summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2020-01-03 00:37:53 +0100
committerDavid S. Miller <davem@davemloft.net>2020-01-03 00:37:53 +0100
commitc9a2069b1dbadf7cb85da0fd9df62d25e3642f03 (patch)
tree9284b79bba0aa682bb0019f1165a5fb50c6edace
parentMerge branch '1GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher... (diff)
parentpage_pool: help compiler remove code in case CONFIG_NUMA=n (diff)
downloadlinux-c9a2069b1dbadf7cb85da0fd9df62d25e3642f03.tar.xz
linux-c9a2069b1dbadf7cb85da0fd9df62d25e3642f03.zip
Merge branch 'page_pool-NUMA-node-handling-fixes'
Jesper Dangaard Brouer says: ==================== page_pool: NUMA node handling fixes The recently added NUMA changes (merged for v5.5) to page_pool, it both contains a bug in handling NUMA_NO_NODE condition, and added code to the fast-path. This patchset fixes the bug and moves code out of fast-path. The first patch contains a fix that should be considered for 5.5. The second patch reduce code size and overhead in case CONFIG_NUMA is disabled. Currently the NUMA_NO_NODE setting bug only affects driver 'ti_cpsw' (drivers/net/ethernet/ti/), but after this patchset, we plan to move other drivers (netsec and mvneta) to use NUMA_NO_NODE setting. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/core/page_pool.c89
1 files changed, 70 insertions, 19 deletions
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index a6aefe989043..9b7cbe35df37 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -96,10 +96,65 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
}
EXPORT_SYMBOL(page_pool_create);
+static void __page_pool_return_page(struct page_pool *pool, struct page *page);
+
+noinline
+static struct page *page_pool_refill_alloc_cache(struct page_pool *pool,
+ bool refill)
+{
+ struct ptr_ring *r = &pool->ring;
+ struct page *page;
+ int pref_nid; /* preferred NUMA node */
+
+ /* Quicker fallback, avoid locks when ring is empty */
+ if (__ptr_ring_empty(r))
+ return NULL;
+
+ /* Softirq guarantee CPU and thus NUMA node is stable. This,
+ * assumes CPU refilling driver RX-ring will also run RX-NAPI.
+ */
+#ifdef CONFIG_NUMA
+ pref_nid = (pool->p.nid == NUMA_NO_NODE) ? numa_mem_id() : pool->p.nid;
+#else
+ /* Ignore pool->p.nid setting if !CONFIG_NUMA, helps compiler */
+ pref_nid = numa_mem_id(); /* will be zero like page_to_nid() */
+#endif
+
+ /* Slower-path: Get pages from locked ring queue */
+ spin_lock(&r->consumer_lock);
+
+ /* Refill alloc array, but only if NUMA match */
+ do {
+ page = __ptr_ring_consume(r);
+ if (unlikely(!page))
+ break;
+
+ if (likely(page_to_nid(page) == pref_nid)) {
+ pool->alloc.cache[pool->alloc.count++] = page;
+ } else {
+ /* NUMA mismatch;
+ * (1) release 1 page to page-allocator and
+ * (2) break out to fallthrough to alloc_pages_node.
+ * This limit stress on page buddy alloactor.
+ */
+ __page_pool_return_page(pool, page);
+ page = NULL;
+ break;
+ }
+ } while (pool->alloc.count < PP_ALLOC_CACHE_REFILL &&
+ refill);
+
+ /* Return last page */
+ if (likely(pool->alloc.count > 0))
+ page = pool->alloc.cache[--pool->alloc.count];
+
+ spin_unlock(&r->consumer_lock);
+ return page;
+}
+
/* fast path */
static struct page *__page_pool_get_cached(struct page_pool *pool)
{
- struct ptr_ring *r = &pool->ring;
bool refill = false;
struct page *page;
@@ -113,20 +168,7 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
refill = true;
}
- /* Quicker fallback, avoid locks when ring is empty */
- if (__ptr_ring_empty(r))
- return NULL;
-
- /* Slow-path: Get page from locked ring queue,
- * refill alloc array if requested.
- */
- spin_lock(&r->consumer_lock);
- page = __ptr_ring_consume(r);
- if (refill)
- pool->alloc.count = __ptr_ring_consume_batched(r,
- pool->alloc.cache,
- PP_ALLOC_CACHE_REFILL);
- spin_unlock(&r->consumer_lock);
+ page = page_pool_refill_alloc_cache(pool, refill);
return page;
}
@@ -163,7 +205,11 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
*/
/* Cache was empty, do real allocation */
+#ifdef CONFIG_NUMA
page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
+#else
+ page = alloc_pages(gfp, pool->p.order);
+#endif
if (!page)
return NULL;
@@ -311,13 +357,10 @@ static bool __page_pool_recycle_direct(struct page *page,
/* page is NOT reusable when:
* 1) allocated when system is under some pressure. (page_is_pfmemalloc)
- * 2) belongs to a different NUMA node than pool->p.nid.
- *
- * To update pool->p.nid users must call page_pool_update_nid.
*/
static bool pool_page_reusable(struct page_pool *pool, struct page *page)
{
- return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid;
+ return !page_is_pfmemalloc(page);
}
void __page_pool_put_page(struct page_pool *pool, struct page *page,
@@ -484,7 +527,15 @@ EXPORT_SYMBOL(page_pool_destroy);
/* Caller must provide appropriate safe context, e.g. NAPI. */
void page_pool_update_nid(struct page_pool *pool, int new_nid)
{
+ struct page *page;
+
trace_page_pool_update_nid(pool, new_nid);
pool->p.nid = new_nid;
+
+ /* Flush pool alloc cache, as refill will check NUMA node */
+ while (pool->alloc.count) {
+ page = pool->alloc.cache[--pool->alloc.count];
+ __page_pool_return_page(pool, page);
+ }
}
EXPORT_SYMBOL(page_pool_update_nid);