1 files changed, 168 insertions, 63 deletions

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5e409b98aba0..8bcc7014a61a 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>
@@ -23,12 +24,16 @@
 
 #include <trace/events/page_pool.h>
 
+#include "page_pool_priv.h"
+
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
-#define BIAS_MAX	LONG_MAX
+#define BIAS_MAX	(LONG_MAX >> 1)
 
 #ifdef CONFIG_PAGE_POOL_STATS
+static DEFINE_PER_CPU(struct page_pool_recycle_stats, pp_system_recycle_stats);
+
 /* alloc_stat_inc is intended to be used in softirq context */
 #define alloc_stat_inc(pool, __stat)	(pool->alloc_stats.__stat++)
 /* recycle_stat_inc is safe to use when preemption is possible. */
@@ -69,7 +74,7 @@ static const char pp_stats[][ETH_GSTRING_LEN] = {
  * is passed to this API which is filled in. The caller can then report
  * those stats to the user (perhaps via ethtool, debugfs, etc.).
  */
-bool page_pool_get_stats(struct page_pool *pool,
+bool page_pool_get_stats(const struct page_pool *pool,
 			 struct page_pool_stats *stats)
 {
 	int cpu = 0;
@@ -119,9 +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;
@@ -169,11 +174,15 @@ static void page_pool_producer_unlock(struct page_pool *pool,
 }
 
 static int page_pool_init(struct page_pool *pool,
-			  const struct page_pool_params *params)
+			  const struct page_pool_params *params,
+			  int cpuid)
 {
 	unsigned int ring_qsize = 1024; /* Default */
 
-	memcpy(&pool->p, params, sizeof(pool->p));
+	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))
@@ -211,14 +220,29 @@ static int page_pool_init(struct page_pool *pool,
 		 */
 	}
 
+	pool->has_init_callback = !!pool->slow.init_callback;
+
 #ifdef CONFIG_PAGE_POOL_STATS
-	pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
-	if (!pool->recycle_stats)
-		return -ENOMEM;
+	if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) {
+		pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
+		if (!pool->recycle_stats)
+			return -ENOMEM;
+	} else {
+		/* For system page pool instance we use a singular stats object
+		 * instead of allocating a separate percpu variable for each
+		 * (also percpu) page pool instance.
+		 */
+		pool->recycle_stats = &pp_system_recycle_stats;
+	}
 #endif
 
-	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
+	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) {
+#ifdef CONFIG_PAGE_POOL_STATS
+		if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+			free_percpu(pool->recycle_stats);
+#endif
 		return -ENOMEM;
+	}
 
 	atomic_set(&pool->pages_state_release_cnt, 0);
 
@@ -231,11 +255,26 @@ static int page_pool_init(struct page_pool *pool,
 	return 0;
 }
 
+static void page_pool_uninit(struct page_pool *pool)
+{
+	ptr_ring_cleanup(&pool->ring, NULL);
+
+	if (pool->p.flags & PP_FLAG_DMA_MAP)
+		put_device(pool->p.dev);
+
+#ifdef CONFIG_PAGE_POOL_STATS
+	if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+		free_percpu(pool->recycle_stats);
+#endif
+}
+
 /**
- * page_pool_create() - create a page pool.
+ * page_pool_create_percpu() - create a page pool for a given cpu.
  * @params: parameters, see struct page_pool_params
+ * @cpuid: cpu identifier
  */
-struct page_pool *page_pool_create(const struct page_pool_params *params)
+struct page_pool *
+page_pool_create_percpu(const struct page_pool_params *params, int cpuid)
 {
 	struct page_pool *pool;
 	int err;
@@ -244,14 +283,32 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
 	if (!pool)
 		return ERR_PTR(-ENOMEM);
 
