* [net-next 10/15] ice: Implement transmit and NAPI support
From: Jeff Kirsher @ 2018-03-26 19:46 UTC (permalink / raw)
To: davem
Cc: Anirudh Venkataramanan, netdev, nhorman, sassmann, jogreene,
tbogendoerfer, bpoirier, Jeff Kirsher
In-Reply-To: <20180326194619.1202-1-jeffrey.t.kirsher@intel.com>
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
This patch implements ice_start_xmit (the handler for ndo_start_xmit) and
related functions. ice_start_xmit ultimately calls ice_tx_map, where the
Tx descriptor is built and posted to the hardware by bumping the ring tail.
This patch also implements ice_napi_poll, which is invoked when there's an
interrupt on the VSI's queues. The interrupt can be due to either a
completed Tx or an Rx event. In case of a completed Tx/Rx event, resources
are reclaimed. Additionally, in case of an Rx event, the skb is fetched
and passed up to the network stack.
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@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_lan_tx_rx.h | 46 ++
drivers/net/ethernet/intel/ice/ice_main.c | 55 ++
drivers/net/ethernet/intel/ice/ice_txrx.c | 1026 +++++++++++++++++++++++-
drivers/net/ethernet/intel/ice/ice_txrx.h | 45 ++
5 files changed, 1171 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 46cf82212ed8..6f01395a7f34 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -60,6 +60,7 @@
(((val) << ICE_AQ_VSI_UP_TABLE_UP##i##_S) & \
ICE_AQ_VSI_UP_TABLE_UP##i##_M)
+#define ICE_TX_DESC(R, i) (&(((struct ice_tx_desc *)((R)->desc))[i]))
#define ICE_RX_DESC(R, i) (&(((union ice_32b_rx_flex_desc *)((R)->desc))[i]))
#define ice_for_each_txq(vsi, i) \
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 3c1aeb74d950..e1221b9839d5 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -131,6 +131,33 @@ enum ice_rx_flg64_bits {
ICE_RXFLG_RSVD = 63
};
+/* for ice_32byte_rx_flex_desc.ptype_flexi_flags0 member */
+#define ICE_RX_FLEX_DESC_PTYPE_M (0x3FF) /* 10-bits */
+
+/* for ice_32byte_rx_flex_desc.pkt_length member */
+#define ICE_RX_FLX_DESC_PKT_LEN_M (0x3FFF) /* 14-bits */
+
+enum ice_rx_flex_desc_status_error_0_bits {
+ /* Note: These are predefined bit offsets */
+ ICE_RX_FLEX_DESC_STATUS0_DD_S = 0,
+ ICE_RX_FLEX_DESC_STATUS0_EOF_S,
+ ICE_RX_FLEX_DESC_STATUS0_HBO_S,
+ ICE_RX_FLEX_DESC_STATUS0_L3L4P_S,
+ ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S,
+ ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S,
+ ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S,
+ ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S,
+ ICE_RX_FLEX_DESC_STATUS0_LPBK_S,
+ ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S,
+ ICE_RX_FLEX_DESC_STATUS0_RXE_S,
+ ICE_RX_FLEX_DESC_STATUS0_CRCP_S,
+ ICE_RX_FLEX_DESC_STATUS0_RSS_VALID_S,
+ ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S,
+ ICE_RX_FLEX_DESC_STATUS0_XTRMD0_VALID_S,
+ ICE_RX_FLEX_DESC_STATUS0_XTRMD1_VALID_S,
+ ICE_RX_FLEX_DESC_STATUS0_LAST /* this entry must be last!!! */
+};
+
#define ICE_RXQ_CTX_SIZE_DWORDS 8
#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
@@ -201,6 +228,25 @@ struct ice_tx_desc {
__le64 cmd_type_offset_bsz;
};
+enum ice_tx_desc_dtype_value {
+ ICE_TX_DESC_DTYPE_DATA = 0x0,
+ ICE_TX_DESC_DTYPE_CTX = 0x1,
+ /* DESC_DONE - HW has completed write-back of descriptor */
+ ICE_TX_DESC_DTYPE_DESC_DONE = 0xF,
+};
+
+#define ICE_TXD_QW1_CMD_S 4
+#define ICE_TXD_QW1_CMD_M (0xFFFUL << ICE_TXD_QW1_CMD_S)
+
+enum ice_tx_desc_cmd_bits {
+ ICE_TX_DESC_CMD_EOP = 0x0001,
+ ICE_TX_DESC_CMD_RS = 0x0002,
+};
+
+#define ICE_TXD_QW1_OFFSET_S 16
+#define ICE_TXD_QW1_TX_BUF_SZ_S 34
+#define ICE_TXD_QW1_L2TAG1_S 48
+
#define ICE_LAN_TXQ_MAX_QGRPS 127
#define ICE_LAN_TXQ_MAX_QDIS 1023
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 58e9eb40f64a..dd07bf862afe 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1258,6 +1258,23 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors)
return -ENOMEM;
}
+/**
+ * ice_msix_clean_rings - MSIX mode Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
+{
+ struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
+
+ if (!q_vector->tx.ring && !q_vector->rx.ring)
+ return IRQ_HANDLED;
+
+ napi_schedule(&q_vector->napi);
+
+ return IRQ_HANDLED;
+}
+
/**
* ice_vsi_alloc - Allocates the next available struct vsi in the PF
* @pf: board private structure
@@ -1298,6 +1315,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type)
if (ice_vsi_alloc_arrays(vsi, true))
goto err_rings;
+ /* Setup default MSIX irq handler for VSI */
+ vsi->irq_handler = ice_msix_clean_rings;
break;
default:
dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
@@ -1741,6 +1760,9 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
if (cpu_online(v_idx))
cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
+ if (vsi->netdev)
+ netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll,
+ NAPI_POLL_WEIGHT);
/* tie q_vector and vsi together */
vsi->q_vectors[v_idx] = q_vector;
@@ -2914,6 +2936,21 @@ static int ice_vsi_stop_tx_rx_rings(struct ice_vsi *vsi)
return 0;
}
+/**
+ * ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI
+ * @vsi: the VSI being configured
+ */
+static void ice_napi_enable_all(struct ice_vsi *vsi)
+{
+ int q_idx;
+
+ if (!vsi->netdev)
+ return;
+
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
+ napi_enable(&vsi->q_vectors[q_idx]->napi);
+}
+
/**
* ice_up_complete - Finish the last steps of bringing up a connection
* @vsi: The VSI being configured
@@ -2939,6 +2976,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
return err;
clear_bit(__ICE_DOWN, vsi->state);
+ ice_napi_enable_all(vsi);
ice_vsi_ena_irq(vsi);
if (vsi->port_info &&
@@ -2954,6 +2992,21 @@ static int ice_up_complete(struct ice_vsi *vsi)
return err;
}
+/**
+ * ice_napi_disable_all - Disable NAPI for all q_vectors in the VSI
+ * @vsi: VSI having NAPI disabled
+ */
+static void ice_napi_disable_all(struct ice_vsi *vsi)
+{
+ int q_idx;
+
+ if (!vsi->netdev)
+ return;
+
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
+ napi_disable(&vsi->q_vectors[q_idx]->napi);
+}
+
/**
* ice_down - Shutdown the connection
* @vsi: The VSI being stopped
@@ -2972,6 +3025,7 @@ static int ice_down(struct ice_vsi *vsi)
ice_vsi_dis_irq(vsi);
err = ice_vsi_stop_tx_rx_rings(vsi);
+ ice_napi_disable_all(vsi);
ice_for_each_txq(vsi, i)
ice_clean_tx_ring(vsi->tx_rings[i]);
@@ -3251,4 +3305,5 @@ static int ice_stop(struct net_device *netdev)
static const struct net_device_ops ice_netdev_ops = {
.ndo_open = ice_open,
.ndo_stop = ice_stop,
+ .ndo_start_xmit = ice_start_xmit,
};
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 6190ea30ee01..1ccf8e69b85a 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -7,6 +7,8 @@
#include <linux/mm.h>
#include "ice.h"
+#define ICE_RX_HDR_SIZE 256
+
/**
* ice_unmap_and_free_tx_buf - Release a Tx buffer
* @ring: the ring that owns the buffer
@@ -92,6 +94,129 @@ 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)
+{
+ unsigned int total_bytes = 0, total_pkts = 0;
+ unsigned int budget = vsi->work_lmt;
+ s16 i = tx_ring->next_to_clean;
+ struct ice_tx_desc *tx_desc;
+ struct ice_tx_buf *tx_buf;
+
+ tx_buf = &tx_ring->tx_buf[i];
+ tx_desc = ICE_TX_DESC(tx_ring, i);
+ i -= tx_ring->count;
+
+ do {
+ struct ice_tx_desc *eop_desc = tx_buf->next_to_watch;
+
+ /* if next_to_watch is not set then there is no work pending */
+ if (!eop_desc)
+ break;
+
+ smp_rmb(); /* prevent any other reads prior to eop_desc */
+
+ /* if the descriptor isn't done, no work yet to do */
+ if (!(eop_desc->cmd_type_offset_bsz &
+ cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
+ break;
+
+ /* clear next_to_watch to prevent false hangs */
+ tx_buf->next_to_watch = NULL;
+
+ /* update the statistics for this packet */
+ total_bytes += tx_buf->bytecount;
+ total_pkts += tx_buf->gso_segs;
+
+ /* free the skb */
+ napi_consume_skb(tx_buf->skb, napi_budget);
+
+ /* unmap skb header data */
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buf, dma),
+ dma_unmap_len(tx_buf, len),
+ DMA_TO_DEVICE);
+
+ /* clear tx_buf data */
+ tx_buf->skb = NULL;
+ dma_unmap_len_set(tx_buf, len, 0);
+
+ /* unmap remaining buffers */
+ while (tx_desc != eop_desc) {
+ tx_buf++;
+ tx_desc++;
+ i++;
+ if (unlikely(!i)) {
+ i -= tx_ring->count;
+ tx_buf = tx_ring->tx_buf;
+ tx_desc = ICE_TX_DESC(tx_ring, 0);
+ }
+
+ /* unmap any remaining paged data */
+ if (dma_unmap_len(tx_buf, len)) {
+ dma_unmap_page(tx_ring->dev,
+ dma_unmap_addr(tx_buf, dma),
+ dma_unmap_len(tx_buf, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buf, len, 0);
+ }
+ }
+
+ /* move us one more past the eop_desc for start of next pkt */
+ tx_buf++;
+ tx_desc++;
+ i++;
+ if (unlikely(!i)) {
+ i -= tx_ring->count;
+ tx_buf = tx_ring->tx_buf;
+ tx_desc = ICE_TX_DESC(tx_ring, 0);
+ }
+
+ prefetch(tx_desc);
+
+ /* update budget accounting */
+ budget--;
+ } while (likely(budget));
+
+ i += tx_ring->count;
+ tx_ring->next_to_clean = i;
+ u64_stats_update_begin(&tx_ring->syncp);
+ tx_ring->stats.bytes += total_bytes;
+ tx_ring->stats.pkts += total_pkts;
+ u64_stats_update_end(&tx_ring->syncp);
+ tx_ring->q_vector->tx.total_bytes += total_bytes;
+ tx_ring->q_vector->tx.total_pkts += total_pkts;
+
+ netdev_tx_completed_queue(txring_txq(tx_ring), total_pkts,
+ total_bytes);
+
+#define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2))
+ if (unlikely(total_pkts && netif_carrier_ok(tx_ring->netdev) &&
+ (ICE_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
+ /* Make sure that anybody stopping the queue after this
+ * sees the new next_to_clean.
+ */
+ smp_mb();
+ if (__netif_subqueue_stopped(tx_ring->netdev,
+ tx_ring->q_index) &&
+ !test_bit(__ICE_DOWN, vsi->state)) {
+ netif_wake_subqueue(tx_ring->netdev,
+ tx_ring->q_index);
+ ++tx_ring->tx_stats.restart_q;
+ }
+ }
+
+ return !!budget;
+}
+
/**
* ice_setup_tx_ring - Allocate the Tx descriptors
* @tx_ring: the tx ring to set up
@@ -274,13 +399,17 @@ static bool ice_alloc_mapped_page(struct ice_ring *rx_ring,
dma_addr_t dma;
/* since we are recycling buffers we should seldom need to alloc */
- if (likely(page))
+ if (likely(page)) {
+ rx_ring->rx_stats.page_reuse_count++;
return true;
+ }
/* alloc new page for storage */
page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
- if (unlikely(!page))
+ if (unlikely(!page)) {
+ rx_ring->rx_stats.alloc_page_failed++;
return false;
+ }
/* map page for use */
dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
@@ -290,6 +419,7 @@ static bool ice_alloc_mapped_page(struct ice_ring *rx_ring,
*/
if (dma_mapping_error(rx_ring->dev, dma)) {
__free_pages(page, 0);
+ rx_ring->rx_stats.alloc_page_failed++;
return false;
}
@@ -359,3 +489,895 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
*/
return true;
}
+
+/**
+ * ice_page_is_reserved - check if reuse is possible
+ * @page: page struct to check
+ */
+static bool ice_page_is_reserved(struct page *page)
+{
+ return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
+}
+
+/**
+ * ice_add_rx_frag - Add contents of Rx buffer to sk_buff
+ * @rx_buf: buffer containing page to add
+ * @rx_desc: descriptor containing length of buffer written by hardware
+ * @skb: sk_buf to place the data into
+ *
+ * This function will add the data contained in rx_buf->page to the skb.
+ * This is done either through a direct copy if the data in the buffer is
+ * less than the skb header size, otherwise it will just attach the page as
+ * a frag to the skb.
+ *
+ * The function will then update the page offset if necessary and return
+ * true if the buffer can be reused by the adapter.
+ */
+static bool ice_add_rx_frag(struct ice_rx_buf *rx_buf,
+ union ice_32b_rx_flex_desc *rx_desc,
+ struct sk_buff *skb)
+{
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = ICE_RXBUF_2048;
+#else
+ unsigned int last_offset = PAGE_SIZE - ICE_RXBUF_2048;
+ unsigned int truesize;
+#endif /* PAGE_SIZE < 8192) */
+
+ struct page *page;
+ unsigned int size;
+
+ size = le16_to_cpu(rx_desc->wb.pkt_len) &
+ ICE_RX_FLX_DESC_PKT_LEN_M;
+
+ page = rx_buf->page;
+
+#if (PAGE_SIZE >= 8192)
+ truesize = ALIGN(size, L1_CACHE_BYTES);
+#endif /* PAGE_SIZE >= 8192) */
+
+ /* will the data fit in the skb we allocated? if so, just
+ * copy it as it is pretty small anyway
+ */
+ if (size <= ICE_RX_HDR_SIZE && !skb_is_nonlinear(skb)) {
+ unsigned char *va = page_address(page) + rx_buf->page_offset;
+
+ memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+
+ /* page is not reserved, we can reuse buffer as-is */
+ if (likely(!ice_page_is_reserved(page)))
+ return true;
+
+ /* this page cannot be reused so discard it */
+ __free_pages(page, 0);
+ return false;
+ }
+
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+ rx_buf->page_offset, size, truesize);
+
+ /* avoid re-using remote pages */
+ if (unlikely(ice_page_is_reserved(page)))
+ return false;
+
+#if (PAGE_SIZE < 8192)
+ /* if we are only owner of page we can reuse it */
+ if (unlikely(page_count(page) != 1))
+ return false;
+
+ /* flip page offset to other buffer */
+ rx_buf->page_offset ^= truesize;
+#else
+ /* move offset up to the next cache line */
+ rx_buf->page_offset += truesize;
+
+ if (rx_buf->page_offset > last_offset)
+ return false;
+#endif /* PAGE_SIZE < 8192) */
+
+ /* Even if we own the page, we are not allowed to use atomic_set()
+ * This would break get_page_unless_zero() users.
+ */
+ get_page(rx_buf->page);
+
+ return true;
+}
+
+/**
+ * ice_reuse_rx_page - page flip buffer and store it back on the ring
+ * @rx_ring: rx descriptor ring to store buffers on
+ * @old_buf: donor buffer to have page reused
+ *
+ * Synchronizes page for reuse by the adapter
+ */
+static void ice_reuse_rx_page(struct ice_ring *rx_ring,
+ struct ice_rx_buf *old_buf)
+{
+ u16 nta = rx_ring->next_to_alloc;
+ struct ice_rx_buf *new_buf;
+
+ new_buf = &rx_ring->rx_buf[nta];
+
+ /* update, and store next to alloc */
+ nta++;
+ rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+ /* transfer page from old buffer to new buffer */
+ *new_buf = *old_buf;
+}
+
+/**
+ * ice_fetch_rx_buf - Allocate skb and populate it
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_desc: descriptor containing info written by hardware
+ *
+ * This function allocates an skb on the fly, and populates it with the page
+ * data from the current receive descriptor, taking care to set up the skb
+ * correctly, as well as handling calling the page recycle function if
+ * necessary.
+ */
+static struct sk_buff *ice_fetch_rx_buf(struct ice_ring *rx_ring,
+ union ice_32b_rx_flex_desc *rx_desc)
+{
+ struct ice_rx_buf *rx_buf;
+ struct sk_buff *skb;
+ struct page *page;
+
+ rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
+ page = rx_buf->page;
+ prefetchw(page);
+
+ skb = rx_buf->skb;
+
+ if (likely(!skb)) {
+ u8 *page_addr = page_address(page) + rx_buf->page_offset;
+
+ /* prefetch first cache line of first page */
+ prefetch(page_addr);
+#if L1_CACHE_BYTES < 128
+ prefetch((void *)(page_addr + L1_CACHE_BYTES));
+#endif /* L1_CACHE_BYTES */
+
+ /* allocate a skb to store the frags */
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+ ICE_RX_HDR_SIZE,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!skb)) {
+ rx_ring->rx_stats.alloc_buf_failed++;
+ return NULL;
+ }
+
+ /* we will be copying header into skb->data in
+ * pskb_may_pull so it is in our interest to prefetch
+ * it now to avoid a possible cache miss
+ */
+ prefetchw(skb->data);
+
+ skb_record_rx_queue(skb, rx_ring->q_index);
+ } else {
+ /* 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,
+ ICE_RXBUF_2048,
+ DMA_FROM_DEVICE);
+
+ rx_buf->skb = NULL;
+ }
+
+ /* pull page into skb */
+ if (ice_add_rx_frag(rx_buf, rx_desc, skb)) {
+ /* 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 {
+ /* we are not reusing the buffer so unmap it */
+ dma_unmap_page(rx_ring->dev, rx_buf->dma, PAGE_SIZE,
+ DMA_FROM_DEVICE);
+ }
+
+ /* clear contents of buffer_info */
+ rx_buf->page = NULL;
+
+ return skb;
+}
+
+/**
+ * ice_pull_tail - ice specific version of skb_pull_tail
+ * @skb: pointer to current skb being adjusted
+ *
+ * This function is an ice specific version of __pskb_pull_tail. The
+ * main difference between this version and the original function is that
+ * this function can make several assumptions about the state of things
+ * that allow for significant optimizations versus the standard function.
+ * As a result we can do things like drop a frag and maintain an accurate
+ * truesize for the skb.
+ */
+static void ice_pull_tail(struct sk_buff *skb)
+{
+ struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ unsigned int pull_len;
+ unsigned char *va;
+
+ /* it is valid to use page_address instead of kmap since we are
+ * working with pages allocated out of the lomem pool per
+ * alloc_page(GFP_ATOMIC)
+ */
+ va = skb_frag_address(frag);
+
+ /* we need the header to contain the greater of either ETH_HLEN or
+ * 60 bytes if the skb->len is less than 60 for skb_pad.
+ */
+ pull_len = eth_get_headlen(va, ICE_RX_HDR_SIZE);
+
+ /* align pull length to size of long to optimize memcpy performance */
+ skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+
+ /* update all of the pointers */
+ skb_frag_size_sub(frag, pull_len);
+ frag->page_offset += pull_len;
+ skb->data_len -= pull_len;
+ skb->tail += pull_len;
+}
+
+/**
+ * ice_cleanup_headers - Correct empty headers
+ * @skb: pointer to current skb being fixed
+ *
+ * Also address the case where we are pulling data in on pages only
+ * and as such no data is present in the skb header.
+ *
+ * In addition if skb is not at least 60 bytes we need to pad it so that
+ * it is large enough to qualify as a valid Ethernet frame.
+ *
+ * Returns true if an error was encountered and skb was freed.
+ */
+static bool ice_cleanup_headers(struct sk_buff *skb)
+{
+ /* place header in linear portion of buffer */
+ if (skb_is_nonlinear(skb))
+ ice_pull_tail(skb);
+
+ /* if eth_skb_pad returns an error the skb was freed */
+ if (eth_skb_pad(skb))
+ return true;
+
+ return false;
+}
+
+/**
+ * ice_test_staterr - tests bits in Rx descriptor status and error fields
+ * @rx_desc: pointer to receive descriptor (in le64 format)
+ * @stat_err_bits: value to mask
+ *
+ * This function does some fast chicanery in order to return the
+ * value of the mask which is really only used for boolean tests.
+ * The status_error_len doesn't need to be shifted because it begins
+ * at offset zero.
+ */
+static bool ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc,
+ const u16 stat_err_bits)
+{
+ return !!(rx_desc->wb.status_error0 &
+ cpu_to_le16(stat_err_bits));
+}
+
+/**
+ * ice_is_non_eop - process handling of non-EOP buffers
+ * @rx_ring: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+ * @skb: Current socket buffer containing buffer in progress
+ *
+ * This function updates next to clean. If the buffer is an EOP buffer
+ * this function exits returning false, otherwise it will place the
+ * sk_buff in the next buffer to be chained and return true indicating
+ * that this is in fact a non-EOP buffer.
+ */
+static bool ice_is_non_eop(struct ice_ring *rx_ring,
+ union ice_32b_rx_flex_desc *rx_desc,
+ struct sk_buff *skb)
+{
+ u32 ntc = rx_ring->next_to_clean + 1;
+
+ /* fetch, update, and store next to clean */
+ ntc = (ntc < rx_ring->count) ? ntc : 0;
+ rx_ring->next_to_clean = ntc;
+
+ prefetch(ICE_RX_DESC(rx_ring, ntc));
+
+ /* if we are the last buffer then there is nothing else to do */
+#define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)
+ if (likely(ice_test_staterr(rx_desc, ICE_RXD_EOF)))
+ return false;
+
+ /* place skb in next buffer to be received */
+ rx_ring->rx_buf[ntc].skb = skb;
+ rx_ring->rx_stats.non_eop_descs++;
+
+ return true;
+}
+
+/**
+ * ice_receive_skb - Send a completed packet up the stack
+ * @rx_ring: rx ring in play
+ * @skb: packet to send up
+ * @vlan_tag: vlan tag for packet
+ *
+ * This function sends the completed packet (via. skb) up the stack using
+ * gro receive functions (with/without vlan tag)
+ */
+static void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb,
+ u16 vlan_tag)
+{
+ if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ (vlan_tag & VLAN_VID_MASK)) {
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+ }
+ napi_gro_receive(&rx_ring->q_vector->napi, skb);
+}
+
+/**
+ * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @budget: Total limit on number of packets to process
+ *
+ * This function provides a "bounce buffer" approach to Rx interrupt
+ * processing. The advantage to this is that on systems that have
+ * expensive overhead for IOMMU access this provides a means of avoiding
+ * it by maintaining the mapping of the page to the system.
+ *
+ * Returns amount of work completed
+ */
+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;
+
+ /* start the loop to process RX packets bounded by 'budget' */
+ while (likely(total_rx_pkts < (unsigned int)budget)) {
+ union ice_32b_rx_flex_desc *rx_desc;
+ struct sk_buff *skb;
+ u16 stat_err_bits;
+ u16 vlan_tag = 0;
+
+ /* 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);
+
+ /* status_error_len will always be zero for unused descriptors
+ * because it's cleared in cleanup, and overlaps with hdr_addr
+ * which is always zero because packet split isn't used, if the
+ * hardware wrote DD then it will be non-zero
+ */
+ stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
+ if (!ice_test_staterr(rx_desc, stat_err_bits))
+ break;
+
+ /* This memory barrier is needed to keep us from reading
+ * any other fields out of the rx_desc until we know the
+ * DD bit is set.
+ */
+ dma_rmb();
+
+ /* allocate (if needed) and populate skb */
+ skb = ice_fetch_rx_buf(rx_ring, rx_desc);
+ if (!skb)
+ break;
+
+ cleaned_count++;
+
+ /* skip if it is NOP desc */
+ if (ice_is_non_eop(rx_ring, rx_desc, skb))
+ continue;
+
+ stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
+ if (unlikely(ice_test_staterr(rx_desc, stat_err_bits))) {
+ dev_kfree_skb_any(skb);
+ continue;
+ }
+
+ 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);
+
+ /* correct empty headers and pad skb if needed (to make valid
+ * ethernet frame
+ */
+ if (ice_cleanup_headers(skb)) {
+ skb = NULL;
+ continue;
+ }
+
+ /* probably a little skewed due to removing CRC */
+ total_rx_bytes += skb->len;
+
+ /* send completed skb up the stack */
+ ice_receive_skb(rx_ring, skb, vlan_tag);
+
+ /* update budget accounting */
+ total_rx_pkts++;
+ }
+
+ /* update queue and vector specific stats */
+ u64_stats_update_begin(&rx_ring->syncp);
+ rx_ring->stats.pkts += total_rx_pkts;
+ rx_ring->stats.bytes += total_rx_bytes;
+ u64_stats_update_end(&rx_ring->syncp);
+ rx_ring->q_vector->rx.total_pkts += total_rx_pkts;
+ rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
+
+ /* guarantee a trip back through this routine if there was a failure */
+ return failure ? budget : (int)total_rx_pkts;
+}
+
+/**
+ * ice_napi_poll - NAPI polling Rx/Tx cleanup routine
+ * @napi: napi struct with our devices info in it
+ * @budget: amount of work driver is allowed to do this pass, in packets
+ *
+ * This function will clean all queues associated with a q_vector.
+ *
+ * Returns the amount of work done
+ */
+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;
+ int work_done = 0;
+
+ /* Since the actual Tx work is minimal, we can give the Tx a larger
+ * 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))
+ clean_complete = false;
+
+ /* Handle case where we are called by netpoll with a budget of 0 */
+ 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)
+ budget_per_ring = max(budget / q_vector->num_ring_rx, 1);
+
+ ice_for_each_ring(ring, q_vector->rx) {
+ int cleaned;
+
+ cleaned = ice_clean_rx_irq(ring, budget_per_ring);
+ work_done += cleaned;
+ /* if we clean as many as budgeted, we must not be done */
+ if (cleaned >= budget_per_ring)
+ clean_complete = false;
+ }
+
+ /* If work not completed, return budget and polling will return */
+ if (!clean_complete)
+ return budget;
+
+ /* Work is done so exit the polling mode and re-enable the interrupt */
+ napi_complete_done(napi, work_done);
+ if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+ ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
+ return 0;
+}
+
+/* helper function for building cmd/type/offset */
+static __le64
+build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
+{
+ return cpu_to_le64(ICE_TX_DESC_DTYPE_DATA |
+ (td_cmd << ICE_TXD_QW1_CMD_S) |
+ (td_offset << ICE_TXD_QW1_OFFSET_S) |
+ ((u64)size << ICE_TXD_QW1_TX_BUF_SZ_S) |
+ (td_tag << ICE_TXD_QW1_L2TAG1_S));
+}
+
+/**
+ * __ice_maybe_stop_tx - 2nd level check for tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size: the size buffer we want to assure is available
+ *
+ * Returns -EBUSY if a stop is needed, else 0
+ */
+static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
+{
+ netif_stop_subqueue(tx_ring->netdev, tx_ring->q_index);
+ /* Memory barrier before checking head and tail */
+ smp_mb();
+
+ /* Check again in a case another CPU has just made room available. */
+ if (likely(ICE_DESC_UNUSED(tx_ring) < size))
+ return -EBUSY;
+
+ /* A reprieve! - use start_subqueue because it doesn't call schedule */
+ netif_start_subqueue(tx_ring->netdev, tx_ring->q_index);
+ ++tx_ring->tx_stats.restart_q;
+ return 0;
+}
+
+/**
+ * ice_maybe_stop_tx - 1st level check for tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size: the size buffer we want to assure is available
+ *
+ * Returns 0 if stop is not needed
+ */
+static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
+{
+ if (likely(ICE_DESC_UNUSED(tx_ring) >= size))
+ return 0;
+ return __ice_maybe_stop_tx(tx_ring, size);
+}
+
+/**
+ * ice_tx_map - Build the Tx descriptor
+ * @tx_ring: ring to send buffer on
+ * @first: first buffer info buffer to use
+ *
+ * This function loops over the skb data pointed to by *first
+ * and gets a physical address for each memory location and programs
+ * it and the length into the transmit descriptor.
+ */
+static void ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first)
+{
+ u64 td_offset = 0, td_tag = 0, td_cmd = 0;
+ u16 i = tx_ring->next_to_use;
+ struct skb_frag_struct *frag;
+ unsigned int data_len, size;
+ struct ice_tx_desc *tx_desc;
+ struct ice_tx_buf *tx_buf;
+ struct sk_buff *skb;
+ dma_addr_t dma;
+
+ skb = first->skb;
+
+ data_len = skb->data_len;
+ size = skb_headlen(skb);
+
+ tx_desc = ICE_TX_DESC(tx_ring, i);
+
+ dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
+
+ tx_buf = first;
+
+ for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
+ unsigned int max_data = ICE_MAX_DATA_PER_TXD_ALIGNED;
+
+ if (dma_mapping_error(tx_ring->dev, dma))
+ goto dma_error;
+
+ /* record length, and DMA address */
+ dma_unmap_len_set(tx_buf, len, size);
+ dma_unmap_addr_set(tx_buf, dma, dma);
+
+ /* align size to end of page */
+ max_data += -dma & (ICE_MAX_READ_REQ_SIZE - 1);
+ tx_desc->buf_addr = cpu_to_le64(dma);
+
+ /* account for data chunks larger than the hardware
+ * can handle
+ */
+ while (unlikely(size > ICE_MAX_DATA_PER_TXD)) {
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset, max_data, td_tag);
+
+ tx_desc++;
+ i++;
+
+ if (i == tx_ring->count) {
+ tx_desc = ICE_TX_DESC(tx_ring, 0);
+ i = 0;
+ }
+
+ dma += max_data;
+ size -= max_data;
+
+ max_data = ICE_MAX_DATA_PER_TXD_ALIGNED;
+ tx_desc->buf_addr = cpu_to_le64(dma);
+ }
+
+ if (likely(!data_len))
+ break;
+
+ tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset,
+ size, td_tag);
+
+ tx_desc++;
+ i++;
+
+ if (i == tx_ring->count) {
+ tx_desc = ICE_TX_DESC(tx_ring, 0);
+ i = 0;
+ }
+
+ size = skb_frag_size(frag);
+ data_len -= size;
+
+ dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size,
+ DMA_TO_DEVICE);
+
+ tx_buf = &tx_ring->tx_buf[i];
+ }
+
+ /* record bytecount for BQL */
+ netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
+
+ /* record SW timestamp if HW timestamp is not available */
+ skb_tx_timestamp(first->skb);
+
+ i++;
+ if (i == tx_ring->count)
+ i = 0;
+
+ /* write last descriptor with RS and EOP bits */
+ td_cmd |= (u64)(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS);
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset, size, td_tag);
+
+ /* Force memory writes to complete before letting h/w know there
+ * are new descriptors to fetch.
+ *
+ * We also use this memory barrier to make certain all of the
+ * status bits have been updated before next_to_watch is written.
+ */
+ wmb();
+
+ /* set next_to_watch value indicating a packet is present */
+ first->next_to_watch = tx_desc;
+
+ tx_ring->next_to_use = i;
+
+ ice_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+ /* notify HW of packet */
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ writel(i, tx_ring->tail);
+
+ /* we need this if more than one processor can write to our tail
+ * at a time, it synchronizes IO on IA64/Altix systems
+ */
+ mmiowb();
+ }
+
+ return;
+
+dma_error:
+ /* clear dma mappings for failed tx_buf map */
+ for (;;) {
+ tx_buf = &tx_ring->tx_buf[i];
+ ice_unmap_and_free_tx_buf(tx_ring, tx_buf);
+ if (tx_buf == first)
+ break;
+ if (i == 0)
+ i = tx_ring->count;
+ i--;
+ }
+
+ tx_ring->next_to_use = i;
+}
+
+/**
+ * ice_txd_use_count - estimate the number of descriptors needed for Tx
+ * @size: transmit request size in bytes
+ *
+ * Due to hardware alignment restrictions (4K alignment), we need to
+ * assume that we can have no more than 12K of data per descriptor, even
+ * though each descriptor can take up to 16K - 1 bytes of aligned memory.
+ * Thus, we need to divide by 12K. But division is slow! Instead,
+ * we decompose the operation into shifts and one relatively cheap
+ * multiply operation.
+ *
+ * To divide by 12K, we first divide by 4K, then divide by 3:
+ * To divide by 4K, shift right by 12 bits
+ * To divide by 3, multiply by 85, then divide by 256
+ * (Divide by 256 is done by shifting right by 8 bits)
+ * Finally, we add one to round up. Because 256 isn't an exact multiple of
+ * 3, we'll underestimate near each multiple of 12K. This is actually more
+ * accurate as we have 4K - 1 of wiggle room that we can fit into the last
+ * segment. For our purposes this is accurate out to 1M which is orders of
+ * magnitude greater than our largest possible GSO size.
+ *
+ * This would then be implemented as:
+ * return (((size >> 12) * 85) >> 8) + 1;
+ *
+ * Since multiplication and division are commutative, we can reorder
+ * operations into:
+ * return ((size * 85) >> 20) + 1;
+ */
+static unsigned int ice_txd_use_count(unsigned int size)
+{
+ return ((size * 85) >> 20) + 1;
+}
+
+/**
+ * ice_xmit_desc_count - calculate number of tx descriptors needed
+ * @skb: send buffer
+ *
+ * Returns number of data descriptors needed for this skb.
+ */
+static unsigned int ice_xmit_desc_count(struct sk_buff *skb)
+{
+ const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
+ unsigned int count = 0, size = skb_headlen(skb);
+
+ for (;;) {
+ count += ice_txd_use_count(size);
+
+ if (!nr_frags--)
+ break;
+
+ size = skb_frag_size(frag++);
+ }
+
+ return count;
+}
+
+/**
+ * __ice_chk_linearize - Check if there are more than 8 buffers per packet
+ * @skb: send buffer
+ *
+ * Note: This HW can't DMA more than 8 buffers to build a packet on the wire
+ * and so we need to figure out the cases where we need to linearize the skb.
+ *
+ * For TSO we need to count the TSO header and segment payload separately.
+ * As such we need to check cases where we have 7 fragments or more as we
+ * can potentially require 9 DMA transactions, 1 for the TSO header, 1 for
+ * the segment payload in the first descriptor, and another 7 for the
+ * fragments.
+ */
+static bool __ice_chk_linearize(struct sk_buff *skb)
+{
+ const struct skb_frag_struct *frag, *stale;
+ int nr_frags, sum;
+
+ /* no need to check if number of frags is less than 7 */
+ nr_frags = skb_shinfo(skb)->nr_frags;
+ if (nr_frags < (ICE_MAX_BUF_TXD - 1))
+ return false;
+
+ /* We need to walk through the list and validate that each group
+ * of 6 fragments totals at least gso_size.
+ */
+ nr_frags -= ICE_MAX_BUF_TXD - 2;
+ frag = &skb_shinfo(skb)->frags[0];
+
+ /* Initialize size to the negative value of gso_size minus 1. We
+ * use this as the worst case scenerio in which the frag ahead
+ * of us only provides one byte which is why we are limited to 6
+ * descriptors for a single transmit as the header and previous
+ * fragment are already consuming 2 descriptors.
+ */
+ sum = 1 - skb_shinfo(skb)->gso_size;
+
+ /* Add size of frags 0 through 4 to create our initial sum */
+ sum += skb_frag_size(frag++);
+ sum += skb_frag_size(frag++);
+ sum += skb_frag_size(frag++);
+ sum += skb_frag_size(frag++);
+ sum += skb_frag_size(frag++);
+
+ /* Walk through fragments adding latest fragment, testing it, and
+ * then removing stale fragments from the sum.
+ */
+ stale = &skb_shinfo(skb)->frags[0];
+ for (;;) {
+ sum += skb_frag_size(frag++);
+
+ /* if sum is negative we failed to make sufficient progress */
+ if (sum < 0)
+ return true;
+
+ if (!nr_frags--)
+ break;
+
+ sum -= skb_frag_size(stale++);
+ }
+
+ return false;
+}
+
+/**
+ * ice_chk_linearize - Check if there are more than 8 fragments per packet
+ * @skb: send buffer
+ * @count: number of buffers used
+ *
+ * Note: Our HW can't scatter-gather more than 8 fragments to build
+ * a packet on the wire and so we need to figure out the cases where we
+ * need to linearize the skb.
+ */
+static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count)
+{
+ /* Both TSO and single send will work if count is less than 8 */
+ if (likely(count < ICE_MAX_BUF_TXD))
+ return false;
+
+ if (skb_is_gso(skb))
+ return __ice_chk_linearize(skb);
+
+ /* we can support up to 8 data buffers for a single send */
+ return count != ICE_MAX_BUF_TXD;
+}
+
+/**
+ * ice_xmit_frame_ring - Sends buffer on Tx ring
+ * @skb: send buffer
+ * @tx_ring: ring to send buffer on
+ *
+ * Returns NETDEV_TX_OK if sent, else an error code
+ */
+static netdev_tx_t
+ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
+{
+ struct ice_tx_buf *first;
+ unsigned int count;
+
+ count = ice_xmit_desc_count(skb);
+ if (ice_chk_linearize(skb, count)) {
+ if (__skb_linearize(skb))
+ goto out_drop;
+ count = ice_txd_use_count(skb->len);
+ tx_ring->tx_stats.tx_linearize++;
+ }
+
+ /* need: 1 descriptor per page * PAGE_SIZE/ICE_MAX_DATA_PER_TXD,
+ * + 1 desc for skb_head_len/ICE_MAX_DATA_PER_TXD,
+ * + 4 desc gap to avoid the cache line where head is,
+ * + 1 desc for context descriptor,
+ * otherwise try next time
+ */
+ if (ice_maybe_stop_tx(tx_ring, count + 4 + 1)) {
+ tx_ring->tx_stats.tx_busy++;
+ return NETDEV_TX_BUSY;
+ }
+
+ /* record the location of the first descriptor for this packet */
+ first = &tx_ring->tx_buf[tx_ring->next_to_use];
+ first->skb = skb;
+ first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
+ first->gso_segs = 1;
+
+ ice_tx_map(tx_ring, first);
+ return NETDEV_TX_OK;
+
+out_drop:
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+}
+
+/**
+ * ice_start_xmit - Selects the correct VSI and Tx queue to send buffer
+ * @skb: send buffer
+ * @netdev: network interface device structure
+ *
+ * Returns NETDEV_TX_OK if sent, else an error code
+ */
+netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_ring *tx_ring;
+
+ tx_ring = vsi->tx_rings[skb->queue_mapping];
+
+ /* hardware can't handle really short frames, hardware padding works
+ * beyond this point
+ */
+ if (skb_put_padto(skb, ICE_MIN_TX_LEN))
+ return NETDEV_TX_OK;
+
+ return ice_xmit_frame_ring(skb, tx_ring);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index b7015cfad2d7..8fa4450514b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -7,8 +7,23 @@
#define ICE_DFLT_IRQ_WORK 256
#define ICE_RXBUF_2048 2048
#define ICE_MAX_CHAINED_RX_BUFS 5
+#define ICE_MAX_BUF_TXD 8
+#define ICE_MIN_TX_LEN 17
+
+/* The size limit for a transmit buffer in a descriptor is (16K - 1).
+ * In order to align with the read requests we will align the value to
+ * the nearest 4K which represents our maximum read request size.
+ */
+#define ICE_MAX_READ_REQ_SIZE 4096
+#define ICE_MAX_DATA_PER_TXD (16 * 1024 - 1)
+#define ICE_MAX_DATA_PER_TXD_ALIGNED \
+ (~(ICE_MAX_READ_REQ_SIZE - 1) & ICE_MAX_DATA_PER_TXD)
+
+#define ICE_RX_BUF_WRITE 16 /* Must be power of 2 */
#define ICE_MAX_TXQ_PER_TXQG 128
+/* Tx Descriptors needed, worst case */
+#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
#define ICE_DESC_UNUSED(R) \
((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
(R)->next_to_clean - (R)->next_to_use - 1)
@@ -30,6 +45,24 @@ struct ice_rx_buf {
unsigned int page_offset;
};
+struct ice_q_stats {
+ u64 pkts;
+ u64 bytes;
+};
+
+struct ice_txq_stats {
+ u64 restart_q;
+ u64 tx_busy;
+ u64 tx_linearize;
+};
+
+struct ice_rxq_stats {
+ u64 non_eop_descs;
+ u64 alloc_page_failed;
+ u64 alloc_buf_failed;
+ u64 page_reuse_count;
+};
+
/* this enum matches hardware bits and is meant to be used by DYN_CTLN
* registers and QINT registers or more generally anywhere in the manual
* mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any
@@ -94,6 +127,15 @@ struct ice_ring {
u16 next_to_clean;
bool ring_active; /* is ring online or not */
+
+ /* stats structs */
+ struct ice_q_stats stats;
+ struct u64_stats_sync syncp;
+ union {
+ struct ice_txq_stats tx_stats;
+ struct ice_rxq_stats rx_stats;
+ };
+
unsigned int size; /* length of descriptor ring in bytes */
dma_addr_t dma; /* physical address of ring */
struct rcu_head rcu; /* to avoid race on free */
@@ -121,10 +163,13 @@ struct ice_ring_container {
for (pos = (head).ring; pos; pos = pos->next)
bool ice_alloc_rx_bufs(struct ice_ring *rxr, u16 cleaned_count);
+netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev);
void ice_clean_tx_ring(struct ice_ring *tx_ring);
void ice_clean_rx_ring(struct ice_ring *rx_ring);
int ice_setup_tx_ring(struct ice_ring *tx_ring);
int ice_setup_rx_ring(struct ice_ring *rx_ring);
void ice_free_tx_ring(struct ice_ring *tx_ring);
void ice_free_rx_ring(struct ice_ring *rx_ring);
+int ice_napi_poll(struct napi_struct *napi, int budget);
+
#endif /* _ICE_TXRX_H_ */
--
2.14.3
^ permalink raw reply related
* [net-next 11/15] ice: Add support for VLANs and offloads
From: Jeff Kirsher @ 2018-03-26 19:46 UTC (permalink / raw)
To: davem
Cc: Anirudh Venkataramanan, netdev, nhorman, sassmann, jogreene,
tbogendoerfer, bpoirier, Jeff Kirsher
In-Reply-To: <20180326194619.1202-1-jeffrey.t.kirsher@intel.com>
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
This patch adds support for VLANs. When a VLAN is created a switch filter
is added to direct the VLAN traffic to the corresponding VSI. When a VLAN
is deleted, the filter is deleted as well.
This patch also adds support for the following hardware offloads.
