Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

1 files changed, 140 insertions, 49 deletions

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5bc65587f1c4..a6aefe989043 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -18,6 +18,9 @@
 
 #include <trace/events/page_pool.h>
 
+#define DEFER_TIME (msecs_to_jiffies(1000))
+#define DEFER_WARN_INTERVAL (60 * HZ)
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params)
 {
@@ -44,6 +47,21 @@ static int page_pool_init(struct page_pool *pool,
 	    (pool->p.dma_dir != DMA_BIDIRECTIONAL))
 		return -EINVAL;
 
+	if (pool->p.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))
+			return -EINVAL;
+
+		if (!pool->p.max_len)
+			return -EINVAL;
+
+		/* pool->p.offset has to be set according to the address
+		 * offset used by the DMA engine to start copying rx data
+		 */
+	}
+
 	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
 		return -ENOMEM;
 
@@ -112,6 +130,16 @@ 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)
+{
+	dma_sync_size = min(dma_sync_size, pool->p.max_len);
+	dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+					 pool->p.offset, dma_sync_size,
+					 pool->p.dma_dir);
+}
+
 /* slow path */
 noinline
 static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
@@ -156,6 +184,9 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	}
 	page->dma_addr = dma;
 
+	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
+
 skip_dma_map:
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
@@ -193,22 +224,14 @@ static s32 page_pool_inflight(struct page_pool *pool)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
-	s32 distance;
+	s32 inflight;
 
-	distance = _distance(hold_cnt, release_cnt);
+	inflight = _distance(hold_cnt, release_cnt);
 
-	trace_page_pool_inflight(pool, distance, hold_cnt, release_cnt);
-	return distance;
-}
-
-static bool __page_pool_safe_to_destroy(struct page_pool *pool)
-{
-	s32 inflight = page_pool_inflight(pool);
-
-	/* The distance should not be able to become negative */
+	trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
 	WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
 
-	return (inflight == 0);
+	return inflight;
 }
 
 /* Cleanup page_pool state from page */
@@ -216,6 +239,7 @@ static void __page_pool_clean_page(struct page_pool *pool,
 				   struct page *page)
 {
 	dma_addr_t dma;
+	int count;
 
 	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
 		goto skip_dma_unmap;
@@ -227,9 +251,11 @@ static void __page_pool_clean_page(struct page_pool *pool,
 			     DMA_ATTR_SKIP_CPU_SYNC);
 	page->dma_addr = 0;
 skip_dma_unmap:
-	atomic_inc(&pool->pages_state_release_cnt);
-	trace_page_pool_state_release(pool, page,
-			      atomic_read(&pool->pages_state_release_cnt));
+	/* This may be the last page returned, releasing the pool, so
+	 * it is not safe to reference pool afterwards.
+	 */
+	count = atomic_inc_return(&pool->pages_state_release_cnt);
+	trace_page_pool_state_release(pool, page, count);
 }
 
 /* unmap the page and clean our state */
@@ -283,8 +309,19 @@ static bool __page_pool_recycle_direct(struct page *page,
 	return true;
 }
 
-void __page_pool_put_page(struct page_pool *pool,
-			  struct page *page, bool allow_direct)
+/* 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;
+}
+
+void __page_pool_put_page(struct page_pool *pool, struct page *page,
+			  unsigned int dma_sync_size, bool allow_direct)
 {
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
@@ -292,9 +329,14 @@ void __page_pool_put_page(struct page_pool *pool,
 	 *
 	 * refcnt == 1 means page_pool owns page, and can recycle it.
 	 */
-	if (likely(page_ref_count(page) == 1)) {
+	if (likely(page_ref_count(page) == 1 &&
+		   pool_page_reusable(pool, 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_serving_softirq())
 			if (__page_pool_recycle_direct(page, pool))
 				return;
@@ -338,31 +380,10 @@ static void __page_pool_empty_ring(struct page_pool *pool)
 	}
 }
 
