summaryrefslogtreecommitdiffstats
path: root/net/core/page_pool.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/page_pool.c')
-rw-r--r--net/core/page_pool.c126
1 files changed, 87 insertions, 39 deletions
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index dd364d738c..3772eb63dc 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -5,6 +5,7 @@
* Copyright (C) 2016 Red Hat, Inc.
*/
+#include <linux/error-injection.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
@@ -123,9 +124,9 @@ int page_pool_ethtool_stats_get_count(void)
}
EXPORT_SYMBOL(page_pool_ethtool_stats_get_count);
-u64 *page_pool_ethtool_stats_get(u64 *data, void *stats)
+u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats)
{
- struct page_pool_stats *pool_stats = stats;
+ const struct page_pool_stats *pool_stats = stats;
*data++ = pool_stats->alloc_stats.fast;
*data++ = pool_stats->alloc_stats.slow;
@@ -172,19 +173,29 @@ static void page_pool_producer_unlock(struct page_pool *pool,
spin_unlock_bh(&pool->ring.producer_lock);
}
+static void page_pool_struct_check(void)
+{
+ CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_users);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_page);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_offset);
+ CACHELINE_ASSERT_GROUP_SIZE(struct page_pool, frag, 4 * sizeof(long));
+}
+
static int page_pool_init(struct page_pool *pool,
const struct page_pool_params *params,
int cpuid)
{
unsigned int ring_qsize = 1024; /* Default */
+ page_pool_struct_check();
+
memcpy(&pool->p, &params->fast, sizeof(pool->p));
memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
pool->cpuid = cpuid;
/* Validate only known flags were used */
- if (pool->p.flags & ~(PP_FLAG_ALL))
+ if (pool->slow.flags & ~PP_FLAG_ALL)
return -EINVAL;
if (pool->p.pool_size)
@@ -198,22 +209,26 @@ static int page_pool_init(struct page_pool *pool,
* DMA_BIDIRECTIONAL is for allowing page used for DMA sending,
* which is the XDP_TX use-case.
*/
- if (pool->p.flags & PP_FLAG_DMA_MAP) {
+ if (pool->slow.flags & PP_FLAG_DMA_MAP) {
if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
(pool->p.dma_dir != DMA_BIDIRECTIONAL))
return -EINVAL;
+
+ pool->dma_map = true;
}
- if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
+ if (pool->slow.flags & PP_FLAG_DMA_SYNC_DEV) {
/* In order to request DMA-sync-for-device the page
* needs to be mapped
*/
- if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+ if (!(pool->slow.flags & PP_FLAG_DMA_MAP))
return -EINVAL;
if (!pool->p.max_len)
return -EINVAL;
+ pool->dma_sync = true;
+
/* pool->p.offset has to be set according to the address
* offset used by the DMA engine to start copying rx data
*/
@@ -222,7 +237,7 @@ static int page_pool_init(struct page_pool *pool,
pool->has_init_callback = !!pool->slow.init_callback;
#ifdef CONFIG_PAGE_POOL_STATS
- if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) {
+ if (!(pool->slow.flags & PP_FLAG_SYSTEM_POOL)) {
pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
if (!pool->recycle_stats)
return -ENOMEM;
@@ -232,12 +247,13 @@ static int page_pool_init(struct page_pool *pool,
* (also percpu) page pool instance.
*/
pool->recycle_stats = &pp_system_recycle_stats;
+ pool->system = true;
}
#endif
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) {
#ifdef CONFIG_PAGE_POOL_STATS
- if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+ if (!pool->system)
free_percpu(pool->recycle_stats);
#endif
return -ENOMEM;
@@ -248,7 +264,7 @@ 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);
- if (pool->p.flags & PP_FLAG_DMA_MAP)
+ if (pool->dma_map)
get_device(pool->p.dev);
return 0;
@@ -258,11 +274,11 @@ static void page_pool_uninit(struct page_pool *pool)
{
ptr_ring_cleanup(&pool->ring, NULL);
- if (pool->p.flags & PP_FLAG_DMA_MAP)
+ if (pool->dma_map)
put_device(pool->p.dev);
#ifdef CONFIG_PAGE_POOL_STATS
- if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+ if (!pool->system)
free_percpu(pool->recycle_stats);
#endif
}
@@ -383,16 +399,26 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
return page;
}
-static void page_pool_dma_sync_for_device(struct page_pool *pool,
- struct page *page,
- unsigned int dma_sync_size)
+static void __page_pool_dma_sync_for_device(const struct page_pool *pool,
+ const struct page *page,
+ u32 dma_sync_size)
{
+#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
dma_addr_t dma_addr = page_pool_get_dma_addr(page);
dma_sync_size = min(dma_sync_size, pool->p.max_len);
- dma_sync_single_range_for_device(pool->p.dev, dma_addr,
- pool->p.offset, dma_sync_size,
- pool->p.dma_dir);
+ __dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset,
+ dma_sync_size, pool->p.dma_dir);
+#endif
+}
+
+static __always_inline void
+page_pool_dma_sync_for_device(const struct page_pool *pool,
+ const struct page *page,
+ u32 dma_sync_size)
+{
+ if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
+ __page_pool_dma_sync_for_device(pool, page, dma_sync_size);
}
static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
@@ -414,13 +440,12 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
if (page_pool_set_dma_addr(page, dma))
goto unmap_failed;
- if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
- page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
+ page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
return true;
unmap_failed:
