Merge commit '8700c95adb03' into timers/nohz

The full dynticks tree needs the latest RCU and sched
upstream updates in order to fix some dependencies.

Merge a common upstream merge point that has these
updates.

Conflicts:
	include/linux/perf_event.h
	kernel/rcutree.h
	kernel/rcutree_plugin.h

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

5 files changed, 34 insertions, 18 deletions

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index bf57b3cb16ab..0bc00991d310 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -779,6 +779,7 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 						tx_queue->txd.entries);
 	}
 
+	efx_device_detach_sync(efx);
 	efx_stop_all(efx);
 	efx_stop_interrupts(efx, true);
 
@@ -832,6 +833,7 @@ out:
 
 	efx_start_interrupts(efx, true);
 	efx_start_all(efx);
+	netif_device_attach(efx->net_dev);
 	return rc;
 
 rollback:
@@ -1641,8 +1643,12 @@ static void efx_stop_all(struct efx_nic *efx)
 	/* Flush efx_mac_work(), refill_workqueue, monitor_work */
 	efx_flush_all(efx);
 
-	/* Stop the kernel transmit interface late, so the watchdog
-	 * timer isn't ticking over the flush */
+	/* Stop the kernel transmit interface.  This is only valid if
+	 * the device is stopped or detached; otherwise the watchdog
+	 * may fire immediately.
+	 */
+	WARN_ON(netif_running(efx->net_dev) &&
+		netif_device_present(efx->net_dev));
 	netif_tx_disable(efx->net_dev);
 
 	efx_stop_datapath(efx);
@@ -1963,16 +1969,18 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 	if (new_mtu > EFX_MAX_MTU)
 		return -EINVAL;
 
-	efx_stop_all(efx);
-
 	netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu);
 
+	efx_device_detach_sync(efx);
+	efx_stop_all(efx);
+
 	mutex_lock(&efx->mac_lock);
 	net_dev->mtu = new_mtu;
 	efx->type->reconfigure_mac(efx);
 	mutex_unlock(&efx->mac_lock);
 
 	efx_start_all(efx);
+	netif_device_attach(efx->net_dev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 50247dfe8f57..d2f790df6dcb 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -171,9 +171,9 @@ static inline void efx_device_detach_sync(struct efx_nic *efx)
 	 * TX scheduler is stopped when we're done and before
 	 * netif_device_present() becomes false.
 	 */
-	netif_tx_lock(dev);
+	netif_tx_lock_bh(dev);
 	netif_device_detach(dev);
-	netif_tx_unlock(dev);
+	netif_tx_unlock_bh(dev);
 }
 
 #endif /* EFX_EFX_H */
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 2d756c1d7142..0a90abd2421b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -210,6 +210,7 @@ struct efx_tx_queue {
  *	Will be %NULL if the buffer slot is currently free.
  * @page: The associated page buffer. Valif iff @flags & %EFX_RX_BUF_PAGE.
  *	Will be %NULL if the buffer slot is currently free.
+ * @page_offset: Offset within page. Valid iff @flags & %EFX_RX_BUF_PAGE.
  * @len: Buffer length, in bytes.
  * @flags: Flags for buffer and packet state.
  */
@@ -219,7 +220,8 @@ struct efx_rx_buffer {
 		struct sk_buff *skb;
 		struct page *page;
 	} u;
-	unsigned int len;
+	u16 page_offset;
+	u16 len;
 	u16 flags;
 };
 #define EFX_RX_BUF_PAGE		0x0001
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 0ad790cc473c..eaa8e874a3cb 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -376,7 +376,8 @@ efx_may_push_tx_desc(struct efx_tx_queue *tx_queue, unsigned int write_count)
 		return false;
 
 	tx_queue->empty_read_count = 0;
-	return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0;
+	return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0
+		&& tx_queue->write_count - write_count == 1;
 }
 