-static void __warn_in_flight(struct page_pool *pool)
+static void page_pool_free(struct page_pool *pool)
 {
-	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
-	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
-	s32 distance;
-
-	distance = _distance(hold_cnt, release_cnt);
-
-	/* Drivers should fix this, but only problematic when DMA is used */
-	WARN(1, "Still in-flight pages:%d hold:%u released:%u",
-	     distance, hold_cnt, release_cnt);
-}
-
-void __page_pool_free(struct page_pool *pool)
-{
-	/* Only last user actually free/release resources */
-	if (!page_pool_put(pool))
-		return;
-
-	WARN(pool->alloc.count, "API usage violation");
-	WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty");
-
-	/* Can happen due to forced shutdown */
-	if (!__page_pool_safe_to_destroy(pool))
-		__warn_in_flight(pool);
+	if (pool->disconnect)
+		pool->disconnect(pool);
 
 	ptr_ring_cleanup(&pool->ring, NULL);
 
@@ -371,15 +392,14 @@ void __page_pool_free(struct page_pool *pool)
 
 	kfree(pool);
 }
-EXPORT_SYMBOL(__page_pool_free);
 
-/* Request to shutdown: release pages cached by page_pool, and check
- * for in-flight pages
- */
-bool __page_pool_request_shutdown(struct page_pool *pool)
+static void page_pool_empty_alloc_cache_once(struct page_pool *pool)
 {
 	struct page *page;
 
+	if (pool->destroy_cnt)
+		return;
+
 	/* Empty alloc cache, assume caller made sure this is
 	 * no-longer in use, and page_pool_alloc_pages() cannot be
 	 * call concurrently.
@@ -388,12 +408,83 @@ bool __page_pool_request_shutdown(struct page_pool *pool)
 		page = pool->alloc.cache[--pool->alloc.count];
 		__page_pool_return_page(pool, page);
 	}
+}
+
+static void page_pool_scrub(struct page_pool *pool)
+{
+	page_pool_empty_alloc_cache_once(pool);
+	pool->destroy_cnt++;
 
 	/* No more consumers should exist, but producers could still
 	 * be in-flight.
 	 */
 	__page_pool_empty_ring(pool);
+}
+
+static int page_pool_release(struct page_pool *pool)
+{
+	int inflight;
+
+	page_pool_scrub(pool);
+	inflight = page_pool_inflight(pool);
+	if (!inflight)
+		page_pool_free(pool);
+
+	return inflight;
+}
+
+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);
+	int inflight;
+
+	inflight = page_pool_release(pool);
+	if (!inflight)
+		return;
+
+	/* Periodic warning */
+	if (time_after_eq(jiffies, pool->defer_warn)) {
+		int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ;
+
+		pr_warn("%s() stalled pool shutdown %d inflight %d sec\n",
+			__func__, inflight, sec);
+		pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
+	}
+
+	/* Still not ready to be disconnected, retry later */
+	schedule_delayed_work(&pool->release_dw, DEFER_TIME);
+}
 
-	return __page_pool_safe_to_destroy(pool);
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *))
+{
+	refcount_inc(&pool->user_cnt);
+	pool->disconnect = disconnect;
+}
+
+void page_pool_destroy(struct page_pool *pool)
+{
+	if (!pool)
+		return;
+
+	if (!page_pool_put(pool))
+		return;
+
+	if (!page_pool_release(pool))
+		return;
+
+	pool->defer_start = jiffies;
+	pool->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
+
+	INIT_DELAYED_WORK(&pool->release_dw, page_pool_release_retry);
+	schedule_delayed_work(&pool->release_dw, DEFER_TIME);
+}
+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)
+{
+	trace_page_pool_update_nid(pool, new_nid);
+	pool->p.nid = new_nid;
 }
-EXPORT_SYMBOL(__page_pool_request_shutdown);
+EXPORT_SYMBOL(page_pool_update_nid);