From d7840976e3915669382c62ddd1700960f348328e Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 22 Jul 2019 20:08:25 -0700
Subject: net: Use skb accessors in network drivers

In preparation for unifying the skb_frag and bio_vec, use the fine
accessors which already exist and use skb_frag_t instead of
struct skb_frag_struct.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 3c83230434b6..dd7392f293bf 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1521,7 +1521,7 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 {
 	u64 td_offset, td_tag, td_cmd;
 	u16 i = tx_ring->next_to_use;
-	struct skb_frag_struct *frag;
+	skb_frag_t *frag;
 	unsigned int data_len, size;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
@@ -1923,7 +1923,7 @@ static unsigned int ice_txd_use_count(unsigned int size)
  */
 static unsigned int ice_xmit_desc_count(struct sk_buff *skb)
 {
-	const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+	const skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
 	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
 	unsigned int count = 0, size = skb_headlen(skb);
 
@@ -1954,7 +1954,7 @@ static unsigned int ice_xmit_desc_count(struct sk_buff *skb)
  */
 static bool __ice_chk_linearize(struct sk_buff *skb)
 {
-	const struct skb_frag_struct *frag, *stale;
+	const skb_frag_t *frag, *stale;
 	int nr_frags, sum;
 
 	/* no need to check if number of frags is less than 7 */
-- 
cgit v1.2.3


From cb7db35641c9a508247bdcd73831c855c8758cd3 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Wed, 26 Jun 2019 02:20:19 -0700
Subject: ice: Only bump Rx tail and release buffers once per napi_poll

Currently we bump the Rx tail and release/give buffers to hardware every
16 descriptors. This causes us to bump Rx tail up to 4 times per
napi_poll call. Also we are always bumping tail on an odd index and this
is a problem because hardware ignores the lower 3 bits in the QRX_TAIL
register. This is making it so hardware sees tail bumps only every 8
descriptors. Instead lets only bump Rx tail once per napi_poll if
the value aligns with hardware's expectations of the lower 3 bits being
cleared. Also only release/give Rx buffers once per napi_poll call.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 42 ++++++++++++++++++++-----------
 1 file changed, 27 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index dd7392f293bf..0c459305c12f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -377,18 +377,28 @@ err:
  */
 static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
 {
+	u16 prev_ntu = rx_ring->next_to_use;
+
 	rx_ring->next_to_use = val;
 
 	/* update next to alloc since we have filled the ring */
 	rx_ring->next_to_alloc = val;
 
-	/* Force memory writes to complete before letting h/w
-	 * know there are new descriptors to fetch. (Only
-	 * applicable for weak-ordered memory model archs,
-	 * such as IA-64).
+	/* QRX_TAIL will be updated with any tail value, but hardware ignores
+	 * the lower 3 bits. This makes it so we only bump tail on meaningful
+	 * boundaries. Also, this allows us to bump tail on intervals of 8 up to
+	 * the budget depending on the current traffic load.
 	 */
-	wmb();
-	writel(val, rx_ring->tail);
+	val &= ~0x7;
+	if (prev_ntu != val) {
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch. (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		writel(val, rx_ring->tail);
+	}
 }
 
 /**
@@ -445,7 +455,13 @@ ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi)
  * @rx_ring: ring to place buffers on
  * @cleaned_count: number of buffers to replace
  *
- * Returns false if all allocations were successful, true if any fail
+ * Returns false if all allocations were successful, true if any fail. Returning
+ * true signals to the caller that we didn't replace cleaned_count buffers and
+ * there is more work to do.
+ *
+ * First, try to clean "cleaned_count" Rx buffers. Then refill the cleaned Rx
+ * buffers. Then bump tail at most one time. Grouping like this lets us avoid
+ * multiple tail writes per call.
  */
 bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
 {
@@ -990,7 +1006,7 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
-	bool failure = false;
+	bool failure;
 
 	/* start the loop to process Rx packets bounded by 'budget' */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
@@ -1002,13 +1018,6 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		u16 vlan_tag = 0;
 		u8 rx_ptype;
 
-		/* return some buffers to hardware, one at a time is too slow */
-		if (cleaned_count >= ICE_RX_BUF_WRITE) {
-			failure = failure ||
-				  ice_alloc_rx_bufs(rx_ring, cleaned_count);
-			cleaned_count = 0;
-		}
-
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
@@ -1085,6 +1094,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		total_rx_pkts++;
 	}
 
+	/* return up to cleaned_count buffers to hardware */
+	failure = ice_alloc_rx_bufs(rx_ring, cleaned_count);
+
 	/* update queue and vector specific stats */
 	u64_stats_update_begin(&rx_ring->syncp);
 	rx_ring->stats.pkts += total_rx_pkts;
-- 
cgit v1.2.3