1) VLAN tag insertion/stripping
2) Receive Side Scaling (RSS)
3) Tx checksum and TCP segmentation
4) Rx checksum
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ice/ice.h | 19 +
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 62 +++
drivers/net/ethernet/intel/ice/ice_common.c | 188 ++++++++
drivers/net/ethernet/intel/ice/ice_common.h | 13 +
drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h | 169 +++++++
drivers/net/ethernet/intel/ice/ice_main.c | 601 +++++++++++++++++++++++-
drivers/net/ethernet/intel/ice/ice_switch.c | 169 +++++++
drivers/net/ethernet/intel/ice/ice_switch.h | 4 +
drivers/net/ethernet/intel/ice/ice_txrx.c | 405 +++++++++++++++-
drivers/net/ethernet/intel/ice/ice_txrx.h | 17 +
10 files changed, 1631 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 6f01395a7f34..51cc955c7220 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -23,7 +23,10 @@
#include <linux/delay.h>
#include <linux/bitmap.h>
#include <linux/log2.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
#include <linux/if_bridge.h>
+#include <net/ipv6.h>
#include "ice_devids.h"
#include "ice_type.h"
#include "ice_txrx.h"
@@ -47,6 +50,8 @@
#define ICE_MAX_SCATTER_RXQS 16
#define ICE_Q_WAIT_RETRY_LIMIT 10
#define ICE_Q_WAIT_MAX_RETRY (5 * ICE_Q_WAIT_RETRY_LIMIT)
+#define ICE_MAX_LG_RSS_QS 256
+#define ICE_MAX_SMALL_RSS_QS 8
#define ICE_RES_VALID_BIT 0x8000
#define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1)
#define ICE_INVAL_Q_INDEX 0xffff
@@ -62,6 +67,7 @@
#define ICE_TX_DESC(R, i) (&(((struct ice_tx_desc *)((R)->desc))[i]))
#define ICE_RX_DESC(R, i) (&(((union ice_32b_rx_flex_desc *)((R)->desc))[i]))
+#define ICE_TX_CTX_DESC(R, i) (&(((struct ice_tx_ctx_desc *)((R)->desc))[i]))
#define ice_for_each_txq(vsi, i) \
for ((i) = 0; (i) < (vsi)->num_txq; (i)++)
@@ -113,6 +119,7 @@ struct ice_vsi {
irqreturn_t (*irq_handler)(int irq, void *data);
DECLARE_BITMAP(state, __ICE_STATE_NBITS);
+ unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
int num_q_vectors;
int base_vector;
enum ice_vsi_type type;
@@ -122,6 +129,13 @@ struct ice_vsi {
/* Interrupt thresholds */
u16 work_lmt;
+ /* RSS config */
+ u16 rss_table_size; /* HW RSS table size */
+ u16 rss_size; /* Allocated RSS queues */
+ u8 *rss_hkey_user; /* User configured hash keys */
+ u8 *rss_lut_user; /* User configured lookup table entries */
+ u8 rss_lut_type; /* used to configure Get/Set RSS LUT AQ call */
+
u16 max_frame;
u16 rx_buf_len;
@@ -181,6 +195,7 @@ struct ice_pf {
struct mutex avail_q_mutex; /* protects access to avail_[rx|tx]qs */
struct mutex sw_mutex; /* lock for protecting VSI alloc flow */
u32 msg_enable;
+ u32 hw_csum_rx_error;
u32 oicr_idx; /* Other interrupt cause vector index */
u32 num_lan_msix; /* Total MSIX vectors for base driver */
u32 num_avail_msix; /* remaining MSIX vectors left unclaimed */
@@ -224,4 +239,8 @@ static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
wr32(hw, GLINT_DYN_CTL(vector), val);
}
+int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
+int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
+void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
+
#endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index c7abcc1dbbcc..051427dcfb3c 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -968,6 +968,60 @@ struct ice_aqc_nvm {
__le32 addr_low;
};
+/* Get/Set RSS key (indirect 0x0B04/0x0B02) */
+struct ice_aqc_get_set_rss_key {
+#define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15)
+#define ICE_AQC_GSET_RSS_KEY_VSI_ID_S 0
+#define ICE_AQC_GSET_RSS_KEY_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_KEY_VSI_ID_S)
+ __le16 vsi_id;
+ u8 reserved[6];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+#define ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE 0x28
+#define ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE 0xC
+
+struct ice_aqc_get_set_rss_keys {
+ u8 standard_rss_key[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE];
+ u8 extended_hash_key[ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE];
+};
+
+/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */
+struct ice_aqc_get_set_rss_lut {
+#define ICE_AQC_GSET_RSS_LUT_VSI_VALID BIT(15)
+#define ICE_AQC_GSET_RSS_LUT_VSI_ID_S 0
+#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x1FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S)
+ __le16 vsi_id;
+#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S 0
+#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M \
+ (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S)
+
+#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI 0
+#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF 1
+#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL 2
+
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S 2
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M \
+ (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S)
+
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128 128
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128_FLAG 0
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512 512
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG 1
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K 2048
+#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG 2
+
+#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S 4
+#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M \
+ (0xF << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S)
+
+ __le16 flags;
+ __le32 reserved;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
/* Add TX LAN Queues (indirect 0x0C30) */
struct ice_aqc_add_txqs {
u8 num_qgrps;
@@ -1089,6 +1143,8 @@ struct ice_aq_desc {
struct ice_aqc_query_txsched_res query_sched_res;
struct ice_aqc_add_move_delete_elem add_move_delete_elem;
struct ice_aqc_nvm nvm;
+ struct ice_aqc_get_set_rss_lut get_set_rss_lut;
+ struct ice_aqc_get_set_rss_key get_set_rss_key;
struct ice_aqc_add_txqs add_txqs;
struct ice_aqc_dis_txqs dis_txqs;
struct ice_aqc_add_get_update_free_vsi vsi_cmd;
@@ -1171,6 +1227,12 @@ enum ice_adminq_opc {
/* NVM commands */
ice_aqc_opc_nvm_read = 0x0701,
+ /* RSS commands */
+ ice_aqc_opc_set_rss_key = 0x0B02,
+ ice_aqc_opc_set_rss_lut = 0x0B03,
+ ice_aqc_opc_get_rss_key = 0x0B04,
+ ice_aqc_opc_get_rss_lut = 0x0B05,
+
/* TX queue handling commands/events */
ice_aqc_opc_add_txqs = 0x0C30,
ice_aqc_opc_dis_txqs = 0x0C31,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 3d5686636656..b4e834359a95 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1261,6 +1261,194 @@ void ice_clear_pxe_mode(struct ice_hw *hw)
ice_aq_clear_pxe_mode(hw);
}
+/**
+ * __ice_aq_get_set_rss_lut
+ * @hw: pointer to the hardware structure
+ * @vsi_id: VSI FW index
+ * @lut_type: LUT table type
+ * @lut: pointer to the LUT buffer provided by the caller
+ * @lut_size: size of the LUT buffer
+ * @glob_lut_idx: global LUT index
+ * @set: set true to set the table, false to get the table
+ *
+ * Internal function to get (0x0B05) or set (0x0B03) RSS look up table
+ */
+static enum ice_status
+__ice_aq_get_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
+ u16 lut_size, u8 glob_lut_idx, bool set)
+{
+ struct ice_aqc_get_set_rss_lut *cmd_resp;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+ u16 flags = 0;
+
+ cmd_resp = &desc.params.get_set_rss_lut;
+
+ if (set) {
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_lut);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ } else {
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_lut);
+ }
+
+ cmd_resp->vsi_id = cpu_to_le16(((vsi_id <<
+ ICE_AQC_GSET_RSS_LUT_VSI_ID_S) &
+ ICE_AQC_GSET_RSS_LUT_VSI_ID_M) |
+ ICE_AQC_GSET_RSS_LUT_VSI_VALID);
+
+ switch (lut_type) {
+ case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI:
+ case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF:
+ case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL:
+ flags |= ((lut_type << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) &
+ ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M);
+ break;
+ default:
+ status = ICE_ERR_PARAM;
+ goto ice_aq_get_set_rss_lut_exit;
+ }
+
+ if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL) {
+ flags |= ((glob_lut_idx << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) &
+ ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M);
+
+ if (!set)
+ goto ice_aq_get_set_rss_lut_send;
+ } else if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) {
+ if (!set)
+ goto ice_aq_get_set_rss_lut_send;
+ } else {
+ goto ice_aq_get_set_rss_lut_send;
+ }
+
+ /* LUT size is only valid for Global and PF table types */
+ if (lut_size == ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128) {
+ flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128_FLAG <<
+ ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) &
+ ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M;
+ } else if (lut_size == ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512) {
+ flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG <<
+ ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) &
+ ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M;
+ } else if ((lut_size == ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K) &&
+ (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF)) {
+ flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG <<
+ ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) &
+ ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M;
+ } else {
+ status = ICE_ERR_PARAM;
+ goto ice_aq_get_set_rss_lut_exit;
+ }
+
+ice_aq_get_set_rss_lut_send:
+ cmd_resp->flags = cpu_to_le16(flags);
+ status = ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL);
+
+ice_aq_get_set_rss_lut_exit:
+ return status;
+}
+
+/**
+ * ice_aq_get_rss_lut
+ * @hw: pointer to the hardware structure
+ * @vsi_id: VSI FW index
+ * @lut_type: LUT table type
+ * @lut: pointer to the LUT buffer provided by the caller
+ * @lut_size: size of the LUT buffer
+ *
+ * get the RSS lookup table, PF or VSI type
+ */
+enum ice_status
+ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
+ u16 lut_size)
+{
+ return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0,
+ false);
+}
+
+/**
+ * ice_aq_set_rss_lut
+ * @hw: pointer to the hardware structure
+ * @vsi_id: VSI FW index
+ * @lut_type: LUT table type
+ * @lut: pointer to the LUT buffer provided by the caller
+ * @lut_size: size of the LUT buffer
+ *
+ * set the RSS lookup table, PF or VSI type
+ */
+enum ice_status
+ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
+ u16 lut_size)
+{
+ return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0,
+ true);
+}
+
+/**
+ * __ice_aq_get_set_rss_key
+ * @hw: pointer to the hw struct
+ * @vsi_id: VSI FW index
+ * @key: pointer to key info struct
+ * @set: set true to set the key, false to get the key
+ *
+ * get (0x0B04) or set (0x0B02) the RSS key per VSI
+ */
+static enum
+ice_status __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id,
+ struct ice_aqc_get_set_rss_keys *key,
+ bool set)
+{
+ struct ice_aqc_get_set_rss_key *cmd_resp;
+ u16 key_size = sizeof(*key);
+ struct ice_aq_desc desc;
+
+ cmd_resp = &desc.params.get_set_rss_key;
+
+ if (set) {
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_key);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ } else {
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_key);
+ }
+
+ cmd_resp->vsi_id = cpu_to_le16(((vsi_id <<
+ ICE_AQC_GSET_RSS_KEY_VSI_ID_S) &
+ ICE_AQC_GSET_RSS_KEY_VSI_ID_M) |
+ ICE_AQC_GSET_RSS_KEY_VSI_VALID);
+
+ return ice_aq_send_cmd(hw, &desc, key, key_size, NULL);
+}
+
+/**
+ * ice_aq_get_rss_key
+ * @hw: pointer to the hw struct
+ * @vsi_id: VSI FW index
+ * @key: pointer to key info struct
+ *
+ * get the RSS key per VSI
+ */
+enum ice_status
+ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id,
+ struct ice_aqc_get_set_rss_keys *key)
+{
+ return __ice_aq_get_set_rss_key(hw, vsi_id, key, false);
+}
+
+/**
+ * ice_aq_set_rss_key
+ * @hw: pointer to the hw struct
+ * @vsi_id: VSI FW index
+ * @keys: pointer to key info struct
+ *
+ * set the RSS key per VSI
+ */
+enum ice_status
+ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id,
+ struct ice_aqc_get_set_rss_keys *keys)
+{
+ return __ice_aq_get_set_rss_key(hw, vsi_id, keys, true);
+}
+
/**
* ice_aq_add_lan_txq
* @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 8ed1135bb189..38719ba01d9b 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -33,6 +33,19 @@ enum ice_status ice_get_caps(struct ice_hw *hw);
enum ice_status
ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
u32 rxq_index);
+
+enum ice_status
+ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
+ u16 lut_size);
+enum ice_status
+ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
+ u16 lut_size);
+enum ice_status
+ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id,
+ struct ice_aqc_get_set_rss_keys *keys);
+enum ice_status
+ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id,
+ struct ice_aqc_get_set_rss_keys *keys);
bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq);
enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading);
void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode);
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index e1221b9839d5..57acbcff740b 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -40,6 +40,65 @@ union ice_32byte_rx_desc {
} wb; /* writeback */
};
+struct ice_rx_ptype_decoded {
+ u32 ptype:10;
+ u32 known:1;
+ u32 outer_ip:1;
+ u32 outer_ip_ver:2;
+ u32 outer_frag:1;
+ u32 tunnel_type:3;
+ u32 tunnel_end_prot:2;
+ u32 tunnel_end_frag:1;
+ u32 inner_prot:4;
+ u32 payload_layer:3;
+};
+
+enum ice_rx_ptype_outer_ip {
+ ICE_RX_PTYPE_OUTER_L2 = 0,
+ ICE_RX_PTYPE_OUTER_IP = 1,
+};
+
+enum ice_rx_ptype_outer_ip_ver {
+ ICE_RX_PTYPE_OUTER_NONE = 0,
+ ICE_RX_PTYPE_OUTER_IPV4 = 1,
+ ICE_RX_PTYPE_OUTER_IPV6 = 2,
+};
+
+enum ice_rx_ptype_outer_fragmented {
+ ICE_RX_PTYPE_NOT_FRAG = 0,
+ ICE_RX_PTYPE_FRAG = 1,
+};
+
+enum ice_rx_ptype_tunnel_type {
+ ICE_RX_PTYPE_TUNNEL_NONE = 0,
+ ICE_RX_PTYPE_TUNNEL_IP_IP = 1,
+ ICE_RX_PTYPE_TUNNEL_IP_GRENAT = 2,
+ ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3,
+ ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4,
+};
+
+enum ice_rx_ptype_tunnel_end_prot {
+ ICE_RX_PTYPE_TUNNEL_END_NONE = 0,
+ ICE_RX_PTYPE_TUNNEL_END_IPV4 = 1,
+ ICE_RX_PTYPE_TUNNEL_END_IPV6 = 2,
+};
+
+enum ice_rx_ptype_inner_prot {
+ ICE_RX_PTYPE_INNER_PROT_NONE = 0,
+ ICE_RX_PTYPE_INNER_PROT_UDP = 1,
+ ICE_RX_PTYPE_INNER_PROT_TCP = 2,
+ ICE_RX_PTYPE_INNER_PROT_SCTP = 3,
+ ICE_RX_PTYPE_INNER_PROT_ICMP = 4,
+ ICE_RX_PTYPE_INNER_PROT_TIMESYNC = 5,
+};
+
+enum ice_rx_ptype_payload_layer {
+ ICE_RX_PTYPE_PAYLOAD_LAYER_NONE = 0,
+ ICE_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1,
+ ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2,
+ ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3,
+};
+
/* RX Flex Descriptor
* This descriptor is used instead of the legacy version descriptor when
* ice_rlan_ctx.adv_desc is set
@@ -88,6 +147,41 @@ union ice_32b_rx_flex_desc {
} wb; /* writeback */
};
+/* Rx Flex Descriptor NIC Profile
+ * This descriptor corresponds to RxDID 2 which contains
+ * metadata fields for RSS, flow id and timestamp info
+ */
+struct ice_32b_rx_flex_desc_nic {
+ /* Qword 0 */
+ u8 rxdid;
+ u8 mir_id_umb_cast;
+ __le16 ptype_flexi_flags0;
+ __le16 pkt_len;
+ __le16 hdr_len_sph_flex_flags1;
+
+ /* Qword 1 */
+ __le16 status_error0;
+ __le16 l2tag1;
+ __le32 rss_hash;
+
+ /* Qword 2 */
+ __le16 status_error1;
+ u8 flexi_flags2;
+ u8 ts_low;
+ __le16 l2tag2_1st;
+ __le16 l2tag2_2nd;
+
+ /* Qword 3 */
+ __le32 flow_id;
+ union {
+ struct {
+ __le16 vlan_id;
+ __le16 flow_id_ipv6;
+ } flex;
+ __le32 ts_high;
+ } flex_ts;
+};
+
/* Receive Flex Descriptor profile IDs: There are a total
* of 64 profiles where profile IDs 0/1 are for legacy; and
* profiles 2-63 are flex profiles that can be programmed
@@ -241,12 +335,56 @@ enum ice_tx_desc_dtype_value {
enum ice_tx_desc_cmd_bits {
ICE_TX_DESC_CMD_EOP = 0x0001,
ICE_TX_DESC_CMD_RS = 0x0002,
+ ICE_TX_DESC_CMD_IL2TAG1 = 0x0008,
+ ICE_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */
+ ICE_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */
+ ICE_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */
+ ICE_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */
+ ICE_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */
};
#define ICE_TXD_QW1_OFFSET_S 16
+#define ICE_TXD_QW1_OFFSET_M (0x3FFFFULL << ICE_TXD_QW1_OFFSET_S)
+
+enum ice_tx_desc_len_fields {
+ /* Note: These are predefined bit offsets */
+ ICE_TX_DESC_LEN_MACLEN_S = 0, /* 7 BITS */
+ ICE_TX_DESC_LEN_IPLEN_S = 7, /* 7 BITS */
+ ICE_TX_DESC_LEN_L4_LEN_S = 14 /* 4 BITS */
+};
+
#define ICE_TXD_QW1_TX_BUF_SZ_S 34
#define ICE_TXD_QW1_L2TAG1_S 48
+/* Context descriptors */
+struct ice_tx_ctx_desc {
+ __le32 tunneling_params;
+ __le16 l2tag2;
+ __le16 rsvd;
+ __le64 qw1;
+};
+
+#define ICE_TXD_CTX_QW1_CMD_S 4
+#define ICE_TXD_CTX_QW1_CMD_M (0x7FUL << ICE_TXD_CTX_QW1_CMD_S)
+
+#define ICE_TXD_CTX_QW1_TSO_LEN_S 30
+#define ICE_TXD_CTX_QW1_TSO_LEN_M \
+ (0x3FFFFULL << ICE_TXD_CTX_QW1_TSO_LEN_S)
+
+#define ICE_TXD_CTX_QW1_MSS_S 50
+
+enum ice_tx_ctx_desc_cmd_bits {
+ ICE_TX_CTX_DESC_TSO = 0x01,
+ ICE_TX_CTX_DESC_TSYN = 0x02,
+ ICE_TX_CTX_DESC_IL2TAG2 = 0x04,
+ ICE_TX_CTX_DESC_IL2TAG2_IL2H = 0x08,
+ ICE_TX_CTX_DESC_SWTCH_NOTAG = 0x00,
+ ICE_TX_CTX_DESC_SWTCH_UPLINK = 0x10,
+ ICE_TX_CTX_DESC_SWTCH_LOCAL = 0x20,
+ ICE_TX_CTX_DESC_SWTCH_VSI = 0x30,
+ ICE_TX_CTX_DESC_RESERVED = 0x40
+};
+
#define ICE_LAN_TXQ_MAX_QGRPS 127
#define ICE_LAN_TXQ_MAX_QDIS 1023
@@ -289,4 +427,35 @@ struct ice_tlan_ctx {
u8 pkt_shaper_prof_idx;
u8 int_q_state; /* width not needed - internal do not write */
};
+
+/* macro to make the table lines short */
+#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+ { PTYPE, \
+ 1, \
+ ICE_RX_PTYPE_OUTER_##OUTER_IP, \
+ ICE_RX_PTYPE_OUTER_##OUTER_IP_VER, \
+ ICE_RX_PTYPE_##OUTER_FRAG, \
+ ICE_RX_PTYPE_TUNNEL_##T, \
+ ICE_RX_PTYPE_TUNNEL_END_##TE, \
+ ICE_RX_PTYPE_##TEF, \
+ ICE_RX_PTYPE_INNER_PROT_##I, \
+ ICE_RX_PTYPE_PAYLOAD_LAYER_##PL }
+
+#define ICE_PTT_UNUSED_ENTRY(PTYPE) { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+
+/* shorter macros makes the table fit but are terse */
+#define ICE_RX_PTYPE_NOF ICE_RX_PTYPE_NOT_FRAG
+
+/* Lookup table mapping the HW PTYPE to the bit field for decoding */
+static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = {
+ /* L2 Packet types */
+ ICE_PTT_UNUSED_ENTRY(0),
+ ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ ICE_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
+};
+
+static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
+{
+ return ice_ptype_lkup[ptype];
+}
#endif /* _ICE_LAN_TX_RX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index dd07bf862afe..2124e7ad640c 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -663,6 +663,35 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
return err;
}
+/**
+ * ice_vsi_set_rss_params - Setup RSS capabilities per VSI type
+ * @vsi: the VSI being configured
+ */
+static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
+{
+ struct ice_hw_common_caps *cap;
+ struct ice_pf *pf = vsi->back;
+
+ if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
+ vsi->rss_size = 1;
+ return;
+ }
+
+ cap = &pf->hw.func_caps.common_cap;
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ /* PF VSI will inherit RSS instance of PF */
+ vsi->rss_table_size = cap->rss_table_size;
+ vsi->rss_size = min_t(int, num_online_cpus(),
+ BIT(cap->rss_table_entry_width));
+ vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF;
+ break;
+ default:
+ dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
+ break;
+ }
+}
+
/**
* ice_vsi_setup_q_map - Setup a VSI queue map
* @vsi: the VSI being configured
@@ -670,7 +699,8 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
*/
static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
{
- u16 offset = 0, qmap = 0, pow = 0, qcount;
+ u16 offset = 0, qmap = 0, numq_tc;
+ u16 pow = 0, max_rss = 0, qcount;
u16 qcount_tx = vsi->alloc_txq;
u16 qcount_rx = vsi->alloc_rxq;
bool ena_tc0 = false;
@@ -689,13 +719,7 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
vsi->tc_cfg.ena_tc |= 1;
}
- qcount = qcount_rx / vsi->tc_cfg.numtc;
-
- /* find higher power-of-2 of qcount */
- pow = ilog2(qcount);
-
- if (!is_power_of_2(qcount))
- pow++;
+ numq_tc = qcount_rx / vsi->tc_cfg.numtc;
/* TC mapping is a function of the number of Rx queues assigned to the
* VSI for each traffic class and the offset of these queues.
@@ -708,6 +732,26 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
*
* Setup number and offset of Rx queues for all TCs for the VSI
*/
+
+ /* qcount will change if RSS is enabled */
+ if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) {
+ if (vsi->type == ICE_VSI_PF)
+ max_rss = ICE_MAX_LG_RSS_QS;
+ else
+ max_rss = ICE_MAX_SMALL_RSS_QS;
+
+ qcount = min_t(int, numq_tc, max_rss);
+ qcount = min_t(int, qcount, vsi->rss_size);
+ } else {
+ qcount = numq_tc;
+ }
+
+ /* find higher power-of-2 of qcount */
+ pow = ilog2(qcount);
+
+ if (!is_power_of_2(qcount))
+ pow++;
+
for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
/* TC is not enabled */
@@ -783,6 +827,33 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt)
/* No Outer tag support outer_tag_flags remains to zero */
}
+/**
+ * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI
+ * @ctxt: the VSI context being set
+ * @vsi: the VSI being configured
+ */
+static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
+{
+ u8 lut_type, hash_type;
+
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ /* PF VSI will inherit RSS instance of PF */
+ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF;
+ hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
+ break;
+ default:
+ dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n",
+ vsi->type);
+ return;
+ }
+
+ ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
+ ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
+ ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) &
+ ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
+}
+
/**
* ice_vsi_add - Create a new VSI or fetch preallocated VSI
* @vsi: the VSI being configured
@@ -810,6 +881,10 @@ static int ice_vsi_add(struct ice_vsi *vsi)
if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB)
ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+ /* Set LUT type and HASH type if RSS is enabled */
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_set_rss_vsi_ctx(&ctxt, vsi);
+
ctxt.info.sw_id = vsi->port_info->sw_id;
ice_vsi_setup_q_map(vsi, &ctxt);
@@ -1629,6 +1704,10 @@ static void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
*/
static int ice_cfg_netdev(struct ice_vsi *vsi)
{
+ netdev_features_t csumo_features;
+ netdev_features_t vlano_features;
+ netdev_features_t dflt_features;
+ netdev_features_t tso_features;
struct ice_netdev_priv *np;
struct net_device *netdev;
u8 mac_addr[ETH_ALEN];
@@ -1642,13 +1721,31 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
np = netdev_priv(netdev);
np->vsi = vsi;
+ dflt_features = NETIF_F_SG |
+ NETIF_F_HIGHDMA |
+ NETIF_F_RXHASH;
+
+ csumo_features = NETIF_F_RXCSUM |
+ NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM;
+
+ vlano_features = NETIF_F_HW_VLAN_CTAG_FILTER |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX;
+
+ tso_features = NETIF_F_TSO;
+
/* set features that user can change */
- netdev->hw_features = NETIF_F_SG |
- NETIF_F_HIGHDMA |
- NETIF_F_RXHASH;
+ netdev->hw_features = dflt_features | csumo_features |
+ vlano_features | tso_features;
/* enable features */
netdev->features |= netdev->hw_features;
+ /* encap and VLAN devices inherit default, csumo and tso features */
+ netdev->hw_enc_features |= dflt_features | csumo_features |
+ tso_features;
+ netdev->vlan_features |= dflt_features | csumo_features |
+ tso_features;
if (vsi->type == ICE_VSI_PF) {
SET_NETDEV_DEV(netdev, &vsi->back->pdev->dev);
@@ -1862,6 +1959,83 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
return 0;
}
+/**
+ * ice_fill_rss_lut - Fill the RSS lookup table with default values
+ * @lut: Lookup table
+ * @rss_table_size: Lookup table size
+ * @rss_size: Range of queue number for hashing
+ */
+void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size)
+{
+ u16 i;
+
+ for (i = 0; i < rss_table_size; i++)
+ lut[i] = i % rss_size;
+}
+
+/**
+ * ice_vsi_cfg_rss - Configure RSS params for a VSI
+ * @vsi: VSI to be configured
+ */
+static int ice_vsi_cfg_rss(struct ice_vsi *vsi)
+{
+ u8 seed[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE];
+ struct ice_aqc_get_set_rss_keys *key;
+ struct ice_pf *pf = vsi->back;
+ enum ice_status status;
+ int err = 0;
+ u8 *lut;
+
+ vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq);
+
+ lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL);
+ if (!lut)
+ return -ENOMEM;
+
+ if (vsi->rss_lut_user)
+ memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size);
+ else
+ ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size);
+
+ status = ice_aq_set_rss_lut(&pf->hw, vsi->vsi_num, vsi->rss_lut_type,
+ lut, vsi->rss_table_size);
+
+ if (status) {
+ dev_err(&vsi->back->pdev->dev,
+ "set_rss_lut failed, error %d\n", status);
+ err = -EIO;
+ goto ice_vsi_cfg_rss_exit;
+ }
+
+ key = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*key), GFP_KERNEL);
+ if (!key) {
+ err = -ENOMEM;
+ goto ice_vsi_cfg_rss_exit;
+ }
+
+ if (vsi->rss_hkey_user)
+ memcpy(seed, vsi->rss_hkey_user,
+ ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
+ else
+ netdev_rss_key_fill((void *)seed,
+ ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
+ memcpy(&key->standard_rss_key, seed,
+ ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
+
+ status = ice_aq_set_rss_key(&pf->hw, vsi->vsi_num, key);
+
+ if (status) {
+ dev_err(&vsi->back->pdev->dev, "set_rss_key failed, error %d\n",
+ status);
+ err = -EIO;
+ }
+
+ devm_kfree(&pf->pdev->dev, key);
+ice_vsi_cfg_rss_exit:
+ devm_kfree(&pf->pdev->dev, lut);
+ return err;
+}
+
/**
* ice_vsi_setup - Set up a VSI by a given type
* @pf: board private structure
@@ -1897,6 +2071,9 @@ ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type,
goto err_get_qs;
}
+ /* set RSS capabilities */
+ ice_vsi_set_rss_params(vsi);
+
/* create the VSI */
ret = ice_vsi_add(vsi);
if (ret)
@@ -1932,6 +2109,12 @@ ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type,
ice_vsi_map_rings_to_vectors(vsi);
+ /* Do not exit if configuring RSS had an issue, at least
+ * receive traffic on first queue. Hence no need to capture
+ * return value
+ */
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_vsi_cfg_rss(vsi);
break;
default:
/* if vsi type is not recognized, clean up the resources and
@@ -1966,6 +2149,140 @@ ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type,
return NULL;
}
+/**
+ * ice_vsi_add_vlan - Add vsi membership for given vlan
+ * @vsi: the vsi being configured
+ * @vid: vlan id to be added
+ */
+static int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
+{
+ struct ice_fltr_list_entry *tmp;
+ struct ice_pf *pf = vsi->back;
+ LIST_HEAD(tmp_add_list);
+ enum ice_status status;
+ int err = 0;
+
+ tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
+
+ tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
+ tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ tmp->fltr_info.flag = ICE_FLTR_TX;
+ tmp->fltr_info.src = vsi->vsi_num;
+ tmp->fltr_info.fwd_id.vsi_id = vsi->vsi_num;
+ tmp->fltr_info.l_data.vlan.vlan_id = vid;
+
+ INIT_LIST_HEAD(&tmp->list_entry);
+ list_add(&tmp->list_entry, &tmp_add_list);
+
+ status = ice_add_vlan(&pf->hw, &tmp_add_list);
+ if (status) {
+ err = -ENODEV;
+ dev_err(&pf->pdev->dev, "Failure Adding VLAN %d on VSI %i\n",
+ vid, vsi->vsi_num);
+ }
+
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+ return err;
+}
+
+/**
+ * ice_vlan_rx_add_vid - Add a vlan id filter to HW offload
+ * @netdev: network interface to be adjusted
+ * @proto: unused protocol
+ * @vid: vlan id to be added
+ *
+ * net_device_ops implementation for adding vlan ids
+ */
+static int ice_vlan_rx_add_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ int ret = 0;
+
+ if (vid >= VLAN_N_VID) {
+ netdev_err(netdev, "VLAN id requested %d is out of range %d\n",
+ vid, VLAN_N_VID);
+ return -EINVAL;
+ }
+
+ if (vsi->info.pvid)
+ return -EINVAL;
+
+ /* Add all VLAN ids including 0 to the switch filter. VLAN id 0 is
+ * needed to continue allowing all untagged packets since VLAN prune
+ * list is applied to all packets by the switch
+ */
+ ret = ice_vsi_add_vlan(vsi, vid);
+
+ if (!ret)
+ set_bit(vid, vsi->active_vlans);
+
+ return ret;
+}
+
+/**
+ * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN
+ * @vsi: the VSI being configured
+ * @vid: VLAN id to be removed
+ */
+static void ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
+{
+ struct ice_fltr_list_entry *list;
+ struct ice_pf *pf = vsi->back;
+ LIST_HEAD(tmp_add_list);
+
+ list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
+ if (!list)
+ return;
+
+ list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
+ list->fltr_info.fwd_id.vsi_id = vsi->vsi_num;
+ list->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ list->fltr_info.l_data.vlan.vlan_id = vid;
+ list->fltr_info.flag = ICE_FLTR_TX;
+ list->fltr_info.src = vsi->vsi_num;
+
+ INIT_LIST_HEAD(&list->list_entry);
+ list_add(&list->list_entry, &tmp_add_list);
+
+ if (ice_remove_vlan(&pf->hw, &tmp_add_list))
+ dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n",
+ vid, vsi->vsi_num);
+
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+}
+
+/**
+ * ice_vlan_rx_kill_vid - Remove a vlan id filter from HW offload
+ * @netdev: network interface to be adjusted
+ * @proto: unused protocol
+ * @vid: vlan id to be removed
+ *
+ * net_device_ops implementation for removing vlan ids
+ */
+static int ice_vlan_rx_kill_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ if (vsi->info.pvid)
+ return -EINVAL;
+
+ /* return code is ignored as there is nothing a user
+ * can do about failure to remove and a log message was
+ * already printed from the other function
+ */
+ ice_vsi_kill_vlan(vsi, vid);
+
+ clear_bit(vid, vsi->active_vlans);
+
+ return 0;
+}
+
/**
* ice_setup_pf_sw - Setup the HW switch on startup or after reset
* @pf: board private structure
@@ -2047,9 +2364,14 @@ static void ice_determine_q_usage(struct ice_pf *pf)
q_left_tx = pf->hw.func_caps.common_cap.num_txq;
q_left_rx = pf->hw.func_caps.common_cap.num_rxq;
- /* initial support for only 1 tx and 1 rx queue */
+ /* initial support for only 1 tx queue */
pf->num_lan_tx = 1;
- pf->num_lan_rx = 1;
+
+ /* only 1 rx queue unless RSS is enabled */
+ if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ pf->num_lan_rx = 1;
+ else
+ pf->num_lan_rx = min_t(int, q_left_rx, num_online_cpus());
pf->q_left_tx = q_left_tx - pf->num_lan_tx;
pf->q_left_rx = q_left_rx - pf->num_lan_rx;
@@ -2087,6 +2409,9 @@ static void ice_init_pf(struct ice_pf *pf)
bitmap_zero(pf->avail_rxqs, ICE_MAX_RXQS);
mutex_unlock(&pf->avail_q_mutex);
+ if (pf->hw.func_caps.common_cap.rss_table_size)
+ set_bit(ICE_FLAG_RSS_ENA, pf->flags);
+
/* setup service timer and periodic service task */
timer_setup(&pf->serv_tmr, ice_service_timer, 0);
pf->serv_tmr_period = HZ;
@@ -2483,6 +2808,144 @@ static void __exit ice_module_exit(void)
}
module_exit(ice_module_exit);
+/**
+ * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx
+ * @vsi: the vsi being changed
+ */
+static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi)
+{
+ struct device *dev = &vsi->back->pdev->dev;
+ struct ice_hw *hw = &vsi->back->hw;
+ struct ice_vsi_ctx ctxt = { 0 };
+ enum ice_status status;
+
+ /* Here we are configuring the VSI to let the driver add VLAN tags by
+ * setting port_vlan_flags to ICE_AQ_VSI_PVLAN_MODE_ALL. The actual VLAN
+ * tag insertion happens in the Tx hot path, in ice_tx_map.
+ */
+ ctxt.info.port_vlan_flags = ICE_AQ_VSI_PVLAN_MODE_ALL;
+
+ ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+ ctxt.vsi_num = vsi->vsi_num;
+
+ status = ice_aq_update_vsi(hw, &ctxt, NULL);
+ if (status) {
+ dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
+ status, hw->adminq.sq_last_status);
+ return -EIO;
+ }
+
+ vsi->info.port_vlan_flags = ctxt.info.port_vlan_flags;
+ return 0;
+}
+
+/**
+ * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx
+ * @vsi: the vsi being changed
+ * @ena: boolean value indicating if this is a enable or disable request
+ */
+static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
+{
+ struct device *dev = &vsi->back->pdev->dev;
+ struct ice_hw *hw = &vsi->back->hw;
+ struct ice_vsi_ctx ctxt = { 0 };
+ enum ice_status status;
+
+ /* Here we are configuring what the VSI should do with the VLAN tag in
+ * the Rx packet. We can either leave the tag in the packet or put it in
+ * the Rx descriptor.
+ */
+ if (ena) {
+ /* Strip VLAN tag from Rx packet and put it in the desc */
+ ctxt.info.port_vlan_flags = ICE_AQ_VSI_PVLAN_EMOD_STR_BOTH;
+ } else {
+ /* Disable stripping. Leave tag in packet */
+ ctxt.info.port_vlan_flags = ICE_AQ_VSI_PVLAN_EMOD_NOTHING;
+ }
+
+ ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+ ctxt.vsi_num = vsi->vsi_num;
+
+ status = ice_aq_update_vsi(hw, &ctxt, NULL);
+ if (status) {
+ dev_err(dev, "update VSI for VALN strip failed, ena = %d err %d aq_err %d\n",
+ ena, status, hw->adminq.sq_last_status);
+ return -EIO;
+ }
+
+ vsi->info.port_vlan_flags = ctxt.info.port_vlan_flags;
+ return 0;
+}
+
+/**
+ * ice_set_features - set the netdev feature flags
+ * @netdev: ptr to the netdev being adjusted
+ * @features: the feature set that the stack is suggesting
+ */
+static int ice_set_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ int ret = 0;
+
+ if ((features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ !(netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
+ ret = ice_vsi_manage_vlan_stripping(vsi, true);
+ else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ (netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
+ ret = ice_vsi_manage_vlan_stripping(vsi, false);
+ else if ((features & NETIF_F_HW_VLAN_CTAG_TX) &&
+ !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
+ ret = ice_vsi_manage_vlan_insertion(vsi);
+ else if (!(features & NETIF_F_HW_VLAN_CTAG_TX) &&
+ (netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
+ ret = ice_vsi_manage_vlan_insertion(vsi);
+
+ return ret;
+}
+
+/**
+ * ice_vsi_vlan_setup - Setup vlan offload properties on a VSI
+ * @vsi: VSI to setup vlan properties for
+ */
+static int ice_vsi_vlan_setup(struct ice_vsi *vsi)
+{
+ int ret = 0;
+
+ if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+ ret = ice_vsi_manage_vlan_stripping(vsi, true);
+ if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_TX)
+ ret = ice_vsi_manage_vlan_insertion(vsi);
+
+ return ret;
+}
+
+/**
+ * ice_restore_vlan - Reinstate VLANs when vsi/netdev comes back up
+ * @vsi: the VSI being brought back up
+ */
+static int ice_restore_vlan(struct ice_vsi *vsi)
+{
+ int err;
+ u16 vid;
+
+ if (!vsi->netdev)
+ return -EINVAL;
+
+ err = ice_vsi_vlan_setup(vsi);
+ if (err)
+ return err;
+
+ for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID) {
+ err = ice_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q), vid);
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
/**
* ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance
* @ring: The Tx ring to configure
@@ -2735,6 +3198,10 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
{
int err;
+ err = ice_restore_vlan(vsi);
+ if (err)
+ return err;
+
err = ice_vsi_cfg_txqs(vsi);
if (!err)
err = ice_vsi_cfg_rxqs(vsi);
@@ -3213,6 +3680,22 @@ static void ice_vsi_close(struct ice_vsi *vsi)
ice_vsi_free_rx_rings(vsi);
}
+/**
+ * ice_rss_clean - Delete RSS related VSI structures that hold user inputs
+ * @vsi: the VSI being removed
+ */
+static void ice_rss_clean(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf;
+
+ pf = vsi->back;
+
+ if (vsi->rss_hkey_user)
+ devm_kfree(&pf->pdev->dev, vsi->rss_hkey_user);
+ if (vsi->rss_lut_user)
+ devm_kfree(&pf->pdev->dev, vsi->rss_lut_user);
+}
+
/**
* ice_vsi_release - Delete a VSI and free its resources
* @vsi: the VSI being removed
@@ -3233,6 +3716,10 @@ static int ice_vsi_release(struct ice_vsi *vsi)
vsi->netdev = NULL;
}
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_rss_clean(vsi);
+
+ /* Disable VSI and free resources */
ice_vsi_dis_irq(vsi);
ice_vsi_close(vsi);
@@ -3254,6 +3741,91 @@ static int ice_vsi_release(struct ice_vsi *vsi)
return 0;
}
+/**
+ * ice_set_rss - Set RSS keys and lut
+ * @vsi: Pointer to VSI structure
+ * @seed: RSS hash seed
+ * @lut: Lookup table
+ * @lut_size: Lookup table size
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status status;
+
+ if (seed) {
+ struct ice_aqc_get_set_rss_keys *buf =
+ (struct ice_aqc_get_set_rss_keys *)seed;
+
+ status = ice_aq_set_rss_key(hw, vsi->vsi_num, buf);
+
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "Cannot set RSS key, err %d aq_err %d\n",
+ status, hw->adminq.rq_last_status);
+ return -EIO;
+ }
+ }
+
+ if (lut) {
+ status = ice_aq_set_rss_lut(hw, vsi->vsi_num,
+ vsi->rss_lut_type, lut, lut_size);
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "Cannot set RSS lut, err %d aq_err %d\n",
+ status, hw->adminq.rq_last_status);
+ return -EIO;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_get_rss - Get RSS keys and lut
+ * @vsi: Pointer to VSI structure
+ * @seed: Buffer to store the keys
+ * @lut: Buffer to store the lookup table entries
+ * @lut_size: Size of buffer to store the lookup table entries
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status status;
+
+ if (seed) {
+ struct ice_aqc_get_set_rss_keys *buf =
+ (struct ice_aqc_get_set_rss_keys *)seed;
+
+ status = ice_aq_get_rss_key(hw, vsi->vsi_num, buf);
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "Cannot get RSS key, err %d aq_err %d\n",
+ status, hw->adminq.rq_last_status);
+ return -EIO;
+ }
+ }
+
+ if (lut) {
+ status = ice_aq_get_rss_lut(hw, vsi->vsi_num,
+ vsi->rss_lut_type, lut, lut_size);
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "Cannot get RSS lut, err %d aq_err %d\n",
+ status, hw->adminq.rq_last_status);
+ return -EIO;
+ }
+ }
+
+ return 0;
+}
+
/**
* ice_open - Called when a network interface becomes active
* @netdev: network interface device structure
@@ -3306,4 +3878,7 @@ static const struct net_device_ops ice_netdev_ops = {
.ndo_open = ice_open,
.ndo_stop = ice_stop,
.ndo_start_xmit = ice_start_xmit,
+ .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
+ .ndo_set_features = ice_set_features,
};
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 3944dac6cfc6..5624df9eb6fc 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1217,6 +1217,117 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list)
return status;
}
+/**
+ * ice_find_vlan_entry
+ * @hw: pointer to the hardware structure
+ * @vlan_id: VLAN id to search for
+ *
+ * Helper function to search for a VLAN entry using a given VLAN id
+ * Returns pointer to the entry if found.
+ */
+static struct ice_fltr_mgmt_list_entry *
+ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id)
+{
+ struct ice_fltr_mgmt_list_entry *vlan_list_itr, *vlan_ret = NULL;
+ struct ice_switch_info *sw = hw->switch_info;
+
+ mutex_lock(&sw->vlan_list_lock);
+ list_for_each_entry(vlan_list_itr, &sw->vlan_list_head, list_entry)
+ if (vlan_list_itr->fltr_info.l_data.vlan.vlan_id == vlan_id) {
+ vlan_ret = vlan_list_itr;
+ break;
+ }
+
+ mutex_unlock(&sw->vlan_list_lock);
+ return vlan_ret;
+}
+
+/**
+ * ice_add_vlan_internal - Add one VLAN based filter rule
+ * @hw: pointer to the hardware structure
+ * @f_entry: filter entry containing one VLAN information
+ */
+static enum ice_status
+ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
+{
+ struct ice_fltr_info *new_fltr, *cur_fltr;
+ struct ice_fltr_mgmt_list_entry *v_list_itr;
+ u16 vlan_id;
+
+ new_fltr = &f_entry->fltr_info;
+ /* VLAN id should only be 12 bits */
+ if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID)
+ return ICE_ERR_PARAM;
+
+ vlan_id = new_fltr->l_data.vlan.vlan_id;
+ v_list_itr = ice_find_vlan_entry(hw, vlan_id);
+ if (!v_list_itr) {
+ u16 vsi_id = ICE_VSI_INVAL_ID;
+ enum ice_status status;
+ u16 vsi_list_id = 0;
+
+ if (new_fltr->fltr_act == ICE_FWD_TO_VSI) {
+ enum ice_sw_lkup_type lkup_type = new_fltr->lkup_type;
+
+ /* All VLAN pruning rules use a VSI list.