-	err = page_pool_init(pool, params);
-	if (err < 0) {
-		pr_warn("%s() gave up with errno %d\n", __func__, err);
-		kfree(pool);
-		return ERR_PTR(err);
-	}
+	err = page_pool_init(pool, params, cpuid);
+	if (err < 0)
+		goto err_free;
+
+	err = page_pool_list(pool);
+	if (err)
+		goto err_uninit;
 
 	return pool;
+
+err_uninit:
+	page_pool_uninit(pool);
+err_free:
+	pr_warn("%s() gave up with errno %d\n", __func__, err);
+	kfree(pool);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(page_pool_create_percpu);
+
+/**
+ * page_pool_create() - create a page pool
+ * @params: parameters, see struct page_pool_params
+ */
+struct page_pool *page_pool_create(const struct page_pool_params *params)
+{
+	return page_pool_create_percpu(params, -1);
 }
 EXPORT_SYMBOL(page_pool_create);
 
@@ -327,8 +384,8 @@ 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,
+static void page_pool_dma_sync_for_device(const struct page_pool *pool,
+					  const struct page *page,
 					  unsigned int dma_sync_size)
 {
 	dma_addr_t dma_addr = page_pool_get_dma_addr(page);
@@ -384,8 +441,8 @@ static void page_pool_set_pp_info(struct page_pool *pool,
 	 * the overhead is negligible.
 	 */
 	page_pool_fragment_page(page, 1);
-	if (pool->p.init_callback)
-		pool->p.init_callback(page, pool->p.init_arg);
+	if (pool->has_init_callback)
+		pool->slow.init_callback(page, pool->slow.init_arg);
 }
 
 static void page_pool_clear_pp_info(struct page *page)
@@ -494,13 +551,14 @@ 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
  */
 #define _distance(a, b)	(s32)((a) - (b))
 
-static s32 page_pool_inflight(struct page_pool *pool)
+s32 page_pool_inflight(const struct page_pool *pool, bool strict)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
@@ -508,27 +566,27 @@ static s32 page_pool_inflight(struct page_pool *pool)
 
 	inflight = _distance(hold_cnt, release_cnt);
 
-	trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
-	WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
+	if (strict) {
+		trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
+		WARN(inflight < 0, "Negative(%d) inflight packet-pages",
+		     inflight);
+	} else {
+		inflight = max(0, inflight);
+	}
 
 	return inflight;
 }
 
-/* Disconnects a page (from a page_pool).  API users can have a need
- * to disconnect a page (from a page_pool), to allow it to be used as
- * a regular page (that will eventually be returned to the normal
- * page-allocator via put_page).
- */
-static void page_pool_return_page(struct page_pool *pool, struct page *page)
+static __always_inline
+void __page_pool_release_page_dma(struct page_pool *pool, struct page *page)
 {
 	dma_addr_t dma;
-	int count;
 
 	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
 		/* Always account for inflight pages, even if we didn't
 		 * map them
 		 */
-		goto skip_dma_unmap;
+		return;
 
 	dma = page_pool_get_dma_addr(page);
 
@@ -537,7 +595,19 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page)
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	page_pool_set_dma_addr(page, 0);
-skip_dma_unmap:
+}
+
+/* Disconnects a page (from a page_pool).  API users can have a need
+ * to disconnect a page (from a page_pool), to allow it to be used as
+ * a regular page (that will eventually be returned to the normal
+ * page-allocator via put_page).
+ */
+void page_pool_return_page(struct page_pool *pool, struct page *page)
+{
+	int count;
+
+	__page_pool_release_page_dma(pool, page);
+
 	page_pool_clear_pp_info(page);
 
 	/* This may be the last page returned, releasing the pool, so
@@ -589,6 +659,11 @@ static bool page_pool_recycle_in_cache(struct page *page,
 	return true;
 }
 
+static bool __page_pool_page_can_be_recycled(const struct page *page)
+{
+	return page_ref_count(page) == 1 && !page_is_pfmemalloc(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
  * the configured size min(dma_sync_size, pool->max_len).
@@ -610,15 +685,14 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
 	 * page is NOT reusable when allocated when system is under
 	 * some pressure. (page_is_pfmemalloc)
 	 */
-	if (likely(page_ref_count(page) == 1 && !page_is_pfmemalloc(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);
 
-		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 */
@@ -643,9 +717,35 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
 	return NULL;
 }
 
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size, bool allow_direct)
+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 */
@@ -653,7 +753,7 @@ void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
 		page_pool_return_page(pool, page);
 	}
 }
-EXPORT_SYMBOL(page_pool_put_defragged_page);
+EXPORT_SYMBOL(page_pool_put_unrefed_page);
 