From a1e9968593234c179fcb3e71875897ae585c8362 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Wed, 26 Jun 2019 02:20:23 -0700
Subject: ice: Remove duplicate code in ice_alloc_rx_bufs

Currently if the call to ice_alloc_mapped_page() fails we jump to the
no_buf label, possibly call ice_release_rx_desc(), and return true
indicating that there is more work to do. In the success case we just
fall out of the while loop, possibly call ice_alloc_mapped_page(), and
return false saying we exhausted cleaned_count. This flow can be
improved by breaking if ice_alloc_mapped_page() fails and then the flow
outside of the while loop is the same for the failure and success case.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 0c459305c12f..020dac283f07 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -478,8 +478,9 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
 	bi = &rx_ring->rx_buf[ntu];
 
 	do {
+		/* if we fail here, we have work remaining */
 		if (!ice_alloc_mapped_page(rx_ring, bi))
-			goto no_bufs;
+			break;
 
 		/* sync the buffer for use by the device */
 		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
@@ -510,16 +511,7 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
 	if (rx_ring->next_to_use != ntu)
 		ice_release_rx_desc(rx_ring, ntu);
 
-	return false;
-
-no_bufs:
-	if (rx_ring->next_to_use != ntu)
-		ice_release_rx_desc(rx_ring, ntu);
-
-	/* make sure to come back via polling to try again after
-	 * allocation failure
-	 */
-	return true;
+	return !!cleaned_count;
 }
 
 /**
-- 
cgit v1.2.3


From ba880734ba9c24eca589b3f734d38309568301b2 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Wed, 26 Jun 2019 02:20:25 -0700
Subject: ice: Remove unnecessary flag ICE_FLAG_MSIX_ENA

This flag is not needed and is called every time we re-enable interrupts
in the hotpath so remove it. Also remove ice_vsi_req_irq() because it
was a wrapper function for ice_vsi_req_irq_msix() whose sole purpose was
checking the ICE_FLAG_MSIX_ENA flag.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h      |  1 -
 drivers/net/ethernet/intel/ice/ice_lib.c  | 71 ++++++++++++-----------------
 drivers/net/ethernet/intel/ice/ice_main.c | 74 ++++++++-----------------------
 drivers/net/ethernet/intel/ice/ice_txrx.c |  4 +-
 4 files changed, 48 insertions(+), 102 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 596b09a905aa..794d97460fc7 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -329,7 +329,6 @@ struct ice_q_vector {
 } ____cacheline_internodealigned_in_smp;
 
 enum ice_pf_flags {
-	ICE_FLAG_MSIX_ENA,
 	ICE_FLAG_FLTR_SYNC,
 	ICE_FLAG_RSS_ENA,
 	ICE_FLAG_SRIOV_ENA,
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 2add10e02280..6e34c40e7840 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1129,12 +1129,7 @@ static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
 		return -EEXIST;
 	}
 
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
-		num_q_vectors = vsi->num_q_vectors;
-	} else {
-		err = -EINVAL;
-		goto err_out;
-	}
+	num_q_vectors = vsi->num_q_vectors;
 
 	for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
 		err = ice_vsi_alloc_q_vector(vsi, v_idx);
@@ -1180,9 +1175,6 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
 		return -EEXIST;
 	}
 
-	if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		return -ENOENT;
-
 	num_q_vectors = vsi->num_q_vectors;
 	/* reserve slots from OS requested IRQs */
 	vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors,
@@ -2605,39 +2597,36 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 	int base = vsi->base_vector;
+	int i;
 
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
-		int i;
-
-		if (!vsi->q_vectors || !vsi->irqs_ready)
-			return;
+	if (!vsi->q_vectors || !vsi->irqs_ready)
+		return;
 
-		ice_vsi_release_msix(vsi);
-		if (vsi->type == ICE_VSI_VF)
-			return;
+	ice_vsi_release_msix(vsi);
+	if (vsi->type == ICE_VSI_VF)
+		return;
 
-		vsi->irqs_ready = false;
-		ice_for_each_q_vector(vsi, i) {
-			u16 vector = i + base;
-			int irq_num;
+	vsi->irqs_ready = false;
+	ice_for_each_q_vector(vsi, i) {
+		u16 vector = i + base;
+		int irq_num;
 
-			irq_num = pf->msix_entries[vector].vector;
+		irq_num = pf->msix_entries[vector].vector;
 