+ * Convert the action to forwarding to a VSI list.
+ */
+ vsi_id = new_fltr->fwd_id.vsi_id;
+ status = ice_create_vsi_list_rule(hw, &vsi_id, 1,
+ &vsi_list_id,
+ lkup_type);
+ if (status)
+ return status;
+ new_fltr->fltr_act = ICE_FWD_TO_VSI_LIST;
+ new_fltr->fwd_id.vsi_list_id = vsi_list_id;
+ }
+
+ status = ice_create_pkt_fwd_rule(hw, f_entry);
+ if (!status && vsi_id != ICE_VSI_INVAL_ID) {
+ v_list_itr = ice_find_vlan_entry(hw, vlan_id);
+ if (!v_list_itr)
+ return ICE_ERR_DOES_NOT_EXIST;
+ v_list_itr->vsi_list_info =
+ ice_create_vsi_list_map(hw, &vsi_id, 1,
+ vsi_list_id);
+ }
+
+ return status;
+ }
+
+ cur_fltr = &v_list_itr->fltr_info;
+ return ice_handle_vsi_list_mgmt(hw, v_list_itr, cur_fltr, new_fltr);
+}
+
+/**
+ * ice_add_vlan - Add VLAN based filter rule
+ * @hw: pointer to the hardware structure
+ * @v_list: list of VLAN entries and forwarding information
+ */
+enum ice_status
+ice_add_vlan(struct ice_hw *hw, struct list_head *v_list)
+{
+ struct ice_fltr_list_entry *v_list_itr;
+
+ if (!v_list || !hw)
+ return ICE_ERR_PARAM;
+
+ list_for_each_entry(v_list_itr, v_list, list_entry) {
+ enum ice_status status;
+
+ if (v_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_VLAN)
+ return ICE_ERR_PARAM;
+
+ status = ice_add_vlan_internal(hw, v_list_itr);
+ if (status) {
+ v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL;
+ return status;
+ }
+ v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS;
+ }
+ return 0;
+}
+
/**
* ice_remove_vsi_list_rule
* @hw: pointer to the hardware structure
@@ -1515,6 +1626,54 @@ ice_remove_mac(struct ice_hw *hw, struct list_head *m_list)
return status;
}
+/**
+ * ice_remove_vlan_internal - Remove one VLAN based filter rule
+ * @hw: pointer to the hardware structure
+ * @f_entry: filter entry containing one VLAN information
+ */
+static enum ice_status
+ice_remove_vlan_internal(struct ice_hw *hw,
+ struct ice_fltr_list_entry *f_entry)
+{
+ struct ice_fltr_info *new_fltr;
+ struct ice_fltr_mgmt_list_entry *v_list_elem;
+ u16 vsi_id;
+
+ new_fltr = &f_entry->fltr_info;
+
+ v_list_elem = ice_find_vlan_entry(hw, new_fltr->l_data.vlan.vlan_id);
+ if (!v_list_elem)
+ return ICE_ERR_PARAM;
+
+ vsi_id = f_entry->fltr_info.fwd_id.vsi_id;
+ return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, v_list_elem);
+}
+
+/**
+ * ice_remove_vlan - Remove VLAN based filter rule
+ * @hw: pointer to the hardware structure
+ * @v_list: list of VLAN entries and forwarding information
+ */
+enum ice_status
+ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list)
+{
+ struct ice_fltr_list_entry *v_list_itr;
+ enum ice_status status = 0;
+
+ if (!v_list || !hw)
+ return ICE_ERR_PARAM;
+
+ list_for_each_entry(v_list_itr, v_list, list_entry) {
+ status = ice_remove_vlan_internal(hw, v_list_itr);
+ if (status) {
+ v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL;
+ return status;
+ }
+ v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS;
+ }
+ return status;
+}
+
/**
* ice_add_to_vsi_fltr_list - Add VSI filters to the list
* @hw: pointer to the hardware structure
@@ -1600,6 +1759,16 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id,
}
break;
case ICE_SW_LKUP_VLAN:
+ mutex_lock(&sw->vlan_list_lock);
+ status = ice_add_to_vsi_fltr_list(hw, vsi_id,
+ &sw->vlan_list_head,
+ &remove_list_head);
+ mutex_unlock(&sw->vlan_list_lock);
+ if (!status) {
+ ice_remove_vlan(hw, &remove_list_head);
+ goto free_fltr_list;
+ }
+ break;
case ICE_SW_LKUP_MAC_VLAN:
case ICE_SW_LKUP_ETHERTYPE:
case ICE_SW_LKUP_ETHERTYPE_MAC:
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 1b312e7ab2b5..80b4e1951b32 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -8,6 +8,7 @@
#define ICE_SW_CFG_MAX_BUF_LEN 2048
#define ICE_DFLT_VSI_INVAL 0xff
+#define ICE_VSI_INVAL_ID 0xffff
/* VSI context structure for add/get/update/free operations */
struct ice_vsi_ctx {
@@ -152,4 +153,7 @@ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw);
enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst);
enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst);
void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id);
+enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
+enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list);
+
#endif /* _ICE_SWITCH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 1ccf8e69b85a..6481e3d86374 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -796,6 +796,134 @@ static bool ice_is_non_eop(struct ice_ring *rx_ring,
return true;
}
+/**
+ * ice_ptype_to_htype - get a hash type
+ * @ptype: the ptype value from the descriptor
+ *
+ * Returns a hash type to be used by skb_set_hash
+ */
+static enum pkt_hash_types ice_ptype_to_htype(u8 __always_unused ptype)
+{
+ return PKT_HASH_TYPE_NONE;
+}
+
+/**
+ * ice_rx_hash - set the hash value in the skb
+ * @rx_ring: descriptor ring
+ * @rx_desc: specific descriptor
+ * @skb: pointer to current skb
+ * @rx_ptype: the ptype value from the descriptor
+ */
+static void
+ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
+ struct sk_buff *skb, u8 rx_ptype)
+{
+ struct ice_32b_rx_flex_desc_nic *nic_mdid;
+ u32 hash;
+
+ if (!(rx_ring->netdev->features & NETIF_F_RXHASH))
+ return;
+
+ if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)
+ return;
+
+ nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+ hash = le32_to_cpu(nic_mdid->rss_hash);
+ skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
+}
+
+/**
+ * ice_rx_csum - Indicate in skb if checksum is good
+ * @vsi: the VSI we care about
+ * @skb: skb currently being received and modified
+ * @rx_desc: the receive descriptor
+ * @ptype: the packet type decoded by hardware
+ *
+ * skb->protocol must be set before this function is called
+ */
+static void ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
+ union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
+{
+ struct ice_rx_ptype_decoded decoded;
+ u32 rx_error, rx_status;
+ bool ipv4, ipv6;
+
+ rx_status = le16_to_cpu(rx_desc->wb.status_error0);
+ rx_error = rx_status;
+
+ decoded = ice_decode_rx_desc_ptype(ptype);
+
+ /* Start with CHECKSUM_NONE and by default csum_level = 0 */
+ skb->ip_summed = CHECKSUM_NONE;
+ skb_checksum_none_assert(skb);
+
+ /* check if Rx checksum is enabled */
+ if (!(vsi->netdev->features & NETIF_F_RXCSUM))
+ return;
+
+ /* check if HW has decoded the packet and checksum */
+ if (!(rx_status & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
+ return;
+
+ if (!(decoded.known && decoded.outer_ip))
+ return;
+
+ ipv4 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
+ (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV4);
+ ipv6 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
+ (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV6);
+
+ if (ipv4 && (rx_error & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |
+ BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S))))
+ goto checksum_fail;
+ else if (ipv6 && (rx_status &
+ (BIT(ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S))))
+ goto checksum_fail;
+
+ /* check for L4 errors and handle packets that were not able to be
+ * checksummed due to arrival speed
+ */
+ if (rx_error & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S))
+ goto checksum_fail;
+
+ /* Only report checksum unnecessary for TCP, UDP, or SCTP */
+ switch (decoded.inner_prot) {
+ case ICE_RX_PTYPE_INNER_PROT_TCP:
+ case ICE_RX_PTYPE_INNER_PROT_UDP:
+ case ICE_RX_PTYPE_INNER_PROT_SCTP:
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ default:
+ break;
+ }
+ return;
+
+checksum_fail:
+ vsi->back->hw_csum_rx_error++;
+}
+
+/**
+ * ice_process_skb_fields - Populate skb header fields from Rx descriptor
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being populated
+ * @ptype: the packet type decoded by hardware
+ *
+ * This function checks the ring, descriptor, and packet information in
+ * order to populate the hash, checksum, VLAN, protocol, and
+ * other fields within the skb.
+ */
+static void ice_process_skb_fields(struct ice_ring *rx_ring,
+ union ice_32b_rx_flex_desc *rx_desc,
+ struct sk_buff *skb, u8 ptype)
+{
+ ice_rx_hash(rx_ring, rx_desc, skb, ptype);
+
+ /* 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_receive_skb - Send a completed packet up the stack
* @rx_ring: rx ring in play
@@ -839,6 +967,7 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
struct sk_buff *skb;
u16 stat_err_bits;
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) {
@@ -882,6 +1011,9 @@ 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);
@@ -897,6 +1029,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
/* probably a little skewed due to removing CRC */
total_rx_bytes += skb->len;
+ /* populate checksum, VLAN, and protocol */
+ ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+
/* send completed skb up the stack */
ice_receive_skb(rx_ring, skb, vlan_tag);
@@ -1026,14 +1161,17 @@ static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
* ice_tx_map - Build the Tx descriptor
* @tx_ring: ring to send buffer on
* @first: first buffer info buffer to use
+ * @off: pointer to struct that holds offload parameters
*
* This function loops over the skb data pointed to by *first
* and gets a physical address for each memory location and programs
* it and the length into the transmit descriptor.
*/
-static void ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first)
+static void
+ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
+ struct ice_tx_offload_params *off)
{
- u64 td_offset = 0, td_tag = 0, td_cmd = 0;
+ u64 td_offset, td_tag, td_cmd;
u16 i = tx_ring->next_to_use;
struct skb_frag_struct *frag;
unsigned int data_len, size;
@@ -1042,6 +1180,9 @@ static void ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first)
struct sk_buff *skb;
dma_addr_t dma;
+ td_tag = off->td_l2tag1;
+ td_cmd = off->td_cmd;
+ td_offset = off->td_offset;
skb = first->skb;
data_len = skb->data_len;
@@ -1049,6 +1190,12 @@ static void ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first)
tx_desc = ICE_TX_DESC(tx_ring, i);
+ if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) {
+ td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1;
+ td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >>
+ ICE_TX_FLAGS_VLAN_S;
+ }
+
dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
tx_buf = first;
@@ -1169,6 +1316,223 @@ static void ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first)
tx_ring->next_to_use = i;
}
+/**
+ * ice_tx_csum - Enable Tx checksum offloads
+ * @first: pointer to the first descriptor
+ * @off: pointer to struct that holds offload parameters
+ *
+ * Returns 0 or error (negative) if checksum offload can't happen, 1 otherwise.
+ */
+static
+int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
+{
+ u32 l4_len = 0, l3_len = 0, l2_len = 0;
+ struct sk_buff *skb = first->skb;
+ union {
+ struct iphdr *v4;
+ struct ipv6hdr *v6;
+ unsigned char *hdr;
+ } ip;
+ union {
+ struct tcphdr *tcp;
+ unsigned char *hdr;
+ } l4;
+ __be16 frag_off, protocol;
+ unsigned char *exthdr;
+ u32 offset, cmd = 0;
+ u8 l4_proto = 0;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
+ ip.hdr = skb_network_header(skb);
+ l4.hdr = skb_transport_header(skb);
+
+ /* compute outer L2 header size */
+ l2_len = ip.hdr - skb->data;
+ offset = (l2_len / 2) << ICE_TX_DESC_LEN_MACLEN_S;
+
+ if (skb->encapsulation)
+ return -1;
+
+ /* Enable IP checksum offloads */
+ protocol = vlan_get_protocol(skb);
+ if (protocol == htons(ETH_P_IP)) {
+ l4_proto = ip.v4->protocol;
+ /* the stack computes the IP header already, the only time we
+ * need the hardware to recompute it is in the case of TSO.
+ */
+ if (first->tx_flags & ICE_TX_FLAGS_TSO)
+ cmd |= ICE_TX_DESC_CMD_IIPT_IPV4_CSUM;
+ else
+ cmd |= ICE_TX_DESC_CMD_IIPT_IPV4;
+
+ } else if (protocol == htons(ETH_P_IPV6)) {
+ cmd |= ICE_TX_DESC_CMD_IIPT_IPV6;
+ exthdr = ip.hdr + sizeof(*ip.v6);
+ l4_proto = ip.v6->nexthdr;
+ if (l4.hdr != exthdr)
+ ipv6_skip_exthdr(skb, exthdr - skb->data, &l4_proto,
+ &frag_off);
+ } else {
+ return -1;
+ }
+
+ /* compute inner L3 header size */
+ l3_len = l4.hdr - ip.hdr;
+ offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S;
+
+ /* Enable L4 checksum offloads */
+ switch (l4_proto) {
+ case IPPROTO_TCP:
+ /* enable checksum offloads */
+ cmd |= ICE_TX_DESC_CMD_L4T_EOFT_TCP;
+ l4_len = l4.tcp->doff;
+ offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
+ break;
+ case IPPROTO_UDP:
+ /* enable UDP checksum offload */
+ cmd |= ICE_TX_DESC_CMD_L4T_EOFT_UDP;
+ l4_len = (sizeof(struct udphdr) >> 2);
+ offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
+ break;
+ case IPPROTO_SCTP:
+ default:
+ if (first->tx_flags & ICE_TX_FLAGS_TSO)
+ return -1;
+ skb_checksum_help(skb);
+ return 0;
+ }
+
+ off->td_cmd |= cmd;
+ off->td_offset |= offset;
+ return 1;
+}
+
+/**
+ * ice_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
+ * @tx_ring: ring to send buffer on
+ * @first: pointer to struct ice_tx_buf
+ *
+ * Checks the skb and set up correspondingly several generic transmit flags
+ * related to VLAN tagging for the HW, such as VLAN, DCB, etc.
+ *
+ * Returns error code indicate the frame should be dropped upon error and the
+ * otherwise returns 0 to indicate the flags has been set properly.
+ */
+static int
+ice_tx_prepare_vlan_flags(struct ice_ring *tx_ring, struct ice_tx_buf *first)
+{
+ struct sk_buff *skb = first->skb;
+ __be16 protocol = skb->protocol;
+
+ if (protocol == htons(ETH_P_8021Q) &&
+ !(tx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) {
+ /* when HW VLAN acceleration is turned off by the user the
+ * stack sets the protocol to 8021q so that the driver
+ * can take any steps required to support the SW only
+ * VLAN handling. In our case the driver doesn't need
+ * to take any further steps so just set the protocol
+ * to the encapsulated ethertype.
+ */
+ skb->protocol = vlan_get_protocol(skb);
+ goto out;
+ }
+
+ /* if we have a HW VLAN tag being added, default to the HW one */
+ if (skb_vlan_tag_present(skb)) {
+ first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S;
+ first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
+ } else if (protocol == htons(ETH_P_8021Q)) {
+ struct vlan_hdr *vhdr, _vhdr;
+
+ /* for SW VLAN, check the next protocol and store the tag */
+ vhdr = (struct vlan_hdr *)skb_header_pointer(skb, ETH_HLEN,
+ sizeof(_vhdr),
+ &_vhdr);
+ if (!vhdr)
+ return -EINVAL;
+
+ first->tx_flags |= ntohs(vhdr->h_vlan_TCI) <<
+ ICE_TX_FLAGS_VLAN_S;
+ first->tx_flags |= ICE_TX_FLAGS_SW_VLAN;
+ }
+
+out:
+ return 0;
+}
+
+/**
+ * ice_tso - computes mss and TSO length to prepare for TSO
+ * @first: pointer to struct ice_tx_buf
+ * @off: pointer to struct that holds offload parameters
+ *
+ * Returns 0 or error (negative) if TSO can't happen, 1 otherwise.
+ */
+static
+int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
+{
+ struct sk_buff *skb = first->skb;
+ union {
+ struct iphdr *v4;
+ struct ipv6hdr *v6;
+ unsigned char *hdr;
+ } ip;
+ union {
+ struct tcphdr *tcp;
+ unsigned char *hdr;
+ } l4;
+ u64 cd_mss, cd_tso_len;
+ u32 paylen, l4_start;
+ int err;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
+ if (!skb_is_gso(skb))
+ return 0;
+
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return err;
+
+ ip.hdr = skb_network_header(skb);
+ l4.hdr = skb_transport_header(skb);
+
+ /* initialize outer IP header fields */
+ if (ip.v4->version == 4) {
+ ip.v4->tot_len = 0;
+ ip.v4->check = 0;
+ } else {
+ ip.v6->payload_len = 0;
+ }
+
+ /* determine offset of transport header */
+ l4_start = l4.hdr - skb->data;
+
+ /* remove payload length from checksum */
+ paylen = skb->len - l4_start;
+ csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));
+
+ /* compute length of segmentation header */
+ off->header_len = (l4.tcp->doff * 4) + l4_start;
+
+ /* update gso_segs and bytecount */
+ first->gso_segs = skb_shinfo(skb)->gso_segs;
+ first->bytecount = (first->gso_segs - 1) * off->header_len;
+
+ cd_tso_len = skb->len - off->header_len;
+ cd_mss = skb_shinfo(skb)->gso_size;
+
+ /* record cdesc_qw1 with TSO parameters */
+ off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX |
+ (ICE_TX_CTX_DESC_TSO << ICE_TXD_CTX_QW1_CMD_S) |
+ (cd_tso_len << ICE_TXD_CTX_QW1_TSO_LEN_S) |
+ (cd_mss << ICE_TXD_CTX_QW1_MSS_S);
+ first->tx_flags |= ICE_TX_FLAGS_TSO;
+ return 1;
+}
+
/**
* ice_txd_use_count - estimate the number of descriptors needed for Tx
* @size: transmit request size in bytes
@@ -1322,8 +1686,10 @@ static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count)
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_tx_buf *first;
unsigned int count;
+ int tso, csum;
count = ice_xmit_desc_count(skb);
if (ice_chk_linearize(skb, count)) {
@@ -1344,13 +1710,46 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
return NETDEV_TX_BUSY;
}
+ offload.tx_ring = tx_ring;
+
/* record the location of the first descriptor for this packet */
first = &tx_ring->tx_buf[tx_ring->next_to_use];
first->skb = skb;
first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
first->gso_segs = 1;
+ first->tx_flags = 0;
+
+ /* prepare the VLAN tagging flags for Tx */
+ if (ice_tx_prepare_vlan_flags(tx_ring, first))
+ goto out_drop;
+
+ /* set up TSO offload */
+ tso = ice_tso(first, &offload);
+ if (tso < 0)
+ goto out_drop;
+
+ /* always set up Tx checksum offload */
+ csum = ice_tx_csum(first, &offload);
+ if (csum < 0)
+ goto out_drop;
+
+ if (tso || offload.cd_tunnel_params) {
+ struct ice_tx_ctx_desc *cdesc;
+ int i = tx_ring->next_to_use;
+
+ /* grab the next descriptor */
+ cdesc = ICE_TX_CTX_DESC(tx_ring, i);
+ i++;
+ tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
+
+ /* setup context descriptor */
+ cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params);
+ cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2);
+ cdesc->rsvd = cpu_to_le16(0);
+ cdesc->qw1 = cpu_to_le64(offload.cd_qw1);
+ }
- ice_tx_map(tx_ring, first);
+ ice_tx_map(tx_ring, first, &offload);
return NETDEV_TX_OK;
out_drop:
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 8fa4450514b4..567067b650c4 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -28,6 +28,12 @@
((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
(R)->next_to_clean - (R)->next_to_use - 1)
+#define ICE_TX_FLAGS_TSO BIT(0)
+#define ICE_TX_FLAGS_HW_VLAN BIT(1)
+#define ICE_TX_FLAGS_SW_VLAN BIT(2)
+#define ICE_TX_FLAGS_VLAN_M 0xffff0000
+#define ICE_TX_FLAGS_VLAN_S 16
+
struct ice_tx_buf {
struct ice_tx_desc *next_to_watch;
struct sk_buff *skb;
@@ -38,6 +44,17 @@ struct ice_tx_buf {
DEFINE_DMA_UNMAP_LEN(len);
};
+struct ice_tx_offload_params {
+ u8 header_len;
+ u32 td_cmd;
+ u32 td_offset;
+ u32 td_l2tag1;
+ u16 cd_l2tag2;
+ u32 cd_tunnel_params;
+ u64 cd_qw1;
+ struct ice_ring *tx_ring;
+};
+
struct ice_rx_buf {
struct sk_buff *skb;
dma_addr_t dma;
--
2.14.3
^ permalink raw reply related
* [net-next 12/15] ice: Add stats and ethtool support
From: Jeff Kirsher @ 2018-03-26 19:46 UTC (permalink / raw)
To: davem
Cc: Anirudh Venkataramanan, netdev, nhorman, sassmann, jogreene,
tbogendoerfer, bpoirier, Andrew Lunn, Jakub Kicinski,
Stephen Hemminger, Jeff Kirsher
In-Reply-To: <20180326194619.1202-1-jeffrey.t.kirsher@intel.com>
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
This patch implements a watchdog task to get packet statistics from
the device.
This patch also adds support for the following ethtool operations:
ethtool devname
ethtool -s devname [msglvl N] [msglevel type on|off]
ethtool -g|--show-ring devname
ethtool -G|--set-ring devname [rx N] [tx N]
ethtool -i|--driver devname
ethtool -d|--register-dump devname [raw on|off] [hex on|off] [file name]
ethtool -k|--show-features|--show-offload devname
ethtool -K|--features|--offload devname feature on|off
ethtool -P|--show-permaddr devname
ethtool -S|--statistics devname
ethtool -a|--show-pause devname
ethtool -A|--pause devname [autoneg on|off] [rx on|off] [tx on|off]
ethtool -r|--negotiate devname
CC: Andrew Lunn <andrew@lunn.ch>
CC: Jakub Kicinski <kubakici@wp.pl>
CC: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ice/Makefile | 3 +-
drivers/net/ethernet/intel/ice/ice.h | 28 +-
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 43 ++
drivers/net/ethernet/intel/ice/ice_common.c | 195 +++++
drivers/net/ethernet/intel/ice/ice_common.h | 5 +
drivers/net/ethernet/intel/ice/ice_ethtool.c | 940 ++++++++++++++++++++++++
drivers/net/ethernet/intel/ice/ice_hw_autogen.h | 80 ++
drivers/net/ethernet/intel/ice/ice_main.c | 469 +++++++++++-
drivers/net/ethernet/intel/ice/ice_type.h | 70 ++
9 files changed, 1828 insertions(+), 5 deletions(-)
create mode 100644 drivers/net/ethernet/intel/ice/ice_ethtool.c
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index de82fc875775..4058673fd853 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -13,4 +13,5 @@ ice-y := ice_main.o \
ice_nvm.o \
ice_switch.o \
ice_sched.o \
- ice_txrx.o
+ ice_txrx.o \
+ ice_ethtool.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 51cc955c7220..66d0976afa46 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -13,12 +13,14 @@
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/cpumask.h>
+#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <linux/dma-mapping.h>
#include <linux/pci.h>
#include <linux/workqueue.h>
#include <linux/aer.h>
#include <linux/interrupt.h>
+#include <linux/ethtool.h>
#include <linux/timer.h>
#include <linux/delay.h>
#include <linux/bitmap.h>
@@ -34,10 +36,14 @@
#include "ice_common.h"
#include "ice_sched.h"
+extern const char ice_drv_ver[];
#define ICE_BAR0 0
#define ICE_DFLT_NUM_DESC 128
+#define ICE_MIN_NUM_DESC 8
+#define ICE_MAX_NUM_DESC 8160
#define ICE_REQ_DESC_MULTIPLE 32
#define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16)
+#define ICE_ETHTOOL_FWVER_LEN 32
#define ICE_AQ_LEN 64
#define ICE_MIN_MSIX 2
#define ICE_NO_VSI 0xffff
@@ -56,6 +62,8 @@
#define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1)
#define ICE_INVAL_Q_INDEX 0xffff
+#define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4)
+
#define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
#define ICE_MAX_MTU (ICE_AQ_SET_MAC_FRAME_SIZE_MAX - \
@@ -102,6 +110,7 @@ enum ice_state {
__ICE_DOWN,
__ICE_PFR_REQ, /* set by driver and peers */
__ICE_ADMINQ_EVENT_PENDING,
+ __ICE_CFG_BUSY,
__ICE_SERVICE_SCHED,
__ICE_STATE_NBITS /* must be last */
};
@@ -118,8 +127,13 @@ struct ice_vsi {
irqreturn_t (*irq_handler)(int irq, void *data);
+ u64 tx_linearize;
DECLARE_BITMAP(state, __ICE_STATE_NBITS);
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+ u32 tx_restart;
+ u32 tx_busy;
+ u32 rx_buf_failed;
+ u32 rx_page_failed;
int num_q_vectors;
int base_vector;
enum ice_vsi_type type;
@@ -141,8 +155,14 @@ struct ice_vsi {
struct ice_aqc_vsi_props info; /* VSI properties */
+ /* VSI stats */
+ struct rtnl_link_stats64 net_stats;
+ struct ice_eth_stats eth_stats;
+ struct ice_eth_stats eth_stats_prev;
+
bool irqs_ready;
bool current_isup; /* Sync 'link up' logging */
+ bool stat_offsets_loaded;
/* queue information */
u8 tx_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */
@@ -205,8 +225,10 @@ struct ice_pf {
u16 q_left_rx; /* remaining num rx queues left unclaimed */
u16 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */
u16 num_alloc_vsi;
-
+ struct ice_hw_port_stats stats;
+ struct ice_hw_port_stats stats_prev;
struct ice_hw hw;
+ bool stat_prev_loaded; /* has previous stats been loaded */
char int_name[ICE_INT_NAME_STR_LEN];
};
@@ -239,8 +261,12 @@ static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
wr32(hw, GLINT_DYN_CTL(vector), val);
}
+void ice_set_ethtool_ops(struct net_device *netdev);
+int ice_up(struct ice_vsi *vsi);
+int ice_down(struct ice_vsi *vsi);
int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
+void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
#endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 051427dcfb3c..ae7376f2135b 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -859,6 +859,45 @@ struct ice_aqc_get_phy_caps_data {
} qual_modules[ICE_AQC_QUAL_MOD_COUNT_MAX];
};
+/* Set PHY capabilities (direct 0x0601)
+ * NOTE: This command must be followed by setup link and restart auto-neg
+ */
+struct ice_aqc_set_phy_cfg {
+ u8 lport_num;
+ u8 reserved[7];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Set PHY config command data structure */
+struct ice_aqc_set_phy_cfg_data {
+ __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
+ __le64 rsvd0;
+ u8 caps;
+#define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY BIT(0)
+#define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY BIT(1)
+#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2)
+#define ICE_AQ_PHY_ENA_LINK BIT(3)
+#define ICE_AQ_PHY_ENA_ATOMIC_LINK BIT(5)
+ u8 low_power_ctrl;
+ __le16 eee_cap; /* Value from ice_aqc_get_phy_caps */
+ __le16 eeer_value;
+ u8 link_fec_opt; /* Use defines from ice_aqc_get_phy_caps */
+ u8 rsvd1;
+};
+
+/* Restart AN command data structure (direct 0x0605)
+ * Also used for response, with only the lport_num field present.
+ */
+struct ice_aqc_restart_an {
+ u8 lport_num;
+ u8 reserved;
+ u8 cmd_flags;
+#define ICE_AQC_RESTART_AN_LINK_RESTART BIT(1)
+#define ICE_AQC_RESTART_AN_LINK_ENABLE BIT(2)
+ u8 reserved2[13];
+};
+
/* Get link status (indirect 0x0607), also used for Link Status Event */
struct ice_aqc_get_link_status {
u8 lport_num;
@@ -1137,6 +1176,8 @@ struct ice_aq_desc {
struct ice_aqc_clear_pxe clear_pxe;
struct ice_aqc_list_caps get_cap;
struct ice_aqc_get_phy_caps get_phy;
+ struct ice_aqc_set_phy_cfg set_phy;
+ struct ice_aqc_restart_an restart_an;
struct ice_aqc_get_sw_cfg get_sw_conf;
struct ice_aqc_sw_rules sw_rules;
struct ice_aqc_get_topo get_topo;
@@ -1222,6 +1263,8 @@ enum ice_adminq_opc {
/* PHY commands */
ice_aqc_opc_get_phy_caps = 0x0600,
+ ice_aqc_opc_set_phy_cfg = 0x0601,
+ ice_aqc_opc_restart_an = 0x0605,
ice_aqc_opc_get_link_status = 0x0607,
/* NVM commands */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index b4e834359a95..02d589275db0 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1261,6 +1261,201 @@ void ice_clear_pxe_mode(struct ice_hw *hw)
ice_aq_clear_pxe_mode(hw);
}
+/**
+ * ice_aq_set_phy_cfg
+ * @hw: pointer to the hw struct
+ * @lport: logical port number
+ * @cfg: structure with PHY configuration data to be set
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set the various PHY configuration parameters supported on the Port.
+ * One or more of the Set PHY config parameters may be ignored in an MFP
+ * mode as the PF may not have the privilege to set some of the PHY Config
+ * parameters. This status will be indicated by the command response (0x0601).
+ */
+static enum ice_status
+ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
+ struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_set_phy_cfg *cmd;
+ struct ice_aq_desc desc;
+
+ if (!cfg)
+ return ICE_ERR_PARAM;
+
+ cmd = &desc.params.set_phy;
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg);
+ cmd->lport_num = lport;
+
+ return ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd);
+}
+
+/**
+ * ice_update_link_info - update status of the HW network link
+ * @pi: port info structure of the interested logical port
+ */
+static enum ice_status
+ice_update_link_info(struct ice_port_info *pi)
+{
+ struct ice_aqc_get_phy_caps_data *pcaps;
+ struct ice_phy_info *phy_info;
+ enum ice_status status;
+ struct ice_hw *hw;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+
+ hw = pi->hw;
+
+ pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL);
+ if (!pcaps)
+ return ICE_ERR_NO_MEMORY;
+
+ phy_info = &pi->phy;
+ status = ice_aq_get_link_info(pi, true, NULL, NULL);
+ if (status)
+ goto out;
+
+ if (phy_info->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG,
+ pcaps, NULL);
+ if (status)
+ goto out;
+
+ memcpy(phy_info->link_info.module_type, &pcaps->module_type,
+ sizeof(phy_info->link_info.module_type));
+ }
+out:
+ devm_kfree(ice_hw_to_dev(hw), pcaps);
+ return status;
+}
+
+/**
+ * ice_set_fc
+ * @pi: port information structure
+ * @aq_failures: pointer to status code, specific to ice_set_fc routine
+ * @atomic_restart: enable automatic link update
+ *
+ * Set the requested flow control mode.
+ */
+enum ice_status
+ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart)
+{
+ struct ice_aqc_set_phy_cfg_data cfg = { 0 };
+ struct ice_aqc_get_phy_caps_data *pcaps;
+ enum ice_status status;
+ u8 pause_mask = 0x0;
+ struct ice_hw *hw;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+ hw = pi->hw;
+ *aq_failures = ICE_SET_FC_AQ_FAIL_NONE;
+
+ switch (pi->fc.req_mode) {
+ case ICE_FC_FULL:
+ pause_mask |= ICE_AQC_PHY_EN_TX_LINK_PAUSE;
+ pause_mask |= ICE_AQC_PHY_EN_RX_LINK_PAUSE;
+ break;
+ case ICE_FC_RX_PAUSE:
+ pause_mask |= ICE_AQC_PHY_EN_RX_LINK_PAUSE;
+ break;
+ case ICE_FC_TX_PAUSE:
+ pause_mask |= ICE_AQC_PHY_EN_TX_LINK_PAUSE;
+ break;
+ default:
+ break;
+ }
+
+ pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL);
+ if (!pcaps)
+ return ICE_ERR_NO_MEMORY;
+
+ /* Get the current phy config */
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+ NULL);
+ if (status) {
+ *aq_failures = ICE_SET_FC_AQ_FAIL_GET;
+ goto out;
+ }
+
+ /* clear the old pause settings */
+ cfg.caps = pcaps->caps & ~(ICE_AQC_PHY_EN_TX_LINK_PAUSE |
+ ICE_AQC_PHY_EN_RX_LINK_PAUSE);
+ /* set the new capabilities */
+ cfg.caps |= pause_mask;
+ /* If the capabilities have changed, then set the new config */
+ if (cfg.caps != pcaps->caps) {
+ int retry_count, retry_max = 10;
+
+ /* Auto restart link so settings take effect */
+ if (atomic_restart)
+ cfg.caps |= ICE_AQ_PHY_ENA_ATOMIC_LINK;
+ /* Copy over all the old settings */
+ cfg.phy_type_low = pcaps->phy_type_low;
+ cfg.low_power_ctrl = pcaps->low_power_ctrl;
+ cfg.eee_cap = pcaps->eee_cap;
+ cfg.eeer_value = pcaps->eeer_value;
+ cfg.link_fec_opt = pcaps->link_fec_options;
+
+ status = ice_aq_set_phy_cfg(hw, pi->lport, &cfg, NULL);
+ if (status) {
+ *aq_failures = ICE_SET_FC_AQ_FAIL_SET;
+ goto out;
+ }
+
+ /* Update the link info
+ * It sometimes takes a really long time for link to
+ * come back from the atomic reset. Thus, we wait a
+ * little bit.
+ */
+ for (retry_count = 0; retry_count < retry_max; retry_count++) {
+ status = ice_update_link_info(pi);
+
+ if (!status)
+ break;
+
+ mdelay(100);
+ }
+
+ if (status)
+ *aq_failures = ICE_SET_FC_AQ_FAIL_UPDATE;
+ }
+
+out:
+ devm_kfree(ice_hw_to_dev(hw), pcaps);
+ return status;
+}
+
+/**
+ * ice_aq_set_link_restart_an
+ * @pi: pointer to the port information structure
+ * @ena_link: if true: enable link, if false: disable link
+ * @cd: pointer to command details structure or NULL
+ *
+ * Sets up the link and restarts the Auto-Negotiation over the link.
+ */
+enum ice_status
+ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_restart_an *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.restart_an;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_restart_an);
+
+ cmd->cmd_flags = ICE_AQC_RESTART_AN_LINK_RESTART;
+ cmd->lport_num = pi->lport;
+ if (ena_link)
+ cmd->cmd_flags |= ICE_AQC_RESTART_AN_LINK_ENABLE;
+ else
+ cmd->cmd_flags &= ~ICE_AQC_RESTART_AN_LINK_ENABLE;
+
+ return ice_aq_send_cmd(pi->hw, &desc, NULL, 0, cd);
+}
+
/**
* __ice_aq_get_set_rss_lut
* @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 38719ba01d9b..c4213fbf9579 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -58,6 +58,11 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc,
enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd);
enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
enum ice_status
+ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart);
+enum ice_status
+ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
+ struct ice_sq_cd *cd);
+enum ice_status
ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
struct ice_link_status *link, struct ice_sq_cd *cd);
enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
new file mode 100644
index 000000000000..186764a5c263
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -0,0 +1,940 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Intel Corporation. */
+
+/* ethtool support for ice */
+
+#include "ice.h"
+
+struct ice_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int sizeof_stat;
+ int stat_offset;
+};
+
+#define ICE_STAT(_type, _name, _stat) { \
+ .stat_string = _name, \
+ .sizeof_stat = FIELD_SIZEOF(_type, _stat), \
+ .stat_offset = offsetof(_type, _stat) \
+}
+
+#define ICE_VSI_STAT(_name, _stat) \
+ ICE_STAT(struct ice_vsi, _name, _stat)
+#define ICE_PF_STAT(_name, _stat) \
+ ICE_STAT(struct ice_pf, _name, _stat)
+
+static int ice_q_stats_len(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+
+ return ((np->vsi->num_txq + np->vsi->num_rxq) *
+ (sizeof(struct ice_q_stats) / sizeof(u64)));
+}
+
+#define ICE_PF_STATS_LEN ARRAY_SIZE(ice_gstrings_pf_stats)
+#define ICE_VSI_STATS_LEN ARRAY_SIZE(ice_gstrings_vsi_stats)
+
+#define ICE_ALL_STATS_LEN(n) (ICE_PF_STATS_LEN + ICE_VSI_STATS_LEN + \
+ ice_q_stats_len(n))
+
+static const struct ice_stats ice_gstrings_vsi_stats[] = {
+ ICE_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
+ ICE_VSI_STAT("rx_unicast", eth_stats.rx_unicast),
+ ICE_VSI_STAT("tx_multicast", eth_stats.tx_multicast),
+ ICE_VSI_STAT("rx_multicast", eth_stats.rx_multicast),
+ ICE_VSI_STAT("tx_broadcast", eth_stats.tx_broadcast),
+ ICE_VSI_STAT("rx_broadcast", eth_stats.rx_broadcast),
+ ICE_VSI_STAT("tx_bytes", eth_stats.tx_bytes),
+ ICE_VSI_STAT("rx_bytes", eth_stats.rx_bytes),
+ ICE_VSI_STAT("rx_discards", eth_stats.rx_discards),
+ ICE_VSI_STAT("tx_errors", eth_stats.tx_errors),
+ ICE_VSI_STAT("tx_linearize", tx_linearize),
+ ICE_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
+ ICE_VSI_STAT("rx_alloc_fail", rx_buf_failed),
+ ICE_VSI_STAT("rx_pg_alloc_fail", rx_page_failed),
+};
+
+/* These PF_STATs might look like duplicates of some NETDEV_STATs,
+ * but they aren't. This device is capable of supporting multiple
+ * VSIs/netdevs on a single PF. The NETDEV_STATs are for individual
+ * netdevs whereas the PF_STATs are for the physical function that's
+ * hosting these netdevs.
+ *
+ * The PF_STATs are appended to the netdev stats only when ethtool -S
+ * is queried on the base PF netdev.
