Received-SPF: pass (google.com: domain of linux-kernel+bounces-149985-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
From: Alexander Lobakin <aleksander.lobakin@intel.com>
To: "David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>,
	Paolo Abeni <pabeni@redhat.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>,
	Alexander Duyck <alexanderduyck@fb.com>,
	Yunsheng Lin <linyunsheng@huawei.com>,
	Jesper Dangaard Brouer <hawk@kernel.org>,
	Ilias Apalodimas <ilias.apalodimas@linaro.org>,
	Christoph Lameter <cl@linux.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	Andrew Morton <akpm@linux-foundation.org>,
	Przemek Kitszel <przemyslaw.kitszel@intel.com>,
	nex.sw.ncis.osdt.itp.upstreaming@intel.com,
	netdev@vger.kernel.org,
	intel-wired-lan@lists.osuosl.org,
	linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH net-next v10 08/10] iavf: pack iavf_ring more efficiently
Date: Thu, 18 Apr 2024 13:36:14 +0200
Message-ID: <20240418113616.1108566-9-aleksander.lobakin@intel.com>
In-Reply-To: <20240418113616.1108566-1-aleksander.lobakin@intel.com>
References: <20240418113616.1108566-1-aleksander.lobakin@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Before replacing the Rx buffer management with libie, clean up
&iavf_ring a bit.
There are several fields not used anywhere in the code -- simply remove
them. Move ::tail up to remove a hole. Replace ::arm_wb boolean with
1-bit flag in ::flags to free 1 more byte. Finally, move ::prev_pkt_ctr
out of &iavf_tx_queue_stats -- it doesn't belong there (used for Tx
stall detection). Place it next to the stats on the ring itself to fill
the 4-byte slot.
The result: no holes and all the hot fields fit into the first 64-byte
cacheline.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_txrx.h | 22 +++------------------
 drivers/net/ethernet/intel/iavf/iavf_txrx.c | 12 +++++------
 2 files changed, 9 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index e01777531635..ed559fa6f214 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -227,7 +227,6 @@ struct iavf_tx_queue_stats {
 	u64 tx_done_old;
 	u64 tx_linearize;
 	u64 tx_force_wb;
-	int prev_pkt_ctr;
 	u64 tx_lost_interrupt;
 };
 
@@ -237,12 +236,6 @@ struct iavf_rx_queue_stats {
 	u64 alloc_buff_failed;
 };
 
-enum iavf_ring_state_t {
-	__IAVF_TX_FDIR_INIT_DONE,
-	__IAVF_TX_XPS_INIT_DONE,
-	__IAVF_RING_STATE_NBITS /* must be last */
-};
-
 /* some useful defines for virtchannel interface, which
  * is the only remaining user of header split
  */
@@ -264,10 +257,8 @@ struct iavf_ring {
 		struct iavf_tx_buffer *tx_bi;
 		struct iavf_rx_buffer *rx_bi;
 	};
-	DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS);
-	u16 queue_index;		/* Queue number of ring */
-	u8 dcb_tc;			/* Traffic class of ring */
 	u8 __iomem *tail;
+	u16 queue_index;		/* Queue number of ring */
 
 	/* high bit set means dynamic, use accessors routines to read/write.
 	 * hardware only supports 2us resolution for the ITR registers.
@@ -277,22 +268,14 @@ struct iavf_ring {
 	u16 itr_setting;
 
 	u16 count;			/* Number of descriptors */
-	u16 reg_idx;			/* HW register index of the ring */
 
 	/* used in interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
 
-	u8 atr_sample_rate;
-	u8 atr_count;
-
-	bool ring_active;		/* is ring online or not */
-	bool arm_wb;		/* do something to arm write back */
-	u8 packet_stride;
-
 	u16 flags;
 #define IAVF_TXR_FLAGS_WB_ON_ITR		BIT(0)
-/* BIT(1) is free, was IAVF_RXR_FLAGS_BUILD_SKB_ENABLED */
+#define IAVF_TXR_FLAGS_ARM_WB			BIT(1)
 /* BIT(2) is free */
 #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1	BIT(3)
 #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2	BIT(4)
@@ -306,6 +289,7 @@ struct iavf_ring {
 		struct iavf_rx_queue_stats rx_stats;
 	};
 
+	int prev_pkt_ctr;		/* For Tx stall detection */
 	unsigned int size;		/* length of descriptor ring in bytes */
 	dma_addr_t dma;			/* physical address of ring */
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index c7602c173420..2ec68b51bebe 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -185,7 +185,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi)
 			 * pending work.
 			 */
 			packets = tx_ring->stats.packets & INT_MAX;
-			if (tx_ring->tx_stats.prev_pkt_ctr == packets) {
+			if (tx_ring->prev_pkt_ctr == packets) {
 				iavf_force_wb(vsi, tx_ring->q_vector);
 				continue;
 			}
@@ -194,7 +194,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi)
 			 * to iavf_get_tx_pending()
 			 */
 			smp_rmb();
-			tx_ring->tx_stats.prev_pkt_ctr =
+			tx_ring->prev_pkt_ctr =
 			  iavf_get_tx_pending(tx_ring, true) ? packets : -1;
 		}
 	}
@@ -320,7 +320,7 @@ static bool iavf_clean_tx_irq(struct iavf_vsi *vsi,
 		    ((j / WB_STRIDE) == 0) && (j > 0) &&
 		    !test_bit(__IAVF_VSI_DOWN, vsi->state) &&
 		    (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count))
-			tx_ring->arm_wb = true;
+			tx_ring->flags |= IAVF_TXR_FLAGS_ARM_WB;
 	}
 
 	/* notify netdev of completed buffers */
@@ -675,7 +675,7 @@ int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring)
 
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
-	tx_ring->tx_stats.prev_pkt_ctr = -1;
+	tx_ring->prev_pkt_ctr = -1;
 	return 0;
 
 err:
@@ -1491,8 +1491,8 @@ int iavf_napi_poll(struct napi_struct *napi, int budget)
 			clean_complete = false;
 			continue;
 		}
-		arm_wb |= ring->arm_wb;
-		ring->arm_wb = false;
+		arm_wb |= !!(ring->flags & IAVF_TXR_FLAGS_ARM_WB);
+		ring->flags &= ~IAVF_TXR_FLAGS_ARM_WB;
 	}
 
 	/* Handle case where we are called by netpoll with a budget of 0 */
-- 
2.44.0