-			/* free only the irqs that were actually requested */
-			if (!vsi->q_vectors[i] ||
-			    !(vsi->q_vectors[i]->num_ring_tx ||
-			      vsi->q_vectors[i]->num_ring_rx))
-				continue;
+		/* free only the irqs that were actually requested */
+		if (!vsi->q_vectors[i] ||
+		    !(vsi->q_vectors[i]->num_ring_tx ||
+		      vsi->q_vectors[i]->num_ring_rx))
+			continue;
 
-			/* clear the affinity notifier in the IRQ descriptor */
-			irq_set_affinity_notifier(irq_num, NULL);
+		/* clear the affinity notifier in the IRQ descriptor */
+		irq_set_affinity_notifier(irq_num, NULL);
 
-			/* clear the affinity_mask in the IRQ descriptor */
-			irq_set_affinity_hint(irq_num, NULL);
-			synchronize_irq(irq_num);
-			devm_free_irq(&pf->pdev->dev, irq_num,
-				      vsi->q_vectors[i]);
-		}
+		/* clear the affinity_mask in the IRQ descriptor */
+		irq_set_affinity_hint(irq_num, NULL);
+		synchronize_irq(irq_num);
+		devm_free_irq(&pf->pdev->dev, irq_num,
+			      vsi->q_vectors[i]);
 	}
 }
 
@@ -2816,15 +2805,13 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
 	}
 
 	/* disable each interrupt */
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
-		ice_for_each_q_vector(vsi, i)
-			wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0);
+	ice_for_each_q_vector(vsi, i)
+		wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0);
 
-		ice_flush(hw);
+	ice_flush(hw);
 
-		ice_for_each_q_vector(vsi, i)
-			synchronize_irq(pf->msix_entries[i + base].vector);
-	}
+	ice_for_each_q_vector(vsi, i)
+		synchronize_irq(pf->msix_entries[i + base].vector);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index e4be9aa79337..8a8f9170e219 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1547,15 +1547,11 @@ static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
  */
 static int ice_vsi_ena_irq(struct ice_vsi *vsi)
 {
-	struct ice_pf *pf = vsi->back;
-	struct ice_hw *hw = &pf->hw;
-
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
-		int i;
+	struct ice_hw *hw = &vsi->back->hw;
+	int i;
 
-		ice_for_each_q_vector(vsi, i)
-			ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);
-	}
+	ice_for_each_q_vector(vsi, i)
+		ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);
 
 	ice_flush(hw);
 	return 0;
@@ -1803,7 +1799,7 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 	wr32(hw, PFINT_OICR_ENA, 0);
 	ice_flush(hw);
 
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) {
+	if (pf->msix_entries) {
 		synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
 		devm_free_irq(&pf->pdev->dev,
 			      pf->msix_entries[pf->oicr_idx].vector, pf);
@@ -2229,7 +2225,6 @@ static void ice_deinit_pf(struct ice_pf *pf)
 static void ice_init_pf(struct ice_pf *pf)
 {
 	bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS);
-	set_bit(ICE_FLAG_MSIX_ENA, pf->flags);
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.common_cap.sr_iov_1_1) {
 		struct ice_hw *hw = &pf->hw;
@@ -2329,7 +2324,6 @@ msix_err:
 
 exit_err:
 	pf->num_lan_msix = 0;
-	clear_bit(ICE_FLAG_MSIX_ENA, pf->flags);
 	return err;
 }
 
@@ -2342,7 +2336,6 @@ static void ice_dis_msix(struct ice_pf *pf)
 	pci_disable_msix(pf->pdev);
 	devm_kfree(&pf->pdev->dev, pf->msix_entries);
 	pf->msix_entries = NULL;
-	clear_bit(ICE_FLAG_MSIX_ENA, pf->flags);
 }
 
 /**
@@ -2351,8 +2344,7 @@ static void ice_dis_msix(struct ice_pf *pf)
  */
 static void ice_clear_interrupt_scheme(struct ice_pf *pf)
 {
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		ice_dis_msix(pf);
+	ice_dis_msix(pf);
 
 	if (pf->irq_tracker) {
 		devm_kfree(&pf->pdev->dev, pf->irq_tracker);
@@ -2368,10 +2360,7 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 {
 	int vectors;
 
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		vectors = ice_ena_msix_range(pf);
-	else
-		return -ENODEV;
+	vectors = ice_ena_msix_range(pf);
 
 	if (vectors < 0)
 		return vectors;
@@ -2528,12 +2517,10 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	 * the misc functionality and queue processing is combined in
 	 * the same vector and that gets setup at open.
 	 */
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
-		err = ice_req_irq_msix_misc(pf);
-		if (err) {
-			dev_err(dev, "setup of misc vector failed: %d\n", err);
-			goto err_init_interrupt_unroll;
-		}
+	err = ice_req_irq_msix_misc(pf);
+	if (err) {
+		dev_err(dev, "setup of misc vector failed: %d\n", err);
+		goto err_init_interrupt_unroll;
 	}
 