+ */
+static struct ice_stats ice_gstrings_pf_stats[] = {
+ ICE_PF_STAT("tx_bytes", stats.eth.tx_bytes),
+ ICE_PF_STAT("rx_bytes", stats.eth.rx_bytes),
+ ICE_PF_STAT("tx_unicast", stats.eth.tx_unicast),
+ ICE_PF_STAT("rx_unicast", stats.eth.rx_unicast),
+ ICE_PF_STAT("tx_multicast", stats.eth.tx_multicast),
+ ICE_PF_STAT("rx_multicast", stats.eth.rx_multicast),
+ ICE_PF_STAT("tx_broadcast", stats.eth.tx_broadcast),
+ ICE_PF_STAT("rx_broadcast", stats.eth.rx_broadcast),
+ ICE_PF_STAT("tx_errors", stats.eth.tx_errors),
+ ICE_PF_STAT("tx_size_64", stats.tx_size_64),
+ ICE_PF_STAT("rx_size_64", stats.rx_size_64),
+ ICE_PF_STAT("tx_size_127", stats.tx_size_127),
+ ICE_PF_STAT("rx_size_127", stats.rx_size_127),
+ ICE_PF_STAT("tx_size_255", stats.tx_size_255),
+ ICE_PF_STAT("rx_size_255", stats.rx_size_255),
+ ICE_PF_STAT("tx_size_511", stats.tx_size_511),
+ ICE_PF_STAT("rx_size_511", stats.rx_size_511),
+ ICE_PF_STAT("tx_size_1023", stats.tx_size_1023),
+ ICE_PF_STAT("rx_size_1023", stats.rx_size_1023),
+ ICE_PF_STAT("tx_size_1522", stats.tx_size_1522),
+ ICE_PF_STAT("rx_size_1522", stats.rx_size_1522),
+ ICE_PF_STAT("tx_size_big", stats.tx_size_big),
+ ICE_PF_STAT("rx_size_big", stats.rx_size_big),
+ ICE_PF_STAT("link_xon_tx", stats.link_xon_tx),
+ ICE_PF_STAT("link_xon_rx", stats.link_xon_rx),
+ ICE_PF_STAT("link_xoff_tx", stats.link_xoff_tx),
+ ICE_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
+ ICE_PF_STAT("tx_dropped_link_down", stats.tx_dropped_link_down),
+ ICE_PF_STAT("rx_undersize", stats.rx_undersize),
+ ICE_PF_STAT("rx_fragments", stats.rx_fragments),
+ ICE_PF_STAT("rx_oversize", stats.rx_oversize),
+ ICE_PF_STAT("rx_jabber", stats.rx_jabber),
+ ICE_PF_STAT("rx_csum_bad", hw_csum_rx_error),
+ ICE_PF_STAT("rx_length_errors", stats.rx_len_errors),
+ ICE_PF_STAT("rx_dropped", stats.eth.rx_discards),
+ ICE_PF_STAT("rx_crc_errors", stats.crc_errors),
+ ICE_PF_STAT("illegal_bytes", stats.illegal_bytes),
+ ICE_PF_STAT("mac_local_faults", stats.mac_local_faults),
+ ICE_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
+};
+
+static u32 ice_regs_dump_list[] = {
+ PFGEN_STATE,
+ PRTGEN_STATUS,
+ QRX_CTRL(0),
+ QINT_TQCTL(0),
+ QINT_RQCTL(0),
+ PFINT_OICR_ENA,
+ QRX_ITR(0),
+};
+
+/**
+ * ice_nvm_version_str - format the NVM version strings
+ * @hw: ptr to the hardware info
+ */
+static char *ice_nvm_version_str(struct ice_hw *hw)
+{
+ static char buf[ICE_ETHTOOL_FWVER_LEN];
+ u8 ver, patch;
+ u32 full_ver;
+ u16 build;
+
+ full_ver = hw->nvm.oem_ver;
+ ver = (u8)((full_ver & ICE_OEM_VER_MASK) >> ICE_OEM_VER_SHIFT);
+ build = (u16)((full_ver & ICE_OEM_VER_BUILD_MASK) >>
+ ICE_OEM_VER_BUILD_SHIFT);
+ patch = (u8)(full_ver & ICE_OEM_VER_PATCH_MASK);
+
+ snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d",
+ (hw->nvm.ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT,
+ (hw->nvm.ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT,
+ hw->nvm.eetrack, ver, build, patch);
+
+ return buf;
+}
+
+static void
+ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+
+ strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, ice_drv_ver, sizeof(drvinfo->version));
+ strlcpy(drvinfo->fw_version, ice_nvm_version_str(&pf->hw),
+ sizeof(drvinfo->fw_version));
+ strlcpy(drvinfo->bus_info, pci_name(pf->pdev),
+ sizeof(drvinfo->bus_info));
+}
+
+static int ice_get_regs_len(struct net_device __always_unused *netdev)
+{
+ return ARRAY_SIZE(ice_regs_dump_list);
+}
+
+static void
+ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ u32 *regs_buf = (u32 *)p;
+ int i;
+
+ regs->version = 1;
+
+ for (i = 0; i < ARRAY_SIZE(ice_regs_dump_list) / sizeof(u32); ++i)
+ regs_buf[i] = rd32(hw, ice_regs_dump_list[i]);
+}
+
+static u32 ice_get_msglevel(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+
+#ifndef CONFIG_DYNAMIC_DEBUG
+ if (pf->hw.debug_mask)
+ netdev_info(netdev, "hw debug_mask: 0x%llX\n",
+ pf->hw.debug_mask);
+#endif /* !CONFIG_DYNAMIC_DEBUG */
+
+ return pf->msg_enable;
+}
+
+static void ice_set_msglevel(struct net_device *netdev, u32 data)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+
+#ifndef CONFIG_DYNAMIC_DEBUG
+ if (ICE_DBG_USER & data)
+ pf->hw.debug_mask = data;
+ else
+ pf->msg_enable = data;
+#else
+ pf->msg_enable = data;
+#endif /* !CONFIG_DYNAMIC_DEBUG */
+}
+
+static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ char *p = (char *)data;
+ unsigned int i;
+
+ switch (stringset) {
+ case ETH_SS_STATS:
+ for (i = 0; i < ICE_VSI_STATS_LEN; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "%s",
+ ice_gstrings_vsi_stats[i].stat_string);
+ p += ETH_GSTRING_LEN;
+ }
+
+ ice_for_each_txq(vsi, i) {
+ snprintf(p, ETH_GSTRING_LEN,
+ "tx-queue-%u.tx_packets", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "tx-queue-%u.tx_bytes", i);
+ p += ETH_GSTRING_LEN;
+ }
+
+ ice_for_each_rxq(vsi, i) {
+ snprintf(p, ETH_GSTRING_LEN,
+ "rx-queue-%u.rx_packets", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "rx-queue-%u.rx_bytes", i);
+ p += ETH_GSTRING_LEN;
+ }
+
+ if (vsi->type != ICE_VSI_PF)
+ return;
+
+ for (i = 0; i < ICE_PF_STATS_LEN; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "port.%s",
+ ice_gstrings_pf_stats[i].stat_string);
+ p += ETH_GSTRING_LEN;
+ }
+
+ break;
+ default:
+ break;
+ }
+}
+
+static int ice_get_sset_count(struct net_device *netdev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return ICE_ALL_STATS_LEN(netdev);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void
+ice_get_ethtool_stats(struct net_device *netdev,
+ struct ethtool_stats __always_unused *stats, u64 *data)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ struct ice_ring *ring;
+ unsigned int j = 0;
+ int i = 0;
+ char *p;
+
+ for (j = 0; j < ICE_VSI_STATS_LEN; j++) {
+ p = (char *)vsi + ice_gstrings_vsi_stats[j].stat_offset;
+ data[i++] = (ice_gstrings_vsi_stats[j].sizeof_stat ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+
+ /* populate per queue stats */
+ rcu_read_lock();
+
+ ice_for_each_txq(vsi, j) {
+ ring = READ_ONCE(vsi->tx_rings[j]);
+ if (!ring)
+ continue;
+ data[i++] = ring->stats.pkts;
+ data[i++] = ring->stats.bytes;
+ }
+
+ ice_for_each_rxq(vsi, j) {
+ ring = READ_ONCE(vsi->rx_rings[j]);
+ data[i++] = ring->stats.pkts;
+ data[i++] = ring->stats.bytes;
+ }
+
+ rcu_read_unlock();
+
+ if (vsi->type != ICE_VSI_PF)
+ return;
+
+ for (j = 0; j < ICE_PF_STATS_LEN; j++) {
+ p = (char *)pf + ice_gstrings_pf_stats[j].stat_offset;
+ data[i++] = (ice_gstrings_pf_stats[j].sizeof_stat ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+}
+
+static int
+ice_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *ks)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_link_status *hw_link_info;
+ struct ice_vsi *vsi = np->vsi;
+ bool link_up;
+
+ hw_link_info = &vsi->port_info->phy.link_info;
+ link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
+
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
+
+ /* set speed and duplex */
+ if (link_up) {
+ switch (hw_link_info->link_speed) {
+ case ICE_AQ_LINK_SPEED_100MB:
+ ks->base.speed = SPEED_100;
+ break;
+ case ICE_AQ_LINK_SPEED_2500MB:
+ ks->base.speed = SPEED_2500;
+ break;
+ case ICE_AQ_LINK_SPEED_5GB:
+ ks->base.speed = SPEED_5000;
+ break;
+ case ICE_AQ_LINK_SPEED_10GB:
+ ks->base.speed = SPEED_10000;
+ break;
+ case ICE_AQ_LINK_SPEED_25GB:
+ ks->base.speed = SPEED_25000;
+ break;
+ case ICE_AQ_LINK_SPEED_40GB:
+ ks->base.speed = SPEED_40000;
+ break;
+ default:
+ ks->base.speed = SPEED_UNKNOWN;
+ break;
+ }
+
+ ks->base.duplex = DUPLEX_FULL;
+ } else {
+ ks->base.speed = SPEED_UNKNOWN;
+ ks->base.duplex = DUPLEX_UNKNOWN;
+ }
+
+ /* set autoneg settings */
+ ks->base.autoneg = ((hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+ /* set media type settings */
+ switch (vsi->port_info->phy.media_type) {
+ case ICE_MEDIA_FIBER:
+ ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE);
+ ks->base.port = PORT_FIBRE;
+ break;
+ case ICE_MEDIA_BASET:
+ ethtool_link_ksettings_add_link_mode(ks, supported, TP);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, TP);
+ ks->base.port = PORT_TP;
+ break;
+ case ICE_MEDIA_BACKPLANE:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported, Backplane);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Backplane);
+ ks->base.port = PORT_NONE;
+ break;
+ case ICE_MEDIA_DA:
+ ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, FIBRE);
+ ks->base.port = PORT_DA;
+ break;
+ default:
+ ks->base.port = PORT_OTHER;
+ break;
+ }
+
+ /* flow control is symmetric and always supported */
+ ethtool_link_ksettings_add_link_mode(ks, supported, Pause);
+
+ switch (vsi->port_info->fc.req_mode) {
+ case ICE_FC_FULL:
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
+ break;
+ case ICE_FC_TX_PAUSE:
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Asym_Pause);
+ break;
+ case ICE_FC_RX_PAUSE:
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Asym_Pause);
+ break;
+ case ICE_FC_PFC:
+ default:
+ ethtool_link_ksettings_del_link_mode(ks, advertising, Pause);
+ ethtool_link_ksettings_del_link_mode(ks, advertising,
+ Asym_Pause);
+ break;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_get_rxnfc - command to get RX flow classification rules
+ * @netdev: network interface device structure
+ * @cmd: ethtool rxnfc command
+ * @rule_locs: buffer to rturn Rx flow classification rules
+ *
+ * Returns Success if the command is supported.
+ */
+static int ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
+ u32 __always_unused *rule_locs)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_GRXRINGS:
+ cmd->data = vsi->rss_size;
+ ret = 0;
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+static void
+ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ ring->rx_max_pending = ICE_MAX_NUM_DESC;
+ ring->tx_max_pending = ICE_MAX_NUM_DESC;
+ ring->rx_pending = vsi->rx_rings[0]->count;
+ ring->tx_pending = vsi->tx_rings[0]->count;
+ ring->rx_mini_pending = ICE_MIN_NUM_DESC;
+ ring->rx_mini_max_pending = 0;
+ ring->rx_jumbo_max_pending = 0;
+ ring->rx_jumbo_pending = 0;
+}
+
+static int
+ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
+{
+ struct ice_ring *tx_rings = NULL, *rx_rings = NULL;
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ int i, timeout = 50, err = 0;
+ u32 new_rx_cnt, new_tx_cnt;
+
+ if (ring->tx_pending > ICE_MAX_NUM_DESC ||
+ ring->tx_pending < ICE_MIN_NUM_DESC ||
+ ring->rx_pending > ICE_MAX_NUM_DESC ||
+ ring->rx_pending < ICE_MIN_NUM_DESC) {
+ netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d]\n",
+ ring->tx_pending, ring->rx_pending,
+ ICE_MIN_NUM_DESC, ICE_MAX_NUM_DESC);
+ return -EINVAL;
+ }
+
+ new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE);
+ new_rx_cnt = ALIGN(ring->rx_pending, ICE_REQ_DESC_MULTIPLE);
+
+ /* if nothing to do return success */
+ if (new_tx_cnt == vsi->tx_rings[0]->count &&
+ new_rx_cnt == vsi->rx_rings[0]->count) {
+ netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n");
+ return 0;
+ }
+
+ while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) {
+ timeout--;
+ if (!timeout)
+ return -EBUSY;
+ usleep_range(1000, 2000);
+ }
+
+ /* set for the next time the netdev is started */
+ if (!netif_running(vsi->netdev)) {
+ for (i = 0; i < vsi->alloc_txq; i++)
+ vsi->tx_rings[i]->count = new_tx_cnt;
+ for (i = 0; i < vsi->alloc_rxq; i++)
+ vsi->rx_rings[i]->count = new_rx_cnt;
+ netdev_dbg(netdev, "Link is down, descriptor count change happens when link is brought up\n");
+ goto done;
+ }
+
+ if (new_tx_cnt == vsi->tx_rings[0]->count)
+ goto process_rx;
+
+ /* alloc updated Tx resources */
+ netdev_info(netdev, "Changing Tx descriptor count from %d to %d\n",
+ vsi->tx_rings[0]->count, new_tx_cnt);
+
+ tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
+ sizeof(struct ice_ring), GFP_KERNEL);
+ if (!tx_rings) {
+ err = -ENOMEM;
+ goto done;
+ }
+
+ for (i = 0; i < vsi->num_txq; i++) {
+ /* clone ring and setup updated count */
+ tx_rings[i] = *vsi->tx_rings[i];
+ tx_rings[i].count = new_tx_cnt;
+ tx_rings[i].desc = NULL;
+ tx_rings[i].tx_buf = NULL;
+ err = ice_setup_tx_ring(&tx_rings[i]);
+ if (err) {
+ while (i) {
+ i--;
+ ice_clean_tx_ring(&tx_rings[i]);
+ }
+ devm_kfree(&pf->pdev->dev, tx_rings);
+ goto done;
+ }
+ }
+
+process_rx:
+ if (new_rx_cnt == vsi->rx_rings[0]->count)
+ goto process_link;
+
+ /* alloc updated Rx resources */
+ netdev_info(netdev, "Changing Rx descriptor count from %d to %d\n",
+ vsi->rx_rings[0]->count, new_rx_cnt);
+
+ rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
+ sizeof(struct ice_ring), GFP_KERNEL);
+ if (!rx_rings) {
+ err = -ENOMEM;
+ goto done;
+ }
+
+ for (i = 0; i < vsi->num_rxq; i++) {
+ /* clone ring and setup updated count */
+ rx_rings[i] = *vsi->rx_rings[i];
+ rx_rings[i].count = new_rx_cnt;
+ rx_rings[i].desc = NULL;
+ rx_rings[i].rx_buf = NULL;
+ /* this is to allow wr32 to have something to write to
+ * during early allocation of Rx buffers
+ */
+ rx_rings[i].tail = vsi->back->hw.hw_addr + PRTGEN_STATUS;
+
+ err = ice_setup_rx_ring(&rx_rings[i]);
+ if (err)
+ goto rx_unwind;
+
+ /* allocate Rx buffers */
+ err = ice_alloc_rx_bufs(&rx_rings[i],
+ ICE_DESC_UNUSED(&rx_rings[i]));
+rx_unwind:
+ if (err) {
+ while (i) {
+ i--;
+ ice_free_rx_ring(&rx_rings[i]);
+ }
+ devm_kfree(&pf->pdev->dev, rx_rings);
+ err = -ENOMEM;
+ goto free_tx;
+ }
+ }
+
+process_link:
+ /* Bring interface down, copy in the new ring info, then restore the
+ * interface. if VSI is up, bring it down and then back up
+ */
+ if (!test_and_set_bit(__ICE_DOWN, vsi->state)) {
+ ice_down(vsi);
+
+ if (tx_rings) {
+ for (i = 0; i < vsi->alloc_txq; i++) {
+ ice_free_tx_ring(vsi->tx_rings[i]);
+ *vsi->tx_rings[i] = tx_rings[i];
+ }
+ devm_kfree(&pf->pdev->dev, tx_rings);
+ }
+
+ if (rx_rings) {
+ for (i = 0; i < vsi->alloc_rxq; i++) {
+ ice_free_rx_ring(vsi->rx_rings[i]);
+ /* copy the real tail offset */
+ rx_rings[i].tail = vsi->rx_rings[i]->tail;
+ /* this is to fake out the allocation routine
+ * into thinking it has to realloc everything
+ * but the recycling logic will let us re-use
+ * the buffers allocated above
+ */
+ rx_rings[i].next_to_use = 0;
+ rx_rings[i].next_to_clean = 0;
+ rx_rings[i].next_to_alloc = 0;
+ *vsi->rx_rings[i] = rx_rings[i];
+ }
+ devm_kfree(&pf->pdev->dev, rx_rings);
+ }
+
+ ice_up(vsi);
+ }
+ goto done;
+
+free_tx:
+ /* error cleanup if the Rx allocations failed after getting Tx */
+ if (tx_rings) {
+ for (i = 0; i < vsi->alloc_txq; i++)
+ ice_free_tx_ring(&tx_rings[i]);
+ devm_kfree(&pf->pdev->dev, tx_rings);
+ }
+
+done:
+ clear_bit(__ICE_CFG_BUSY, pf->state);
+ return err;
+}
+
+static int ice_nway_reset(struct net_device *netdev)
+{
+ /* restart autonegotiation */
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_link_status *hw_link_info;
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_port_info *pi;
+ enum ice_status status;
+ bool link_up;
+
+ pi = vsi->port_info;
+ hw_link_info = &pi->phy.link_info;
+ link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
+
+ status = ice_aq_set_link_restart_an(pi, link_up, NULL);
+ if (status) {
+ netdev_info(netdev, "link restart failed, err %d aq_err %d\n",
+ status, pi->hw->adminq.sq_last_status);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_get_pauseparam - Get Flow Control status
+ * @netdev: network interface device structure
+ * @pause: ethernet pause (flow control) parameters
+ */
+static void
+ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_port_info *pi;
+
+ pi = np->vsi->port_info;
+ pause->autoneg =
+ ((pi->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+ if (pi->fc.current_mode == ICE_FC_RX_PAUSE) {
+ pause->rx_pause = 1;
+ } else if (pi->fc.current_mode == ICE_FC_TX_PAUSE) {
+ pause->tx_pause = 1;
+ } else if (pi->fc.current_mode == ICE_FC_FULL) {
+ pause->rx_pause = 1;
+ pause->tx_pause = 1;
+ }
+}
+
+/**
+ * ice_set_pauseparam - Set Flow Control parameter
+ * @netdev: network interface device structure
+ * @pause: return tx/rx flow control status
+ */
+static int
+ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_link_status *hw_link_info;
+ struct ice_pf *pf = np->vsi->back;
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_hw *hw = &pf->hw;
+ struct ice_port_info *pi;
+ enum ice_status status;
+ u8 aq_failures;
+ bool link_up;
+ int err = 0;
+
+ pi = vsi->port_info;
+ hw_link_info = &pi->phy.link_info;
+ link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
+
+ /* Changing the port's flow control is not supported if this isn't the
+ * PF VSI
+ */
+ if (vsi->type != ICE_VSI_PF) {
+ netdev_info(netdev, "Changing flow control parameters only supported for PF VSI\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (pause->autoneg != (hw_link_info->an_info & ICE_AQ_AN_COMPLETED)) {
+ netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* If we have link and don't have autoneg */
+ if (!test_bit(__ICE_DOWN, pf->state) &&
+ !(hw_link_info->an_info & ICE_AQ_AN_COMPLETED)) {
+ /* Send message that it might not necessarily work*/
+ netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n");
+ }
+
+ if (pause->rx_pause && pause->tx_pause)
+ pi->fc.req_mode = ICE_FC_FULL;
+ else if (pause->rx_pause && !pause->tx_pause)
+ pi->fc.req_mode = ICE_FC_RX_PAUSE;
+ else if (!pause->rx_pause && pause->tx_pause)
+ pi->fc.req_mode = ICE_FC_TX_PAUSE;
+ else if (!pause->rx_pause && !pause->tx_pause)
+ pi->fc.req_mode = ICE_FC_NONE;
+ else
+ return -EINVAL;
+
+ /* Tell the OS link is going down, the link will go back up when fw
+ * says it is ready asynchronously
+ */
+ ice_print_link_msg(vsi, false);
+ netif_carrier_off(netdev);
+ netif_tx_stop_all_queues(netdev);
+
+ /* Set the FC mode and only restart AN if link is up */
+ status = ice_set_fc(pi, &aq_failures, link_up);
+
+ if (aq_failures & ICE_SET_FC_AQ_FAIL_GET) {
+ netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %d aq_err %d\n",
+ status, hw->adminq.sq_last_status);
+ err = -EAGAIN;
+ } else if (aq_failures & ICE_SET_FC_AQ_FAIL_SET) {
+ netdev_info(netdev, "Set fc failed on the set_phy_config call with err %d aq_err %d\n",
+ status, hw->adminq.sq_last_status);
+ err = -EAGAIN;
+ } else if (aq_failures & ICE_SET_FC_AQ_FAIL_UPDATE) {
+ netdev_info(netdev, "Set fc failed on the get_link_info call with err %d aq_err %d\n",
+ status, hw->adminq.sq_last_status);
+ err = -EAGAIN;
+ }
+
+ if (!test_bit(__ICE_DOWN, pf->state)) {
+ /* Give it a little more time to try to come back */
+ msleep(75);
+ if (!test_bit(__ICE_DOWN, pf->state))
+ return ice_nway_reset(netdev);
+ }
+
+ return err;
+}
+
+/**
+ * ice_get_rxfh_key_size - get the RSS hash key size
+ * @netdev: network interface device structure
+ *
+ * Returns the table size.
+ */
+static u32 ice_get_rxfh_key_size(struct net_device __always_unused *netdev)
+{
+ return ICE_VSIQF_HKEY_ARRAY_SIZE;
+}
+
+/**
+ * ice_get_rxfh_indir_size - get the rx flow hash indirection table size
+ * @netdev: network interface device structure
+ *
+ * Returns the table size.
+ */
+static u32 ice_get_rxfh_indir_size(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+
+ return np->vsi->rss_table_size;
+}
+
+/**
+ * ice_get_rxfh - get the rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @indir: indirection table
+ * @key: hash key
+ * @hfunc: hash function
+ *
+ * Reads the indirection table directly from the hardware.
+ */
+static int
+ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ int ret = 0, i;
+ u8 *lut;
+
+ if (hfunc)
+ *hfunc = ETH_RSS_HASH_TOP;
+
+ if (!indir)
+ return 0;
+
+ if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
+ /* RSS not supported return error here */
+ netdev_warn(netdev, "RSS is not configured on this VSI!\n");
+ return -EIO;
+ }
+
+ lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL);
+ if (!lut)
+ return -ENOMEM;
+
+ if (ice_get_rss(vsi, key, lut, vsi->rss_table_size)) {
+ ret = -EIO;
+ goto out;
+ }
+
+ for (i = 0; i < vsi->rss_table_size; i++)
+ indir[i] = (u32)(lut[i]);
+
+out:
+ devm_kfree(&pf->pdev->dev, lut);
+ return ret;
+}
+
+/**
+ * ice_set_rxfh - set the rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @indir: indirection table
+ * @key: hash key
+ * @hfunc: hash function
+ *
+ * Returns -EINVAL if the table specifies an invalid queue id, otherwise
+ * returns 0 after programming the table.
+ */
+static int ice_set_rxfh(struct net_device *netdev, const u32 *indir,
+ const u8 *key, const u8 hfunc)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ u8 *seed = NULL;
+
+ if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+ return -EOPNOTSUPP;
+
+ if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
+ /* RSS not supported return error here */
+ netdev_warn(netdev, "RSS is not configured on this VSI!\n");
+ return -EIO;
+ }
+
+ if (key) {
+ if (!vsi->rss_hkey_user) {
+ vsi->rss_hkey_user =
+ devm_kzalloc(&pf->pdev->dev,
+ ICE_VSIQF_HKEY_ARRAY_SIZE,
+ GFP_KERNEL);
+ if (!vsi->rss_hkey_user)
+ return -ENOMEM;
+ }
+ memcpy(vsi->rss_hkey_user, key, ICE_VSIQF_HKEY_ARRAY_SIZE);
+ seed = vsi->rss_hkey_user;
+ }
+
+ if (!vsi->rss_lut_user) {
+ vsi->rss_lut_user = devm_kzalloc(&pf->pdev->dev,
+ vsi->rss_table_size,
+ GFP_KERNEL);
+ if (!vsi->rss_lut_user)
+ return -ENOMEM;
+ }
+
+ /* Each 32 bits pointed by 'indir' is stored with a lut entry */
+ if (indir) {
+ int i;
+
+ for (i = 0; i < vsi->rss_table_size; i++)
+ vsi->rss_lut_user[i] = (u8)(indir[i]);
+ } else {
+ ice_fill_rss_lut(vsi->rss_lut_user, vsi->rss_table_size,
+ vsi->rss_size);
+ }
+
+ if (ice_set_rss(vsi, seed, vsi->rss_lut_user, vsi->rss_table_size))
+ return -EIO;
+
+ return 0;
+}
+
+static const struct ethtool_ops ice_ethtool_ops = {
+ .get_link_ksettings = ice_get_link_ksettings,
+ .get_drvinfo = ice_get_drvinfo,
+ .get_regs_len = ice_get_regs_len,
+ .get_regs = ice_get_regs,
+ .get_msglevel = ice_get_msglevel,
+ .set_msglevel = ice_set_msglevel,
+ .get_link = ethtool_op_get_link,
+ .get_strings = ice_get_strings,
+ .get_ethtool_stats = ice_get_ethtool_stats,
+ .get_sset_count = ice_get_sset_count,
+ .get_rxnfc = ice_get_rxnfc,
+ .get_ringparam = ice_get_ringparam,
+ .set_ringparam = ice_set_ringparam,
+ .nway_reset = ice_nway_reset,
+ .get_pauseparam = ice_get_pauseparam,
+ .set_pauseparam = ice_set_pauseparam,
+ .get_rxfh_key_size = ice_get_rxfh_key_size,
+ .get_rxfh_indir_size = ice_get_rxfh_indir_size,
+ .get_rxfh = ice_get_rxfh,
+ .set_rxfh = ice_set_rxfh,
+};
+
+/**
+ * ice_set_ethtool_ops - setup netdev ethtool ops
+ * @netdev: network interface device structure
+ *
+ * setup netdev ethtool ops with ice specific ops
+ */
+void ice_set_ethtool_ops(struct net_device *netdev)
+{
+ netdev->ethtool_ops = &ice_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index fc9b0b179e99..777a1c653edb 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -94,6 +94,8 @@
#define PFGEN_CTRL 0x00091000
#define PFGEN_CTRL_PFSWR_S 0
#define PFGEN_CTRL_PFSWR_M BIT(PFGEN_CTRL_PFSWR_S)
+#define PFGEN_STATE 0x00088000
+#define PRTGEN_STATUS 0x000B8100
#define PFHMC_ERRORDATA 0x00520500
#define PFHMC_ERRORINFO 0x00520400
#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4))
@@ -165,6 +167,7 @@
#define QRX_CTRL_QENA_REQ_M BIT(QRX_CTRL_QENA_REQ_S)
#define QRX_CTRL_QENA_STAT_S 2
#define QRX_CTRL_QENA_STAT_M BIT(QRX_CTRL_QENA_STAT_S)
+#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4))
#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4))
#define GLNVM_FLA 0x000B6108
#define GLNVM_FLA_LOCKED_S 6
@@ -180,5 +183,82 @@
#define PF_FUNC_RID 0x0009E880
#define PF_FUNC_RID_FUNC_NUM_S 0
#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, PF_FUNC_RID_FUNC_NUM_S)
+#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8))
+#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8))
+#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8))
+#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8))
+#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8))
+#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8))
+#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8))
+#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8))
+#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8))
+#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8))
+#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8))
+#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8))
+#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8))
+#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8))
+#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8))
+#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8))
+#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8))
+#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8))
+#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8))
+#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8))
+#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8))
+#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8))
+#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8))
+#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8))
+#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8))
+#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8))
+#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8))
+#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8))
+#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8))
+#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8))
+#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8))
+#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8))
+#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8))
+#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8))
+#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8))
+#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8))
+#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8))
+#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8))
+#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8))
+#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8))
+#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8))
+#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8))
+#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8))
+#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8))
+#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8))
+#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8))
+#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8))
+#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8))
+#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8))
+#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8))
+#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8))
+#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8))
+#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8))
+#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8))
+#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8))
+#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8))
+#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8))
+#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8))
+#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8))
+#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8))
+#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8))
+#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8))
+#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8))
+#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8))
+#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8))
+#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8))
+#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8))
+#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8))
+#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8))
+#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8))
+#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4))
+#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4))
+#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8))
+#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8))
+#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8))
+#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8))
+#define VSIQF_HKEY_MAX_INDEX 12
#endif /* _ICE_HW_AUTOGEN_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2124e7ad640c..9c1841700314 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -9,7 +9,7 @@
#define DRV_VERSION "ice-0.0.1-k"
#define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver"
-static const char ice_drv_ver[] = DRV_VERSION;
+const char ice_drv_ver[] = DRV_VERSION;
static const char ice_driver_string[] = DRV_SUMMARY;
static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";
@@ -30,6 +30,8 @@ static struct workqueue_struct *ice_wq;
static const struct net_device_ops ice_netdev_ops;
static int ice_vsi_release(struct ice_vsi *vsi);
+static void ice_update_vsi_stats(struct ice_vsi *vsi);
+static void ice_update_pf_stats(struct ice_pf *pf);
/**
* ice_get_free_slot - get the next non-NULL location index in array
@@ -214,12 +216,41 @@ static void ice_free_fltr_list(struct device *dev, struct list_head *h)
}
}
+/**
+ * ice_watchdog_subtask - periodic tasks not using event driven scheduling
+ * @pf: board private structure
+ */
+static void ice_watchdog_subtask(struct ice_pf *pf)
+{
+ int i;
+
+ /* if interface is down do nothing */
+ if (test_bit(__ICE_DOWN, pf->state) ||
+ test_bit(__ICE_CFG_BUSY, pf->state))
+ return;
+
+ /* make sure we don't do these things too often */
+ if (time_before(jiffies,
+ pf->serv_tmr_prev + pf->serv_tmr_period))
+ return;
+
+ pf->serv_tmr_prev = jiffies;
+
+ /* Update the stats for active netdevs so the network stack
+ * can look at updated numbers whenever it cares to
+ */
+ ice_update_pf_stats(pf);
+ for (i = 0; i < pf->num_alloc_vsi; i++)
+ if (pf->vsi[i] && pf->vsi[i]->netdev)
+ ice_update_vsi_stats(pf->vsi[i]);
+}
+
/**
* ice_print_link_msg - print link up or down message
* @vsi: the VSI whose link status is being queried
* @isup: boolean for if the link is now up or down
*/
-static void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
+void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
{
const char *speed;
const char *fc;
@@ -452,6 +483,7 @@ static void ice_service_task(struct work_struct *work)
unsigned long start_time = jiffies;
/* subtasks */
+ ice_watchdog_subtask(pf);
ice_clean_adminq_subtask(pf);
/* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */
@@ -1763,6 +1795,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
/* setup watchdog timeout value to be 5 second */
netdev->watchdog_timeo = 5 * HZ;
+ ice_set_ethtool_ops(netdev);
+
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = ICE_MAX_MTU;
@@ -3459,6 +3493,434 @@ static int ice_up_complete(struct ice_vsi *vsi)
return err;
}
+/**
+ * ice_up - Bring the connection back up after being down
+ * @vsi: VSI being configured
+ */
+int ice_up(struct ice_vsi *vsi)
+{
+ int err;
+
+ err = ice_vsi_cfg(vsi);
+ if (!err)
+ err = ice_up_complete(vsi);
+
+ return err;
+}
+
+/**
+ * ice_fetch_u64_stats_per_ring - get packets and bytes stats per ring
+ * @ring: Tx or Rx ring to read stats from
+ * @pkts: packets stats counter
+ * @bytes: bytes stats counter
+ *
+ * This function fetches stats from the ring considering the atomic operations
+ * that needs to be performed to read u64 values in 32 bit machine.
+ */
+static void ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts,
+ u64 *bytes)
+{
+ unsigned int start;
+ *pkts = 0;
+ *bytes = 0;
+
+ if (!ring)
+ return;
+ do {
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
+ *pkts = ring->stats.pkts;
+ *bytes = ring->stats.bytes;
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
+}
+
+/**
+ * ice_stat_update40 - read 40 bit stat from the chip and update stat values
+ * @hw: ptr to the hardware info
+ * @hireg: high 32 bit HW register to read from
+ * @loreg: low 32 bit HW register to read from
+ * @prev_stat_loaded: bool to specify if previous stats are loaded
+ * @prev_stat: ptr to previous loaded stat value
+ * @cur_stat: ptr to current stat value
+ */
+static void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg,
+ bool prev_stat_loaded, u64 *prev_stat,
+ u64 *cur_stat)
+{
+ u64 new_data;
+
+ new_data = rd32(hw, loreg);
+ new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32;
+
+ /* device stats are not reset at PFR, they likely will not be zeroed
+ * when the driver starts. So save the first values read and use them as
+ * offsets to be subtracted from the raw values in order to report stats
+ * that count from zero.
+ */
+ if (!prev_stat_loaded)
+ *prev_stat = new_data;
+ if (likely(new_data >= *prev_stat))
+ *cur_stat = new_data - *prev_stat;
+ else
+ /* to manage the potential roll-over */
+ *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat;
+ *cur_stat &= 0xFFFFFFFFFFULL;
+}
+
+/**
+ * ice_stat_update32 - read 32 bit stat from the chip and update stat values
+ * @hw: ptr to the hardware info
+ * @reg: HW register to read from
+ * @prev_stat_loaded: bool to specify if previous stats are loaded
+ * @prev_stat: ptr to previous loaded stat value
+ * @cur_stat: ptr to current stat value
+ */
+static void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
+ u64 *prev_stat, u64 *cur_stat)
+{
+ u32 new_data;
+
+ new_data = rd32(hw, reg);
+
+ /* device stats are not reset at PFR, they likely will not be zeroed
+ * when the driver starts. So save the first values read and use them as
+ * offsets to be subtracted from the raw values in order to report stats
+ * that count from zero.
+ */
+ if (!prev_stat_loaded)
+ *prev_stat = new_data;
+ if (likely(new_data >= *prev_stat))
+ *cur_stat = new_data - *prev_stat;
+ else
+ /* to manage the potential roll-over */
+ *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat;
+}
+
+/**
+ * ice_update_eth_stats - Update VSI-specific ethernet statistics counters
+ * @vsi: the VSI to be updated
+ */
+static void ice_update_eth_stats(struct ice_vsi *vsi)
+{
+ struct ice_eth_stats *prev_es, *cur_es;
+ struct ice_hw *hw = &vsi->back->hw;
+ u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */
+
+ prev_es = &vsi->eth_stats_prev;
+ cur_es = &vsi->eth_stats;
+
+ ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->rx_bytes,
+ &cur_es->rx_bytes);
+
+ ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->rx_unicast,
+ &cur_es->rx_unicast);
+
+ ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->rx_multicast,
+ &cur_es->rx_multicast);
+
+ ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->rx_broadcast,
+ &cur_es->rx_broadcast);
+
+ ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->rx_discards, &cur_es->rx_discards);
+
+ ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->tx_bytes,
+ &cur_es->tx_bytes);
+
+ ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->tx_unicast,
+ &cur_es->tx_unicast);
+
+ ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->tx_multicast,
+ &cur_es->tx_multicast);
+
+ ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num),
+ vsi->stat_offsets_loaded, &prev_es->tx_broadcast,
+ &cur_es->tx_broadcast);
+
+ ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->tx_errors, &cur_es->tx_errors);
+
+ vsi->stat_offsets_loaded = true;
+}
+
+/**
+ * ice_update_vsi_ring_stats - Update VSI stats counters
+ * @vsi: the VSI to be updated
+ */
+static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
+{
+ struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
+ struct ice_ring *ring;
+ u64 pkts, bytes;
+ int i;
+
+ /* reset netdev stats */
+ vsi_stats->tx_packets = 0;
+ vsi_stats->tx_bytes = 0;
+ vsi_stats->rx_packets = 0;
+ vsi_stats->rx_bytes = 0;
+
+ /* reset non-netdev (extended) stats */
+ vsi->tx_restart = 0;
+ vsi->tx_busy = 0;
+ vsi->tx_linearize = 0;
+ vsi->rx_buf_failed = 0;
+ vsi->rx_page_failed = 0;
+
+ rcu_read_lock();
+
+ /* update Tx rings counters */
+ ice_for_each_txq(vsi, i) {
+ ring = READ_ONCE(vsi->tx_rings[i]);
+ ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes);
+ vsi_stats->tx_packets += pkts;
+ vsi_stats->tx_bytes += bytes;
+ vsi->tx_restart += ring->tx_stats.restart_q;
+ vsi->tx_busy += ring->tx_stats.tx_busy;
+ vsi->tx_linearize += ring->tx_stats.tx_linearize;
+ }
+
+ /* update Rx rings counters */
+ ice_for_each_rxq(vsi, i) {
+ ring = READ_ONCE(vsi->rx_rings[i]);
+ ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes);
+ vsi_stats->rx_packets += pkts;
+ vsi_stats->rx_bytes += bytes;
+ vsi->rx_buf_failed += ring->rx_stats.alloc_buf_failed;
+ vsi->rx_page_failed += ring->rx_stats.alloc_page_failed;
+ }
+
+ rcu_read_unlock();
+}
+
+/**
+ * ice_update_vsi_stats - Update VSI stats counters
+ * @vsi: the VSI to be updated
+ */
+static void ice_update_vsi_stats(struct ice_vsi *vsi)
+{
+ struct rtnl_link_stats64 *cur_ns = &vsi->net_stats;
+ struct ice_eth_stats *cur_es = &vsi->eth_stats;
+ struct ice_pf *pf = vsi->back;
+
+ if (test_bit(__ICE_DOWN, vsi->state) ||
+ test_bit(__ICE_CFG_BUSY, pf->state))
+ return;
+
+ /* get stats as recorded by Tx/Rx rings */
+ ice_update_vsi_ring_stats(vsi);
+
+ /* get VSI stats as recorded by the hardware */
+ ice_update_eth_stats(vsi);
+
+ cur_ns->tx_errors = cur_es->tx_errors;
+ cur_ns->rx_dropped = cur_es->rx_discards;
+ cur_ns->tx_dropped = cur_es->tx_discards;
+ cur_ns->multicast = cur_es->rx_multicast;
+
+ /* update some more netdev stats if this is main VSI */
+ if (vsi->type == ICE_VSI_PF) {
+ cur_ns->rx_crc_errors = pf->stats.crc_errors;
+ cur_ns->rx_errors = pf->stats.crc_errors +
+ pf->stats.illegal_bytes;
+ cur_ns->rx_length_errors = pf->stats.rx_len_errors;
+ }
+}
+
+/**
+ * ice_update_pf_stats - Update PF port stats counters
+ * @pf: PF whose stats needs to be updated
+ */
+static void ice_update_pf_stats(struct ice_pf *pf)
+{
+ struct ice_hw_port_stats *prev_ps, *cur_ps;
+ struct ice_hw *hw = &pf->hw;
+ u8 pf_id;
+
+ prev_ps = &pf->stats_prev;
+ cur_ps = &pf->stats;
+ pf_id = hw->pf_id;
+
+ ice_stat_update40(hw, GLPRT_GORCH(pf_id), GLPRT_GORCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.rx_bytes,
+ &cur_ps->eth.rx_bytes);
+
+ ice_stat_update40(hw, GLPRT_UPRCH(pf_id), GLPRT_UPRCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.rx_unicast,
+ &cur_ps->eth.rx_unicast);
+
+ ice_stat_update40(hw, GLPRT_MPRCH(pf_id), GLPRT_MPRCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.rx_multicast,
+ &cur_ps->eth.rx_multicast);
+
+ ice_stat_update40(hw, GLPRT_BPRCH(pf_id), GLPRT_BPRCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.rx_broadcast,
+ &cur_ps->eth.rx_broadcast);
+
+ ice_stat_update40(hw, GLPRT_GOTCH(pf_id), GLPRT_GOTCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.tx_bytes,
+ &cur_ps->eth.tx_bytes);
+
+ ice_stat_update40(hw, GLPRT_UPTCH(pf_id), GLPRT_UPTCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.tx_unicast,
+ &cur_ps->eth.tx_unicast);
+
+ ice_stat_update40(hw, GLPRT_MPTCH(pf_id), GLPRT_MPTCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.tx_multicast,
+ &cur_ps->eth.tx_multicast);
+
+ ice_stat_update40(hw, GLPRT_BPTCH(pf_id), GLPRT_BPTCL(pf_id),
+ pf->stat_prev_loaded, &prev_ps->eth.tx_broadcast,
+ &cur_ps->eth.tx_broadcast);
+
+ ice_stat_update32(hw, GLPRT_TDOLD(pf_id), pf->stat_prev_loaded,
+ &prev_ps->tx_dropped_link_down,
+ &cur_ps->tx_dropped_link_down);
+
+ ice_stat_update40(hw, GLPRT_PRC64H(pf_id), GLPRT_PRC64L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->rx_size_64,
+ &cur_ps->rx_size_64);
+
+ ice_stat_update40(hw, GLPRT_PRC127H(pf_id), GLPRT_PRC127L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->rx_size_127,
+ &cur_ps->rx_size_127);
+
+ ice_stat_update40(hw, GLPRT_PRC255H(pf_id), GLPRT_PRC255L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->rx_size_255,
+ &cur_ps->rx_size_255);
+
+ ice_stat_update40(hw, GLPRT_PRC511H(pf_id), GLPRT_PRC511L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->rx_size_511,
+ &cur_ps->rx_size_511);
+
+ ice_stat_update40(hw, GLPRT_PRC1023H(pf_id),
+ GLPRT_PRC1023L(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_size_1023, &cur_ps->rx_size_1023);
+
+ ice_stat_update40(hw, GLPRT_PRC1522H(pf_id),
+ GLPRT_PRC1522L(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_size_1522, &cur_ps->rx_size_1522);
+
+ ice_stat_update40(hw, GLPRT_PRC9522H(pf_id),
+ GLPRT_PRC9522L(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_size_big, &cur_ps->rx_size_big);
+
+ ice_stat_update40(hw, GLPRT_PTC64H(pf_id), GLPRT_PTC64L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->tx_size_64,
+ &cur_ps->tx_size_64);
+
+ ice_stat_update40(hw, GLPRT_PTC127H(pf_id), GLPRT_PTC127L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->tx_size_127,
+ &cur_ps->tx_size_127);
+
+ ice_stat_update40(hw, GLPRT_PTC255H(pf_id), GLPRT_PTC255L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->tx_size_255,
+ &cur_ps->tx_size_255);
+
+ ice_stat_update40(hw, GLPRT_PTC511H(pf_id), GLPRT_PTC511L(pf_id),
+ pf->stat_prev_loaded, &prev_ps->tx_size_511,
+ &cur_ps->tx_size_511);
+
+ ice_stat_update40(hw, GLPRT_PTC1023H(pf_id),
+ GLPRT_PTC1023L(pf_id), pf->stat_prev_loaded,
+ &prev_ps->tx_size_1023, &cur_ps->tx_size_1023);
+
+ ice_stat_update40(hw, GLPRT_PTC1522H(pf_id),
+ GLPRT_PTC1522L(pf_id), pf->stat_prev_loaded,
+ &prev_ps->tx_size_1522, &cur_ps->tx_size_1522);
+
+ ice_stat_update40(hw, GLPRT_PTC9522H(pf_id),
+ GLPRT_PTC9522L(pf_id), pf->stat_prev_loaded,
+ &prev_ps->tx_size_big, &cur_ps->tx_size_big);
+
+ ice_stat_update32(hw, GLPRT_LXONRXC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->link_xon_rx, &cur_ps->link_xon_rx);
+
+ ice_stat_update32(hw, GLPRT_LXOFFRXC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->link_xoff_rx, &cur_ps->link_xoff_rx);
+
+ ice_stat_update32(hw, GLPRT_LXONTXC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->link_xon_tx, &cur_ps->link_xon_tx);
+
+ ice_stat_update32(hw, GLPRT_LXOFFTXC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->link_xoff_tx, &cur_ps->link_xoff_tx);
+
+ ice_stat_update32(hw, GLPRT_CRCERRS(pf_id), pf->stat_prev_loaded,
+ &prev_ps->crc_errors, &cur_ps->crc_errors);
+
+ ice_stat_update32(hw, GLPRT_ILLERRC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->illegal_bytes, &cur_ps->illegal_bytes);
+
+ ice_stat_update32(hw, GLPRT_MLFC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->mac_local_faults,
+ &cur_ps->mac_local_faults);
+
+ ice_stat_update32(hw, GLPRT_MRFC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->mac_remote_faults,
+ &cur_ps->mac_remote_faults);
+
+ ice_stat_update32(hw, GLPRT_RLEC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_len_errors, &cur_ps->rx_len_errors);
+
+ ice_stat_update32(hw, GLPRT_RUC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_undersize, &cur_ps->rx_undersize);
+
+ ice_stat_update32(hw, GLPRT_RFC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_fragments, &cur_ps->rx_fragments);
+
+ ice_stat_update32(hw, GLPRT_ROC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_oversize, &cur_ps->rx_oversize);
+
+ ice_stat_update32(hw, GLPRT_RJC(pf_id), pf->stat_prev_loaded,
+ &prev_ps->rx_jabber, &cur_ps->rx_jabber);
+
+ pf->stat_prev_loaded = true;
+}
+
+/**
+ * ice_get_stats64 - get statistics for network device structure
+ * @netdev: network interface device structure
+ * @stats: main device statistics structure
+ */
+static
+void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct rtnl_link_stats64 *vsi_stats;
+ struct ice_vsi *vsi = np->vsi;
+
+ vsi_stats = &vsi->net_stats;
+
+ if (test_bit(__ICE_DOWN, vsi->state) || !vsi->num_txq || !vsi->num_rxq)
+ return;
+ /* netdev packet/byte stats come from ring counter. These are obtained
+ * by summing up ring counters (done by ice_update_vsi_ring_stats).
+ */
+ ice_update_vsi_ring_stats(vsi);
+ stats->tx_packets = vsi_stats->tx_packets;
+ stats->tx_bytes = vsi_stats->tx_bytes;
+ stats->rx_packets = vsi_stats->rx_packets;
+ stats->rx_bytes = vsi_stats->rx_bytes;
+
+ /* The rest of the stats can be read from the hardware but instead we
+ * just return values that the watchdog task has already obtained from
+ * the hardware.