- WARN_ON_ONCE("unexpected DMA address, please report to netdev@");
+ WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
dma_unmap_page_attrs(pool->p.dev, dma,
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
@@ -460,8 +485,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
if (unlikely(!page))
return NULL;
- if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
- unlikely(!page_pool_dma_map(pool, page))) {
+ if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page))) {
put_page(page);
return NULL;
}
@@ -481,8 +505,8 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
gfp_t gfp)
{
const int bulk = PP_ALLOC_CACHE_REFILL;
- unsigned int pp_flags = pool->p.flags;
unsigned int pp_order = pool->p.order;
+ bool dma_map = pool->dma_map;
struct page *page;
int i, nr_pages;
@@ -507,8 +531,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
*/
for (i = 0; i < nr_pages; i++) {
page = pool->alloc.cache[i];
- if ((pp_flags & PP_FLAG_DMA_MAP) &&
- unlikely(!page_pool_dma_map(pool, page))) {
+ if (dma_map && unlikely(!page_pool_dma_map(pool, page))) {
put_page(page);
continue;
}
@@ -550,6 +573,7 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
return page;
}
EXPORT_SYMBOL(page_pool_alloc_pages);
+ALLOW_ERROR_INJECTION(page_pool_alloc_pages, NULL);
/* Calculate distance between two u32 values, valid if distance is below 2^(31)
* https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution
@@ -580,7 +604,7 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page)
{
dma_addr_t dma;
- if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+ if (!pool->dma_map)
/* Always account for inflight pages, even if we didn't
* map them
*/
@@ -663,7 +687,7 @@ static bool __page_pool_page_can_be_recycled(const struct page *page)
}
/* If the page refcnt == 1, this will try to recycle the page.
- * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for
+ * If pool->dma_sync is set, we'll try to sync the DMA area for
* the configured size min(dma_sync_size, pool->max_len).
* If the page refcnt != 1, then the page will be returned to memory
* subsystem.
@@ -686,12 +710,9 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
if (likely(__page_pool_page_can_be_recycled(page))) {
/* Read barrier done in page_ref_count / READ_ONCE */
- if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
- page_pool_dma_sync_for_device(pool, page,
- dma_sync_size);
+ page_pool_dma_sync_for_device(pool, page, dma_sync_size);
- if (allow_direct && in_softirq() &&
- page_pool_recycle_in_cache(page, pool))
+ if (allow_direct && page_pool_recycle_in_cache(page, pool))
return NULL;
/* Page found as candidate for recycling */
@@ -716,9 +737,35 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
return NULL;
}
+static bool page_pool_napi_local(const struct page_pool *pool)
+{
+ const struct napi_struct *napi;
+ u32 cpuid;
+
+ if (unlikely(!in_softirq()))
+ return false;
+
+ /* Allow direct recycle if we have reasons to believe that we are
+ * in the same context as the consumer would run, so there's
+ * no possible race.
+ * __page_pool_put_page() makes sure we're not in hardirq context
+ * and interrupts are enabled prior to accessing the cache.
+ */
+ cpuid = smp_processor_id();
+ if (READ_ONCE(pool->cpuid) == cpuid)
+ return true;
+
+ napi = READ_ONCE(pool->p.napi);
+
+ return napi && READ_ONCE(napi->list_owner) == cpuid;
+}
+
void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
unsigned int dma_sync_size, bool allow_direct)
{
+ if (!allow_direct)
+ allow_direct = page_pool_napi_local(pool);
+
page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
if (page && !page_pool_recycle_in_ring(pool, page)) {
/* Cache full, fallback to free pages */
@@ -747,8 +794,11 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
int count)
{
int i, bulk_len = 0;
+ bool allow_direct;
bool in_softirq;
+ allow_direct = page_pool_napi_local(pool);
+
for (i = 0; i < count; i++) {
struct page *page = virt_to_head_page(data[i]);
@@ -756,13 +806,13 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
if (!page_pool_is_last_ref(page))
continue;
- page = __page_pool_put_page(pool, page, -1, false);
+ page = __page_pool_put_page(pool, page, -1, allow_direct);
/* Approved for bulk recycling in ptr_ring cache */
if (page)
data[bulk_len++] = page;
}
- if (unlikely(!bulk_len))
+ if (!bulk_len)
return;
/* Bulk producer into ptr_ring page_pool cache */
@@ -799,9 +849,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
return NULL;
if (__page_pool_page_can_be_recycled(page)) {
- if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
- page_pool_dma_sync_for_device(pool, page, -1);
-
+ page_pool_dma_sync_for_device(pool, page, -1);
return page;
}
@@ -959,7 +1007,7 @@ static void page_pool_release_retry(struct work_struct *wq)
}
void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
- struct xdp_mem_info *mem)
+ const struct xdp_mem_info *mem)
{
refcount_inc(&pool->user_cnt);
pool->disconnect = disconnect;
@@ -969,7 +1017,7 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
static void page_pool_disable_direct_recycling(struct page_pool *pool)
{
/* Disable direct recycling based on pool->cpuid.
- * Paired with READ_ONCE() in napi_pp_put_page().
+ * Paired with READ_ONCE() in page_pool_napi_local().
*/
WRITE_ONCE(pool->cpuid, -1);
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-17 23:01:45 +0000