 	/* create switch struct for the switch element created by FW on boot */
@@ -3146,10 +3133,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 	struct ice_pf *pf = vsi->back;
 	int err;
 
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		ice_vsi_cfg_msix(vsi);
-	else
-		return -ENOTSUPP;
+	ice_vsi_cfg_msix(vsi);
 
 	/* Enable only Rx rings, Tx rings were enabled by the FW when the
 	 * Tx queue group list was configured and the context bits were
@@ -3609,24 +3593,6 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
 	return err;
 }
 
-/**
- * ice_vsi_req_irq - Request IRQ from the OS
- * @vsi: The VSI IRQ is being requested for
- * @basename: name for the vector
- *
- * Return 0 on success and a negative value on error
- */
-static int ice_vsi_req_irq(struct ice_vsi *vsi, char *basename)
-{
-	struct ice_pf *pf = vsi->back;
-	int err = -EINVAL;
-
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		err = ice_vsi_req_irq_msix(vsi, basename);
-
-	return err;
-}
-
 /**
  * ice_vsi_open - Called when a network interface is made active
  * @vsi: the VSI to open
@@ -3656,7 +3622,7 @@ static int ice_vsi_open(struct ice_vsi *vsi)
 
 	snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
 		 dev_driver_string(&pf->pdev->dev), vsi->netdev->name);
-	err = ice_vsi_req_irq(vsi, int_name);
+	err = ice_vsi_req_irq_msix(vsi, int_name);
 	if (err)
 		goto err_setup_rx;
 
@@ -3893,12 +3859,10 @@ static void ice_rebuild(struct ice_pf *pf)
 	}
 
 	/* start misc vector */
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
-		err = ice_req_irq_msix_misc(pf);
-		if (err) {
-			dev_err(dev, "misc vector setup failed: %d\n", err);
-			goto err_vsi_rebuild;
-		}
+	err = ice_req_irq_msix_misc(pf);
+	if (err) {
+		dev_err(dev, "misc vector setup failed: %d\n", err);
+		goto err_vsi_rebuild;
 	}
 
 	/* restart the VSIs that were rebuilt and running before the reset */
@@ -4295,9 +4259,7 @@ static void ice_tx_timeout(struct net_device *netdev)
 		head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) &
 			QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
 		/* Read interrupt register */
-		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-			val = rd32(hw,
-				   GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
+		val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, hung_queue, tx_ring->next_to_clean,
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 020dac283f07..9234fd203929 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1413,7 +1413,6 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	struct ice_q_vector *q_vector =
 				container_of(napi, struct ice_q_vector, napi);
 	struct ice_vsi *vsi = q_vector->vsi;
-	struct ice_pf *pf = vsi->back;
 	bool clean_complete = true;
 	int budget_per_ring = 0;
 	struct ice_ring *ring;
@@ -1454,8 +1453,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * poll us due to busy-polling
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
-		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-			ice_update_ena_itr(vsi, q_vector);
+		ice_update_ena_itr(vsi, q_vector);
 
 	return min_t(int, work_done, budget - 1);
 }
-- 
cgit v1.2.3


From 9118fcd5255f6d3891c90e01edd98dfc402ac663 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Thu, 25 Jul 2019 01:55:29 -0700
Subject: ice: Assume that more than one Rx queue is rare in ice_napi_poll

Currently we divide budget by the number of Rx queues per Rx ring
container in ice_napi_poll even if there is only 1. This is an
unnecessary divide for the normal case of 1 Rx ring per Rx ring
container. Fix this by using an unlikely() call in the case where we
actually need to divide.

Also, we will always set budget_per_ring even if there are no Rx rings
in the Rx ring container so we don't need to initialize it to 0.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 9234fd203929..837d6ae2f33b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1414,8 +1414,8 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 				container_of(napi, struct ice_q_vector, napi);
 	struct ice_vsi *vsi = q_vector->vsi;
 	bool clean_complete = true;
-	int budget_per_ring = 0;
 	struct ice_ring *ring;
+	int budget_per_ring;
 	int work_done = 0;
 
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
@@ -1429,11 +1429,16 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	if (budget <= 0)
 		return budget;
 