+ */
+ stats->multicast = vsi_stats->multicast;
+ stats->tx_errors = vsi_stats->tx_errors;
+ stats->tx_dropped = vsi_stats->tx_dropped;
+ stats->rx_errors = vsi_stats->rx_errors;
+ stats->rx_dropped = vsi_stats->rx_dropped;
+ stats->rx_crc_errors = vsi_stats->rx_crc_errors;
+ stats->rx_length_errors = vsi_stats->rx_length_errors;
+}
+
/**
* ice_napi_disable_all - Disable NAPI for all q_vectors in the VSI
* @vsi: VSI having NAPI disabled
@@ -3478,7 +3940,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
* ice_down - Shutdown the connection
* @vsi: The VSI being stopped
*/
-static int ice_down(struct ice_vsi *vsi)
+int ice_down(struct ice_vsi *vsi)
{
int i, err;
@@ -3878,6 +4340,7 @@ static const struct net_device_ops ice_netdev_ops = {
.ndo_open = ice_open,
.ndo_stop = ice_stop,
.ndo_start_xmit = ice_start_xmit,
+ .ndo_get_stats64 = ice_get_stats64,
.ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
.ndo_set_features = ice_set_features,
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 991ac56ca7b3..c7e0de3b8662 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -20,6 +20,7 @@
#define ICE_DBG_RES BIT_ULL(17)
#define ICE_DBG_AQ_MSG BIT_ULL(24)
#define ICE_DBG_AQ_CMD BIT_ULL(27)
+#define ICE_DBG_USER BIT_ULL(31)
enum ice_aq_res_ids {
ICE_NVM_RES_ID = 1,
@@ -42,6 +43,13 @@ enum ice_fc_mode {
ICE_FC_DFLT
};
+enum ice_set_fc_aq_failures {
+ ICE_SET_FC_AQ_FAIL_NONE = 0,
+ ICE_SET_FC_AQ_FAIL_GET,
+ ICE_SET_FC_AQ_FAIL_SET,
+ ICE_SET_FC_AQ_FAIL_UPDATE
+};
+
/* Various MAC types */
enum ice_mac_type {
ICE_MAC_UNKNOWN = 0,
@@ -301,10 +309,72 @@ struct ice_hw {
};
+/* Statistics collected by each port, VSI, VEB, and S-channel */
+struct ice_eth_stats {
+ u64 rx_bytes; /* gorc */
+ u64 rx_unicast; /* uprc */
+ u64 rx_multicast; /* mprc */
+ u64 rx_broadcast; /* bprc */
+ u64 rx_discards; /* rdpc */
+ u64 rx_unknown_protocol; /* rupp */
+ u64 tx_bytes; /* gotc */
+ u64 tx_unicast; /* uptc */
+ u64 tx_multicast; /* mptc */
+ u64 tx_broadcast; /* bptc */
+ u64 tx_discards; /* tdpc */
+ u64 tx_errors; /* tepc */
+};
+
+/* Statistics collected by the MAC */
+struct ice_hw_port_stats {
+ /* eth stats collected by the port */
+ struct ice_eth_stats eth;
+ /* additional port specific stats */
+ u64 tx_dropped_link_down; /* tdold */
+ u64 crc_errors; /* crcerrs */
+ u64 illegal_bytes; /* illerrc */
+ u64 error_bytes; /* errbc */
+ u64 mac_local_faults; /* mlfc */
+ u64 mac_remote_faults; /* mrfc */
+ u64 rx_len_errors; /* rlec */
+ u64 link_xon_rx; /* lxonrxc */
+ u64 link_xoff_rx; /* lxoffrxc */
+ u64 link_xon_tx; /* lxontxc */
+ u64 link_xoff_tx; /* lxofftxc */
+ u64 rx_size_64; /* prc64 */
+ u64 rx_size_127; /* prc127 */
+ u64 rx_size_255; /* prc255 */
+ u64 rx_size_511; /* prc511 */
+ u64 rx_size_1023; /* prc1023 */
+ u64 rx_size_1522; /* prc1522 */
+ u64 rx_size_big; /* prc9522 */
+ u64 rx_undersize; /* ruc */
+ u64 rx_fragments; /* rfc */
+ u64 rx_oversize; /* roc */
+ u64 rx_jabber; /* rjc */
+ u64 tx_size_64; /* ptc64 */
+ u64 tx_size_127; /* ptc127 */
+ u64 tx_size_255; /* ptc255 */
+ u64 tx_size_511; /* ptc511 */
+ u64 tx_size_1023; /* ptc1023 */
+ u64 tx_size_1522; /* ptc1522 */
+ u64 tx_size_big; /* ptc9522 */
+};
+
/* Checksum and Shadow RAM pointers */
#define ICE_SR_NVM_DEV_STARTER_VER 0x18
#define ICE_SR_NVM_EETRACK_LO 0x2D
#define ICE_SR_NVM_EETRACK_HI 0x2E
+#define ICE_NVM_VER_LO_SHIFT 0
+#define ICE_NVM_VER_LO_MASK (0xff << ICE_NVM_VER_LO_SHIFT)
+#define ICE_NVM_VER_HI_SHIFT 12
+#define ICE_NVM_VER_HI_MASK (0xf << ICE_NVM_VER_HI_SHIFT)
+#define ICE_OEM_VER_PATCH_SHIFT 0
+#define ICE_OEM_VER_PATCH_MASK (0xff << ICE_OEM_VER_PATCH_SHIFT)
+#define ICE_OEM_VER_BUILD_SHIFT 8
+#define ICE_OEM_VER_BUILD_MASK (0xffff << ICE_OEM_VER_BUILD_SHIFT)
+#define ICE_OEM_VER_SHIFT 24
+#define ICE_OEM_VER_MASK (0xff << ICE_OEM_VER_SHIFT)
#define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800
#define ICE_SR_WORDS_IN_1KB 512
--
2.14.3
^ permalink raw reply related
* [net-next 13/15] ice: Update Tx scheduler tree for VSI multi-Tx queue support
From: Jeff Kirsher @ 2018-03-26 19:46 UTC (permalink / raw)
To: davem
Cc: Anirudh Venkataramanan, netdev, nhorman, sassmann, jogreene,
tbogendoerfer, bpoirier, Jeff Kirsher
In-Reply-To: <20180326194619.1202-1-jeffrey.t.kirsher@intel.com>
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
This patch adds the ability for a VSI to use multiple Tx queues. More
specifically, the patch
1) Provides the ability to update the Tx scheduler tree in the
firmware. The driver can configure the Tx scheduler tree by
adding/removing multiple Tx queues per TC per VSI.
2) Allows a VSI to reconfigure its Tx queues during runtime.
3) Synchronizes the Tx scheduler update operations using locks.
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ice/ice.h | 7 +
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 28 +
drivers/net/ethernet/intel/ice/ice_common.c | 54 ++
drivers/net/ethernet/intel/ice/ice_common.h | 3 +
drivers/net/ethernet/intel/ice/ice_main.c | 20 +-
drivers/net/ethernet/intel/ice/ice_sched.c | 886 ++++++++++++++++++++++++
drivers/net/ethernet/intel/ice/ice_sched.h | 4 +
drivers/net/ethernet/intel/ice/ice_type.h | 7 +
8 files changed, 1006 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 66d0976afa46..8898255e5a65 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -42,6 +42,7 @@ extern const char ice_drv_ver[];
#define ICE_MIN_NUM_DESC 8
#define ICE_MAX_NUM_DESC 8160
#define ICE_REQ_DESC_MULTIPLE 32
+#define ICE_DFLT_TRAFFIC_CLASS BIT(0)
#define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16)
#define ICE_ETHTOOL_FWVER_LEN 32
#define ICE_AQ_LEN 64
@@ -261,6 +262,12 @@ static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
wr32(hw, GLINT_DYN_CTL(vector), val);
}
+static inline void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
+{
+ vsi->tc_cfg.ena_tc = ICE_DFLT_TRAFFIC_CLASS;
+ vsi->tc_cfg.numtc = 1;
+}
+
void ice_set_ethtool_ops(struct net_device *netdev);
int ice_up(struct ice_vsi *vsi);
int ice_down(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index ae7376f2135b..348b9cc3c596 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -631,6 +631,25 @@ struct ice_aqc_get_topo {
__le32 addr_low;
};
+/* Update TSE (indirect 0x0403)
+ * Get TSE (indirect 0x0404)
+ */
+struct ice_aqc_get_cfg_elem {
+ __le16 num_elem_req; /* Used by commands */
+ __le16 num_elem_resp; /* Used by responses */
+ __le32 reserved;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* This is the buffer for:
+ * Suspend Nodes (indirect 0x0409)
+ * Resume Nodes (indirect 0x040A)
+ */
+struct ice_aqc_suspend_resume_elem {
+ __le32 teid[1];
+};
+
/* Add TSE (indirect 0x0401)
* Delete TSE (indirect 0x040F)
* Move TSE (indirect 0x0408)
@@ -691,6 +710,11 @@ struct ice_aqc_txsched_topo_grp_info_hdr {
__le16 reserved2;
};
+struct ice_aqc_add_elem {
+ struct ice_aqc_txsched_topo_grp_info_hdr hdr;
+ struct ice_aqc_txsched_elem_data generic[1];
+};
+
struct ice_aqc_get_topo_elem {
struct ice_aqc_txsched_topo_grp_info_hdr hdr;
struct ice_aqc_txsched_elem_data
@@ -1181,6 +1205,7 @@ struct ice_aq_desc {
struct ice_aqc_get_sw_cfg get_sw_conf;
struct ice_aqc_sw_rules sw_rules;
struct ice_aqc_get_topo get_topo;
+ struct ice_aqc_get_cfg_elem get_update_elem;
struct ice_aqc_query_txsched_res query_sched_res;
struct ice_aqc_add_move_delete_elem add_move_delete_elem;
struct ice_aqc_nvm nvm;
@@ -1258,6 +1283,9 @@ enum ice_adminq_opc {
/* transmit scheduler commands */
ice_aqc_opc_get_dflt_topo = 0x0400,
+ ice_aqc_opc_add_sched_elems = 0x0401,
+ ice_aqc_opc_suspend_sched_elems = 0x0409,
+ ice_aqc_opc_resume_sched_elems = 0x040A,
ice_aqc_opc_delete_sched_elems = 0x040F,
ice_aqc_opc_query_sched_res = 0x0412,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 02d589275db0..0ab9bf66c84e 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2089,3 +2089,57 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
mutex_unlock(&pi->sched_lock);
return status;
}
+
+/**
+ * ice_cfg_vsi_qs - configure the new/exisiting VSI queues
+ * @pi: port information structure
+ * @vsi_id: VSI Id
+ * @tc_bitmap: TC bitmap
+ * @maxqs: max queues array per TC
+ * @owner: lan or rdma
+ *
+ * This function adds/updates the VSI queues per TC.
+ */
+static enum ice_status
+ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap,
+ u16 *maxqs, u8 owner)
+{
+ enum ice_status status = 0;
+ u8 i;
+
+ if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
+ return ICE_ERR_CFG;
+
+ mutex_lock(&pi->sched_lock);
+
+ for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+ /* configuration is possible only if TC node is present */
+ if (!ice_sched_get_tc_node(pi, i))
+ continue;
+
+ status = ice_sched_cfg_vsi(pi, vsi_id, i, maxqs[i], owner,
+ ice_is_tc_ena(tc_bitmap, i));
+ if (status)
+ break;
+ }
+
+ mutex_unlock(&pi->sched_lock);
+ return status;
+}
+
+/**
+ * ice_cfg_vsi_lan - configure VSI lan queues
+ * @pi: port information structure
+ * @vsi_id: VSI Id
+ * @tc_bitmap: TC bitmap
+ * @max_lanqs: max lan queues array per TC
+ *
+ * This function adds/updates the VSI lan queues per TC.
+ */
+enum ice_status
+ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap,
+ u16 *max_lanqs)
+{
+ return ice_cfg_vsi_qs(pi, vsi_id, tc_bitmap, max_lanqs,
+ ICE_SCHED_NODE_OWNER_LAN);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index c4213fbf9579..971277ebcc86 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -69,6 +69,9 @@ enum ice_status
ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
u32 *q_teids, struct ice_sq_cd *cmd_details);
enum ice_status
+ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap,
+ u16 *max_lanqs);
+enum ice_status
ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps,
struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
struct ice_sq_cd *cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 9c1841700314..0f8637b97a34 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2085,10 +2085,11 @@ static struct ice_vsi *
ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type,
struct ice_port_info *pi)
{
+ u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
struct device *dev = &pf->pdev->dev;
struct ice_vsi_ctx ctxt = { 0 };
struct ice_vsi *vsi;
- int ret;
+ int ret, i;
vsi = ice_vsi_alloc(pf, type);
if (!vsi) {
@@ -2156,6 +2157,20 @@ ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type,
*/
goto err_rings;
}
+
+ ice_vsi_set_tc_cfg(vsi);
+
+ /* configure VSI nodes based on number of queues and TC's */
+ for (i = 0; i < vsi->tc_cfg.numtc; i++)
+ max_txqs[i] = vsi->num_txq;
+
+ ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num,
+ vsi->tc_cfg.ena_tc, max_txqs);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "Failed VSI lan queue config\n");
+ goto err_rings;
+ }
+
return vsi;
err_rings:
@@ -2398,8 +2413,7 @@ static void ice_determine_q_usage(struct ice_pf *pf)
q_left_tx = pf->hw.func_caps.common_cap.num_txq;
q_left_rx = pf->hw.func_caps.common_cap.num_rxq;
- /* initial support for only 1 tx queue */
- pf->num_lan_tx = 1;
+ pf->num_lan_tx = min_t(int, q_left_tx, num_online_cpus());
/* only 1 rx queue unless RSS is enabled */
if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index e50eebbf78e3..f16ff3e4a840 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -359,6 +359,110 @@ ice_aq_get_dflt_topo(struct ice_hw *hw, u8 lport,
return status;
}
+/**
+ * ice_aq_add_sched_elems - adds scheduling element
+ * @hw: pointer to the hw struct
+ * @grps_req: the number of groups that are requested to be added
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @grps_added: returns total number of groups added
+ * @cd: pointer to command details structure or NULL
+ *
+ * Add scheduling elements (0x0401)
+ */
+static enum ice_status
+ice_aq_add_sched_elems(struct ice_hw *hw, u16 grps_req,
+ struct ice_aqc_add_elem *buf, u16 buf_size,
+ u16 *grps_added, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_add_move_delete_elem *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ cmd = &desc.params.add_move_delete_elem;
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_sched_elems);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+ cmd->num_grps_req = cpu_to_le16(grps_req);
+ status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+ if (!status && grps_added)
+ *grps_added = le16_to_cpu(cmd->num_grps_updated);
+
+ return status;
+}
+
+/**
+ * ice_suspend_resume_elems - suspend/resume scheduler elements
+ * @hw: pointer to the hw struct
+ * @elems_req: number of elements to suspend
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_ret: returns total number of elements suspended
+ * @cd: pointer to command details structure or NULL
+ * @cmd_code: command code for suspend or resume
+ *
+ * suspend/resume scheduler elements
+ */
+static enum ice_status
+ice_suspend_resume_elems(struct ice_hw *hw, u16 elems_req,
+ struct ice_aqc_suspend_resume_elem *buf, u16 buf_size,
+ u16 *elems_ret, struct ice_sq_cd *cd,
+ enum ice_adminq_opc cmd_code)
+{
+ struct ice_aqc_get_cfg_elem *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ cmd = &desc.params.get_update_elem;
+ ice_fill_dflt_direct_cmd_desc(&desc, cmd_code);
+ cmd->num_elem_req = cpu_to_le16(elems_req);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+ if (!status && elems_ret)
+ *elems_ret = le16_to_cpu(cmd->num_elem_resp);
+ return status;
+}
+
+/**
+ * ice_aq_suspend_sched_elems - suspend scheduler elements
+ * @hw: pointer to the hw struct
+ * @elems_req: number of elements to suspend
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_ret: returns total number of elements suspended
+ * @cd: pointer to command details structure or NULL
+ *
+ * Suspend scheduling elements (0x0409)
+ */
+static enum ice_status
+ice_aq_suspend_sched_elems(struct ice_hw *hw, u16 elems_req,
+ struct ice_aqc_suspend_resume_elem *buf,
+ u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
+{
+ return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
+ cd, ice_aqc_opc_suspend_sched_elems);
+}
+
+/**
+ * ice_aq_resume_sched_elems - resume scheduler elements
+ * @hw: pointer to the hw struct
+ * @elems_req: number of elements to resume
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_ret: returns total number of elements resumed
+ * @cd: pointer to command details structure or NULL
+ *
+ * resume scheduling elements (0x040A)
+ */
+static enum ice_status
+ice_aq_resume_sched_elems(struct ice_hw *hw, u16 elems_req,
+ struct ice_aqc_suspend_resume_elem *buf,
+ u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
+{
+ return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
+ cd, ice_aqc_opc_resume_sched_elems);
+}
+
/**
* ice_aq_query_sched_res - query scheduler resource
* @hw: pointer to the hw struct
@@ -379,6 +483,46 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size,
return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
}
+/**
+ * ice_sched_suspend_resume_elems - suspend or resume hw nodes
+ * @hw: pointer to the hw struct
+ * @num_nodes: number of nodes
+ * @node_teids: array of node teids to be suspended or resumed
+ * @suspend: true means suspend / false means resume
+ *
+ * This function suspends or resumes hw nodes
+ */
+static enum ice_status
+ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
+ bool suspend)
+{
+ struct ice_aqc_suspend_resume_elem *buf;
+ u16 i, buf_size, num_elem_ret = 0;
+ enum ice_status status;
+
+ buf_size = sizeof(*buf) * num_nodes;
+ buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL);
+ if (!buf)
+ return ICE_ERR_NO_MEMORY;
+
+ for (i = 0; i < num_nodes; i++)
+ buf->teid[i] = cpu_to_le32(node_teids[i]);
+
+ if (suspend)
+ status = ice_aq_suspend_sched_elems(hw, num_nodes, buf,
+ buf_size, &num_elem_ret,
+ NULL);
+ else
+ status = ice_aq_resume_sched_elems(hw, num_nodes, buf,
+ buf_size, &num_elem_ret,
+ NULL);
+ if (status || num_elem_ret != num_nodes)
+ ice_debug(hw, ICE_DBG_SCHED, "suspend/resume failed\n");
+
+ devm_kfree(ice_hw_to_dev(hw), buf);
+ return status;
+}
+
/**
* ice_sched_clear_tx_topo - clears the schduler tree nodes
* @pi: port information structure
@@ -462,6 +606,215 @@ void ice_sched_cleanup_all(struct ice_hw *hw)
hw->max_cgds = 0;
}
+/**
+ * ice_sched_create_vsi_info_entry - create an empty new VSI entry
+ * @pi: port information structure
+ * @vsi_id: VSI Id
+ *
+ * This function creates a new VSI entry and adds it to list
+ */
+static struct ice_sched_vsi_info *
+ice_sched_create_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id)
+{
+ struct ice_sched_vsi_info *vsi_elem;
+
+ if (!pi)
+ return NULL;
+
+ vsi_elem = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*vsi_elem),
+ GFP_KERNEL);
+ if (!vsi_elem)
+ return NULL;
+
+ list_add(&vsi_elem->list_entry, &pi->vsi_info_list);
+ vsi_elem->vsi_id = vsi_id;
+ return vsi_elem;
+}
+
+/**
+ * ice_sched_add_elems - add nodes to hw and SW DB
+ * @pi: port information structure
+ * @tc_node: pointer to the branch node
+ * @parent: pointer to the parent node
+ * @layer: layer number to add nodes
+ * @num_nodes: number of nodes
+ * @num_nodes_added: pointer to num nodes added
+ * @first_node_teid: if new nodes are added then return the teid of first node
+ *
+ * This function add nodes to hw as well as to SW DB for a given layer
+ */
+static enum ice_status
+ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node,
+ struct ice_sched_node *parent, u8 layer, u16 num_nodes,
+ u16 *num_nodes_added, u32 *first_node_teid)
+{
+ struct ice_sched_node *prev, *new_node;
+ struct ice_aqc_add_elem *buf;
+ u16 i, num_groups_added = 0;
+ enum ice_status status = 0;
+ struct ice_hw *hw = pi->hw;
+ u16 buf_size;
+ u32 teid;
+
+ buf_size = sizeof(*buf) + sizeof(*buf->generic) * (num_nodes - 1);
+ buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL);
+ if (!buf)
+ return ICE_ERR_NO_MEMORY;
+
+ buf->hdr.parent_teid = parent->info.node_teid;
+ buf->hdr.num_elems = cpu_to_le16(num_nodes);
+ for (i = 0; i < num_nodes; i++) {
+ buf->generic[i].parent_teid = parent->info.node_teid;
+ buf->generic[i].data.elem_type = ICE_AQC_ELEM_TYPE_SE_GENERIC;
+ buf->generic[i].data.valid_sections =
+ ICE_AQC_ELEM_VALID_GENERIC | ICE_AQC_ELEM_VALID_CIR |
+ ICE_AQC_ELEM_VALID_EIR;
+ buf->generic[i].data.generic = 0;
+ buf->generic[i].data.cir_bw.bw_profile_idx =
+ ICE_SCHED_DFLT_RL_PROF_ID;
+ buf->generic[i].data.eir_bw.bw_profile_idx =
+ ICE_SCHED_DFLT_RL_PROF_ID;
+ }
+
+ status = ice_aq_add_sched_elems(hw, 1, buf, buf_size,
+ &num_groups_added, NULL);
+ if (status || num_groups_added != 1) {
+ ice_debug(hw, ICE_DBG_SCHED, "add elements failed\n");
+ devm_kfree(ice_hw_to_dev(hw), buf);
+ return ICE_ERR_CFG;
+ }
+
+ *num_nodes_added = num_nodes;
+ /* add nodes to the SW DB */
+ for (i = 0; i < num_nodes; i++) {
+ status = ice_sched_add_node(pi, layer, &buf->generic[i]);
+ if (status) {
+ ice_debug(hw, ICE_DBG_SCHED,
+ "add nodes in SW DB failed status =%d\n",
+ status);
+ break;
+ }
+
+ teid = le32_to_cpu(buf->generic[i].node_teid);
+ new_node = ice_sched_find_node_by_teid(parent, teid);
+
+ if (!new_node) {
+ ice_debug(hw, ICE_DBG_SCHED,
+ "Node is missing for teid =%d\n", teid);
+ break;
+ }
+
+ new_node->sibling = NULL;
+ new_node->tc_num = tc_node->tc_num;
+
+ /* add it to previous node sibling pointer */
+ /* Note: siblings are not linked across branches */
+ prev = ice_sched_get_first_node(hw, tc_node, layer);
+
+ if (prev && prev != new_node) {
+ while (prev->sibling)
+ prev = prev->sibling;
+ prev->sibling = new_node;
+ }
+
+ if (i == 0)
+ *first_node_teid = teid;
+ }
+
+ devm_kfree(ice_hw_to_dev(hw), buf);
+ return status;
+}
+
+/**
+ * ice_sched_add_nodes_to_layer - Add nodes to a given layer
+ * @pi: port information structure
+ * @tc_node: pointer to TC node
+ * @parent: pointer to parent node
+ * @layer: layer number to add nodes
+ * @num_nodes: number of nodes to be added
+ * @first_node_teid: pointer to the first node teid
+ * @num_nodes_added: pointer to number of nodes added
+ *
+ * This function add nodes to a given layer.
+ */
+static enum ice_status
+ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
+ struct ice_sched_node *tc_node,
+ struct ice_sched_node *parent, u8 layer,
+ u16 num_nodes, u32 *first_node_teid,
+ u16 *num_nodes_added)
+{
+ u32 *first_teid_ptr = first_node_teid;
+ u16 new_num_nodes, max_child_nodes;
+ enum ice_status status = 0;
+ struct ice_hw *hw = pi->hw;
+ u16 num_added = 0;
+ u32 temp;
+
+ if (!num_nodes)
+ return status;
+
+ if (!parent || layer < hw->sw_entry_point_layer)
+ return ICE_ERR_PARAM;
+
+ *num_nodes_added = 0;
+
+ /* max children per node per layer */
+ max_child_nodes =
+ le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children);
+
+ /* current number of children + required nodes exceed max children ? */
+ if ((parent->num_children + num_nodes) > max_child_nodes) {
+ /* Fail if the parent is a TC node */
+ if (parent == tc_node)
+ return ICE_ERR_CFG;
+
+ /* utilize all the spaces if the parent is not full */
+ if (parent->num_children < max_child_nodes) {
+ new_num_nodes = max_child_nodes - parent->num_children;
+ /* this recursion is intentional, and wouldn't
+ * go more than 2 calls
+ */
+ status = ice_sched_add_nodes_to_layer(pi, tc_node,
+ parent, layer,
+ new_num_nodes,
+ first_node_teid,
+ &num_added);
+ if (status)
+ return status;
+
+ *num_nodes_added += num_added;
+ }
+ /* Don't modify the first node teid memory if the first node was
+ * added already in the above call. Instead send some temp
+ * memory for all other recursive calls.
+ */
+ if (num_added)
+ first_teid_ptr = &temp;
+
+ new_num_nodes = num_nodes - num_added;
+
+ /* This parent is full, try the next sibling */
+ parent = parent->sibling;
+
+ /* this recursion is intentional, for 1024 queues
+ * per VSI, it goes max of 16 iterations.
+ * 1024 / 8 = 128 layer 8 nodes
+ * 128 /8 = 16 (add 8 nodes per iteration)
+ */
+ status = ice_sched_add_nodes_to_layer(pi, tc_node, parent,
+ layer, new_num_nodes,
+ first_teid_ptr,
+ &num_added);
+ *num_nodes_added += num_added;
+ return status;
+ }
+
+ status = ice_sched_add_elems(pi, tc_node, parent, layer, num_nodes,
+ num_nodes_added, first_node_teid);
+ return status;
+}
+
/**
* ice_sched_get_qgrp_layer - get the current queue group layer number
* @hw: pointer to the hw struct
@@ -474,6 +827,101 @@ static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw)
return hw->num_tx_sched_layers - ICE_QGRP_LAYER_OFFSET;
}
+/**
+ * ice_sched_get_vsi_layer - get the current VSI layer number
+ * @hw: pointer to the hw struct
+ *
+ * This function returns the current VSI layer number
+ */
+static u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
+{
+ /* Num Layers VSI layer
+ * 9 6
+ * 7 4
+ * 5 or less sw_entry_point_layer
+ */
+ /* calculate the vsi layer based on number of layers. */
+ if (hw->num_tx_sched_layers > ICE_VSI_LAYER_OFFSET + 1) {
+ u8 layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
+
+ if (layer > hw->sw_entry_point_layer)
+ return layer;
+ }
+ return hw->sw_entry_point_layer;
+}
+
+/**
+ * ice_sched_get_num_nodes_per_layer - Get the total number of nodes per layer
+ * @pi: pointer to the port info struct
+ * @layer: layer number
+ *
+ * This function calculates the number of nodes present in the scheduler tree
+ * including all the branches for a given layer
+ */
+static u16
+ice_sched_get_num_nodes_per_layer(struct ice_port_info *pi, u8 layer)
+{
+ struct ice_hw *hw;
+ u16 num_nodes = 0;
+ u8 i;
+
+ if (!pi)
+ return num_nodes;
+
+ hw = pi->hw;
+
+ /* Calculate the number of nodes for all TCs */
+ for (i = 0; i < pi->root->num_children; i++) {
+ struct ice_sched_node *tc_node, *node;
+
+ tc_node = pi->root->children[i];
+
+ /* Get the first node */
+ node = ice_sched_get_first_node(hw, tc_node, layer);
+ if (!node)
+ continue;
+
+ /* count the siblings */
+ while (node) {
+ num_nodes++;
+ node = node->sibling;
+ }
+ }
+
+ return num_nodes;
+}
+
+/**
+ * ice_sched_val_max_nodes - check max number of nodes reached or not
+ * @pi: port information structure
+ * @new_num_nodes_per_layer: pointer to the new number of nodes array
+ *
+ * This function checks whether the scheduler tree layers have enough space to
+ * add new nodes
+ */
+static enum ice_status
+ice_sched_validate_for_max_nodes(struct ice_port_info *pi,
+ u16 *new_num_nodes_per_layer)
+{
+ struct ice_hw *hw = pi->hw;
+ u8 i, qg_layer;
+ u16 num_nodes;
+
+ qg_layer = ice_sched_get_qgrp_layer(hw);
+
+ /* walk through all the layers from SW entry point to qgroup layer */
+ for (i = hw->sw_entry_point_layer; i <= qg_layer; i++) {
+ num_nodes = ice_sched_get_num_nodes_per_layer(pi, i);
+ if (num_nodes + new_num_nodes_per_layer[i] >
+ le16_to_cpu(hw->layer_info[i].max_pf_nodes)) {
+ ice_debug(hw, ICE_DBG_SCHED,
+ "max nodes reached for layer = %d\n", i);
+ return ICE_ERR_CFG;
+ }
+ }
+ return 0;
+}
+
/**
* ice_rm_dflt_leaf_node - remove the default leaf node in the tree
* @pi: port information structure
@@ -516,6 +964,7 @@ ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
struct ice_sched_node *node;
ice_rm_dflt_leaf_node(pi);
+
/* remove the default nodes except TC and root nodes */
node = pi->root;
while (node) {
@@ -525,6 +974,7 @@ ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
ice_free_sched_node(pi, node);
break;
}
+
if (!node->num_children)
break;
node = node->children[0];
@@ -720,8 +1170,10 @@ ice_sched_find_node_in_subtree(struct ice_hw *hw, struct ice_sched_node *base,
if (node == child)
return true;
+
if (child->tx_sched_layer > node->tx_sched_layer)
return false;
+
/* this recursion is intentional, and wouldn't
* go more than 8 calls
*/
@@ -751,13 +1203,17 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc,
qgrp_layer = ice_sched_get_qgrp_layer(pi->hw);
max_children = le16_to_cpu(pi->hw->layer_info[qgrp_layer].max_children);
+
list_elem = ice_sched_get_vsi_info_entry(pi, vsi_id);
if (!list_elem)
goto lan_q_exit;
+
vsi_node = list_elem->vsi_node[tc];
+
/* validate invalid VSI id */
if (!vsi_node)
goto lan_q_exit;
+
/* get the first q group node from VSI sub-tree */
qgrp_node = ice_sched_get_first_node(pi->hw, vsi_node, qgrp_layer);
while (qgrp_node) {
@@ -768,6 +1224,436 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc,
break;
qgrp_node = qgrp_node->sibling;
}
+
lan_q_exit:
return qgrp_node;
}
+
+/**
+ * ice_sched_get_vsi_node - Get a VSI node based on VSI id
+ * @hw: pointer to the hw struct
+ * @tc_node: pointer to the TC node
+ * @vsi_id: VSI id
+ *
+ * This function retrieves a VSI node for a given VSI id from a given
+ * TC branch
+ */
+static struct ice_sched_node *
+ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node,
+ u16 vsi_id)
+{
+ struct ice_sched_node *node;
+ u8 vsi_layer;
+
+ vsi_layer = ice_sched_get_vsi_layer(hw);
+ node = ice_sched_get_first_node(hw, tc_node, vsi_layer);
+
+ /* Check whether it already exists */
+ while (node) {
+ if (node->vsi_id == vsi_id)
+ return node;
+ node = node->sibling;
+ }
+
+ return node;
+}
+
+/**
+ * ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes
+ * @hw: pointer to the hw struct
+ * @num_qs: number of queues
+ * @num_nodes: num nodes array
+ *
+ * This function calculates the number of VSI child nodes based on the
+ * number of queues.
+ */
+static void
+ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes)
+{
+ u16 num = num_qs;
+ u8 i, qgl, vsil;
+
+ qgl = ice_sched_get_qgrp_layer(hw);
+ vsil = ice_sched_get_vsi_layer(hw);
+
+ /* calculate num nodes from q group to VSI layer */
+ for (i = qgl; i > vsil; i--) {
+ u16 max_children = le16_to_cpu(hw->layer_info[i].max_children);
+
+ /* round to the next integer if there is a remainder */
+ num = DIV_ROUND_UP(num, max_children);
+
+ /* need at least one node */
+ num_nodes[i] = num ? num : 1;
+ }
+}
+
+/**
+ * ice_sched_add_vsi_child_nodes - add VSI child nodes to tree
+ * @pi: port information structure
+ * @vsi_id: VSI id
+ * @tc_node: pointer to the TC node
+ * @num_nodes: pointer to the num nodes that needs to be added per layer
+ * @owner: node owner (lan or rdma)
+ *
+ * This function adds the VSI child nodes to tree. It gets called for
+ * lan and rdma separately.
+ */
+static enum ice_status
+ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id,
+ struct ice_sched_node *tc_node, u16 *num_nodes,
+ u8 owner)
+{
+ struct ice_sched_node *parent, *node;
+ struct ice_hw *hw = pi->hw;
+ enum ice_status status;
+ u32 first_node_teid;
+ u16 num_added = 0;
+ u8 i, qgl, vsil;
+
+ status = ice_sched_validate_for_max_nodes(pi, num_nodes);
+ if (status)
+ return status;
+
+ qgl = ice_sched_get_qgrp_layer(hw);
+ vsil = ice_sched_get_vsi_layer(hw);
+ parent = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
+ for (i = vsil + 1; i <= qgl; i++) {
+ if (!parent)
+ return ICE_ERR_CFG;
+ status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i,
+ num_nodes[i],
+ &first_node_teid,
+ &num_added);
+ if (status || num_nodes[i] != num_added)
+ return ICE_ERR_CFG;
+
+ /* The newly added node can be a new parent for the next
+ * layer nodes
+ */
+ if (num_added) {
+ parent = ice_sched_find_node_by_teid(tc_node,
+ first_node_teid);
+ node = parent;
+ while (node) {
+ node->owner = owner;
+ node = node->sibling;
+ }
+ } else {
+ parent = parent->children[0];
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_sched_rm_vsi_child_nodes - remove VSI child nodes from the tree
+ * @pi: port information structure
+ * @vsi_node: pointer to the VSI node
+ * @num_nodes: pointer to the num nodes that needs to be removed per layer
+ * @owner: node owner (lan or rdma)
+ *
+ * This function removes the VSI child nodes from the tree. It gets called for
+ * lan and rdma separately.
+ */
+static void
+ice_sched_rm_vsi_child_nodes(struct ice_port_info *pi,
+ struct ice_sched_node *vsi_node, u16 *num_nodes,
+ u8 owner)
+{
+ struct ice_sched_node *node, *next;
+ u8 i, qgl, vsil;
+ u16 num;
+
+ qgl = ice_sched_get_qgrp_layer(pi->hw);
+ vsil = ice_sched_get_vsi_layer(pi->hw);
+
+ for (i = qgl; i > vsil; i--) {
+ num = num_nodes[i];
+ node = ice_sched_get_first_node(pi->hw, vsi_node, i);
+ while (node && num) {
+ next = node->sibling;
+ if (node->owner == owner && !node->num_children) {
+ ice_free_sched_node(pi, node);
+ num--;
+ }
+ node = next;
+ }
+ }
+}
+
+/**
+ * ice_sched_calc_vsi_support_nodes - calculate number of VSI support nodes
+ * @hw: pointer to the hw struct
+ * @tc_node: pointer to TC node
+ * @num_nodes: pointer to num nodes array
+ *
+ * This function calculates the number of supported nodes needed to add this
+ * VSI into tx tree including the VSI, parent and intermediate nodes in below
+ * layers
+ */
+static void
+ice_sched_calc_vsi_support_nodes(struct ice_hw *hw,
+ struct ice_sched_node *tc_node, u16 *num_nodes)
+{
+ struct ice_sched_node *node;
+ u16 max_child;
+ u8 i, vsil;
+
+ vsil = ice_sched_get_vsi_layer(hw);
+ for (i = vsil; i >= hw->sw_entry_point_layer; i--)
+ /* Add intermediate nodes if TC has no children and
+ * need at least one node for VSI
+ */
+ if (!tc_node->num_children || i == vsil) {
+ num_nodes[i]++;
+ } else {
+ /* If intermediate nodes are reached max children
+ * then add a new one.
+ */
+ node = ice_sched_get_first_node(hw, tc_node, i);
+ max_child = le16_to_cpu(hw->layer_info[i].max_children);
+
+ /* scan all the siblings */
+ while (node) {
+ if (node->num_children < max_child)
+ break;
+ node = node->sibling;
+ }
+
+ /* all the nodes are full, allocate a new one */
+ if (!node)
+ num_nodes[i]++;
+ }
+}
+
+/**
+ * ice_sched_add_vsi_support_nodes - add VSI supported nodes into tx tree
+ * @pi: port information structure
+ * @vsi_id: VSI Id
+ * @tc_node: pointer to TC node
+ * @num_nodes: pointer to num nodes array
+ *
+ * This function adds the VSI supported nodes into tx tree including the
+ * VSI, its parent and intermediate nodes in below layers
+ */
+static enum ice_status
+ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id,
+ struct ice_sched_node *tc_node, u16 *num_nodes)
+{
+ struct ice_sched_node *parent = tc_node;
+ enum ice_status status;
+ u32 first_node_teid;
+ u16 num_added = 0;
+ u8 i, vsil;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+
+ status = ice_sched_validate_for_max_nodes(pi, num_nodes);
+ if (status)
+ return status;
+
+ vsil = ice_sched_get_vsi_layer(pi->hw);
+ for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) {
+ status = ice_sched_add_nodes_to_layer(pi, tc_node, parent,
+ i, num_nodes[i],
+ &first_node_teid,
+ &num_added);
+ if (status || num_nodes[i] != num_added)
+ return ICE_ERR_CFG;
+
+ /* The newly added node can be a new parent for the next
+ * layer nodes
+ */
+ if (num_added)
+ parent = ice_sched_find_node_by_teid(tc_node,
+ first_node_teid);
+ else
+ parent = parent->children[0];
+
+ if (!parent)
+ return ICE_ERR_CFG;
+
+ if (i == vsil)
+ parent->vsi_id = vsi_id;
+ }
+ return 0;
+}
+
+/**
+ * ice_sched_add_vsi_to_topo - add a new VSI into tree
+ * @pi: port information structure
+ * @vsi_id: VSI Id
+ * @tc: TC number
+ *
+ * This function adds a new VSI into scheduler tree
+ */
+static enum ice_status
+ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc)
+{
+ u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
+ struct ice_sched_node *tc_node;
+ struct ice_hw *hw = pi->hw;
+
+ tc_node = ice_sched_get_tc_node(pi, tc);
+ if (!tc_node)
+ return ICE_ERR_PARAM;
+
+ /* calculate number of supported nodes needed for this VSI */
+ ice_sched_calc_vsi_support_nodes(hw, tc_node, num_nodes);
+
+ /* add vsi supported nodes to tc subtree */
+ return ice_sched_add_vsi_support_nodes(pi, vsi_id, tc_node, num_nodes);
+}
+
+/**
+ * ice_sched_update_vsi_child_nodes - update VSI child nodes
+ * @pi: port information structure
+ * @vsi_id: VSI Id
+ * @tc: TC number
+ * @new_numqs: new number of max queues
+ * @owner: owner of this subtree
+ *
+ * This function updates the VSI child nodes based on the number of queues
+ */
+static enum ice_status
+ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc,
+ u16 new_numqs, u8 owner)
+{
+ u16 prev_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
+ u16 new_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
+ struct ice_sched_node *vsi_node;
+ struct ice_sched_node *tc_node;
+ struct ice_sched_vsi_info *vsi;
+ enum ice_status status = 0;
+ struct ice_hw *hw = pi->hw;
+ u16 prev_numqs;
+ u8 i;
+
+ tc_node = ice_sched_get_tc_node(pi, tc);
+ if (!tc_node)
+ return ICE_ERR_CFG;
+
+ vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
+ if (!vsi_node)
+ return ICE_ERR_CFG;
+
+ vsi = ice_sched_get_vsi_info_entry(pi, vsi_id);
+ if (!vsi)
+ return ICE_ERR_CFG;
+
+ if (owner == ICE_SCHED_NODE_OWNER_LAN)
+ prev_numqs = vsi->max_lanq[tc];
+ else
+ return ICE_ERR_PARAM;
+
+ /* num queues are not changed */
+ if (prev_numqs == new_numqs)
+ return status;
+
+ /* calculate number of nodes based on prev/new number of qs */
+ if (prev_numqs)
+ ice_sched_calc_vsi_child_nodes(hw, prev_numqs, prev_num_nodes);
+
+ if (new_numqs)
+ ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
+
+ if (prev_numqs > new_numqs) {
+ for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++)
+ new_num_nodes[i] = prev_num_nodes[i] - new_num_nodes[i];
+
+ ice_sched_rm_vsi_child_nodes(pi, vsi_node, new_num_nodes,
+ owner);
+ } else {
+ for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++)
+ new_num_nodes[i] -= prev_num_nodes[i];
+
+ status = ice_sched_add_vsi_child_nodes(pi, vsi_id, tc_node,
+ new_num_nodes, owner);
+ if (status)
+ return status;
+ }
+
+ if (owner == ICE_SCHED_NODE_OWNER_LAN)
+ vsi->max_lanq[tc] = new_numqs;
+
+ return status;
+}
+
+/**
+ * ice_sched_cfg_vsi - configure the new/exisiting VSI
+ * @pi: port information structure
+ * @vsi_id: VSI Id
+ * @tc: TC number
+ * @maxqs: max number of queues
+ * @owner: lan or rdma
+ * @enable: TC enabled or disabled
+ *
+ * This function adds/updates VSI nodes based on the number of queues. If TC is
+ * enabled and VSI is in suspended state then resume the VSI back. If TC is
+ * disabled then suspend the VSI if it is not already.
+ */
+enum ice_status
+ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs,
+ u8 owner, bool enable)
+{
+ struct ice_sched_node *vsi_node, *tc_node;
+ struct ice_sched_vsi_info *vsi;
+ enum ice_status status = 0;
+ struct ice_hw *hw = pi->hw;
+
+ tc_node = ice_sched_get_tc_node(pi, tc);
+ if (!tc_node)
+ return ICE_ERR_PARAM;
+
+ vsi = ice_sched_get_vsi_info_entry(pi, vsi_id);
+ if (!vsi)
+ vsi = ice_sched_create_vsi_info_entry(pi, vsi_id);
+ if (!vsi)
+ return ICE_ERR_NO_MEMORY;
+
+ vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
+
+ /* suspend the VSI if tc is not enabled */
+ if (!enable) {
+ if (vsi_node && vsi_node->in_use) {
+ u32 teid = le32_to_cpu(vsi_node->info.node_teid);
+
+ status = ice_sched_suspend_resume_elems(hw, 1, &teid,
+ true);
+ if (!status)
+ vsi_node->in_use = false;
+ }
+ return status;
+ }
+
+ /* TC is enabled, if it is a new VSI then add it to the tree */
+ if (!vsi_node) {
+ status = ice_sched_add_vsi_to_topo(pi, vsi_id, tc);
+ if (status)
+ return status;
+ vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
+ if (!vsi_node)
+ return ICE_ERR_CFG;
+ vsi->vsi_node[tc] = vsi_node;
+ vsi_node->in_use = true;
+ }
+
+ /* update the VSI child nodes */
+ status = ice_sched_update_vsi_child_nodes(pi, vsi_id, tc, maxqs, owner);
+ if (status)
+ return status;
+
+ /* TC is enabled, resume the VSI if it is in the suspend state */
+ if (!vsi_node->in_use) {
+ u32 teid = le32_to_cpu(vsi_node->info.node_teid);
+
+ status = ice_sched_suspend_resume_elems(hw, 1, &teid, false);
+ if (!status)
+ vsi_node->in_use = true;
+ }
+
+ return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 639859a3d0f0..badadcc120d3 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -7,6 +7,7 @@
#include "ice_common.h"
#define ICE_QGRP_LAYER_OFFSET 2
+#define ICE_VSI_LAYER_OFFSET 4
struct ice_sched_agg_vsi_info {
struct list_head list_entry;
@@ -36,4 +37,7 @@ struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc);
struct ice_sched_node *
ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc,
u8 owner);
+enum ice_status
+ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs,
+ u8 owner, bool enable);
#endif /* _ICE_SCHED_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index c7e0de3b8662..137a59a74b71 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -10,6 +10,11 @@
#include "ice_controlq.h"
#include "ice_lan_tx_rx.h"
+static inline bool ice_is_tc_ena(u8 bitmap, u8 tc)
+{
+ return test_bit(tc, (unsigned long *)&bitmap);
+}
+
/* debug masks - set these bits in hw->debug_mask to control output */
#define ICE_DBG_INIT BIT_ULL(1)
#define ICE_DBG_QCTX BIT_ULL(6)
@@ -194,6 +199,8 @@ enum ice_agg_type {
ICE_AGG_TYPE_QG
};
+#define ICE_SCHED_DFLT_RL_PROF_ID 0
+
/* vsi type list entry to locate corresponding vsi/ag nodes */
struct ice_sched_vsi_info {
struct ice_sched_node *vsi_node[ICE_MAX_TRAFFIC_CLASS];
--
2.14.3
^ permalink raw reply related
* [net-next 14/15] ice: Support link events, reset and rebuild
From: Jeff Kirsher @ 2018-03-26 19:46 UTC (permalink / raw)
To: davem
Cc: Anirudh Venkataramanan, netdev, nhorman, sassmann, jogreene,
tbogendoerfer, bpoirier, Jeff Kirsher
In-Reply-To: <20180326194619.1202-1-jeffrey.t.kirsher@intel.com>
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Link events are posted to a PF's admin receive queue (ARQ). This patch
adds the ability to detect and process link events.