 /**
  * page_pool_put_page_bulk() - release references on multiple pages
@@ -674,22 +774,25 @@ 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]);
 
 		/* It is not the last user for the page frag case */
-		if (!page_pool_is_last_frag(page))
+		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 */
@@ -722,10 +825,10 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
 	long drain_count = BIAS_MAX - pool->frag_users;
 
 	/* Some user is still using the page frag */
-	if (likely(page_pool_defrag_page(page, drain_count)))
+	if (likely(page_pool_unref_page(page, drain_count)))
 		return NULL;
 
-	if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
+	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);
 
@@ -743,7 +846,7 @@ static void page_pool_free_frag(struct page_pool *pool)
 
 	pool->frag_page = NULL;
 
-	if (!page || page_pool_defrag_page(page, drain_count))
+	if (!page || page_pool_unref_page(page, drain_count))
 		return;
 
 	page_pool_return_page(pool, page);
@@ -814,14 +917,8 @@ static void __page_pool_destroy(struct page_pool *pool)
 	if (pool->disconnect)
 		pool->disconnect(pool);
 
-	ptr_ring_cleanup(&pool->ring, NULL);
-
-	if (pool->p.flags & PP_FLAG_DMA_MAP)
-		put_device(pool->p.dev);
-
-#ifdef CONFIG_PAGE_POOL_STATS
-	free_percpu(pool->recycle_stats);
-#endif
+	page_pool_unlist(pool);
+	page_pool_uninit(pool);
 	kfree(pool);
 }
 
@@ -858,7 +955,7 @@ static int page_pool_release(struct page_pool *pool)
 	int inflight;
 
 	page_pool_scrub(pool);
-	inflight = page_pool_inflight(pool);
+	inflight = page_pool_inflight(pool, true);
 	if (!inflight)
 		__page_pool_destroy(pool);
 
@@ -869,18 +966,21 @@ static void page_pool_release_retry(struct work_struct *wq)
 {
 	struct delayed_work *dwq = to_delayed_work(wq);
 	struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw);
+	void *netdev;
 	int inflight;
 
 	inflight = page_pool_release(pool);
 	if (!inflight)
 		return;
 
-	/* Periodic warning */
-	if (time_after_eq(jiffies, pool->defer_warn)) {
+	/* Periodic warning for page pools the user can't see */
+	netdev = READ_ONCE(pool->slow.netdev);
+	if (time_after_eq(jiffies, pool->defer_warn) &&
+	    (!netdev || netdev == NET_PTR_POISON)) {
 		int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ;
 
-		pr_warn("%s() stalled pool shutdown %d inflight %d sec\n",
-			__func__, inflight, sec);
+		pr_warn("%s() stalled pool shutdown: id %u, %d inflight %d sec\n",
+			__func__, pool->user.id, inflight, sec);
 		pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
 	}
 
@@ -889,15 +989,20 @@ 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;
 	pool->xdp_mem_id = mem->id;
 }
 
-void page_pool_unlink_napi(struct page_pool *pool)
+static void page_pool_disable_direct_recycling(struct page_pool *pool)
 {
+	/* Disable direct recycling based on pool->cpuid.
+	 * Paired with READ_ONCE() in page_pool_napi_local().
+	 */
+	WRITE_ONCE(pool->cpuid, -1);
+
 	if (!pool->p.napi)
 		return;
 
@@ -909,7 +1014,6 @@ void page_pool_unlink_napi(struct page_pool *pool)
 
 	WRITE_ONCE(pool->p.napi, NULL);
 }
-EXPORT_SYMBOL(page_pool_unlink_napi);
 
 void page_pool_destroy(struct page_pool *pool)
 {
@@ -919,12 +1023,13 @@ void page_pool_destroy(struct page_pool *pool)
 	if (!page_pool_put(pool))
 		return;
 
-	page_pool_unlink_napi(pool);
+	page_pool_disable_direct_recycling(pool);
 	page_pool_free_frag(pool);
 
 	if (!page_pool_release(pool))
 		return;
 
+	page_pool_detached(pool);
 	pool->defer_start = jiffies;
 	pool->defer_warn  = jiffies + DEFER_WARN_INTERVAL;