-	/* We attempt to distribute budget to each Rx queue fairly, but don't
-	 * allow the budget to go below 1 because that would exit polling early.
-	 */
-	if (q_vector->num_ring_rx)
+	/* normally we have 1 Rx ring per q_vector */
+	if (unlikely(q_vector->num_ring_rx > 1))
+		/* We attempt to distribute budget to each Rx queue fairly, but
+		 * don't allow the budget to go below 1 because that would exit
+		 * polling early.
+		 */
 		budget_per_ring = max(budget / q_vector->num_ring_rx, 1);
+	else
+		/* Max of 1 Rx ring in this q_vector so give it the budget */
+		budget_per_ring = budget;
 
 	ice_for_each_ring(ring, q_vector->rx) {
 		int cleaned;
-- 
cgit v1.2.3


From 2ab28bb04ce6432f15cd5086e7c7384f3deab639 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Thu, 25 Jul 2019 01:55:32 -0700
Subject: ice: Set WB_ON_ITR when we don't re-enable interrupts

Currently when busy polling is enabled we aren't setting/enabling
WB_ON_ITR in the driver. This doesn't break the driver, but it does
cause issues. If we don't enable WB_ON_ITR mode we will still get
write-backs from hardware during polling when a cache line has been
filled, but if a cache line is not filled we will not get the
write-back because WB_ON_ITR is not set. Fix this by enabling
WB_ON_ITR in the driver when interrupts are disabled.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h |  3 ++
 drivers/net/ethernet/intel/ice/ice_txrx.c       | 54 +++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_txrx.h       | 13 ++++++
 3 files changed, 70 insertions(+)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 87652d722a30..6f78ff5534af 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -127,8 +127,11 @@
 #define GLINT_DYN_CTL_CLEARPBA_M		BIT(1)
 #define GLINT_DYN_CTL_SWINT_TRIG_M		BIT(2)
 #define GLINT_DYN_CTL_ITR_INDX_S		3
+#define GLINT_DYN_CTL_ITR_INDX_M		ICE_M(0x3, 3)
 #define GLINT_DYN_CTL_INTERVAL_S		5
+#define GLINT_DYN_CTL_INTERVAL_M		ICE_M(0xFFF, 5)
 #define GLINT_DYN_CTL_SW_ITR_INDX_M		ICE_M(0x3, 25)
+#define GLINT_DYN_CTL_WB_ON_ITR_M		BIT(30)
 #define GLINT_DYN_CTL_INTENA_MSK_M		BIT(31)
 #define GLINT_ITR(_i, _INT)			(0x00154000 + ((_i) * 8192 + (_INT) * 4))
 #define GLINT_RATE(_INT)			(0x0015A000 + ((_INT) * 4))
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 837d6ae2f33b..c88e0701e1d7 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1355,6 +1355,23 @@ ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
 	struct ice_ring_container *rx = &q_vector->rx;
 	u32 itr_val;
 
+	/* when exiting WB_ON_ITR lets set a low ITR value and trigger
+	 * interrupts to expire right away in case we have more work ready to go
+	 * already
+	 */
+	if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE) {
+		itr_val = ice_buildreg_itr(rx->itr_idx, ICE_WB_ON_ITR_USECS);
+		wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val);
+		/* set target back to last user set value */
+		rx->target_itr = rx->itr_setting;
+		/* set current to what we just wrote and dynamic if needed */
+		rx->current_itr = ICE_WB_ON_ITR_USECS |
+			(rx->itr_setting & ICE_ITR_DYNAMIC);
+		/* allow normal interrupt flow to start */
+		q_vector->itr_countdown = 0;
+		return;
+	}
+
 	/* This will do nothing if dynamic updates are not enabled */
 	ice_update_itr(q_vector, tx);
 	ice_update_itr(q_vector, rx);
@@ -1399,6 +1416,41 @@ ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
 		     itr_val);
 }
 
+/**
+ * ice_set_wb_on_itr - set WB_ON_ITR for this q_vector
+ * @vsi: pointer to the VSI structure
+ * @q_vector: q_vector to set WB_ON_ITR on
+ *
+ * We need to tell hardware to write-back completed descriptors even when
+ * interrupts are disabled. Descriptors will be written back on cache line
+ * boundaries without WB_ON_ITR enabled, but if we don't enable WB_ON_ITR
+ * descriptors may not be written back if they don't fill a cache line until the
+ * next interrupt.
+ *
+ * This sets the write-back frequency to 2 microseconds as that is the minimum
+ * value that's not 0 due to ITR granularity. Also, set the INTENA_MSK bit to
+ * make sure hardware knows we aren't meddling with the INTENA_M bit.
+ */
+static void
+ice_set_wb_on_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+{
+	/* already in WB_ON_ITR mode no need to change it */
+	if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE)
+		return;
+
+	if (q_vector->num_ring_rx)
+		wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
+		     ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS,
+						 ICE_RX_ITR));
+
+	if (q_vector->num_ring_tx)
+		wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
+		     ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS,
+						 ICE_TX_ITR));
+
+	q_vector->itr_countdown = ICE_IN_WB_ON_ITR_MODE;
+}
+
 /**
  * ice_napi_poll - NAPI polling Rx/Tx cleanup routine
  * @napi: napi struct with our devices info in it
@@ -1459,6 +1511,8 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
 		ice_update_ena_itr(vsi, q_vector);
+	else
+		ice_set_wb_on_itr(vsi, q_vector);
 
