_node(PAGE_SIZE * 2,
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!acomp_ctx->buffers[i]) {
+ for (j = 0; j < i; ++j)
+ kfree(acomp_ctx->buffers[j]);
+ kfree(acomp_ctx->buffers);
+ ret = -ENOMEM;
+ goto buf_fail;
+ }
}
- acomp_ctx->req = req;
+ acomp_ctx->reqs = kmalloc_node(nr_reqs * sizeof(struct acomp_req *),
+ GFP_KERNEL, cpu_to_node(cpu));
+ for (i = 0; i < nr_reqs; ++i) {
+ acomp_ctx->reqs[i] = acomp_request_alloc(acomp_ctx->acomp);
+ if (!acomp_ctx->reqs[i]) {
+ pr_err("could not alloc crypto acomp_request reqs[%d] %s\n",
+ i, tfm_name);
+ for (j = 0; j < i; ++j)
+ acomp_request_free(acomp_ctx->reqs[j]);
+ kfree(acomp_ctx->reqs);
+ ret = -ENOMEM;
+ goto req_fail;
+ }
+ }
+
+ /*
+ * The crypto_wait is used only in fully synchronous, i.e., with scomp
+ * or non-poll mode of acomp, hence there is only one "wait" per
+ * acomp_ctx, with callback set to reqs[0], under the assumption that
+ * there is at least 1 request per acomp_ctx.
+ */
crypto_init_wait(&acomp_ctx->wait);
/*
* if the backend of acomp is async zip, crypto_req_done() will wakeup
* crypto_wait_req(); if the backend of acomp is scomp, the callback
* won't be called, crypto_wait_req() will return without blocking.
*/
- acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ acomp_request_set_callback(acomp_ctx->reqs[0], CRYPTO_TFM_REQ_MAY_BACKLOG,
crypto_req_done, &acomp_ctx->wait);
+ acomp_ctx->nr_reqs = nr_reqs;
return 0;
req_fail:
+ for (i = 0; i < nr_reqs; ++i)
+ kfree(acomp_ctx->buffers[i]);
+ kfree(acomp_ctx->buffers);
+buf_fail:
crypto_free_acomp(acomp_ctx->acomp);
-acomp_fail:
- kfree(acomp_ctx->buffer);
return ret;
}
-static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
+static void zswap_delete_acomp_ctx(struct crypto_acomp_ctx *acomp_ctx)
{
- struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
- struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
-
if (!IS_ERR_OR_NULL(acomp_ctx)) {
- if (!IS_ERR_OR_NULL(acomp_ctx->req))
- acomp_request_free(acomp_ctx->req);
+ int i;
+
+ for (i = 0; i < acomp_ctx->nr_reqs; ++i)
+ if (!IS_ERR_OR_NULL(acomp_ctx->reqs[i]))
+ acomp_request_free(acomp_ctx->reqs[i]);
+ kfree(acomp_ctx->reqs);
+
+ for (i = 0; i < acomp_ctx->nr_reqs; ++i)
+ kfree(acomp_ctx->buffers[i]);
+ kfree(acomp_ctx->buffers);
+
if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
crypto_free_acomp(acomp_ctx->acomp);
- kfree(acomp_ctx->buffer);
+
+ acomp_ctx->nr_reqs = 0;
+ acomp_ctx = NULL;
}
+}
+
+static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
+{
+ struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
+ struct crypto_acomp_ctx *acomp_ctx;
+
+ acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
+ return zswap_create_acomp_ctx(cpu, acomp_ctx, pool->tfm_name, 1);
+}
+
+static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
+{
+ struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
+ struct crypto_acomp_ctx *acomp_ctx;
+
+ acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
+ zswap_delete_acomp_ctx(acomp_ctx);
return 0;
}
@@ -898,7 +957,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
- dst = acomp_ctx->buffer;
+ dst = acomp_ctx->buffers[0];
sg_init_table(&input, 1);
sg_set_page(&input, page, PAGE_SIZE, 0);
@@ -908,7 +967,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
* giving the dst buffer with enough length to avoid buffer overflow.
*/
sg_init_one(&output, dst, PAGE_SIZE * 2);
- acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
+ acomp_request_set_params(acomp_ctx->reqs[0], &input, &output, PAGE_SIZE, dlen);
/*
* it maybe looks a little bit silly that we send an asynchronous request,
@@ -922,8 +981,8 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
* but in different threads running on different cpu, we have different
* acomp instance, so multiple threads can do (de)compression in parallel.
*/
- comp_ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait);
- dlen = acomp_ctx->req->dlen;
+ comp_ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->reqs[0]), &acomp_ctx->wait);
+ dlen = acomp_ctx->reqs[0]->dlen;
if (comp_ret)
goto unlock;
@@ -975,24 +1034,24 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
*/
if ((acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) ||
!virt_addr_valid(src)) {
- memcpy(acomp_ctx->buffer, src, entry->length);
- src = acomp_ctx->buffer;
+ memcpy(acomp_ctx->buffers[0], src, entry->length);
+ src = acomp_ctx->buffers[0];
zpool_unmap_handle(zpool, entry->handle);
}
sg_init_one(&input, src, entry->length);
sg_init_table(&output, 1);
sg_set_folio(&output, folio, PAGE_SIZE, 0);
- acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE);
- BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait));
- BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
+ acomp_request_set_params(acomp_ctx->reqs[0], &input, &output, entry->length, PAGE_SIZE);
+ BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->reqs[0]), &acomp_ctx->wait));
+ BUG_ON(acomp_ctx->reqs[0]->dlen != PAGE_SIZE);
- if (src != acomp_ctx->buffer)
+ if (src != acomp_ctx->buffers[0])
zpool_unmap_handle(zpool, entry->handle);
/*
* It is safer to unlock the mutex after the check for
- * "src != acomp_ctx->buffer" so that the value of "src"
+ * "src != acomp_ctx->buffers[0]" so that the value of "src"
* does not change.
*/
mutex_unlock(&acomp_ctx->mutex);
--
2.27.0
Powered by blists - more mailing lists