This patch also adds the ability to process resets.
The driver can process the following resets:
1) EMP Reset (EMPR)
2) Global Reset (GLOBR)
3) Core Reset (CORER)
4) Physical Function Reset (PFR)
EMPR is the largest level of reset that the driver can handle. An EMPR
resets the manageability block and also the data path, including PHY and
link for all the PFs. The affected PFs are notified of this event through
a miscellaneous interrupt.
GLOBR is a subset of EMPR. It does everything EMPR does except that it
doesn't reset the manageability block.
CORER is a subset of GLOBR. It does everything GLOBR does but doesn't
reset PHY and link.
PFR is a subset of CORER and affects only the given physical function.
In other words, PFR can be thought of as a CORER for a single PF. Since
only the issuing PF is affected, a PFR doesn't result in the miscellaneous
interrupt being triggered.
All the resets have the following in common:
1) Tx/Rx is halted and all queues are stopped.
2) All the VSIs and filters programmed for the PF are lost and have to be
reprogrammed.
3) Control queue interfaces are reset and have to be reprogrammed.
In the rebuild flow, control queues are reinitialized, VSIs are reallocated
and filters are restored.
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ice/ice.h | 19 +
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 19 +
drivers/net/ethernet/intel/ice/ice_common.c | 60 +++
drivers/net/ethernet/intel/ice/ice_common.h | 5 +
drivers/net/ethernet/intel/ice/ice_hw_autogen.h | 2 +
drivers/net/ethernet/intel/ice/ice_main.c | 581 +++++++++++++++++++++++-
drivers/net/ethernet/intel/ice/ice_type.h | 1 +
7 files changed, 681 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 8898255e5a65..24ce4b71c9ce 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -78,6 +78,11 @@ extern const char ice_drv_ver[];
#define ICE_RX_DESC(R, i) (&(((union ice_32b_rx_flex_desc *)((R)->desc))[i]))
#define ICE_TX_CTX_DESC(R, i) (&(((struct ice_tx_ctx_desc *)((R)->desc))[i]))
+/* Macro for each VSI in a PF */
+#define ice_for_each_vsi(pf, i) \
+ for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++)
+
+/* Macros for each tx/rx ring in a VSI */
#define ice_for_each_txq(vsi, i) \
for ((i) = 0; (i) < (vsi)->num_txq; (i)++)
@@ -109,7 +114,16 @@ struct ice_sw {
enum ice_state {
__ICE_DOWN,
+ __ICE_NEEDS_RESTART,
+ __ICE_RESET_RECOVERY_PENDING, /* set by driver when reset starts */
__ICE_PFR_REQ, /* set by driver and peers */
+ __ICE_CORER_REQ, /* set by driver and peers */
+ __ICE_GLOBR_REQ, /* set by driver and peers */
+ __ICE_CORER_RECV, /* set by OICR handler */
+ __ICE_GLOBR_RECV, /* set by OICR handler */
+ __ICE_EMPR_RECV, /* set by OICR handler */
+ __ICE_SUSPENDED, /* set on module remove path */
+ __ICE_RESET_FAILED, /* set by reset/rebuild */
__ICE_ADMINQ_EVENT_PENDING,
__ICE_CFG_BUSY,
__ICE_SERVICE_SCHED,
@@ -226,6 +240,11 @@ struct ice_pf {
u16 q_left_rx; /* remaining num rx queues left unclaimed */
u16 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */
u16 num_alloc_vsi;
+ u16 corer_count; /* Core reset count */
+ u16 globr_count; /* Global reset count */
+ u16 empr_count; /* EMP reset count */
+ u16 pfr_count; /* PF reset count */
+
struct ice_hw_port_stats stats;
struct ice_hw_port_stats stats_prev;
struct ice_hw hw;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 348b9cc3c596..ea822a9edce8 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1009,6 +1009,23 @@ struct ice_aqc_get_link_status_data {
__le64 reserved4;
};
+/* Set event mask command (direct 0x0613) */
+struct ice_aqc_set_event_mask {
+ u8 lport_num;
+ u8 reserved[7];
+ __le16 event_mask;
+#define ICE_AQ_LINK_EVENT_UPDOWN BIT(1)
+#define ICE_AQ_LINK_EVENT_MEDIA_NA BIT(2)
+#define ICE_AQ_LINK_EVENT_LINK_FAULT BIT(3)
+#define ICE_AQ_LINK_EVENT_PHY_TEMP_ALARM BIT(4)
+#define ICE_AQ_LINK_EVENT_EXCESSIVE_ERRORS BIT(5)
+#define ICE_AQ_LINK_EVENT_SIGNAL_DETECT BIT(6)
+#define ICE_AQ_LINK_EVENT_AN_COMPLETED BIT(7)
+#define ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL BIT(8)
+#define ICE_AQ_LINK_EVENT_PORT_TX_SUSPENDED BIT(9)
+ u8 reserved1[6];
+};
+
/* NVM Read command (indirect 0x0701)
* NVM Erase commands (direct 0x0702)
* NVM Update commands (indirect 0x0703)
@@ -1215,6 +1232,7 @@ struct ice_aq_desc {
struct ice_aqc_dis_txqs dis_txqs;
struct ice_aqc_add_get_update_free_vsi vsi_cmd;
struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
+ struct ice_aqc_set_event_mask set_event_mask;
struct ice_aqc_get_link_status get_link_status;
} params;
};
@@ -1294,6 +1312,7 @@ enum ice_adminq_opc {
ice_aqc_opc_set_phy_cfg = 0x0601,
ice_aqc_opc_restart_an = 0x0605,
ice_aqc_opc_get_link_status = 0x0607,
+ ice_aqc_opc_set_event_mask = 0x0613,
/* NVM commands */
ice_aqc_opc_nvm_read = 0x0701,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 0ab9bf66c84e..791f1eba5953 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1427,6 +1427,39 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart)
return status;
}
+/**
+ * ice_get_link_status - get status of the HW network link
+ * @pi: port information structure
+ * @link_up: pointer to bool (true/false = linkup/linkdown)
+ *
+ * Variable link_up is true if link is up, false if link is down.
+ * The variable link_up is invalid if status is non zero. As a
+ * result of this call, link status reporting becomes enabled
+ */
+enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up)
+{
+ struct ice_phy_info *phy_info;
+ enum ice_status status = 0;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+
+ phy_info = &pi->phy;
+
+ if (phy_info->get_link_info) {
+ status = ice_update_link_info(pi);
+
+ if (status)
+ ice_debug(pi->hw, ICE_DBG_LINK,
+ "get link status error, status = %d\n",
+ status);
+ }
+
+ *link_up = phy_info->link_info.link_info & ICE_AQ_LINK_UP;
+
+ return status;
+}
+
/**
* ice_aq_set_link_restart_an
* @pi: pointer to the port information structure
@@ -1456,6 +1489,33 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
return ice_aq_send_cmd(pi->hw, &desc, NULL, 0, cd);
}
+/**
+ * ice_aq_set_event_mask
+ * @hw: pointer to the hw struct
+ * @port_num: port number of the physical function
+ * @mask: event mask to be set
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set event mask (0x0613)
+ */
+enum ice_status
+ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_set_event_mask *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.set_event_mask;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_event_mask);
+
+ cmd->lport_num = port_num;
+
+ cmd->event_mask = cpu_to_le16(mask);
+
+ return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
/**
* __ice_aq_get_set_rss_lut
* @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 971277ebcc86..ad350a4921a1 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -20,6 +20,8 @@ enum ice_status
ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
struct ice_rq_event_info *e, u16 *pending);
enum ice_status
+ice_get_link_status(struct ice_port_info *pi, bool *link_up);
+enum ice_status
ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
enum ice_aq_res_access_type access);
void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res);
@@ -66,6 +68,9 @@ enum ice_status
ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
struct ice_link_status *link, struct ice_sq_cd *cd);
enum ice_status
+ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
+ struct ice_sq_cd *cd);
+enum ice_status
ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
u32 *q_teids, struct ice_sq_cd *cmd_details);
enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 777a1c653edb..1b9e2ef48a9d 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -85,6 +85,8 @@
#define GLGEN_RSTCTL 0x000B8180
#define GLGEN_RSTCTL_GRSTDEL_S 0
#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S)
+#define GLGEN_RSTAT_RESET_TYPE_S 2
+#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, GLGEN_RSTAT_RESET_TYPE_S)
#define GLGEN_RTRIG 0x000B8190
#define GLGEN_RTRIG_CORER_S 0
#define GLGEN_RTRIG_CORER_M BIT(GLGEN_RTRIG_CORER_S)
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0f8637b97a34..2478dbe9bf4d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -29,6 +29,8 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
static struct workqueue_struct *ice_wq;
static const struct net_device_ops ice_netdev_ops;
+static void ice_pf_dis_all_vsi(struct ice_pf *pf);
+static void ice_rebuild(struct ice_pf *pf);
static int ice_vsi_release(struct ice_vsi *vsi);
static void ice_update_vsi_stats(struct ice_vsi *vsi);
static void ice_update_pf_stats(struct ice_pf *pf);
@@ -216,6 +218,132 @@ static void ice_free_fltr_list(struct device *dev, struct list_head *h)
}
}
+/**
+ * ice_is_reset_recovery_pending - schedule a reset
+ * @state: pf state field
+ */
+static bool ice_is_reset_recovery_pending(unsigned long int *state)
+{
+ return test_bit(__ICE_RESET_RECOVERY_PENDING, state);
+}
+
+/**
+ * ice_prepare_for_reset - prep for the core to reset
+ * @pf: board private structure
+ *
+ * Inform or close all dependent features in prep for reset.
+ */
+static void
+ice_prepare_for_reset(struct ice_pf *pf)
+{
+ struct ice_hw *hw = &pf->hw;
+ u32 v;
+
+ ice_for_each_vsi(pf, v)
+ if (pf->vsi[v])
+ ice_remove_vsi_fltr(hw, pf->vsi[v]->vsi_num);
+
+ dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n");
+
+ /* disable the VSIs and their queues that are not already DOWN */
+ /* pf_dis_all_vsi modifies netdev structures -rtnl_lock needed */
+ ice_pf_dis_all_vsi(pf);
+
+ ice_for_each_vsi(pf, v)
+ if (pf->vsi[v])
+ pf->vsi[v]->vsi_num = 0;
+
+ ice_shutdown_all_ctrlq(hw);
+}
+
+/**
+ * ice_do_reset - Initiate one of many types of resets
+ * @pf: board private structure
+ * @reset_type: reset type requested
+ * before this function was called.
+ */
+static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
+{
+ struct device *dev = &pf->pdev->dev;
+ struct ice_hw *hw = &pf->hw;
+
+ dev_dbg(dev, "reset_type 0x%x requested\n", reset_type);
+ WARN_ON(in_interrupt());
+
+ /* PFR is a bit of a special case because it doesn't result in an OICR
+ * interrupt. So for PFR, we prepare for reset, issue the reset and
+ * rebuild sequentially.
+ */
+ if (reset_type == ICE_RESET_PFR) {
+ set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ ice_prepare_for_reset(pf);
+ }
+
+ /* trigger the reset */
+ if (ice_reset(hw, reset_type)) {
+ dev_err(dev, "reset %d failed\n", reset_type);
+ set_bit(__ICE_RESET_FAILED, pf->state);
+ clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ return;
+ }
+
+ if (reset_type == ICE_RESET_PFR) {
+ pf->pfr_count++;
+ ice_rebuild(pf);
+ clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ }
+}
+
+/**
+ * ice_reset_subtask - Set up for resetting the device and driver
+ * @pf: board private structure
+ */
+static void ice_reset_subtask(struct ice_pf *pf)
+{
+ enum ice_reset_req reset_type;
+
+ rtnl_lock();
+
+ /* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an
+ * OICR interrupt. The OICR handler (ice_misc_intr) determines what
+ * type of reset happened and sets __ICE_RESET_RECOVERY_PENDING bit in
+ * pf->state. So if reset/recovery is pending (as indicated by this bit)
+ * we do a rebuild and return.
+ */
+ if (ice_is_reset_recovery_pending(pf->state)) {
+ clear_bit(__ICE_GLOBR_RECV, pf->state);
+ clear_bit(__ICE_CORER_RECV, pf->state);
+ ice_prepare_for_reset(pf);
+
+ /* make sure we are ready to rebuild */
+ if (ice_check_reset(&pf->hw))
+ set_bit(__ICE_RESET_FAILED, pf->state);
+ else
+ ice_rebuild(pf);
+ clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ goto unlock;
+ }
+
+ /* No pending resets to finish processing. Check for new resets */
+ if (test_and_clear_bit(__ICE_GLOBR_REQ, pf->state))
+ reset_type = ICE_RESET_GLOBR;
+ else if (test_and_clear_bit(__ICE_CORER_REQ, pf->state))
+ reset_type = ICE_RESET_CORER;
+ else if (test_and_clear_bit(__ICE_PFR_REQ, pf->state))
+ reset_type = ICE_RESET_PFR;
+ else
+ goto unlock;
+
+ /* reset if not already down or resetting */
+ if (!test_bit(__ICE_DOWN, pf->state) &&
+ !test_bit(__ICE_CFG_BUSY, pf->state)) {
+ ice_do_reset(pf, reset_type);
+ }
+
+unlock:
+ rtnl_unlock();
+}
+
/**
* ice_watchdog_subtask - periodic tasks not using event driven scheduling
* @pf: board private structure
@@ -314,6 +442,144 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
speed, fc);
}
+/**
+ * ice_init_link_events - enable/initialize link events
+ * @pi: pointer to the port_info instance
+ *
+ * Returns -EIO on failure, 0 on success
+ */
+static int ice_init_link_events(struct ice_port_info *pi)
+{
+ u16 mask;
+
+ mask = ~((u16)(ICE_AQ_LINK_EVENT_UPDOWN | ICE_AQ_LINK_EVENT_MEDIA_NA |
+ ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL));
+
+ if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) {
+ dev_dbg(ice_hw_to_dev(pi->hw),
+ "Failed to set link event mask for port %d\n",
+ pi->lport);
+ return -EIO;
+ }
+
+ if (ice_aq_get_link_info(pi, true, NULL, NULL)) {
+ dev_dbg(ice_hw_to_dev(pi->hw),
+ "Failed to enable link events for port %d\n",
+ pi->lport);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_vsi_link_event - update the vsi's netdev
+ * @vsi: the vsi on which the link event occurred
+ * @link_up: whether or not the vsi needs to be set up or down
+ */
+static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up)
+{
+ if (!vsi || test_bit(__ICE_DOWN, vsi->state))
+ return;
+
+ if (vsi->type == ICE_VSI_PF) {
+ if (!vsi->netdev) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "vsi->netdev is not initialized!\n");
+ return;
+ }
+ if (link_up) {
+ netif_carrier_on(vsi->netdev);
+ netif_tx_wake_all_queues(vsi->netdev);
+ } else {
+ netif_carrier_off(vsi->netdev);
+ netif_tx_stop_all_queues(vsi->netdev);
+ }
+ }
+}
+
+/**
+ * ice_link_event - process the link event
+ * @pf: pf that the link event is associated with
+ * @pi: port_info for the port that the link event is associated with
+ *
+ * Returns -EIO if ice_get_link_status() fails
+ * Returns 0 on success
+ */
+static int
+ice_link_event(struct ice_pf *pf, struct ice_port_info *pi)
+{
+ u8 new_link_speed, old_link_speed;
+ struct ice_phy_info *phy_info;
+ bool new_link_same_as_old;
+ bool new_link, old_link;
+ u8 lport;
+ u16 v;
+
+ phy_info = &pi->phy;
+ phy_info->link_info_old = phy_info->link_info;
+ /* Force ice_get_link_status() to update link info */
+ phy_info->get_link_info = true;
+
+ old_link = (phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
+ old_link_speed = phy_info->link_info_old.link_speed;
+
+ lport = pi->lport;
+ if (ice_get_link_status(pi, &new_link)) {
+ dev_dbg(&pf->pdev->dev,
+ "Could not get link status for port %d\n", lport);
+ return -EIO;
+ }
+
+ new_link_speed = phy_info->link_info.link_speed;
+
+ new_link_same_as_old = (new_link == old_link &&
+ new_link_speed == old_link_speed);
+
+ ice_for_each_vsi(pf, v) {
+ struct ice_vsi *vsi = pf->vsi[v];
+
+ if (!vsi || !vsi->port_info)
+ continue;
+
+ if (new_link_same_as_old &&
+ (test_bit(__ICE_DOWN, vsi->state) ||
+ new_link == netif_carrier_ok(vsi->netdev)))
+ continue;
+
+ if (vsi->port_info->lport == lport) {
+ ice_print_link_msg(vsi, new_link);
+ ice_vsi_link_event(vsi, new_link);
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_handle_link_event - handle link event via ARQ
+ * @pf: pf that the link event is associated with
+ *
+ * Return -EINVAL if port_info is null
+ * Return status on succes
+ */
+static int ice_handle_link_event(struct ice_pf *pf)
+{
+ struct ice_port_info *port_info;
+ int status;
+
+ port_info = pf->hw.port_info;
+ if (!port_info)
+ return -EINVAL;
+
+ status = ice_link_event(pf, port_info);
+ if (status)
+ dev_dbg(&pf->pdev->dev,
+ "Could not process link event, error %d\n", status);
+
+ return status;
+}
+
/**
* __ice_clean_ctrlq - helper function to clean controlq rings
* @pf: ptr to struct ice_pf
@@ -328,6 +594,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
const char *qtype;
u32 oldval, val;
+ /* Do not clean control queue if/when PF reset fails */
+ if (test_bit(__ICE_RESET_FAILED, pf->state))
+ return 0;
+
switch (q_type) {
case ICE_CTL_Q_ADMIN:
cq = &hw->adminq;
@@ -394,6 +664,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
do {
enum ice_status ret;
+ u16 opcode;
ret = ice_clean_rq_elem(hw, cq, &event, &pending);
if (ret == ICE_ERR_AQ_NO_WORK)
@@ -404,6 +675,21 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
ret);
break;
}
+
+ opcode = le16_to_cpu(event.desc.opcode);
+
+ switch (opcode) {
+ case ice_aqc_opc_get_link_status:
+ if (ice_handle_link_event(pf))
+ dev_err(&pf->pdev->dev,
+ "Could not handle link event");
+ break;
+ default:
+ dev_dbg(&pf->pdev->dev,
+ "%s Receive Queue unknown event 0x%04x ignored\n",
+ qtype, opcode);
+ break;
+ }
} while (pending && (i++ < ICE_DFLT_IRQ_WORK));
devm_kfree(&pf->pdev->dev, event.msg_buf);
@@ -483,6 +769,17 @@ static void ice_service_task(struct work_struct *work)
unsigned long start_time = jiffies;
/* subtasks */
+
+ /* process reset requests first */
+ ice_reset_subtask(pf);
+
+ /* bail if a reset/recovery cycle is pending */
+ if (ice_is_reset_recovery_pending(pf->state) ||
+ test_bit(__ICE_SUSPENDED, pf->state)) {
+ ice_service_task_complete(pf);
+ return;
+ }
+
ice_watchdog_subtask(pf);
ice_clean_adminq_subtask(pf);
@@ -1208,6 +1505,37 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
if (!(oicr & PFINT_OICR_INTEVENT_M))
goto ena_intr;
+ if (oicr & PFINT_OICR_GRST_M) {
+ u32 reset;
+ /* we have a reset warning */
+ ena_mask &= ~PFINT_OICR_GRST_M;
+ reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >>
+ GLGEN_RSTAT_RESET_TYPE_S;
+
+ if (reset == ICE_RESET_CORER)
+ pf->corer_count++;
+ else if (reset == ICE_RESET_GLOBR)
+ pf->globr_count++;
+ else
+ pf->empr_count++;
+
+ /* If a reset cycle isn't already in progress, we set a bit in
+ * pf->state so that the service task can start a reset/rebuild.
+ * We also make note of which reset happened so that peer
+ * devices/drivers can be informed.
+ */
+ if (!test_bit(__ICE_RESET_RECOVERY_PENDING, pf->state)) {
+ if (reset == ICE_RESET_CORER)
+ set_bit(__ICE_CORER_RECV, pf->state);
+ else if (reset == ICE_RESET_GLOBR)
+ set_bit(__ICE_GLOBR_RECV, pf->state);
+ else
+ set_bit(__ICE_EMPR_RECV, pf->state);
+
+ set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ }
+ }
+
if (oicr & PFINT_OICR_HMC_ERR_M) {
ena_mask &= ~PFINT_OICR_HMC_ERR_M;
dev_dbg(&pf->pdev->dev,
@@ -1226,9 +1554,10 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
*/
if (oicr & (PFINT_OICR_PE_CRITERR_M |
PFINT_OICR_PCI_EXCEPTION_M |
- PFINT_OICR_ECC_ERR_M))
+ PFINT_OICR_ECC_ERR_M)) {
set_bit(__ICE_PFR_REQ, pf->state);
-
+ ice_service_task_schedule(pf);
+ }
ena_mask &= ~oicr;
}
ret = IRQ_HANDLED;
@@ -1485,6 +1814,13 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
dev_driver_string(&pf->pdev->dev),
dev_name(&pf->pdev->dev));
+ /* Do not request IRQ but do enable OICR interrupt since settings are
+ * lost during reset. Note that this function is called only during
+ * rebuild path and not while reset is in progress.
+ */
+ if (ice_is_reset_recovery_pending(pf->state))
+ goto skip_req_irq;
+
/* reserve one vector in irq_tracker for misc interrupts */
oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
if (oicr_idx < 0)
@@ -1503,6 +1839,7 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
return err;
}
+skip_req_irq:
ice_ena_misc_vector(pf);
val = (pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
@@ -2070,6 +2407,100 @@ static int ice_vsi_cfg_rss(struct ice_vsi *vsi)
return err;
}
+/**
+ * ice_vsi_reinit_setup - return resource and reallocate resource for a VSI
+ * @vsi: pointer to the ice_vsi
+ *
+ * This reallocates the VSIs queue resources
+ *
+ * Returns 0 on success and negative value on failure
+ */
+static int ice_vsi_reinit_setup(struct ice_vsi *vsi)
+{
+ u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+ int ret, i;
+
+ if (!vsi)
+ return -EINVAL;
+
+ ice_vsi_free_q_vectors(vsi);
+ ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx);
+ vsi->base_vector = 0;
+ ice_vsi_clear_rings(vsi);
+ ice_vsi_free_arrays(vsi, false);
+ ice_vsi_set_num_qs(vsi);
+
+ /* Initialize VSI struct elements and create VSI in FW */
+ ret = ice_vsi_add(vsi);
+ if (ret < 0)
+ goto err_vsi;
+
+ ret = ice_vsi_alloc_arrays(vsi, false);
+ if (ret < 0)
+ goto err_vsi;
+
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ if (!vsi->netdev) {
+ ret = ice_cfg_netdev(vsi);
+ if (ret)
+ goto err_rings;
+
+ ret = register_netdev(vsi->netdev);
+ if (ret)
+ goto err_rings;
+
+ netif_carrier_off(vsi->netdev);
+ netif_tx_stop_all_queues(vsi->netdev);
+ }
+
+ ret = ice_vsi_alloc_q_vectors(vsi);
+ if (ret)
+ goto err_rings;
+
+ ret = ice_vsi_setup_vector_base(vsi);
+ if (ret)
+ goto err_vectors;
+
+ ret = ice_vsi_alloc_rings(vsi);
+ if (ret)
+ goto err_vectors;
+
+ ice_vsi_map_rings_to_vectors(vsi);
+ break;
+ default:
+ break;
+ }
+
+ ice_vsi_set_tc_cfg(vsi);
+
+ /* configure VSI nodes based on number of queues and TC's */
+ for (i = 0; i < vsi->tc_cfg.numtc; i++)
+ max_txqs[i] = vsi->num_txq;
+
+ ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num,
+ vsi->tc_cfg.ena_tc, max_txqs);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "Failed VSI lan queue config\n");
+ goto err_vectors;
+ }
+ return 0;
+
+err_vectors:
+ ice_vsi_free_q_vectors(vsi);
+err_rings:
+ if (vsi->netdev) {
+ unregister_netdev(vsi->netdev);
+ free_netdev(vsi->netdev);
+ vsi->netdev = NULL;
+ }
+err_vsi:
+ ice_vsi_clear(vsi);
+ set_bit(__ICE_RESET_FAILED, vsi->back->state);
+ return ret;
+}
+
/**
* ice_vsi_setup - Set up a VSI by a given type
* @pf: board private structure
@@ -2345,10 +2776,17 @@ static int ice_setup_pf_sw(struct ice_pf *pf)
struct ice_vsi *vsi;
int status = 0;
- vsi = ice_vsi_setup(pf, ICE_VSI_PF, pf->hw.port_info);
- if (!vsi) {
- status = -ENOMEM;
- goto error_exit;
+ if (!ice_is_reset_recovery_pending(pf->state)) {
+ vsi = ice_vsi_setup(pf, ICE_VSI_PF, pf->hw.port_info);
+ if (!vsi) {
+ status = -ENOMEM;
+ goto error_exit;
+ }
+ } else {
+ vsi = pf->vsi[0];
+ status = ice_vsi_reinit_setup(vsi);
+ if (status < 0)
+ return -EIO;
}
/* tmp_add_list contains a list of MAC addresses for which MAC
@@ -2737,6 +3175,12 @@ static int ice_probe(struct pci_dev *pdev,
/* since everything is good, start the service timer */
mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
+ err = ice_init_link_events(pf->hw.port_info);
+ if (err) {
+ dev_err(&pdev->dev, "ice_init_link_events failed: %d\n", err);
+ goto err_alloc_sw_unroll;
+ }
+
return 0;
err_alloc_sw_unroll:
@@ -4217,6 +4661,131 @@ static int ice_vsi_release(struct ice_vsi *vsi)
return 0;
}
+/**
+ * ice_dis_vsi - pause a VSI
+ * @vsi: the VSI being paused
+ */
+static void ice_dis_vsi(struct ice_vsi *vsi)
+{
+ if (test_bit(__ICE_DOWN, vsi->state))
+ return;
+
+ set_bit(__ICE_NEEDS_RESTART, vsi->state);
+
+ if (vsi->netdev && netif_running(vsi->netdev) &&
+ vsi->type == ICE_VSI_PF)
+ vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+
+ ice_vsi_close(vsi);
+}
+
+/**
+ * ice_ena_vsi - resume a VSI
+ * @vsi: the VSI being resume
+ */
+static void ice_ena_vsi(struct ice_vsi *vsi)
+{
+ if (!test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state))
+ return;
+
+ if (vsi->netdev && netif_running(vsi->netdev))
+ vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
+ else if (ice_vsi_open(vsi))
+ /* this clears the DOWN bit */
+ dev_dbg(&vsi->back->pdev->dev, "Failed open VSI 0x%04X on switch 0x%04X\n",
+ vsi->vsi_num, vsi->vsw->sw_id);
+}
+
+/**
+ * ice_pf_dis_all_vsi - Pause all VSIs on a PF
+ * @pf: the PF
+ */
+static void ice_pf_dis_all_vsi(struct ice_pf *pf)
+{
+ int v;
+
+ ice_for_each_vsi(pf, v)
+ if (pf->vsi[v])
+ ice_dis_vsi(pf->vsi[v]);
+}
+
+/**
+ * ice_pf_ena_all_vsi - Resume all VSIs on a PF
+ * @pf: the PF
+ */
+static void ice_pf_ena_all_vsi(struct ice_pf *pf)
+{
+ int v;
+
+ ice_for_each_vsi(pf, v)
+ if (pf->vsi[v])
+ ice_ena_vsi(pf->vsi[v]);
+}
+
+/**
+ * ice_rebuild - rebuild after reset
+ * @pf: pf to rebuild
+ */
+static void ice_rebuild(struct ice_pf *pf)
+{
+ struct device *dev = &pf->pdev->dev;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status ret;
+ int err;
+
+ if (test_bit(__ICE_DOWN, pf->state))
+ goto clear_recovery;
+
+ dev_dbg(dev, "rebuilding pf\n");
+
+ ret = ice_init_all_ctrlq(hw);
+ if (ret) {
+ dev_err(dev, "control queues init failed %d\n", ret);
+ goto fail_reset;
+ }
+
+ ret = ice_clear_pf_cfg(hw);
+ if (ret) {
+ dev_err(dev, "clear PF configuration failed %d\n", ret);
+ goto fail_reset;
+ }
+
+ ice_clear_pxe_mode(hw);
+
+ ret = ice_get_caps(hw);
+ if (ret) {
+ dev_err(dev, "ice_get_caps failed %d\n", ret);
+ goto fail_reset;
+ }
+
+ /* basic nic switch setup */
+ err = ice_setup_pf_sw(pf);
+ if (err) {
+ dev_err(dev, "ice_setup_pf_sw failed\n");
+ goto fail_reset;
+ }
+
+ /* 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 fail_reset;
+ }
+ }
+
+ /* restart the VSIs that were rebuilt and running before the reset */
+ ice_pf_ena_all_vsi(pf);
+
+ return;
+
+fail_reset:
+ ice_shutdown_all_ctrlq(hw);
+ set_bit(__ICE_RESET_FAILED, pf->state);
+clear_recovery:
+ set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+}
+
/**
* ice_set_rss - Set RSS keys and lut
* @vsi: Pointer to VSI structure
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 137a59a74b71..c45cdee4e03c 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -17,6 +17,7 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc)
/* debug masks - set these bits in hw->debug_mask to control output */
#define ICE_DBG_INIT BIT_ULL(1)
+#define ICE_DBG_LINK BIT_ULL(4)
#define ICE_DBG_QCTX BIT_ULL(6)
#define ICE_DBG_NVM BIT_ULL(7)
#define ICE_DBG_LAN BIT_ULL(8)
--
2.14.3
^ permalink raw reply related
* [net-next 15/15] ice: Implement filter sync, NDO operations and bump version
From: Jeff Kirsher @ 2018-03-26 19:46 UTC (permalink / raw)
To: davem
Cc: Anirudh Venkataramanan, netdev, nhorman, sassmann, jogreene,
tbogendoerfer, bpoirier, Jeff Kirsher
In-Reply-To: <20180326194619.1202-1-jeffrey.t.kirsher@intel.com>
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
This patch implements multiple pieces of functionality:
1. Added ice_vsi_sync_filters, which is called through the service task
to push filter updates to the hardware.
2. Add support to enable/disable promiscuous mode on an interface.
Enabling/disabling promiscuous mode on an interface results in
addition/removal of a promisc filter rule through ice_vsi_sync_filters.
3. Implement handlers for ndo_set_mac_address, ndo_change_mtu,
ndo_poll_controller and ndo_set_rx_mode.
This patch also marks the end of the driver addition by bumping up the
driver version.
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ice/ice.h | 14 +
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 21 +
drivers/net/ethernet/intel/ice/ice_common.c | 28 ++
drivers/net/ethernet/intel/ice/ice_common.h | 3 +
drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h | 12 +
drivers/net/ethernet/intel/ice/ice_main.c | 567 +++++++++++++++++++++++-
drivers/net/ethernet/intel/ice/ice_switch.c | 77 ++++
drivers/net/ethernet/intel/ice/ice_switch.h | 2 +
drivers/net/ethernet/intel/ice/ice_type.h | 5 +
9 files changed, 728 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 24ce4b71c9ce..d8b5fff581e7 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -125,11 +125,20 @@ enum ice_state {
__ICE_SUSPENDED, /* set on module remove path */
__ICE_RESET_FAILED, /* set by reset/rebuild */
__ICE_ADMINQ_EVENT_PENDING,
+ __ICE_FLTR_OVERFLOW_PROMISC,
__ICE_CFG_BUSY,
__ICE_SERVICE_SCHED,
__ICE_STATE_NBITS /* must be last */
};
+enum ice_vsi_flags {
+ ICE_VSI_FLAG_UMAC_FLTR_CHANGED,
+ ICE_VSI_FLAG_MMAC_FLTR_CHANGED,
+ ICE_VSI_FLAG_VLAN_FLTR_CHANGED,
+ ICE_VSI_FLAG_PROMISC_CHANGED,
+ ICE_VSI_FLAG_NBITS /* must be last */
+};
+
/* struct that defines a VSI, associated with a dev */
struct ice_vsi {
struct net_device *netdev;
@@ -144,7 +153,9 @@ struct ice_vsi {
u64 tx_linearize;
DECLARE_BITMAP(state, __ICE_STATE_NBITS);
+ DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS);
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+ unsigned int current_netdev_flags;
u32 tx_restart;
u32 tx_busy;
u32 rx_buf_failed;
@@ -175,6 +186,9 @@ struct ice_vsi {
struct ice_eth_stats eth_stats;
struct ice_eth_stats eth_stats_prev;
+ struct list_head tmp_sync_list; /* MAC filters to be synced */
+ struct list_head tmp_unsync_list; /* MAC filters to be unsynced */
+
bool irqs_ready;
bool current_isup; /* Sync 'link up' logging */
bool stat_offsets_loaded;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index ea822a9edce8..5b13ca1bd85f 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -135,6 +135,24 @@ struct ice_aqc_manage_mac_read_resp {
u8 mac_addr[ETH_ALEN];
};
+/* Manage MAC address, write command - direct (0x0108) */
+struct ice_aqc_manage_mac_write {
+ u8 port_num;
+ u8 flags;
+#define ICE_AQC_MAN_MAC_WR_MC_MAG_EN BIT(0)
+#define ICE_AQC_MAN_MAC_WR_WOL_LAA_PFR_KEEP BIT(1)
+#define ICE_AQC_MAN_MAC_WR_S 6
+#define ICE_AQC_MAN_MAC_WR_M (3 << ICE_AQC_MAN_MAC_WR_S)
+#define ICE_AQC_MAN_MAC_UPDATE_LAA 0
+#define ICE_AQC_MAN_MAC_UPDATE_LAA_WOL (BIT(0) << ICE_AQC_MAN_MAC_WR_S)
+ /* High 16 bits of MAC address in big endian order */
+ __be16 sah;
+ /* Low 32 bits of MAC address in big endian order */
+ __be32 sal;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
/* Clear PXE Command and response (direct 0x0110) */
struct ice_aqc_clear_pxe {
u8 rx_cnt;
@@ -1214,6 +1232,7 @@ struct ice_aq_desc {
struct ice_aqc_q_shutdown q_shutdown;
struct ice_aqc_req_res res_owner;
struct ice_aqc_manage_mac_read mac_read;
+ struct ice_aqc_manage_mac_write mac_write;
struct ice_aqc_clear_pxe clear_pxe;
struct ice_aqc_list_caps get_cap;
struct ice_aqc_get_phy_caps get_phy;
@@ -1258,6 +1277,7 @@ enum ice_aq_err {
ICE_AQ_RC_ENOMEM = 9, /* Out of memory */
ICE_AQ_RC_EBUSY = 12, /* Device or resource busy */
ICE_AQ_RC_EEXIST = 13, /* object already exists */
+ ICE_AQ_RC_ENOSPC = 16, /* No space left or allocation failure */
};
/* Admin Queue command opcodes */
@@ -1276,6 +1296,7 @@ enum ice_adminq_opc {
/* manage MAC address */
ice_aqc_opc_manage_mac_read = 0x0107,
+ ice_aqc_opc_manage_mac_write = 0x0108,
/* PXE */
ice_aqc_opc_clear_pxe_mode = 0x0110,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 791f1eba5953..385f5d425d19 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1232,6 +1232,34 @@ enum ice_status ice_get_caps(struct ice_hw *hw)
return status;
}
+/**
+ * ice_aq_manage_mac_write - manage MAC address write command
+ * @hw: pointer to the hw struct
+ * @mac_addr: MAC address to be written as LAA/LAA+WoL/Port address
+ * @flags: flags to control write behavior
+ * @cd: pointer to command details structure or NULL
+ *
+ * This function is used to write MAC address to the NVM (0x0108).
+ */
+enum ice_status
+ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_manage_mac_write *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.mac_write;
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_manage_mac_write);
+
+ cmd->flags = flags;
+
+ /* Prep values for flags, sah, sal */
+ cmd->sah = htons(*((u16 *)mac_addr));
+ cmd->sal = htonl(*((u32 *)(mac_addr + 2)));
+
+ return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
/**
* ice_aq_clear_pxe_mode
* @hw: pointer to the hw struct
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index ad350a4921a1..9a5519130af1 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -58,6 +58,9 @@ enum ice_status
ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc,
void *buf, u16 buf_size, struct ice_sq_cd *cd);
enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ struct ice_sq_cd *cd);
enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
enum ice_status
ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart);
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 57acbcff740b..d23a91665b46 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -353,6 +353,18 @@ enum ice_tx_desc_len_fields {
ICE_TX_DESC_LEN_L4_LEN_S = 14 /* 4 BITS */
};
+#define ICE_TXD_QW1_MACLEN_M (0x7FUL << ICE_TX_DESC_LEN_MACLEN_S)
+#define ICE_TXD_QW1_IPLEN_M (0x7FUL << ICE_TX_DESC_LEN_IPLEN_S)
+#define ICE_TXD_QW1_L4LEN_M (0xFUL << ICE_TX_DESC_LEN_L4_LEN_S)
+
+/* Tx descriptor field limits in bytes */
+#define ICE_TXD_MACLEN_MAX ((ICE_TXD_QW1_MACLEN_M >> \
+ ICE_TX_DESC_LEN_MACLEN_S) * ICE_BYTES_PER_WORD)
+#define ICE_TXD_IPLEN_MAX ((ICE_TXD_QW1_IPLEN_M >> \
+ ICE_TX_DESC_LEN_IPLEN_S) * ICE_BYTES_PER_DWORD)
+#define ICE_TXD_L4LEN_MAX ((ICE_TXD_QW1_L4LEN_M >> \
+ ICE_TX_DESC_LEN_L4_LEN_S) * ICE_BYTES_PER_DWORD)
+
#define ICE_TXD_QW1_TX_BUF_SZ_S 34
#define ICE_TXD_QW1_L2TAG1_S 48
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2478dbe9bf4d..210b7910f1cd 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -7,7 +7,7 @@
#include "ice.h"
-#define DRV_VERSION "ice-0.0.1-k"
+#define DRV_VERSION "ice-0.7.0-k"
#define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver"
const char ice_drv_ver[] = DRV_VERSION;
static const char ice_driver_string[] = DRV_SUMMARY;
@@ -200,6 +200,48 @@ static int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
return 0;
}
+/**
+ * ice_add_mac_to_sync_list - creates list of mac addresses to be synced
+ * @netdev: the net device on which the sync is happening
+ * @addr: mac address to sync
+ *
+ * This is a callback function which is called by the in kernel device sync
+ * functions (like __dev_uc_sync, __dev_mc_sync, etc). This function only
+ * populates the tmp_sync_list, which is later used by ice_add_mac to add the
+ * mac filters from the hardware.
+ */
+static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ if (ice_add_mac_to_list(vsi, &vsi->tmp_sync_list, addr))
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * ice_add_mac_to_unsync_list - creates list of mac addresses to be unsynced
+ * @netdev: the net device on which the unsync is happening
+ * @addr: mac address to unsync
+ *
+ * This is a callback function which is called by the in kernel device unsync
+ * functions (like __dev_uc_unsync, __dev_mc_unsync, etc). This function only
+ * populates the tmp_unsync_list, which is later used by ice_remove_mac to
+ * delete the mac filters from the hardware.
+ */
+static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ if (ice_add_mac_to_list(vsi, &vsi->tmp_unsync_list, addr))
+ return -EINVAL;
+
+ return 0;
+}
+
/**
* ice_free_fltr_list - free filter lists helper
* @dev: pointer to the device struct
@@ -218,6 +260,183 @@ static void ice_free_fltr_list(struct device *dev, struct list_head *h)
}
}
+/**
+ * ice_vsi_fltr_changed - check if filter state changed
+ * @vsi: VSI to be checked
+ *
+ * returns true if filter state has changed, false otherwise.
+ */
+static bool ice_vsi_fltr_changed(struct ice_vsi *vsi)
+{
+ return test_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags) ||
+ test_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags) ||
+ test_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+}
+
+/**
+ * ice_vsi_sync_fltr - Update the VSI filter list to the HW
+ * @vsi: ptr to the VSI
+ *
+ * Push any outstanding VSI filter changes through the AdminQ.
+ */
+static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
+{
+ struct device *dev = &vsi->back->pdev->dev;
+ struct net_device *netdev = vsi->netdev;
+ bool promisc_forced_on = false;
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status status = 0;
+ u32 changed_flags = 0;
+ int err = 0;
+
+ if (!vsi->netdev)
+ return -EINVAL;
+
+ while (test_and_set_bit(__ICE_CFG_BUSY, vsi->state))
+ usleep_range(1000, 2000);
+
+ changed_flags = vsi->current_netdev_flags ^ vsi->netdev->flags;
+ vsi->current_netdev_flags = vsi->netdev->flags;
+
+ INIT_LIST_HEAD(&vsi->tmp_sync_list);
+ INIT_LIST_HEAD(&vsi->tmp_unsync_list);
+
+ if (ice_vsi_fltr_changed(vsi)) {
+ clear_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags);
+ clear_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags);
+ clear_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+
+ /* grab the netdev's addr_list_lock */
+ netif_addr_lock_bh(netdev);
+ __dev_uc_sync(netdev, ice_add_mac_to_sync_list,
+ ice_add_mac_to_unsync_list);
+ __dev_mc_sync(netdev, ice_add_mac_to_sync_list,
+ ice_add_mac_to_unsync_list);
+ /* our temp lists are populated. release lock */
+ netif_addr_unlock_bh(netdev);
+ }
+
+ /* Remove mac addresses in the unsync list */
+ status = ice_remove_mac(hw, &vsi->tmp_unsync_list);
+ ice_free_fltr_list(dev, &vsi->tmp_unsync_list);
+ if (status) {
+ netdev_err(netdev, "Failed to delete MAC filters\n");
+ /* if we failed because of alloc failures, just bail */
+ if (status == ICE_ERR_NO_MEMORY) {
+ err = -ENOMEM;
+ goto out;
+ }
+ }
+
+ /* Add mac addresses in the sync list */
+ status = ice_add_mac(hw, &vsi->tmp_sync_list);
+ ice_free_fltr_list(dev, &vsi->tmp_sync_list);
+ if (status) {
+ netdev_err(netdev, "Failed to add MAC filters\n");
+ /* If there is no more space for new umac filters, vsi
+ * should go into promiscuous mode. There should be some
+ * space reserved for promiscuous filters.