 	return min_t(int, work_done, budget - 1);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index ec76aba347b9..94a9280193e2 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -144,6 +144,19 @@ enum ice_rx_dtype {
 #define ICE_DFLT_INTRL	0
 #define ICE_MAX_INTRL	236
 
+#define ICE_WB_ON_ITR_USECS	2
+#define ICE_IN_WB_ON_ITR_MODE	255
+/* Sets WB_ON_ITR and assumes INTENA bit is already cleared, which allows
+ * setting the MSK_M bit to tell hardware to ignore the INTENA_M bit. Also,
+ * set the write-back latency to the usecs passed in.
+ */
+#define ICE_GLINT_DYN_CTL_WB_ON_ITR(usecs, itr_idx)	\
+	((((usecs) << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S)) & \
+	  GLINT_DYN_CTL_INTERVAL_M) | \
+	 (((itr_idx) << GLINT_DYN_CTL_ITR_INDX_S) & \
+	  GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | \
+	 GLINT_DYN_CTL_WB_ON_ITR_M)
+
 /* Legacy or Advanced Mode Queue */
 #define ICE_TX_ADVANCED	0
 #define ICE_TX_LEGACY	1
-- 
cgit v1.2.3


From ac6f733a7bd5e23ce9d58ef995f51fbd1ad2fa97 Mon Sep 17 00:00:00 2001
From: Mitch Williams <mitch.a.williams@intel.com>
Date: Thu, 25 Jul 2019 01:55:34 -0700
Subject: ice: allow empty Rx descriptors

In some circumstances, the hardware will hand us a receive descriptor
which has no data attached, but is otherwise valid. The receive code was
improperly ignoring these descriptors, which result in an infinite loop.

To fix this, change the receive code to process all descriptors,
regardless of the size of the associated data. Add checks to the
memory-handling functions to allow for zero size.

Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index c88e0701e1d7..e5c4c9139e54 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -607,6 +607,8 @@ ice_add_rx_frag(struct ice_rx_buf *rx_buf, struct sk_buff *skb,
 	unsigned int truesize = ICE_RXBUF_2048;
 #endif
 
+	if (!size)
+		return;
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
 			rx_buf->page_offset, size, truesize);
 
@@ -662,6 +664,8 @@ ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb,
 	prefetchw(rx_buf->page);
 	*skb = rx_buf->skb;
 
+	if (!size)
+		return rx_buf;
 	/* we are reusing so sync this buffer for CPU use */
 	dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
 				      rx_buf->page_offset, size,
@@ -745,8 +749,11 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
  */
 static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
 {
-		/* hand second half of page back to the ring */
+	if (!rx_buf)
+		return;
+
 	if (ice_can_reuse_rx_page(rx_buf)) {
+		/* hand second half of page back to the ring */
 		ice_reuse_rx_page(rx_ring, rx_buf);
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
@@ -1031,8 +1038,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 			ICE_RX_FLX_DESC_PKT_LEN_M;
 
+		/* retrieve a buffer from the ring */
 		rx_buf = ice_get_rx_buf(rx_ring, &skb, size);
-		/* allocate (if needed) and populate skb */
+
 		if (skb)
 			ice_add_rx_frag(rx_buf, skb, size);
 		else
@@ -1041,7 +1049,8 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buf_failed++;
-			rx_buf->pagecnt_bias++;
+			if (rx_buf)
+				rx_buf->pagecnt_bias++;
 			break;
 		}
 
-- 
cgit v1.2.3


From 0c3a6101ff2df98d5d960bda9b159d7c4a952f27 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Mon, 29 Jul 2019 02:04:43 -0700
Subject: ice: Allow egress control packets from PF_VSI

For control packets (i.e. LLDP packets) to be able to egress
from the main VSI, a bit has to be set in the TX_descriptor.
This should only be done for the main VSI and only if the
FW LLDP agent is disabled.  A bit to allow this also has to
be set in the VSI context.