 /* For each entry inserted into the software descriptor ring, create a
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index d780a0d096b4..bb579a6128c8 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -90,11 +90,7 @@ static unsigned int rx_refill_threshold;
 static inline unsigned int efx_rx_buf_offset(struct efx_nic *efx,
 					     struct efx_rx_buffer *buf)
 {
-	/* Offset is always within one page, so we don't need to consider
-	 * the page order.
-	 */
-	return ((unsigned int) buf->dma_addr & (PAGE_SIZE - 1)) +
-		efx->type->rx_buffer_hash_size;
+	return buf->page_offset + efx->type->rx_buffer_hash_size;
 }
 static inline unsigned int efx_rx_buf_size(struct efx_nic *efx)
 {
@@ -187,6 +183,7 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 	struct efx_nic *efx = rx_queue->efx;
 	struct efx_rx_buffer *rx_buf;
 	struct page *page;
+	unsigned int page_offset;
 	struct efx_rx_page_state *state;
 	dma_addr_t dma_addr;
 	unsigned index, count;
@@ -211,12 +208,14 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 		state->dma_addr = dma_addr;
 
 		dma_addr += sizeof(struct efx_rx_page_state);
+		page_offset = sizeof(struct efx_rx_page_state);
 
 	split:
 		index = rx_queue->added_count & rx_queue->ptr_mask;
 		rx_buf = efx_rx_buffer(rx_queue, index);
 		rx_buf->dma_addr = dma_addr + EFX_PAGE_IP_ALIGN;
 		rx_buf->u.page = page;
+		rx_buf->page_offset = page_offset + EFX_PAGE_IP_ALIGN;
 		rx_buf->len = efx->rx_buffer_len - EFX_PAGE_IP_ALIGN;
 		rx_buf->flags = EFX_RX_BUF_PAGE;
 		++rx_queue->added_count;
@@ -227,6 +226,7 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 			/* Use the second half of the page */
 			get_page(page);
 			dma_addr += (PAGE_SIZE >> 1);
+			page_offset += (PAGE_SIZE >> 1);
 			++count;
 			goto split;
 		}
@@ -236,7 +236,8 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 }
 
 static void efx_unmap_rx_buffer(struct efx_nic *efx,
-				struct efx_rx_buffer *rx_buf)
+				struct efx_rx_buffer *rx_buf,
+				unsigned int used_len)
 {
 	if ((rx_buf->flags & EFX_RX_BUF_PAGE) && rx_buf->u.page) {
 		struct efx_rx_page_state *state;
@@ -247,6 +248,10 @@ static void efx_unmap_rx_buffer(struct efx_nic *efx,
 				       state->dma_addr,
 				       efx_rx_buf_size(efx),
 				       DMA_FROM_DEVICE);
+		} else if (used_len) {
+			dma_sync_single_for_cpu(&efx->pci_dev->dev,
+						rx_buf->dma_addr, used_len,
+						DMA_FROM_DEVICE);
 		}
 	} else if (!(rx_buf->flags & EFX_RX_BUF_PAGE) && rx_buf->u.skb) {
 		dma_unmap_single(&efx->pci_dev->dev, rx_buf->dma_addr,
@@ -269,7 +274,7 @@ static void efx_free_rx_buffer(struct efx_nic *efx,
 static void efx_fini_rx_buffer(struct efx_rx_queue *rx_queue,
 			       struct efx_rx_buffer *rx_buf)
 {
-	efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
+	efx_unmap_rx_buffer(rx_queue->efx, rx_buf, 0);
 	efx_free_rx_buffer(rx_queue->efx, rx_buf);
 }
 
@@ -535,10 +540,10 @@ void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
 		goto out;
 	}
 
-	/* Release card resources - assumes all RX buffers consumed in-order
-	 * per RX queue
+	/* Release and/or sync DMA mapping - assumes all RX buffers
+	 * consumed in-order per RX queue
 	 */
-	efx_unmap_rx_buffer(efx, rx_buf);
+	efx_unmap_rx_buffer(efx, rx_buf, len);
 
 	/* Prefetch nice and early so data will (hopefully) be in cache by
 	 * the time we look at it.