+ */
+ if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOSPC &&
+ !test_and_set_bit(__ICE_FLTR_OVERFLOW_PROMISC,
+ vsi->state)) {
+ promisc_forced_on = true;
+ netdev_warn(netdev,
+ "Reached MAC filter limit, forcing promisc mode on VSI %d\n",
+ vsi->vsi_num);
+ } else {
+ err = -EIO;
+ goto out;
+ }
+ }
+ /* check for changes in promiscuous modes */
+ if (changed_flags & IFF_ALLMULTI)
+ netdev_warn(netdev, "Unsupported configuration\n");
+
+ if (((changed_flags & IFF_PROMISC) || promisc_forced_on) ||
+ test_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags)) {
+ clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags);
+ if (vsi->current_netdev_flags & IFF_PROMISC) {
+ /* Apply TX filter rule to get traffic from VMs */
+ status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true,
+ ICE_FLTR_TX);
+ if (status) {
+ netdev_err(netdev, "Error setting default VSI %i tx rule\n",
+ vsi->vsi_num);
+ vsi->current_netdev_flags &= ~IFF_PROMISC;
+ err = -EIO;
+ goto out_promisc;
+ }
+ /* Apply RX filter rule to get traffic from wire */
+ status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true,
+ ICE_FLTR_RX);
+ if (status) {
+ netdev_err(netdev, "Error setting default VSI %i rx rule\n",
+ vsi->vsi_num);
+ vsi->current_netdev_flags &= ~IFF_PROMISC;
+ err = -EIO;
+ goto out_promisc;
+ }
+ } else {
+ /* Clear TX filter rule to stop traffic from VMs */
+ status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false,
+ ICE_FLTR_TX);
+ if (status) {
+ netdev_err(netdev, "Error clearing default VSI %i tx rule\n",
+ vsi->vsi_num);
+ vsi->current_netdev_flags |= IFF_PROMISC;
+ err = -EIO;
+ goto out_promisc;
+ }
+ /* Clear filter RX to remove traffic from wire */
+ status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false,
+ ICE_FLTR_RX);
+ if (status) {
+ netdev_err(netdev, "Error clearing default VSI %i rx rule\n",
+ vsi->vsi_num);
+ vsi->current_netdev_flags |= IFF_PROMISC;
+ err = -EIO;
+ goto out_promisc;
+ }
+ }
+ }
+ goto exit;
+
+out_promisc:
+ set_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags);
+ goto exit;
+out:
+ /* if something went wrong then set the changed flag so we try again */
+ set_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags);
+ set_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags);
+exit:
+ clear_bit(__ICE_CFG_BUSY, vsi->state);
+ return err;
+}
+
+/**
+ * ice_sync_fltr_subtask - Sync the VSI filter list with HW
+ * @pf: board private structure
+ */
+static void ice_sync_fltr_subtask(struct ice_pf *pf)
+{
+ int v;
+
+ if (!pf || !(test_bit(ICE_FLAG_FLTR_SYNC, pf->flags)))
+ return;
+
+ clear_bit(ICE_FLAG_FLTR_SYNC, pf->flags);
+
+ for (v = 0; v < pf->num_alloc_vsi; v++)
+ if (pf->vsi[v] && ice_vsi_fltr_changed(pf->vsi[v]) &&
+ ice_vsi_sync_fltr(pf->vsi[v])) {
+ /* come back and try again later */
+ set_bit(ICE_FLAG_FLTR_SYNC, pf->flags);
+ break;
+ }
+}
+
/**
* ice_is_reset_recovery_pending - schedule a reset
* @state: pf state field
@@ -780,6 +999,7 @@ static void ice_service_task(struct work_struct *work)
return;
}
+ ice_sync_fltr_subtask(pf);
ice_watchdog_subtask(pf);
ice_clean_adminq_subtask(pf);
@@ -2491,6 +2711,7 @@ static int ice_vsi_reinit_setup(struct ice_vsi *vsi)
ice_vsi_free_q_vectors(vsi);
err_rings:
if (vsi->netdev) {
+ vsi->current_netdev_flags = 0;
unregister_netdev(vsi->netdev);
free_netdev(vsi->netdev);
vsi->netdev = NULL;
@@ -3300,6 +3521,197 @@ static void __exit ice_module_exit(void)
}
module_exit(ice_module_exit);
+/**
+ * ice_set_mac_address - NDO callback to set mac address
+ * @netdev: network interface device structure
+ * @pi: pointer to an address structure
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int ice_set_mac_address(struct net_device *netdev, void *pi)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ struct sockaddr *addr = pi;
+ enum ice_status status;
+ LIST_HEAD(a_mac_list);
+ LIST_HEAD(r_mac_list);
+ u8 flags = 0;
+ int err;
+ u8 *mac;
+
+ mac = (u8 *)addr->sa_data;
+
+ if (!is_valid_ether_addr(mac))
+ return -EADDRNOTAVAIL;
+
+ if (ether_addr_equal(netdev->dev_addr, mac)) {
+ netdev_warn(netdev, "already using mac %pM\n", mac);
+ return 0;
+ }
+
+ if (test_bit(__ICE_DOWN, pf->state) ||
+ ice_is_reset_recovery_pending(pf->state)) {
+ netdev_err(netdev, "can't set mac %pM. device not ready\n",
+ mac);
+ return -EBUSY;
+ }
+
+ /* When we change the mac address we also have to change the mac address
+ * based filter rules that were created previously for the old mac
+ * address. So first, we remove the old filter rule using ice_remove_mac
+ * and then create a new filter rule using ice_add_mac. Note that for
+ * both these operations, we first need to form a "list" of mac
+ * addresses (even though in this case, we have only 1 mac address to be
+ * added/removed) and this done using ice_add_mac_to_list. Depending on
+ * the ensuing operation this "list" of mac addresses is either to be
+ * added or removed from the filter.
+ */
+ err = ice_add_mac_to_list(vsi, &r_mac_list, netdev->dev_addr);
+ if (err) {
+ err = -EADDRNOTAVAIL;
+ goto free_lists;
+ }
+
+ status = ice_remove_mac(hw, &r_mac_list);
+ if (status) {
+ err = -EADDRNOTAVAIL;
+ goto free_lists;
+ }
+
+ err = ice_add_mac_to_list(vsi, &a_mac_list, mac);
+ if (err) {
+ err = -EADDRNOTAVAIL;
+ goto free_lists;
+ }
+
+ status = ice_add_mac(hw, &a_mac_list);
+ if (status) {
+ err = -EADDRNOTAVAIL;
+ goto free_lists;
+ }
+
+free_lists:
+ /* free list entries */
+ ice_free_fltr_list(&pf->pdev->dev, &r_mac_list);
+ ice_free_fltr_list(&pf->pdev->dev, &a_mac_list);
+
+ if (err) {
+ netdev_err(netdev, "can't set mac %pM. filter update failed\n",
+ mac);
+ return err;
+ }
+
+ /* change the netdev's mac address */
+ memcpy(netdev->dev_addr, mac, netdev->addr_len);
+ netdev_dbg(vsi->netdev, "updated mac address to %pM\n",
+ netdev->dev_addr);
+
+ /* write new mac address to the firmware */
+ flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL;
+ status = ice_aq_manage_mac_write(hw, mac, flags, NULL);
+ if (status) {
+ netdev_err(netdev, "can't set mac %pM. write to firmware failed.\n",
+ mac);
+ }
+ return 0;
+}
+
+/**
+ * ice_set_rx_mode - NDO callback to set the netdev filters
+ * @netdev: network interface device structure
+ */
+static void ice_set_rx_mode(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ if (!vsi)
+ return;
+
+ /* Set the flags to synchronize filters
+ * ndo_set_rx_mode may be triggered even without a change in netdev
+ * flags
+ */
+ set_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags);
+ set_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags);
+ set_bit(ICE_FLAG_FLTR_SYNC, vsi->back->flags);
+
+ /* schedule our worker thread which will take care of
+ * applying the new filter changes
+ */
+ ice_service_task_schedule(vsi->back);
+}
+
+/**
+ * ice_fdb_add - add an entry to the hardware database
+ * @ndm: the input from the stack
+ * @tb: pointer to array of nladdr (unused)
+ * @dev: the net device pointer
+ * @addr: the MAC address entry being added
+ * @vid: VLAN id
+ * @flags: instructions from stack about fdb operation
+ */
+static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
+ struct net_device *dev, const unsigned char *addr,
+ u16 vid, u16 flags)
+{
+ int err;
+
+ if (vid) {
+ netdev_err(dev, "VLANs aren't supported yet for dev_uc|mc_add()\n");
+ return -EINVAL;
+ }
+ if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
+ netdev_err(dev, "FDB only supports static addresses\n");
+ return -EINVAL;
+ }
+
+ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+ err = dev_uc_add_excl(dev, addr);
+ else if (is_multicast_ether_addr(addr))
+ err = dev_mc_add_excl(dev, addr);
+ else
+ err = -EINVAL;
+
+ /* Only return duplicate errors if NLM_F_EXCL is set */
+ if (err == -EEXIST && !(flags & NLM_F_EXCL))
+ err = 0;
+
+ return err;
+}
+
+/**
+ * ice_fdb_del - delete an entry from the hardware database
+ * @ndm: the input from the stack
+ * @tb: pointer to array of nladdr (unused)
+ * @dev: the net device pointer
+ * @addr: the MAC address entry being added
+ * @vid: VLAN id
+ */
+static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
+ struct net_device *dev, const unsigned char *addr,
+ __always_unused u16 vid)
+{
+ int err;
+
+ if (ndm->ndm_state & NUD_PERMANENT) {
+ netdev_err(dev, "FDB only supports static addresses\n");
+ return -EINVAL;
+ }
+
+ if (is_unicast_ether_addr(addr))
+ err = dev_uc_del(dev, addr);
+ else if (is_multicast_ether_addr(addr))
+ err = dev_mc_del(dev, addr);
+ else
+ err = -EINVAL;
+
+ return err;
+}
+
/**
* ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx
* @vsi: the vsi being changed
@@ -3690,6 +4102,8 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
{
int err;
+ ice_set_rx_mode(vsi->netdev);
+
err = ice_restore_vlan(vsi);
if (err)
return err;
@@ -4379,6 +4793,30 @@ void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
stats->rx_length_errors = vsi_stats->rx_length_errors;
}
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/**
+ * ice_netpoll - polling "interrupt" handler
+ * @netdev: network interface device structure
+ *
+ * Used by netconsole to send skbs without having to re-enable interrupts.
+ * This is not called in the normal interrupt path.
+ */
+static void ice_netpoll(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ int i;
+
+ if (test_bit(__ICE_DOWN, vsi->state) ||
+ !test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+ return;
+
+ for (i = 0; i < vsi->num_q_vectors; i++)
+ ice_msix_clean_rings(0, vsi->q_vectors[i]);
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
/**
* ice_napi_disable_all - Disable NAPI for all q_vectors in the VSI
* @vsi: VSI having NAPI disabled
@@ -4786,6 +5224,73 @@ static void ice_rebuild(struct ice_pf *pf)
set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
}
+/**
+ * ice_change_mtu - NDO callback to change the MTU
+ * @netdev: network interface device structure
+ * @new_mtu: new value for maximum frame size
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int ice_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ u8 count = 0;
+
+ if (new_mtu == netdev->mtu) {
+ netdev_warn(netdev, "mtu is already %d\n", netdev->mtu);
+ return 0;
+ }
+
+ if (new_mtu < netdev->min_mtu) {
+ netdev_err(netdev, "new mtu invalid. min_mtu is %d\n",
+ netdev->min_mtu);
+ return -EINVAL;
+ } else if (new_mtu > netdev->max_mtu) {
+ netdev_err(netdev, "new mtu invalid. max_mtu is %d\n",
+ netdev->min_mtu);
+ return -EINVAL;
+ }
+ /* if a reset is in progress, wait for some time for it to complete */
+ do {
+ if (ice_is_reset_recovery_pending(pf->state)) {
+ count++;
+ usleep_range(1000, 2000);
+ } else {
+ break;
+ }
+
+ } while (count < 100);
+
+ if (count == 100) {
+ netdev_err(netdev, "can't change mtu. Device is busy\n");
+ return -EBUSY;
+ }
+
+ netdev->mtu = new_mtu;
+
+ /* if VSI is up, bring it down and then back up */
+ if (!test_and_set_bit(__ICE_DOWN, vsi->state)) {
+ int err;
+
+ err = ice_down(vsi);
+ if (err) {
+ netdev_err(netdev, "change mtu if_up err %d\n", err);
+ return err;
+ }
+
+ err = ice_up(vsi);
+ if (err) {
+ netdev_err(netdev, "change mtu if_up err %d\n", err);
+ return err;
+ }
+ }
+
+ netdev_dbg(netdev, "changed mtu to %d\n", new_mtu);
+ return 0;
+}
+
/**
* ice_set_rss - Set RSS keys and lut
* @vsi: Pointer to VSI structure
@@ -4919,12 +5424,72 @@ static int ice_stop(struct net_device *netdev)
return 0;
}
+/**
+ * ice_features_check - Validate encapsulated packet conforms to limits
+ * @skb: skb buffer
+ * @netdev: This port's netdev
+ * @features: Offload features that the stack believes apply
+ */
+static netdev_features_t
+ice_features_check(struct sk_buff *skb,
+ struct net_device __always_unused *netdev,
+ netdev_features_t features)
+{
+ size_t len;
+
+ /* No point in doing any of this if neither checksum nor GSO are
+ * being requested for this frame. We can rule out both by just
+ * checking for CHECKSUM_PARTIAL
+ */
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return features;
+
+ /* We cannot support GSO if the MSS is going to be less than
+ * 64 bytes. If it is then we need to drop support for GSO.
+ */
+ if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64))
+ features &= ~NETIF_F_GSO_MASK;
+
+ len = skb_network_header(skb) - skb->data;
+ if (len & ~(ICE_TXD_MACLEN_MAX))
+ goto out_rm_features;
+
+ len = skb_transport_header(skb) - skb_network_header(skb);
+ if (len & ~(ICE_TXD_IPLEN_MAX))
+ goto out_rm_features;
+
+ if (skb->encapsulation) {
+ len = skb_inner_network_header(skb) - skb_transport_header(skb);
+ if (len & ~(ICE_TXD_L4LEN_MAX))
+ goto out_rm_features;
+
+ len = skb_inner_transport_header(skb) -
+ skb_inner_network_header(skb);
+ if (len & ~(ICE_TXD_IPLEN_MAX))
+ goto out_rm_features;
+ }
+
+ return features;
+out_rm_features:
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+}
+
static const struct net_device_ops ice_netdev_ops = {
.ndo_open = ice_open,
.ndo_stop = ice_stop,
.ndo_start_xmit = ice_start_xmit,
+ .ndo_features_check = ice_features_check,
+ .ndo_set_rx_mode = ice_set_rx_mode,
+ .ndo_set_mac_address = ice_set_mac_address,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = ice_change_mtu,
.ndo_get_stats64 = ice_get_stats64,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = ice_netpoll,
+#endif /* CONFIG_NET_POLL_CONTROLLER */
.ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
.ndo_set_features = ice_set_features,
+ .ndo_fdb_add = ice_fdb_add,
+ .ndo_fdb_del = ice_fdb_del,
};
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 5624df9eb6fc..723d15f1e90b 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1626,6 +1626,83 @@ ice_remove_mac(struct ice_hw *hw, struct list_head *m_list)
return status;
}
+/**
+ * ice_cfg_dflt_vsi - add filter rule to set/unset given VSI as default
+ * VSI for the switch (represented by swid)
+ * @hw: pointer to the hardware structure
+ * @vsi_id: number of VSI to set as default
+ * @set: true to add the above mentioned switch rule, false to remove it
+ * @direction: ICE_FLTR_RX or ICE_FLTR_TX
+ */
+enum ice_status
+ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction)
+{
+ struct ice_aqc_sw_rules_elem *s_rule;
+ struct ice_fltr_info f_info;
+ enum ice_adminq_opc opcode;
+ enum ice_status status;
+ u16 s_rule_size;
+
+ s_rule_size = set ? ICE_SW_RULE_RX_TX_ETH_HDR_SIZE :
+ ICE_SW_RULE_RX_TX_NO_HDR_SIZE;
+ s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL);
+ if (!s_rule)
+ return ICE_ERR_NO_MEMORY;
+
+ memset(&f_info, 0, sizeof(f_info));
+
+ f_info.lkup_type = ICE_SW_LKUP_DFLT;
+ f_info.flag = direction;
+ f_info.fltr_act = ICE_FWD_TO_VSI;
+ f_info.fwd_id.vsi_id = vsi_id;
+
+ if (f_info.flag & ICE_FLTR_RX) {
+ f_info.src = hw->port_info->lport;
+ if (!set)
+ f_info.fltr_rule_id =
+ hw->port_info->dflt_rx_vsi_rule_id;
+ } else if (f_info.flag & ICE_FLTR_TX) {
+ f_info.src = vsi_id;
+ if (!set)
+ f_info.fltr_rule_id =
+ hw->port_info->dflt_tx_vsi_rule_id;
+ }
+
+ if (set)
+ opcode = ice_aqc_opc_add_sw_rules;
+ else
+ opcode = ice_aqc_opc_remove_sw_rules;
+
+ ice_fill_sw_rule(hw, &f_info, s_rule, opcode);
+
+ status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, opcode, NULL);
+ if (status || !(f_info.flag & ICE_FLTR_TX_RX))
+ goto out;
+ if (set) {
+ u16 index = le16_to_cpu(s_rule->pdata.lkup_tx_rx.index);
+
+ if (f_info.flag & ICE_FLTR_TX) {
+ hw->port_info->dflt_tx_vsi_num = vsi_id;
+ hw->port_info->dflt_tx_vsi_rule_id = index;
+ } else if (f_info.flag & ICE_FLTR_RX) {
+ hw->port_info->dflt_rx_vsi_num = vsi_id;
+ hw->port_info->dflt_rx_vsi_rule_id = index;
+ }
+ } else {
+ if (f_info.flag & ICE_FLTR_TX) {
+ hw->port_info->dflt_tx_vsi_num = ICE_DFLT_VSI_INVAL;
+ hw->port_info->dflt_tx_vsi_rule_id = ICE_INVAL_ACT;
+ } else if (f_info.flag & ICE_FLTR_RX) {
+ hw->port_info->dflt_rx_vsi_num = ICE_DFLT_VSI_INVAL;
+ hw->port_info->dflt_rx_vsi_rule_id = ICE_INVAL_ACT;
+ }
+ }
+
+out:
+ devm_kfree(ice_hw_to_dev(hw), s_rule);
+ return status;
+}
+
/**
* ice_remove_vlan_internal - Remove one VLAN based filter rule
* @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 80b4e1951b32..6f4a0d159dbf 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -155,5 +155,7 @@ enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst);
void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id);
enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list);
+enum ice_status
+ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction);
#endif /* _ICE_SWITCH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index c45cdee4e03c..99c8a9a71b5e 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -10,6 +10,9 @@
#include "ice_controlq.h"
#include "ice_lan_tx_rx.h"
+#define ICE_BYTES_PER_WORD 2
+#define ICE_BYTES_PER_DWORD 4
+
static inline bool ice_is_tc_ena(u8 bitmap, u8 tc)
{
return test_bit(tc, (unsigned long *)&bitmap);
@@ -227,7 +230,9 @@ struct ice_port_info {
u8 port_state;
#define ICE_SCHED_PORT_STATE_INIT 0x0
#define ICE_SCHED_PORT_STATE_READY 0x1
+ u16 dflt_tx_vsi_rule_id;
u16 dflt_tx_vsi_num;
+ u16 dflt_rx_vsi_rule_id;
u16 dflt_rx_vsi_num;
struct ice_fc_info fc;
struct ice_mac_info mac;
--
2.14.3
^ permalink raw reply related
* Re: [PATCH v2 iproute2-next 3/6] rdma: Add CM_ID resource tracking information
From: Steve Wise @ 2018-03-26 19:55 UTC (permalink / raw)
To: David Ahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <5e6c4b3c-03b2-aab2-d2e6-52f0edf960bb@gmail.com>
On 3/26/2018 10:40 AM, David Ahern wrote:
> On 2/27/18 9:07 AM, Steve Wise wrote:
>> Sample output:
>>
>> # rdma resource
>> 2: cxgb4_0: pd 5 cq 2 qp 2 cm_id 3 mr 7
>> 3: mlx4_0: pd 7 cq 3 qp 3 cm_id 3 mr 7
>>
>> # rdma resource show cm_id
>> link cxgb4_0/- lqpn 0 qp-type RC state LISTEN ps TCP pid 30485 comm rping src-addr 0.0.0.0:7174
>> link cxgb4_0/2 lqpn 1048 qp-type RC state CONNECT ps TCP pid 30503 comm rping src-addr 172.16.2.1:7174 dst-addr 172.16.2.1:38246
>> link cxgb4_0/2 lqpn 1040 qp-type RC state CONNECT ps TCP pid 30498 comm rping src-addr 172.16.2.1:38246 dst-addr 172.16.2.1:7174
>> link mlx4_0/- lqpn 0 qp-type RC state LISTEN ps TCP pid 30485 comm rping src-addr 0.0.0.0:7174
>> link mlx4_0/1 lqpn 539 qp-type RC state CONNECT ps TCP pid 30494 comm rping src-addr 172.16.99.1:7174 dst-addr 172.16.99.1:43670
>> link mlx4_0/1 lqpn 538 qp-type RC state CONNECT ps TCP pid 30492 comm rping src-addr 172.16.99.1:43670 dst-addr 172.16.99.1:7174
>>
>> # rdma resource show cm_id dst-port 7174
>> link cxgb4_0/2 lqpn 1040 qp-type RC state CONNECT ps TCP pid 30498 comm rping src-addr 172.16.2.1:38246 dst-addr 172.16.2.1:7174
>> link mlx4_0/1 lqpn 538 qp-type RC state CONNECT ps TCP pid 30492 comm rping src-addr 172.16.99.1:43670 dst-addr 172.16.99.1:7174
>>
>> Signed-off-by: Steve Wise <swise@opengridcomputing.com>
>> ---
>> rdma/rdma.h | 2 +
>> rdma/res.c | 258 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>> rdma/utils.c | 5 ++
>> 3 files changed, 264 insertions(+), 1 deletion(-)
>>
>> diff --git a/rdma/rdma.h b/rdma/rdma.h
>> index 5809f70..e55205b 100644
>> --- a/rdma/rdma.h
>> +++ b/rdma/rdma.h
>> @@ -18,10 +18,12 @@
>> #include <libmnl/libmnl.h>
>> #include <rdma/rdma_netlink.h>
>> #include <time.h>
>> +#include <net/if_arp.h>
>>
>> #include "list.h"
>> #include "utils.h"
>> #include "json_writer.h"
>> +#include <rdma/rdma_cma.h>
>>
>> #define pr_err(args...) fprintf(stderr, ##args)
>> #define pr_out(args...) fprintf(stdout, ##args)
>> diff --git a/rdma/res.c b/rdma/res.c
>> index 62f5c54..1ef4f20 100644
>> --- a/rdma/res.c
>> +++ b/rdma/res.c
>> @@ -16,9 +16,11 @@ static int res_help(struct rd *rd)
>> {
>> pr_out("Usage: %s resource\n", rd->filename);
>> pr_out(" resource show [DEV]\n");
>> - pr_out(" resource show [qp]\n");
>> + pr_out(" resource show [qp|cm_id]\n");
>> pr_out(" resource show qp link [DEV/PORT]\n");
>> pr_out(" resource show qp link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
>> + pr_out(" resource show cm_id link [DEV/PORT]\n");
>> + pr_out(" resource show cm_id link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
>> return 0;
>> }
>>
>> @@ -433,6 +435,230 @@ static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
>> return MNL_CB_OK;
>> }
>>
>> +static void print_qp_type(struct rd *rd, uint32_t val)
>> +{
>> + if (rd->json_output)
>> + jsonw_string_field(rd->jw, "qp-type",
>> + qp_types_to_str(val));
>> + else
>> + pr_out("qp-type %s ", qp_types_to_str(val));
>> +}
>> +
>> +static const char *cm_id_state_to_str(uint8_t idx)
>> +{
>> + static const char * const cm_id_states_str[] = { "IDLE", "ADDR_QUERY",
>> + "ADDR_RESOLVED", "ROUTE_QUERY", "ROUTE_RESOLVED",
>> + "CONNECT", "DISCONNECT",
>> + "ADDR_BOUND", "LISTEN", "DEVICE_REMOVAL", "DESTROYING" };
>> +
> In general lines should stay under 80 columns. There are a few
> exceptions to the rule (e.g., print strings), but most of the long lines
> you have in this patch need to conform.
Ok. Will do.
>> @@ -457,11 +683,41 @@ filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {{ .name = "link",
>>
>> RES_FUNC(res_qp, RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
>>
>> +static const struct
>> +filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {{ .name = "link",
>> + .is_number = false },
>> + { .name = "lqpn",
>> + .is_number = true },
>> + { .name = "qp-type",
>> + .is_number = false },
>> + { .name = "state",
>> + .is_number = false },
>> + { .name = "ps",
>> + .is_number = false },
>> + { .name = "dev-type",
>> + .is_number = false },
>> + { .name = "transport-type",
>> + .is_number = false },
>> + { .name = "pid",
>> + .is_number = true },
>> + { .name = "src-addr",
>> + .is_number = false },
>> + { .name = "src-port",
>> + .is_number = true },
>> + { .name = "dst-addr",
>> + .is_number = false },
>> + { .name = "dst-port",
>> + .is_number = true }};
>> +
> The above would be more readable as
> static const
> struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
> { .name = "link", .is_number = false },
> { .name = "lqpn", .is_number = true },
> ...
>
> Definitely do not split between struct and filters.
Your formatting is easier to read/maintain.
Thanks for the comments!
^ permalink raw reply
* [net-next PATCH 2/5] soc: ti: K2G: provide APIs to support driver probe deferral
From: Murali Karicheri @ 2018-03-26 20:15 UTC (permalink / raw)
To: robh+dt, mark.rutland, ssantosh, malat, w-kwok2, devicetree,
linux-kernel, linux-arm-kernel, davem, netdev
In-Reply-To: <1522095312-23249-1-git-send-email-m-karicheri2@ti.com>
This patch provide APIs to allow client drivers to support
probe deferral. On K2G SoC, devices can be probed only
after the ti_sci_pm_domains driver is probed and ready.
As drivers may get probed at different order, any driver
that depends on knav dma and qmss drivers, for example
netcp network driver, needs to defer probe until
knav devices are probed and ready to service. To do this,
add an API to query the device ready status from the knav
dma and qmss devices.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
---
drivers/soc/ti/knav_dma.c | 8 ++++++++
drivers/soc/ti/knav_qmss_queue.c | 8 ++++++++
include/linux/soc/ti/knav_dma.h | 12 ++++++++++++
include/linux/soc/ti/knav_qmss.h | 1 +
4 files changed, 29 insertions(+)
diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c
index 026182d..224d7dd 100644
--- a/drivers/soc/ti/knav_dma.c
+++ b/drivers/soc/ti/knav_dma.c
@@ -134,6 +134,13 @@ struct knav_dma_chan {
static struct knav_dma_pool_device *kdev;
+static bool device_ready;
+bool knav_dma_device_ready(void)
+{
+ return device_ready;
+}
+EXPORT_SYMBOL_GPL(knav_dma_device_ready);
+
static bool check_config(struct knav_dma_chan *chan, struct knav_dma_cfg *cfg)
{
if (!memcmp(&chan->cfg, cfg, sizeof(*cfg)))
@@ -773,6 +780,7 @@ static int knav_dma_probe(struct platform_device *pdev)
debugfs_create_file("knav_dma", S_IFREG | S_IRUGO, NULL, NULL,
&knav_dma_debug_ops);
+ device_ready = true;
return ret;
}
diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c
index 5b2c4e9..f0e67aa 100644
--- a/drivers/soc/ti/knav_qmss_queue.c
+++ b/drivers/soc/ti/knav_qmss_queue.c
@@ -74,6 +74,13 @@
*/
const char *knav_acc_firmwares[] = {"ks2_qmss_pdsp_acc48.bin"};
+static bool device_ready;
+bool knav_qmss_device_ready(void)
+{
+ return device_ready;
+}
+EXPORT_SYMBOL_GPL(knav_qmss_device_ready);
+
/**
* knav_queue_notify: qmss queue notfier call
*
@@ -1849,6 +1856,7 @@ static int knav_queue_probe(struct platform_device *pdev)
debugfs_create_file("qmss", S_IFREG | S_IRUGO, NULL, NULL,
&knav_queue_debug_ops);
+ device_ready = true;
return 0;
err:
diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h
index 66693bc..7127ec3 100644
--- a/include/linux/soc/ti/knav_dma.h
+++ b/include/linux/soc/ti/knav_dma.h
@@ -167,6 +167,8 @@ struct knav_dma_desc {
void *knav_dma_open_channel(struct device *dev, const char *name,
struct knav_dma_cfg *config);
void knav_dma_close_channel(void *channel);
+int knav_dma_get_flow(void *channel);
+bool knav_dma_device_ready(void);
#else
static inline void *knav_dma_open_channel(struct device *dev, const char *name,
struct knav_dma_cfg *config)
@@ -176,6 +178,16 @@ static inline void *knav_dma_open_channel(struct device *dev, const char *name,
static inline void knav_dma_close_channel(void *channel)
{}
+static inline int knav_dma_get_flow(void *channel)
+{
+ return -EINVAL;
+}
+
+static inline bool knav_dma_device_ready(void)
+{
+ return false;
+}
+
#endif
#endif /* __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ */
diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h
index 9f0ebb3b..9745df6 100644
--- a/include/linux/soc/ti/knav_qmss.h
+++ b/include/linux/soc/ti/knav_qmss.h
@@ -86,5 +86,6 @@ int knav_pool_desc_map(void *ph, void *desc, unsigned size,
void *knav_pool_desc_unmap(void *ph, dma_addr_t dma, unsigned dma_sz);
dma_addr_t knav_pool_desc_virt_to_dma(void *ph, void *virt);
void *knav_pool_desc_dma_to_virt(void *ph, dma_addr_t dma);
+bool knav_qmss_device_ready(void);
#endif /* __SOC_TI_KNAV_QMSS_H__ */
--
1.9.1
^ permalink raw reply related
* [net-next PATCH 0/5] Add support for netcp driver on K2G SoC
From: Murali Karicheri @ 2018-03-26 20:15 UTC (permalink / raw)
To: robh+dt, mark.rutland, ssantosh, malat, w-kwok2, devicetree,
linux-kernel, linux-arm-kernel, davem, netdev
K2G SoC is another variant of Keystone family of SoCs. This patch
series add support for NetCP driver on this SoC. The QMSS found on
K2G SoC is a cut down version of the QMSS found on other keystone
devices with less number of queues, internal link ram etc. The patch
series has 2 patch sets that goes into the drivers/soc and the
rest has to be applied to net sub system. Please review and merge
if this looks good.
Thanks
The boot logs on K2G ICE board (tftp boot over Ethernet)
is at https://pastebin.ubuntu.com/p/VQTv3c2XBS/
The boot logs on K2G GP board (tftp boot over Ethernet)
is at https://pastebin.ubuntu.com/p/6Vh55DW8vT/
This series applies to net-next master branch.
Murali Karicheri (5):
soc: ti: K2G: enhancement to support QMSS in NSS
soc: ti: K2G: provide APIs to support driver probe deferral
net: netcp: ethss enhancements to support 2u cpsw h/w on K2G SoC
Revert "net: netcp: remove dead code from the driver"
net: netcp: support probe deferral
.../bindings/soc/ti/keystone-navigator-qmss.txt | 7 ++
drivers/net/ethernet/ti/netcp.h | 3 +
drivers/net/ethernet/ti/netcp_core.c | 13 +++
drivers/net/ethernet/ti/netcp_ethss.c | 75 ++++++++++++++---
drivers/soc/ti/knav_dma.c | 8 ++
drivers/soc/ti/knav_qmss.h | 6 ++
drivers/soc/ti/knav_qmss_queue.c | 98 +++++++++++++++++-----
include/linux/soc/ti/knav_dma.h | 12 +++
include/linux/soc/ti/knav_qmss.h | 1 +
9 files changed, 190 insertions(+), 33 deletions(-)
--
1.9.1
^ permalink raw reply
* [net-next PATCH 1/5] soc: ti: K2G: enhancement to support QMSS in NSS
From: Murali Karicheri @ 2018-03-26 20:15 UTC (permalink / raw)
To: robh+dt, mark.rutland, ssantosh, malat, w-kwok2, devicetree,
linux-kernel, linux-arm-kernel, davem, netdev
In-Reply-To: <1522095312-23249-1-git-send-email-m-karicheri2@ti.com>
Navigator Subsystem (NSS) available on K2G SoC has a cut down
version of QMSS with less number of queues, internal linking ram
with lesser number of buffers etc. It doesn't have status and
explicit push register space as in QMSS available on other K2 SoCs.
So define reg indices specific to QMSS on K2G. This patch introduces
"keystone-navigator-qmss-l" compatibility to identify QMSS on
K2G NSS (QMSS Lite) and to customize the dts handling code. Per
Device manual, descriptors with index less than or equal to
regions0_size is in region 0 in the case of QMSS where as for
QMSS Lite, descriptors with index less than regions0_size is in
region 0. So update the size accordingly in the regions0_size bits
of the linking ram size 0 register.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: WingMan Kwok <w-kwok2@ti.com>
---
.../bindings/soc/ti/keystone-navigator-qmss.txt | 7 ++
drivers/soc/ti/knav_qmss.h | 6 ++
drivers/soc/ti/knav_qmss_queue.c | 90 ++++++++++++++++------
3 files changed, 81 insertions(+), 22 deletions(-)
diff --git a/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt b/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt
index 77cd42c..1b0878a 100644
--- a/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt
+++ b/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt
@@ -18,6 +18,7 @@ pool management.
Required properties:
- compatible : Must be "ti,keystone-navigator-qmss";
+ : Must be "ti,keystone-navigator-qmss-l" for NSS Lite
- clocks : phandle to the reference clock for this device.
- queue-range : <start number> total range of queue numbers for the device.
- linkram0 : <address size> for internal link ram, where size is the total
@@ -39,6 +40,12 @@ Required properties:
- Descriptor memory setup region.
- Queue Management/Queue Proxy region for queue Push.
- Queue Management/Queue Proxy region for queue Pop.
+
+For NSS lite, following QMSS reg indexes are used in that order
+ - Queue Peek region.
+ - Queue configuration region.
+ - Queue Management/Queue Proxy region for queue Push/Pop.
+
- queue-pools : child node classifying the queue ranges into pools.
Queue ranges are grouped into 3 type of pools:
- qpend : pool of qpend(interruptible) queues
diff --git a/drivers/soc/ti/knav_qmss.h b/drivers/soc/ti/knav_qmss.h
index 905b974..5fa1ce6 100644
--- a/drivers/soc/ti/knav_qmss.h
+++ b/drivers/soc/ti/knav_qmss.h
@@ -292,6 +292,11 @@ struct knav_queue {
struct list_head list;
};
+enum qmss_version {
+ QMSS,
+ QMSS_LITE,
+};
+
struct knav_device {
struct device *dev;
unsigned base_id;
@@ -305,6 +310,7 @@ struct knav_device {
struct list_head pools;
struct list_head pdsps;
struct list_head qmgrs;
+ enum qmss_version version;
};
struct knav_range_ops {
diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c
index 77d6b5c..5b2c4e9 100644
--- a/drivers/soc/ti/knav_qmss_queue.c
+++ b/drivers/soc/ti/knav_qmss_queue.c
@@ -42,6 +42,15 @@
#define KNAV_QUEUE_PUSH_REG_INDEX 4
#define KNAV_QUEUE_POP_REG_INDEX 5
+/* Queue manager register indices in DTS for QMSS in NSS lite.
+ * There are no status and vbusm push registers on this version
+ * QMSS. Push registers are same as pop, So all indices above 1
+ * are to be re-defined
+ */
+#define KNAV_L_QUEUE_CONFIG_REG_INDEX 1
+#define KNAV_L_QUEUE_REGION_REG_INDEX 2
+#define KNAV_L_QUEUE_PUSH_REG_INDEX 3
+
/* PDSP register indices in DTS */
#define KNAV_QUEUE_PDSP_IRAM_REG_INDEX 0
#define KNAV_QUEUE_PDSP_REGS_REG_INDEX 1
@@ -1169,8 +1178,12 @@ static int knav_queue_setup_link_ram(struct knav_device *kdev)
dev_dbg(kdev->dev, "linkram0: dma:%pad, virt:%p, size:%x\n",
&block->dma, block->virt, block->size);
writel_relaxed((u32)block->dma, &qmgr->reg_config->link_ram_base0);
- writel_relaxed(block->size, &qmgr->reg_config->link_ram_size0);
-
+ if (kdev->version == QMSS_LITE)
+ writel_relaxed(block->size,
+ &qmgr->reg_config->link_ram_size0);
+ else
+ writel_relaxed(block->size - 1,
+ &qmgr->reg_config->link_ram_size0);
block++;
if (!block->size)
continue;
@@ -1387,42 +1400,64 @@ static int knav_queue_init_qmgrs(struct knav_device *kdev,
qmgr->reg_peek =
knav_queue_map_reg(kdev, child,
KNAV_QUEUE_PEEK_REG_INDEX);
- qmgr->reg_status =
- knav_queue_map_reg(kdev, child,
- KNAV_QUEUE_STATUS_REG_INDEX);
+
+ if (kdev->version == QMSS) {
+ qmgr->reg_status =
+ knav_queue_map_reg(kdev, child,
+ KNAV_QUEUE_STATUS_REG_INDEX);
+ }
+
qmgr->reg_config =
knav_queue_map_reg(kdev, child,
+ (kdev->version == QMSS_LITE) ?
+ KNAV_L_QUEUE_CONFIG_REG_INDEX :
KNAV_QUEUE_CONFIG_REG_INDEX);
qmgr->reg_region =
knav_queue_map_reg(kdev, child,
+ (kdev->version == QMSS_LITE) ?
+ KNAV_L_QUEUE_REGION_REG_INDEX :
KNAV_QUEUE_REGION_REG_INDEX);
+
qmgr->reg_push =
knav_queue_map_reg(kdev, child,
- KNAV_QUEUE_PUSH_REG_INDEX);
- qmgr->reg_pop =
- knav_queue_map_reg(kdev, child,
- KNAV_QUEUE_POP_REG_INDEX);
+ (kdev->version == QMSS_LITE) ?
+ KNAV_L_QUEUE_PUSH_REG_INDEX :
+ KNAV_QUEUE_PUSH_REG_INDEX);
+
+ if (kdev->version == QMSS) {
+ qmgr->reg_pop =
+ knav_queue_map_reg(kdev, child,
+ KNAV_QUEUE_POP_REG_INDEX);
+ }
- if (IS_ERR(qmgr->reg_peek) || IS_ERR(qmgr->reg_status) ||
+ if (IS_ERR(qmgr->reg_peek) ||
+ ((kdev->version == QMSS) &&
+ (IS_ERR(qmgr->reg_status) || IS_ERR(qmgr->reg_pop))) ||
IS_ERR(qmgr->reg_config) || IS_ERR(qmgr->reg_region) ||
- IS_ERR(qmgr->reg_push) || IS_ERR(qmgr->reg_pop)) {
+ IS_ERR(qmgr->reg_push)) {
dev_err(dev, "failed to map qmgr regs\n");
+ if (kdev->version == QMSS) {
+ if (!IS_ERR(qmgr->reg_status))
+ devm_iounmap(dev, qmgr->reg_status);
+ if (!IS_ERR(qmgr->reg_pop))
+ devm_iounmap(dev, qmgr->reg_pop);
+ }
if (!IS_ERR(qmgr->reg_peek))
devm_iounmap(dev, qmgr->reg_peek);
- if (!IS_ERR(qmgr->reg_status))
- devm_iounmap(dev, qmgr->reg_status);
if (!IS_ERR(qmgr->reg_config))
devm_iounmap(dev, qmgr->reg_config);
if (!IS_ERR(qmgr->reg_region))
devm_iounmap(dev, qmgr->reg_region);
if (!IS_ERR(qmgr->reg_push))
devm_iounmap(dev, qmgr->reg_push);
- if (!IS_ERR(qmgr->reg_pop))
- devm_iounmap(dev, qmgr->reg_pop);
devm_kfree(dev, qmgr);
continue;
}
+ /* Use same push register for pop as well */
+ if (kdev->version == QMSS_LITE)
+ qmgr->reg_pop = qmgr->reg_push;
+
list_add_tail(&qmgr->list, &kdev->qmgrs);
dev_info(dev, "added qmgr start queue %d, num of queues %d, reg_peek %p, reg_status %p, reg_config %p, reg_region %p, reg_push %p, reg_pop %p\n",
qmgr->start_queue, qmgr->num_queues,
@@ -1681,10 +1716,24 @@ static int knav_queue_init_queues(struct knav_device *kdev)
return 0;
}
+/* Match table for of_platform binding */
+static const struct of_device_id keystone_qmss_of_match[] = {
+ {
+ .compatible = "ti,keystone-navigator-qmss",
+ },
+ {
+ .compatible = "ti,keystone-navigator-qmss-l",
+ .data = (void *)QMSS_LITE,
+ },
+ {},
+};
+MODULE_DEVICE_TABLE(of, keystone_qmss_of_match);
+
static int knav_queue_probe(struct platform_device *pdev)
{
struct device_node *node = pdev->dev.of_node;
struct device_node *qmgrs, *queue_pools, *regions, *pdsps;
+ const struct of_device_id *match;
struct device *dev = &pdev->dev;
u32 temp[2];
int ret;
@@ -1700,6 +1749,10 @@ static int knav_queue_probe(struct platform_device *pdev)
return -ENOMEM;
}
+ match = of_match_device(of_match_ptr(keystone_qmss_of_match), dev);
+ if (match && match->data)
+ kdev->version = QMSS_LITE;
+
platform_set_drvdata(pdev, kdev);
kdev->dev = dev;
INIT_LIST_HEAD(&kdev->queue_ranges);
@@ -1815,13 +1868,6 @@ static int knav_queue_remove(struct platform_device *pdev)
return 0;
}
-/* Match table for of_platform binding */
-static struct of_device_id keystone_qmss_of_match[] = {
- { .compatible = "ti,keystone-navigator-qmss", },
- {},
-};
-MODULE_DEVICE_TABLE(of, keystone_qmss_of_match);
-
static struct platform_driver keystone_qmss_driver = {
.probe = knav_queue_probe,
.remove = knav_queue_remove,
--
1.9.1
^ permalink raw reply related
* [net-next PATCH 3/5] net: netcp: ethss enhancements to support 2u cpsw h/w on K2G SoC
From: Murali Karicheri @ 2018-03-26 20:15 UTC (permalink / raw)
To: robh+dt, mark.rutland, ssantosh, malat, w-kwok2, devicetree,
linux-kernel, linux-arm-kernel, davem, netdev
In-Reply-To: <1522095312-23249-1-git-send-email-m-karicheri2@ti.com>
K2G SoC uses 2u cpsw h/w. It uses RGMII instead of SGMII to interface with
Phy. This patch enhances the driver to check RGMII status instead of SGMII
status for link state determination. Also map all of the vlan priorities
to zero as the packet DMA is enabled to receive only flow id 0 which maps
to priority zero.