Add the logic to add the necessary bits in the VSI context
for the PF_VSI and the TX_descriptors for control packets
egressing the PF_VSI.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c  |  7 +++++++
 drivers/net/ethernet/intel/ice/ice_txrx.c | 11 ++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 6e34c40e7840..d6279dfe029e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1010,6 +1010,13 @@ static int ice_vsi_init(struct ice_vsi *vsi)
 			ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
 	}
 
+	/* Allow control frames out of main VSI */
+	if (vsi->type == ICE_VSI_PF) {
+		ctxt->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
+		ctxt->info.valid_sections |=
+			cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+	}
+
 	ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL);
 	if (ret) {
 		dev_err(&pf->pdev->dev,
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index e5c4c9139e54..5bf5c179a738 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -2106,6 +2106,7 @@ static netdev_tx_t
 ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 {
 	struct ice_tx_offload_params offload = { 0 };
+	struct ice_vsi *vsi = tx_ring->vsi;
 	struct ice_tx_buf *first;
 	unsigned int count;
 	int tso, csum;
@@ -2153,7 +2154,15 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 	if (csum < 0)
 		goto out_drop;
 
-	if (tso || offload.cd_tunnel_params) {
+	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
+	if (unlikely(skb->priority == TC_PRIO_CONTROL &&
+		     vsi->type == ICE_VSI_PF &&
+		     vsi->port_info->is_sw_lldp))
+		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
+					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
+					ICE_TXD_CTX_QW1_CMD_S);
+
+	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
 		int i = tx_ring->next_to_use;
 
-- 
cgit v1.2.3


From 2fb0821fd54cbc6c87f58f1ab5449af191bf8aac Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Thu, 8 Aug 2019 07:39:35 -0700
Subject: ice: clean up arguments

There are a couple of functions that don't need two arguments
passed in when the second argument already had access to
the pointer pointed to by the first.

Remove the unnecessary arguments.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 43 +++++++++++++++----------------
 1 file changed, 21 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 5bf5c179a738..4fe1b332e67e 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -95,17 +95,16 @@ void ice_free_tx_ring(struct ice_ring *tx_ring)
 
 /**
  * ice_clean_tx_irq - Reclaim resources after transmit completes
- * @vsi: the VSI we care about
  * @tx_ring: Tx ring to clean
  * @napi_budget: Used to determine if we are in netpoll
  *
  * Returns true if there's any budget left (e.g. the clean is finished)
  */
-static bool
-ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget)
+static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget)
 {
 	unsigned int total_bytes = 0, total_pkts = 0;
-	unsigned int budget = vsi->work_lmt;
+	unsigned int budget = ICE_DFLT_IRQ_WORK;
+	struct ice_vsi *vsi = tx_ring->vsi;
 	s16 i = tx_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
@@ -114,6 +113,8 @@ ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget)
 	tx_desc = ICE_TX_DESC(tx_ring, i);
 	i -= tx_ring->count;
 
+	prefetch(&vsi->state);
+
 	do {
 		struct ice_tx_desc *eop_desc = tx_buf->next_to_watch;
 
@@ -206,7 +207,7 @@ ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget)
 		smp_mb();
 		if (__netif_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->q_index) &&
-		   !test_bit(__ICE_DOWN, vsi->state)) {
+		    !test_bit(__ICE_DOWN, vsi->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->q_index);
 			++tx_ring->tx_stats.restart_q;
@@ -879,7 +880,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
 
 /**
  * ice_rx_csum - Indicate in skb if checksum is good
- * @vsi: the VSI we care about
+ * @ring: the ring we care about
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
  * @ptype: the packet type decoded by hardware
@@ -887,7 +888,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
  * skb->protocol must be set before this function is called
  */
 static void
-ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
+ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
 	    union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
 {
 	struct ice_rx_ptype_decoded decoded;
@@ -904,7 +905,7 @@ ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
 	skb_checksum_none_assert(skb);
 
 	/* check if Rx checksum is enabled */
-	if (!(vsi->netdev->features & NETIF_F_RXCSUM))
+	if (!(ring->netdev->features & NETIF_F_RXCSUM))
 		return;
 
 	/* check if HW has decoded the packet and checksum */
@@ -944,7 +945,7 @@ ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
 	return;
 
 checksum_fail:
-	vsi->back->hw_csum_rx_error++;
+	ring->vsi->back->hw_csum_rx_error++;
 }
 
 /**
@@ -968,7 +969,7 @@ ice_process_skb_fields(struct ice_ring *rx_ring,
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
-	ice_rx_csum(rx_ring->vsi, skb, rx_desc, ptype);
+	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
 }
 
 /**
@@ -1354,14 +1355,13 @@ static u32 ice_buildreg_itr(u16 itr_idx, u16 itr)
 
