| 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: <20231106024413.2801438-3-almasrymina@google.com>
Date: Sun, 5 Nov 2023 18:44:01 -0800
From: Mina Almasry <almasrymina@...gle.com>
To: netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-arch@...r.kernel.org, linux-kselftest@...r.kernel.org,
linux-media@...r.kernel.org, dri-devel@...ts.freedesktop.org,
linaro-mm-sig@...ts.linaro.org
Cc: Mina Almasry <almasrymina@...gle.com>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Jesper Dangaard Brouer <hawk@...nel.org>,
Ilias Apalodimas <ilias.apalodimas@...aro.org>,
Arnd Bergmann <arnd@...db.de>,
David Ahern <dsahern@...nel.org>,
Willem de Bruijn <willemdebruijn.kernel@...il.com>,
Shuah Khan <shuah@...nel.org>,
Sumit Semwal <sumit.semwal@...aro.org>,
"Christian König" <christian.koenig@....com>,
Shakeel Butt <shakeelb@...gle.com>,
Jeroen de Borst <jeroendb@...gle.com>,
Praveen Kaligineedi <pkaligineedi@...gle.com>
Subject: [RFC PATCH v3 02/12] net: page_pool: create hooks for custom page providers
From: Jakub Kicinski <kuba@...nel.org>
The page providers which try to reuse the same pages will
need to hold onto the ref, even if page gets released from
the pool - as in releasing the page from the pp just transfers
the "ownership" reference from pp to the provider, and provider
will wait for other references to be gone before feeding this
page back into the pool.
Signed-off-by: Jakub Kicinski <kuba@...nel.org>
Signed-off-by: Mina Almasry <almasrymina@...gle.com>
---
This is implemented by Jakub in his RFC:
https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.com/T/
I take no credit for the idea or implementation; I only added minor
edits to make this workable with device memory TCP, and removed some
hacky test code. This is a critical dependency of device memory TCP
and thus I'm pulling it into this series to make it revewable and
mergable.
---
include/net/page_pool/types.h | 18 +++++++++++++
net/core/page_pool.c | 51 +++++++++++++++++++++++++++++++----
2 files changed, 64 insertions(+), 5 deletions(-)
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 6fc5134095ed..d4bea053bb7e 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -60,6 +60,8 @@ struct page_pool_params {
int nid;
struct device *dev;
struct napi_struct *napi;
+ u8 memory_provider;
+ void *mp_priv;
enum dma_data_direction dma_dir;
unsigned int max_len;
unsigned int offset;
@@ -118,6 +120,19 @@ struct page_pool_stats {
};
#endif
+struct mem_provider;
+
+enum pp_memory_provider_type {
+ __PP_MP_NONE, /* Use system allocator directly */
+};
+
+struct pp_memory_provider_ops {
+ int (*init)(struct page_pool *pool);
+ void (*destroy)(struct page_pool *pool);
+ struct page *(*alloc_pages)(struct page_pool *pool, gfp_t gfp);
+ bool (*release_page)(struct page_pool *pool, struct page *page);
+};
+
struct page_pool {
struct page_pool_params p;
@@ -165,6 +180,9 @@ struct page_pool {
*/
struct ptr_ring ring;
+ const struct pp_memory_provider_ops *mp_ops;
+ void *mp_priv;
+
#ifdef CONFIG_PAGE_POOL_STATS
/* recycle stats are per-cpu to avoid locking */
struct page_pool_recycle_stats __percpu *recycle_stats;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 578b6f2eeb46..7ea1f4682479 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -23,6 +23,8 @@
#include <trace/events/page_pool.h>
+static DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers);
+
#define DEFER_TIME (msecs_to_jiffies(1000))
#define DEFER_WARN_INTERVAL (60 * HZ)
@@ -172,6 +174,7 @@ static int page_pool_init(struct page_pool *pool,
const struct page_pool_params *params)
{
unsigned int ring_qsize = 1024; /* Default */
+ int err;
memcpy(&pool->p, params, sizeof(pool->p));
@@ -225,10 +228,34 @@ static int page_pool_init(struct page_pool *pool,
/* Driver calling page_pool_create() also call page_pool_destroy() */
refcount_set(&pool->user_cnt, 1);
+ switch (pool->p.memory_provider) {
+ case __PP_MP_NONE:
+ break;
+ default:
+ err = -EINVAL;
+ goto free_ptr_ring;
+ }
+
+ pool->mp_priv = pool->p.mp_priv;
+ if (pool->mp_ops) {
+ err = pool->mp_ops->init(pool);
+ if (err) {
+ pr_warn("%s() mem-provider init failed %d\n",
+ __func__, err);
+ goto free_ptr_ring;
+ }
+
+ static_branch_inc(&page_pool_mem_providers);
+ }
+
if (pool->p.flags & PP_FLAG_DMA_MAP)
get_device(pool->p.dev);
return 0;
+
+free_ptr_ring:
+ ptr_ring_cleanup(&pool->ring, NULL);
+ return err;
}
/**
@@ -490,7 +517,10 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
return page;
/* Slow-path: cache empty, do real allocation */
- page = __page_pool_alloc_pages_slow(pool, gfp);
+ if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
+ page = pool->mp_ops->alloc_pages(pool, gfp);
+ else
+ page = __page_pool_alloc_pages_slow(pool, gfp);
return page;
}
EXPORT_SYMBOL(page_pool_alloc_pages);
@@ -542,10 +572,13 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page)
void page_pool_return_page(struct page_pool *pool, struct page *page)
{
int count;
+ bool put;
- __page_pool_release_page_dma(pool, page);
-
- page_pool_clear_pp_info(page);
+ put = true;
+ if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
+ put = pool->mp_ops->release_page(pool, page);
+ else
+ __page_pool_release_page_dma(pool, page);
/* This may be the last page returned, releasing the pool, so
* it is not safe to reference pool afterwards.
@@ -553,7 +586,10 @@ void page_pool_return_page(struct page_pool *pool, struct page *page)
count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt);
trace_page_pool_state_release(pool, page, count);
- put_page(page);
+ if (put) {
+ page_pool_clear_pp_info(page);
+ put_page(page);
+ }
/* An optimization would be to call __free_pages(page, pool->p.order)
* knowing page is not part of page-cache (thus avoiding a
* __page_cache_release() call).
@@ -821,6 +857,11 @@ static void __page_pool_destroy(struct page_pool *pool)
if (pool->disconnect)
pool->disconnect(pool);
+ if (pool->mp_ops) {
+ pool->mp_ops->destroy(pool);
+ static_branch_dec(&page_pool_mem_providers);
+ }
+
ptr_ring_cleanup(&pool->ring, NULL);
if (pool->p.flags & PP_FLAG_DMA_MAP)
--
2.42.0.869.gea05f2083d-goog
Powered by blists - more mailing lists