 /**
  * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt
- * @vsi: the VSI associated with the q_vector
  * @q_vector: q_vector for which ITR is being updated and interrupt enabled
  */
-static void
-ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+static void ice_update_ena_itr(struct ice_q_vector *q_vector)
 {
 	struct ice_ring_container *tx = &q_vector->tx;
 	struct ice_ring_container *rx = &q_vector->rx;
+	struct ice_vsi *vsi = q_vector->vsi;
 	u32 itr_val;
 
 	/* when exiting WB_ON_ITR lets set a low ITR value and trigger
@@ -1419,15 +1419,14 @@ ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
 			q_vector->itr_countdown--;
 	}
 
-	if (!test_bit(__ICE_DOWN, vsi->state))
-		wr32(&vsi->back->hw,
+	if (!test_bit(__ICE_DOWN, q_vector->vsi->state))
+		wr32(&q_vector->vsi->back->hw,
 		     GLINT_DYN_CTL(q_vector->reg_idx),
 		     itr_val);
 }
 
 /**
  * ice_set_wb_on_itr - set WB_ON_ITR for this q_vector
- * @vsi: pointer to the VSI structure
  * @q_vector: q_vector to set WB_ON_ITR on
  *
  * We need to tell hardware to write-back completed descriptors even when
@@ -1440,9 +1439,10 @@ ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
  * value that's not 0 due to ITR granularity. Also, set the INTENA_MSK bit to
  * make sure hardware knows we aren't meddling with the INTENA_M bit.
  */
-static void
-ice_set_wb_on_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+static void ice_set_wb_on_itr(struct ice_q_vector *q_vector)
 {
+	struct ice_vsi *vsi = q_vector->vsi;
+
 	/* already in WB_ON_ITR mode no need to change it */
 	if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE)
 		return;
@@ -1473,7 +1473,6 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct ice_q_vector *q_vector =
 				container_of(napi, struct ice_q_vector, napi);
-	struct ice_vsi *vsi = q_vector->vsi;
 	bool clean_complete = true;
 	struct ice_ring *ring;
 	int budget_per_ring;
@@ -1483,7 +1482,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_ring(ring, q_vector->tx)
-		if (!ice_clean_tx_irq(vsi, ring, budget))
+		if (!ice_clean_tx_irq(ring, budget))
 			clean_complete = false;
 
 	/* Handle case where we are called by netpoll with a budget of 0 */
@@ -1519,9 +1518,9 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * poll us due to busy-polling
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
-		ice_update_ena_itr(vsi, q_vector);
+		ice_update_ena_itr(q_vector);
 	else
-		ice_set_wb_on_itr(vsi, q_vector);
+		ice_set_wb_on_itr(q_vector);
 
 	return min_t(int, work_done, budget - 1);
 }
-- 
cgit v1.2.3


From 6503b659302893af700d9e9b82d3210d09a3aefb Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Thu, 8 Aug 2019 07:39:36 -0700
Subject: ice: move code closer together

This is a simple patch to move the assignment to a local variable
closer to the site where the local variable is used.  This
can help readability and also maybe performance, although the
performance enhancement is really dependent upon the compiler.

No functional change.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 4fe1b332e67e..ec581b1f0fcb 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1068,9 +1068,6 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 			continue;
 		}
 
-		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
-			ICE_RX_FLEX_DESC_PTYPE_M;
-
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S);
 		if (ice_test_staterr(rx_desc, stat_err_bits))
 			vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1);
@@ -1087,6 +1084,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		total_rx_bytes += skb->len;
 
 		/* populate checksum, VLAN, and protocol */
+		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
+			ICE_RX_FLEX_DESC_PTYPE_M;
+
 		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 
 		/* send completed skb up the stack */
-- 
cgit v1.2.3


From d27525ec1fdd01740edb7d4f3dc801256d543393 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Thu, 8 Aug 2019 07:39:37 -0700
Subject: ice: small efficiency fixes

Add a small bit of efficiency to the code by adding a
prefetch of the port_info structure in order to help
avoid a cache miss a little later on in execution.

Also add an unlikely statement to a branch which
generally will never happen in normal operation.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_txrx.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index ec581b1f0fcb..33dd103035dc 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1226,6 +1226,8 @@ ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc)
 	if (time_after(next_update, rc->next_update))
 		goto clear_counts;
 
+	prefetch(q_vector->vsi->port_info);
+
 	packets = rc->total_pkts;
 	bytes = rc->total_bytes;
 
@@ -1486,7 +1488,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 			clean_complete = false;
 
 	/* Handle case where we are called by netpoll with a budget of 0 */
-	if (budget <= 0)
+	if (unlikely(budget <= 0))
 		return budget;
 
 	/* normally we have 1 Rx ring per q_vector */
-- 
cgit v1.2.3