Additionally, When a phy with rgmii interface requires internal delay, the
same is set in the phy driver. To support such phy devices, add a phy-mode
handling code in the driver using of_get_phy_mode() and pass the obtained
phy mode to of_phy_connect()
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: Wingman Kwok <w-kwok2@ti.com>
---
drivers/net/ethernet/ti/netcp.h | 3 ++
drivers/net/ethernet/ti/netcp_ethss.c | 75 ++++++++++++++++++++++++++++++-----
2 files changed, 67 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index 8900a6f..3e3193c 100644
--- a/drivers/net/ethernet/ti/netcp.h
+++ b/drivers/net/ethernet/ti/netcp.h
@@ -33,6 +33,9 @@
#define SGMII_LINK_MAC_MAC_FORCED 2
#define SGMII_LINK_MAC_FIBER 3
#define SGMII_LINK_MAC_PHY_NO_MDIO 4
+#define RGMII_LINK_MAC_PHY 5
+#define RGMII_LINK_MAC_MAC_FORCED 6
+#define RGMII_LINK_MAC_PHY_NO_MDIO 7
#define XGMII_LINK_MAC_PHY 10
#define XGMII_LINK_MAC_MAC_FORCED 11
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 56dbc0b..df163ec 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -21,6 +21,7 @@
#include <linux/io.h>
#include <linux/module.h>
#include <linux/of_mdio.h>
+#include <linux/of_net.h>
#include <linux/of_address.h>
#include <linux/if_vlan.h>
#include <linux/ptp_classify.h>
@@ -166,6 +167,9 @@
#define GBE_RXHOOK_ORDER 0
#define GBE_DEFAULT_ALE_AGEOUT 30
#define SLAVE_LINK_IS_XGMII(s) ((s)->link_interface >= XGMII_LINK_MAC_PHY)
+#define SLAVE_LINK_IS_RGMII(s) \
+ (((s)->link_interface >= RGMII_LINK_MAC_PHY) && \
+ ((s)->link_interface <= RGMII_LINK_MAC_PHY_NO_MDIO))
#define NETCP_LINK_STATE_INVALID -1
#define GBE_SET_REG_OFS(p, rb, rn) p->rb##_ofs.rn = \
@@ -549,6 +553,7 @@ struct gbe_ss_regs {
struct gbe_ss_regs_ofs {
u16 id_ver;
u16 control;
+ u16 rgmii_status; /* 2U */
};
struct gbe_switch_regs {
@@ -591,6 +596,7 @@ struct gbe_port_regs {
struct gbe_port_regs_ofs {
u16 port_vlan;
u16 tx_pri_map;
+ u16 rx_pri_map;
u16 sa_lo;
u16 sa_hi;
u16 ts_ctl;
@@ -695,6 +701,7 @@ struct gbe_slave {
u32 link_interface;
u32 mac_control;
u8 phy_port_t;
+ struct device_node *node;
struct device_node *phy_node;
struct ts_ctl ts_ctl;
struct list_head slave_list;
@@ -2091,8 +2098,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev,
ALE_PORT_STATE_FORWARD);
if (ndev && slave->open &&
- slave->link_interface != SGMII_LINK_MAC_PHY &&
- slave->link_interface != XGMII_LINK_MAC_PHY)
+ ((slave->link_interface != SGMII_LINK_MAC_PHY) &&
+ (slave->link_interface != RGMII_LINK_MAC_PHY) &&
+ (slave->link_interface != XGMII_LINK_MAC_PHY)))
netif_carrier_on(ndev);
} else {
writel(mac_control, GBE_REG_ADDR(slave, emac_regs,
@@ -2101,8 +2109,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev,
ALE_PORT_STATE,
ALE_PORT_STATE_DISABLE);
if (ndev &&
- slave->link_interface != SGMII_LINK_MAC_PHY &&
- slave->link_interface != XGMII_LINK_MAC_PHY)
+ ((slave->link_interface != SGMII_LINK_MAC_PHY) &&
+ (slave->link_interface != RGMII_LINK_MAC_PHY) &&
+ (slave->link_interface != XGMII_LINK_MAC_PHY)))
netif_carrier_off(ndev);
}
@@ -2115,23 +2124,39 @@ static bool gbe_phy_link_status(struct gbe_slave *slave)
return !slave->phy || slave->phy->link;
}
+#define RGMII_REG_STATUS_LINK BIT(0)
+
+static void netcp_2u_rgmii_get_port_link(struct gbe_priv *gbe_dev, bool *status)
+{
+ u32 val = 0;
+
+ val = readl(GBE_REG_ADDR(gbe_dev, ss_regs, rgmii_status));
+ *status = false;
+ if ((val & RGMII_REG_STATUS_LINK) != 0)
+ *status = true;
+}
+
static void netcp_ethss_update_link_state(struct gbe_priv *gbe_dev,
struct gbe_slave *slave,
struct net_device *ndev)
{
- int sp = slave->slave_num;
- int phy_link_state, sgmii_link_state = 1, link_state;
+ bool sw_link_state = true, phy_link_state;
+ int sp = slave->slave_num, link_state;
if (!slave->open)
return;
if (!SLAVE_LINK_IS_XGMII(slave)) {
- sgmii_link_state =
+ if (SLAVE_LINK_IS_RGMII(slave))
+ netcp_2u_rgmii_get_port_link(gbe_dev,
+ &sw_link_state);
+ else
+ sw_link_state =
netcp_sgmii_get_port_link(SGMII_BASE(gbe_dev, sp), sp);
}
phy_link_state = gbe_phy_link_status(slave);
- link_state = phy_link_state & sgmii_link_state;
+ link_state = phy_link_state & sw_link_state;
if (atomic_xchg(&slave->link_state, link_state) != link_state)
netcp_ethss_link_state_action(gbe_dev, ndev, slave,
@@ -2271,11 +2296,19 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf)
void (*hndlr)(struct net_device *) = gbe_adjust_link;
- gbe_sgmii_config(priv, slave);
+ if ((priv->ss_version == GBE_SS_VERSION_14) || IS_SS_ID_NU(priv))
+ gbe_sgmii_config(priv, slave);
gbe_port_reset(slave);
gbe_sgmii_rtreset(priv, slave, false);
gbe_port_config(priv, slave, priv->rx_packet_max);
gbe_set_slave_mac(slave, gbe_intf);
+ /* For NU & 2U switch, map the vlan priorities to zero
+ * as we only configure to use priority 0
+ */
+ if (IS_SS_ID_MU(priv))
+ writel(HOST_TX_PRI_MAP_DEFAULT,
+ GBE_REG_ADDR(slave, port_regs, rx_pri_map));
+
/* enable forwarding */
cpsw_ale_control_set(priv->ale, slave->port_num,
ALE_PORT_STATE, ALE_PORT_STATE_FORWARD);
@@ -2286,6 +2319,15 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf)
has_phy = true;
phy_mode = PHY_INTERFACE_MODE_SGMII;
slave->phy_port_t = PORT_MII;
+ } else if (slave->link_interface == RGMII_LINK_MAC_PHY) {
+ has_phy = true;
+ phy_mode = of_get_phy_mode(slave->node);
+ /* if phy-mode is not present, default to
+ * PHY_INTERFACE_MODE_RGMII
+ */
+ if (phy_mode < 0)
+ phy_mode = PHY_INTERFACE_MODE_RGMII;
+ slave->phy_port_t = PORT_MII;
} else if (slave->link_interface == XGMII_LINK_MAC_PHY) {
has_phy = true;
phy_mode = PHY_INTERFACE_MODE_NA;
@@ -2911,8 +2953,10 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave,
slave->link_interface = SGMII_LINK_MAC_PHY;
}
+ slave->node = node;
slave->open = false;
if ((slave->link_interface == SGMII_LINK_MAC_PHY) ||
+ (slave->link_interface == RGMII_LINK_MAC_PHY) ||
(slave->link_interface == XGMII_LINK_MAC_PHY))
slave->phy_node = of_parse_phandle(node, "phy-handle", 0);
slave->port_num = gbe_get_slave_port(gbe_dev, slave->slave_num);
@@ -2976,6 +3020,7 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave,
/* Initialize slave port register offsets */
GBENU_SET_REG_OFS(slave, port_regs, port_vlan);
GBENU_SET_REG_OFS(slave, port_regs, tx_pri_map);
+ GBENU_SET_REG_OFS(slave, port_regs, rx_pri_map);
GBENU_SET_REG_OFS(slave, port_regs, sa_lo);
GBENU_SET_REG_OFS(slave, port_regs, sa_hi);
GBENU_SET_REG_OFS(slave, port_regs, ts_ctl);
@@ -3039,7 +3084,9 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev,
continue;
}
- gbe_sgmii_config(gbe_dev, slave);
+ if ((gbe_dev->ss_version == GBE_SS_VERSION_14) ||
+ IS_SS_ID_NU(gbe_dev))
+ gbe_sgmii_config(gbe_dev, slave);
gbe_port_reset(slave);
gbe_port_config(gbe_dev, slave, gbe_dev->rx_packet_max);
list_add_tail(&slave->slave_list, &gbe_dev->secondary_slaves);
@@ -3073,6 +3120,9 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev,
if (slave->link_interface == SGMII_LINK_MAC_PHY) {
phy_mode = PHY_INTERFACE_MODE_SGMII;
slave->phy_port_t = PORT_MII;
+ } else if (slave->link_interface == RGMII_LINK_MAC_PHY) {
+ phy_mode = PHY_INTERFACE_MODE_RGMII;
+ slave->phy_port_t = PORT_MII;
} else {
phy_mode = PHY_INTERFACE_MODE_NA;
slave->phy_port_t = PORT_FIBRE;
@@ -3080,6 +3130,7 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev,
for_each_sec_slave(slave, gbe_dev) {
if ((slave->link_interface != SGMII_LINK_MAC_PHY) &&
+ (slave->link_interface != RGMII_LINK_MAC_PHY) &&
(slave->link_interface != XGMII_LINK_MAC_PHY))
continue;
slave->phy =
@@ -3355,7 +3406,7 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev,
gbe_dev->num_stats_mods = gbe_dev->max_num_ports;
gbe_dev->et_stats = gbenu_et_stats;
- if (IS_SS_ID_NU(gbe_dev))
+ if (IS_SS_ID_MU(gbe_dev))
gbe_dev->num_et_stats = GBENU_ET_STATS_HOST_SIZE +
(gbe_dev->max_num_slaves * GBENU_ET_STATS_PORT_SIZE);
else
@@ -3419,6 +3470,8 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev,
/* Subsystem registers */
GBENU_SET_REG_OFS(gbe_dev, ss_regs, id_ver);
+ /* ok to set for MU, but used by 2U only */
+ GBENU_SET_REG_OFS(gbe_dev, ss_regs, rgmii_status);
/* Switch module registers */
GBENU_SET_REG_OFS(gbe_dev, switch_regs, id_ver);
--
1.9.1
^ permalink raw reply related
* [net-next PATCH 4/5] Revert "net: netcp: remove dead code from the driver"
From: Murali Karicheri @ 2018-03-26 20:15 UTC (permalink / raw)
To: robh+dt, mark.rutland, ssantosh, malat, w-kwok2, devicetree,
linux-kernel, linux-arm-kernel, davem, netdev
In-Reply-To: <1522095312-23249-1-git-send-email-m-karicheri2@ti.com>
As the probe sequence is not guaranteed contrary to the assumption
of the commit 2d8e276a9030, same has to be reverted.
commit 2d8e276a9030 ("net: netcp: remove dead code from the driver")
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
---
drivers/net/ethernet/ti/netcp_core.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index f5a7eb2..9c51b25 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -2155,6 +2155,7 @@ static int netcp_probe(struct platform_device *pdev)
struct device_node *child, *interfaces;
struct netcp_device *netcp_device;
struct device *dev = &pdev->dev;
+ struct netcp_module *module;
int ret;
if (!node) {
@@ -2203,6 +2204,14 @@ static int netcp_probe(struct platform_device *pdev)
/* Add the device instance to the list */
list_add_tail(&netcp_device->device_list, &netcp_devices);
+ /* Probe & attach any modules already registered */
+ mutex_lock(&netcp_modules_lock);
+ for_each_netcp_module(module) {
+ ret = netcp_module_probe(netcp_device, module);
+ if (ret < 0)
+ dev_err(dev, "module(%s) probe failed\n", module->name);
+ }
+ mutex_unlock(&netcp_modules_lock);
return 0;
probe_quit_interface:
--
1.9.1
^ permalink raw reply related
* [net-next PATCH 5/5] net: netcp: support probe deferral
From: Murali Karicheri @ 2018-03-26 20:15 UTC (permalink / raw)
To: robh+dt, mark.rutland, ssantosh, malat, w-kwok2, devicetree,
linux-kernel, linux-arm-kernel, davem, netdev
In-Reply-To: <1522095312-23249-1-git-send-email-m-karicheri2@ti.com>
The netcp driver shouldn't proceed until the knav qmss and dma
devices are ready. So return -EPROBE_DEFER if these devices are not
ready.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
---
drivers/net/ethernet/ti/netcp_core.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 9c51b25..736f6f7 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -2158,6 +2158,10 @@ static int netcp_probe(struct platform_device *pdev)
struct netcp_module *module;
int ret;
+ if (!knav_dma_device_ready() ||
+ !knav_qmss_device_ready())
+ return -EPROBE_DEFER;
+
if (!node) {
dev_err(dev, "could not find device info\n");
return -ENODEV;
--
1.9.1
^ permalink raw reply related
* Re: [net-next PATCH 3/5] net: netcp: ethss enhancements to support 2u cpsw h/w on K2G SoC
From: Andrew Lunn @ 2018-03-26 20:28 UTC (permalink / raw)
To: Murali Karicheri
Cc: mark.rutland, devicetree, malat, netdev, linux-kernel, w-kwok2,
robh+dt, ssantosh, davem, linux-arm-kernel
In-Reply-To: <1522095312-23249-4-git-send-email-m-karicheri2@ti.com>
On Mon, Mar 26, 2018 at 04:15:10PM -0400, Murali Karicheri wrote:
> K2G SoC uses 2u cpsw h/w. It uses RGMII instead of SGMII to interface with
> Phy. This patch enhances the driver to check RGMII status instead of SGMII
> status for link state determination. Also map all of the vlan priorities
> to zero as the packet DMA is enabled to receive only flow id 0 which maps
> to priority zero.
>
> Additionally, When a phy with rgmii interface requires internal delay, the
> same is set in the phy driver. To support such phy devices, add a phy-mode
> handling code in the driver using of_get_phy_mode() and pass the obtained
> phy mode to of_phy_connect()
Hi Murali
Please break this patch up. One patch should do one thing. That makes
it easy to review. There are too many things going on at once here.
Andrew
^ permalink raw reply
* [PATCH net-next] liquidio: Removed duplicate Tx queue status check
From: Felix Manlunas @ 2018-03-26 20:40 UTC (permalink / raw)
To: davem
Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla,
felix.manlunas, intiyaz.basha
From: Intiyaz Basha <intiyaz.basha@cavium.com>
Napi is checking Tx queue status and waking the Tx queue if required.
Same operation is being done while freeing every Tx buffer.
So removed the duplicate operation of checking Tx queue status from the Tx
buffer free functions.
Signed-off-by: Intiyaz Basha <intiyaz.basha@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
---
drivers/net/ethernet/cavium/liquidio/lio_main.c | 28 ---------------------
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 29 ----------------------
2 files changed, 57 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 58b5c75..43c5ba0 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1635,28 +1635,6 @@ static int octeon_pci_os_setup(struct octeon_device *oct)
}
/**
- * \brief Check Tx queue state for a given network buffer
- * @param lio per-network private data
- * @param skb network buffer
- */
-static inline int check_txq_state(struct lio *lio, struct sk_buff *skb)
-{
- int q, iq;
-
- q = skb->queue_mapping;
- iq = lio->linfo.txpciq[(q % lio->oct_dev->num_iqs)].s.q_no;
-
- if (octnet_iq_is_full(lio->oct_dev, iq))
- return 0;
-
- if (__netif_subqueue_stopped(lio->netdev, q)) {
- INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq, tx_restart, 1);
- netif_wake_subqueue(lio->netdev, q);
- }
- return 1;
-}
-
-/**
* \brief Unmap and free network buffer
* @param buf buffer
*/
@@ -1673,8 +1651,6 @@ static void free_netbuf(void *buf)
dma_unmap_single(&lio->oct_dev->pci_dev->dev, finfo->dptr, skb->len,
DMA_TO_DEVICE);
- check_txq_state(lio, skb);
-
tx_buffer_free(skb);
}
@@ -1715,8 +1691,6 @@ static void free_netsgbuf(void *buf)
list_add_tail(&g->list, &lio->glist[iq]);
spin_unlock(&lio->glist_lock[iq]);
- check_txq_state(lio, skb); /* mq support: sub-queue state check */
-
tx_buffer_free(skb);
}
@@ -1762,8 +1736,6 @@ static void free_netsgbuf_with_resp(void *buf)
spin_unlock(&lio->glist_lock[iq]);
/* Don't free the skb yet */
-
- check_txq_state(lio, skb);
}
/**
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index d5f5c9a..dc62698 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -954,29 +954,6 @@ static int octeon_pci_os_setup(struct octeon_device *oct)
}
/**
- * \brief Check Tx queue state for a given network buffer
- * @param lio per-network private data
- * @param skb network buffer
- */
-static int check_txq_state(struct lio *lio, struct sk_buff *skb)
-{
- int q, iq;
-
- q = skb->queue_mapping;
- iq = lio->linfo.txpciq[q % lio->oct_dev->num_iqs].s.q_no;
-
- if (octnet_iq_is_full(lio->oct_dev, iq))
- return 0;
-
- if (__netif_subqueue_stopped(lio->netdev, q)) {
- INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq, tx_restart, 1);
- netif_wake_subqueue(lio->netdev, q);
- }
-
- return 1;
-}
-
-/**
* \brief Unmap and free network buffer
* @param buf buffer
*/
@@ -993,8 +970,6 @@ static void free_netbuf(void *buf)
dma_unmap_single(&lio->oct_dev->pci_dev->dev, finfo->dptr, skb->len,
DMA_TO_DEVICE);
- check_txq_state(lio, skb);
-
tx_buffer_free(skb);
}
@@ -1036,8 +1011,6 @@ static void free_netsgbuf(void *buf)
list_add_tail(&g->list, &lio->glist[iq]);
spin_unlock(&lio->glist_lock[iq]);
- check_txq_state(lio, skb); /* mq support: sub-queue state check */
-
tx_buffer_free(skb);
}
@@ -1083,8 +1056,6 @@ static void free_netsgbuf_with_resp(void *buf)
spin_unlock(&lio->glist_lock[iq]);
/* Don't free the skb yet */
-
- check_txq_state(lio, skb);
}
/**
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH net] strparser: Fix sign of err codes
From: Tom Herbert @ 2018-03-26 20:44 UTC (permalink / raw)
To: Dave Watson; +Cc: David S. Miller, Linux Kernel Network Developers
In-Reply-To: <20180326193121.GA78356@davejwatson-mba.local>
On Mon, Mar 26, 2018 at 12:31 PM, Dave Watson <davejwatson@fb.com> wrote:
> strp_parser_err is called with a negative code everywhere, which then
> calls abort_parser with a negative code. strp_msg_timeout calls
> abort_parser directly with a positive code. Negate ETIMEDOUT
> to match signed-ness of other calls.
>
> The default abort_parser callback, strp_abort_strp, sets
> sk->sk_err to err. Also negate the error here so sk_err always
> holds a positive value, as the rest of the net code expects. Currently
> a negative sk_err can result in endless loops, or user code that
> thinks it actually sent/received err bytes.
>
> Found while testing net/tls_sw recv path.
>
Nice catch!
It might be nice to have a comment at strp_parser_err and abort_parser
description in Documentation/networking/strparser.txt should also be
updated that err is a negative error value.
Tom
> Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
> Signed-off-by: Dave Watson <davejwatson@fb.com>
> ---
> net/strparser/strparser.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
> index 1fdab5c..b9283ce 100644
> --- a/net/strparser/strparser.c
> +++ b/net/strparser/strparser.c
> @@ -60,7 +60,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
> struct sock *sk = strp->sk;
>
> /* Report an error on the lower socket */
> - sk->sk_err = err;
> + sk->sk_err = -err;
> sk->sk_error_report(sk);
> }
> }
> @@ -458,7 +458,7 @@ static void strp_msg_timeout(struct work_struct *w)
> /* Message assembly timed out */
> STRP_STATS_INCR(strp->stats.msg_timeouts);
> strp->cb.lock(strp);
> - strp->cb.abort_parser(strp, ETIMEDOUT);
> + strp->cb.abort_parser(strp, -ETIMEDOUT);
> strp->cb.unlock(strp);
> }
>
> --
> 2.9.5
>
^ permalink raw reply
* Re: [net-next PATCH 2/5] soc: ti: K2G: provide APIs to support driver probe deferral
From: Andrew Lunn @ 2018-03-26 20:48 UTC (permalink / raw)
To: Murali Karicheri
Cc: robh+dt, mark.rutland, ssantosh, malat, w-kwok2, devicetree,
linux-kernel, linux-arm-kernel, davem, netdev
In-Reply-To: <1522095312-23249-3-git-send-email-m-karicheri2@ti.com>
On Mon, Mar 26, 2018 at 04:15:09PM -0400, Murali Karicheri wrote:
> This patch provide APIs to allow client drivers to support
> probe deferral. On K2G SoC, devices can be probed only
> after the ti_sci_pm_domains driver is probed and ready.
> As drivers may get probed at different order, any driver
> that depends on knav dma and qmss drivers, for example
> netcp network driver, needs to defer probe until
> knav devices are probed and ready to service. To do this,
> add an API to query the device ready status from the knav
> dma and qmss devices.
Hi Murali
Shouldn't you really re-write this to be a dma driver? You would then
do something like of_dma_request_slave_channel() in the ethernet
driver probe function. That probably correctly returns EPROBE_DEFER.
Andrew
^ permalink raw reply
* [pull request][net-next V2 00/15] Mellanox, mlx5 misc updates 2018-03-22
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
Hi Dave,
This series includes some misc updates to mlx5 core and netdev driver,
please note that there is a small change to net/core/ethtool.c and
include/uapi/linux/ethtool.h that adds new tunable for PFC stall
prevention on/off support, which was already reviewed as RFC [1].
For more information please review and see the tag log below.
Please pull and let me know if there's any problem.
P.S.: This series doesn't introduce any conflict with the ongoing
mlx5 fixes series, mlx5-fixes-2018-03-23.
[1] https://patchwork.ozlabs.org/cover/838314/
v1->v2: Addressed comment's by Andrew Lunn
- Added a inline documentation for ETHTOOL_PFC_PREVENTION_TOUT
- Fixed 3rd patch commit message
Thanks,
Saeed.
---
The following changes since commit 336f2c038da1b7f3faf098f2f61bca51e19089ad:
Merge branch 'mlxsw-Offload-IPv6-multicast-routes' (2018-03-26 13:14:45 -0400)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux.git tags/mlx5-updates-2018-03-22
for you to fetch changes up to 71186172b71fe7266eaa768f028c20725202dfd5:
net/mlx5e: Add VLAN offload features to hw_enc_features (2018-03-26 13:47:16 -0700)
----------------------------------------------------------------
mlx5-updates-2018-03-22 (Misc updates)
This series includes misc updates for mlx5 core and netdev dirver,
Highlights:
>From Inbar, three patches to add support for PFC stall prevention
statistics and enable/disable through new ethtool tunable, as requested
from previous submission.
>From Moshe, four patches, added more drop counters:
- drop counter for netdev steering miss
- drop counter for when VF logical link is down
- drop counter for when netdev logical link is down.
>From Or, three patches to support vlan push/pop offload via tc HW action,
for newer HW (Connectx-5 and onward) via HW steering flow actions rather
than the emulated path for the older HW brands.
And five more misc small trivial patches.
----------------------------------------------------------------
Aviv Heller (1):
net/mlx5e: Add VLAN offload features to hw_enc_features
Gal Pressman (3):
net/mlx5e: Remove redundant check in get ethtool stats
net/mlx5e: Make choose LRO timeout function static
net/mlx5e: Add a helper macro in set features ndo
Inbar Karmy (3):
net/mlx5e: Expose PFC stall prevention counters
ethtool: Add support for configuring PFC stall prevention in ethtool
net/mlx5e: PFC stall prevention support
Leon Romanovsky (1):
net/mlx5: Protect from command bit overflow
Moshe Shemesh (4):
net/mlx5: Add support for QUERY_VNIC_ENV command
net/mlx5e: Add vnic steering drop statistics
net/mlx5: Add packet dropped while vport down statistics
net/mlx5e: Add interface down dropped packets statistics
Or Gerlitz (3):
net/mlx5: E-Switch, Use same source for offloaded actions check
net/mlx5: Add core support for vlan push/pop steering action
net/mlx5e: Offload tc vlan push/pop using HW action
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 +-
.../mellanox/mlx5/core/diag/fs_tracepoint.h | 2 +
drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 +-
.../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 60 +++++++++-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 77 +++++++------
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 126 +++++++++++++++++++--
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 6 +
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 15 ++-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 31 ++++-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 13 ++-
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 30 +++--
drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 10 +-
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 4 +-
drivers/net/ethernet/mellanox/mlx5/core/fw.c | 3 +
drivers/net/ethernet/mellanox/mlx5/core/port.c | 64 +++++++++--
drivers/net/ethernet/mellanox/mlx5/core/vport.c | 26 +++++
include/linux/mlx5/device.h | 4 +
include/linux/mlx5/fs.h | 7 ++
include/linux/mlx5/mlx5_ifc.h | 116 +++++++++++++++++--
include/linux/mlx5/port.h | 6 +
include/linux/mlx5/vport.h | 3 +
include/uapi/linux/ethtool.h | 4 +
net/core/ethtool.c | 6 +
23 files changed, 531 insertions(+), 90 deletions(-)
^ permalink raw reply
* [net-next V2 01/15] net/mlx5e: Expose PFC stall prevention counters
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Inbar Karmy, Saeed Mahameed
In-Reply-To: <20180326205603.9450-1-saeedm@mellanox.com>
From: Inbar Karmy <inbark@mellanox.com>
Add the needed capability bit and counters to device spec description.
Expose the following two counters in ethtool:
tx_pause_storm_warning_events: when the device is stalled for a period
longer than a pre-configured watermark, the counter increase, allowing
the debug utility an insight into current device status.
tx_pause_storm_error_events: when the device is stalled for a period
longer than a pre-configured timeout, the pause transmission is disabled,
and the counter increase.
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 19 ++++++++++++++-
drivers/net/ethernet/mellanox/mlx5/core/fw.c | 3 +++
include/linux/mlx5/device.h | 4 ++++
include/linux/mlx5/mlx5_ifc.h | 28 +++++++++++++++++++---
4 files changed, 50 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 5f0f3493d747..2553c58dcf1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -754,7 +754,15 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
};
+static const struct counter_desc pport_pfc_stall_stats_desc[] = {
+ { "tx_pause_storm_warning_events ", PPORT_PER_PRIO_OFF(device_stall_minor_watermark_cnt) },
+ { "tx_pause_storm_error_events", PPORT_PER_PRIO_OFF(device_stall_critical_watermark_cnt) },
+};
+
#define NUM_PPORT_PER_PRIO_PFC_COUNTERS ARRAY_SIZE(pport_per_prio_pfc_stats_desc)
+#define NUM_PPORT_PFC_STALL_COUNTERS(priv) (ARRAY_SIZE(pport_pfc_stall_stats_desc) * \
+ MLX5_CAP_PCAM_FEATURE((priv)->mdev, pfcc_mask) * \
+ MLX5_CAP_DEBUG((priv)->mdev, stall_detect))
static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
{
@@ -790,7 +798,8 @@ static int mlx5e_grp_per_prio_pfc_get_num_stats(struct mlx5e_priv *priv)
{
return (mlx5e_query_global_pause_combined(priv) +
hweight8(mlx5e_query_pfc_combined(priv))) *
- NUM_PPORT_PER_PRIO_PFC_COUNTERS;
+ NUM_PPORT_PER_PRIO_PFC_COUNTERS +
+ NUM_PPORT_PFC_STALL_COUNTERS(priv);
}
static int mlx5e_grp_per_prio_pfc_fill_strings(struct mlx5e_priv *priv,
@@ -818,6 +827,10 @@ static int mlx5e_grp_per_prio_pfc_fill_strings(struct mlx5e_priv *priv,
}
}
+ for (i = 0; i < NUM_PPORT_PFC_STALL_COUNTERS(priv); i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ pport_pfc_stall_stats_desc[i].format);
+
return idx;
}
@@ -845,6 +858,10 @@ static int mlx5e_grp_per_prio_pfc_fill_stats(struct mlx5e_priv *priv,
}
}
+ for (i = 0; i < NUM_PPORT_PFC_STALL_COUNTERS(priv); i++)
+ data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
+ pport_pfc_stall_stats_desc, i);
+
return idx;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 9d11e92fb541..d7bb10ab2173 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -183,6 +183,9 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
return err;
}
+ if (MLX5_CAP_GEN(dev, debug))
+ mlx5_core_get_caps(dev, MLX5_CAP_DEBUG);
+
if (MLX5_CAP_GEN(dev, pcam_reg))
mlx5_get_pcam_reg(dev);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index e5258ee4e38b..4b5939c78cdd 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1013,6 +1013,7 @@ enum mlx5_cap_type {
MLX5_CAP_RESERVED,
MLX5_CAP_VECTOR_CALC,
MLX5_CAP_QOS,
+ MLX5_CAP_DEBUG,
/* NUM OF CAP Types */
MLX5_CAP_NUM
};
@@ -1140,6 +1141,9 @@ enum mlx5_qcam_feature_groups {
#define MLX5_CAP_QOS(mdev, cap)\
MLX5_GET(qos_cap, mdev->caps.hca_cur[MLX5_CAP_QOS], cap)
+#define MLX5_CAP_DEBUG(mdev, cap)\
+ MLX5_GET(debug_cap, mdev->caps.hca_cur[MLX5_CAP_DEBUG], cap)
+
#define MLX5_CAP_PCAM_FEATURE(mdev, fld) \
MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 14ad84afe8ba..c7d50eccff9e 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -593,6 +593,16 @@ struct mlx5_ifc_qos_cap_bits {
u8 reserved_at_100[0x700];
};
+struct mlx5_ifc_debug_cap_bits {
+ u8 reserved_at_0[0x20];
+
+ u8 reserved_at_20[0x2];
+ u8 stall_detect[0x1];
+ u8 reserved_at_23[0x1d];
+
+ u8 reserved_at_40[0x7c0];
+};
+
struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
u8 csum_cap[0x1];
u8 vlan_cap[0x1];
@@ -855,7 +865,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 out_of_seq_cnt[0x1];
u8 vport_counters[0x1];
u8 retransmission_q_counters[0x1];
- u8 reserved_at_183[0x1];
+ u8 debug[0x1];
u8 modify_rq_counter_set_id[0x1];
u8 rq_delay_drop[0x1];
u8 max_qp_cnt[0xa];
@@ -1572,7 +1582,17 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
u8 rx_pause_transition_low[0x20];
- u8 reserved_at_3c0[0x400];
+ u8 reserved_at_3c0[0x40];
+
+ u8 device_stall_minor_watermark_cnt_high[0x20];
+
+ u8 device_stall_minor_watermark_cnt_low[0x20];
+
+ u8 device_stall_critical_watermark_cnt_high[0x20];
+
+ u8 device_stall_critical_watermark_cnt_low[0x20];
+
+ u8 reserved_at_480[0x340];
};
struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits {
@@ -7874,8 +7894,10 @@ struct mlx5_ifc_peir_reg_bits {
};
struct mlx5_ifc_pcam_enhanced_features_bits {
- u8 reserved_at_0[0x7b];
+ u8 reserved_at_0[0x76];
+ u8 pfcc_mask[0x1];
+ u8 reserved_at_77[0x4];
u8 rx_buffer_fullness_counters[0x1];
u8 ptys_connector_type[0x1];
u8 reserved_at_7d[0x1];
--
2.14.3
^ permalink raw reply related
* [net-next V2 03/15] net/mlx5e: PFC stall prevention support
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Inbar Karmy, Saeed Mahameed
In-Reply-To: <20180326205603.9450-1-saeedm@mellanox.com>
From: Inbar Karmy <inbark@mellanox.com>
Implement set/get functions to configure PFC stall prevention
timeout by tunables api through ethtool.
By default the stall prevention timeout is configured to 8 sec.
Timeout range is: 80-8000 msec.
Enabling stall prevention with the auto timeout will set
the timeout to 100 msec.
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 57 +++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/port.c | 64 +++++++++++++++++++---
include/linux/mlx5/mlx5_ifc.h | 17 ++++--
include/linux/mlx5/port.h | 6 ++
4 files changed, 132 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cc8048f68f11..62061fd23143 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1066,6 +1066,57 @@ static int mlx5e_get_rxnfc(struct net_device *netdev,
return err;
}
+#define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC 100
+#define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC 8000
+#define MLX5E_PFC_PREVEN_MINOR_PRECENT 85
+#define MLX5E_PFC_PREVEN_TOUT_MIN_MSEC 80
+#define MLX5E_DEVICE_STALL_MINOR_WATERMARK(critical_tout) \
+ max_t(u16, MLX5E_PFC_PREVEN_TOUT_MIN_MSEC, \
+ (critical_tout * MLX5E_PFC_PREVEN_MINOR_PRECENT) / 100)
+
+static int mlx5e_get_pfc_prevention_tout(struct net_device *netdev,
+ u16 *pfc_prevention_tout)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5_core_dev *mdev = priv->mdev;
+
+ if (!MLX5_CAP_PCAM_FEATURE((priv)->mdev, pfcc_mask) ||
+ !MLX5_CAP_DEBUG((priv)->mdev, stall_detect))
+ return -EOPNOTSUPP;
+
+ return mlx5_query_port_stall_watermark(mdev, pfc_prevention_tout, NULL);
+}
+
+static int mlx5e_set_pfc_prevention_tout(struct net_device *netdev,
+ u16 pfc_preven)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5_core_dev *mdev = priv->mdev;
+ u16 critical_tout;
+ u16 minor;
+
+ if (!MLX5_CAP_PCAM_FEATURE((priv)->mdev, pfcc_mask) ||
+ !MLX5_CAP_DEBUG((priv)->mdev, stall_detect))
+ return -EOPNOTSUPP;
+
+ critical_tout = (pfc_preven == PFC_STORM_PREVENTION_AUTO) ?
+ MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC :
+ pfc_preven;
+
+ if (critical_tout != PFC_STORM_PREVENTION_DISABLE &&
+ (critical_tout > MLX5E_PFC_PREVEN_TOUT_MAX_MSEC ||
+ critical_tout < MLX5E_PFC_PREVEN_TOUT_MIN_MSEC)) {
+ netdev_info(netdev, "%s: pfc prevention tout not in range (%d-%d)\n",
+ __func__, MLX5E_PFC_PREVEN_TOUT_MIN_MSEC,
+ MLX5E_PFC_PREVEN_TOUT_MAX_MSEC);
+ return -EINVAL;
+ }
+
+ minor = MLX5E_DEVICE_STALL_MINOR_WATERMARK(critical_tout);
+ return mlx5_set_port_stall_watermark(mdev, critical_tout,
+ minor);
+}
+
static int mlx5e_get_tunable(struct net_device *dev,
const struct ethtool_tunable *tuna,
void *data)
@@ -1077,6 +1128,9 @@ static int mlx5e_get_tunable(struct net_device *dev,
case ETHTOOL_TX_COPYBREAK:
*(u32 *)data = priv->channels.params.tx_max_inline;
break;
+ case ETHTOOL_PFC_PREVENTION_TOUT:
+ err = mlx5e_get_pfc_prevention_tout(dev, data);
+ break;
default:
err = -EINVAL;
break;
@@ -1118,6 +1172,9 @@ static int mlx5e_set_tunable(struct net_device *dev,
break;
mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+ break;
+ case ETHTOOL_PFC_PREVENTION_TOUT:
+ err = mlx5e_set_pfc_prevention_tout(dev, *(u16 *)data);
break;
default:
err = -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index c37d00cd472a..fa9d0760dd36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -483,6 +483,17 @@ int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev,
}
EXPORT_SYMBOL_GPL(mlx5_core_query_ib_ppcnt);
+static int mlx5_query_pfcc_reg(struct mlx5_core_dev *dev, u32 *out,
+ u32 out_size)
+{
+ u32 in[MLX5_ST_SZ_DW(pfcc_reg)] = {0};
+
+ MLX5_SET(pfcc_reg, in, local_port, 1);
+
+ return mlx5_core_access_reg(dev, in, sizeof(in), out,
+ out_size, MLX5_REG_PFCC, 0, 0);
+}
+
int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause)
{
u32 in[MLX5_ST_SZ_DW(pfcc_reg)] = {0};
@@ -500,13 +511,10 @@ EXPORT_SYMBOL_GPL(mlx5_set_port_pause);
int mlx5_query_port_pause(struct mlx5_core_dev *dev,
u32 *rx_pause, u32 *tx_pause)
{
- u32 in[MLX5_ST_SZ_DW(pfcc_reg)] = {0};
u32 out[MLX5_ST_SZ_DW(pfcc_reg)];
int err;
- MLX5_SET(pfcc_reg, in, local_port, 1);
- err = mlx5_core_access_reg(dev, in, sizeof(in), out,
- sizeof(out), MLX5_REG_PFCC, 0, 0);
+ err = mlx5_query_pfcc_reg(dev, out, sizeof(out));
if (err)
return err;
@@ -520,6 +528,49 @@ int mlx5_query_port_pause(struct mlx5_core_dev *dev,
}
EXPORT_SYMBOL_GPL(mlx5_query_port_pause);
+int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
+ u16 stall_critical_watermark,
+ u16 stall_minor_watermark)
+{
+ u32 in[MLX5_ST_SZ_DW(pfcc_reg)] = {0};
+ u32 out[MLX5_ST_SZ_DW(pfcc_reg)];
+
+ MLX5_SET(pfcc_reg, in, local_port, 1);
+ MLX5_SET(pfcc_reg, in, pptx_mask_n, 1);
+ MLX5_SET(pfcc_reg, in, pprx_mask_n, 1);
+ MLX5_SET(pfcc_reg, in, ppan_mask_n, 1);
+ MLX5_SET(pfcc_reg, in, critical_stall_mask, 1);
+ MLX5_SET(pfcc_reg, in, minor_stall_mask, 1);
+ MLX5_SET(pfcc_reg, in, device_stall_critical_watermark,
+ stall_critical_watermark);
+ MLX5_SET(pfcc_reg, in, device_stall_minor_watermark, stall_minor_watermark);
+
+ return mlx5_core_access_reg(dev, in, sizeof(in), out,
+ sizeof(out), MLX5_REG_PFCC, 0, 1);
+}
+
+int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev,
+ u16 *stall_critical_watermark,
+ u16 *stall_minor_watermark)
+{
+ u32 out[MLX5_ST_SZ_DW(pfcc_reg)];
+ int err;
+
+ err = mlx5_query_pfcc_reg(dev, out, sizeof(out));
+ if (err)
+ return err;
+
+ if (stall_critical_watermark)
+ *stall_critical_watermark = MLX5_GET(pfcc_reg, out,
+ device_stall_critical_watermark);
+
+ if (stall_minor_watermark)
+ *stall_minor_watermark = MLX5_GET(pfcc_reg, out,
+ device_stall_minor_watermark);
+
+ return 0;
+}
+
int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx)
{
u32 in[MLX5_ST_SZ_DW(pfcc_reg)] = {0};
@@ -538,13 +589,10 @@ EXPORT_SYMBOL_GPL(mlx5_set_port_pfc);
int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
{
- u32 in[MLX5_ST_SZ_DW(pfcc_reg)] = {0};
u32 out[MLX5_ST_SZ_DW(pfcc_reg)];
int err;
- MLX5_SET(pfcc_reg, in, local_port, 1);
- err = mlx5_core_access_reg(dev, in, sizeof(in), out,
- sizeof(out), MLX5_REG_PFCC, 0, 0);
+ err = mlx5_query_pfcc_reg(dev, out, sizeof(out));
if (err)
return err;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c7d50eccff9e..f3200a9696d6 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -7833,7 +7833,11 @@ struct mlx5_ifc_pifr_reg_bits {
struct mlx5_ifc_pfcc_reg_bits {
u8 reserved_at_0[0x8];
u8 local_port[0x8];
- u8 reserved_at_10[0x10];
+ u8 reserved_at_10[0xb];
+ u8 ppan_mask_n[0x1];
+ u8 minor_stall_mask[0x1];
+ u8 critical_stall_mask[0x1];
+ u8 reserved_at_1e[0x2];
u8 ppan[0x4];
u8 reserved_at_24[0x4];
@@ -7843,17 +7847,22 @@ struct mlx5_ifc_pfcc_reg_bits {
u8 pptx[0x1];
u8 aptx[0x1];
- u8 reserved_at_42[0x6];
+ u8 pptx_mask_n[0x1];
+ u8 reserved_at_43[0x5];
u8 pfctx[0x8];
u8 reserved_at_50[0x10];
u8 pprx[0x1];
u8 aprx[0x1];
- u8 reserved_at_62[0x6];
+ u8 pprx_mask_n[0x1];
+ u8 reserved_at_63[0x5];
u8 pfcrx[0x8];
u8 reserved_at_70[0x10];
- u8 reserved_at_80[0x80];
+ u8 device_stall_minor_watermark[0x10];
+ u8 device_stall_critical_watermark[0x10];
+
+ u8 reserved_at_a0[0x60];
};
struct mlx5_ifc_pelc_reg_bits {
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 035f0d4dc9fe..34aed6032f86 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -151,6 +151,12 @@ int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx);
int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx,
u8 *pfc_en_rx);
+int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
+ u16 stall_critical_watermark,
+ u16 stall_minor_watermark);
+int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev,
+ u16 *stall_critical_watermark, u16 *stall_minor_watermark);
+
int mlx5_max_tc(struct mlx5_core_dev *mdev);
int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc);
--
2.14.3
^ permalink raw reply related
* [net-next V2 02/15] ethtool: Add support for configuring PFC stall prevention in ethtool
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Inbar Karmy, Michal Kubecek, Andrew Lunn, Saeed Mahameed
In-Reply-To: <20180326205603.9450-1-saeedm@mellanox.com>
From: Inbar Karmy <inbark@mellanox.com>
In the event where the device unexpectedly becomes unresponsive
for a long period of time, flow control mechanism may propagate
pause frames which will cause congestion spreading to the entire
network.
To prevent this scenario, when the device is stalled for a period
longer than a pre-configured timeout, flow control mechanisms are
automatically disabled.
This patch adds support for the ETHTOOL_PFC_STALL_PREVENTION
as a tunable.
This API provides support for configuring flow control storm prevention
timeout (msec).
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Cc: Michal Kubecek <mkubecek@suse.cz>
Cc: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
include/uapi/linux/ethtool.h | 4 ++++
net/core/ethtool.c | 6 ++++++
2 files changed, 10 insertions(+)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 20da156aaf64..4ca65b56084f 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -217,10 +217,14 @@ struct ethtool_value {
__u32 data;
};
+#define PFC_STORM_PREVENTION_AUTO 0xffff
+#define PFC_STORM_PREVENTION_DISABLE 0
+
enum tunable_id {
ETHTOOL_ID_UNSPEC,
ETHTOOL_RX_COPYBREAK,
ETHTOOL_TX_COPYBREAK,
+ ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
/*
* Add your fresh new tubale attribute above and remember to update
* tunable_strings[] in net/core/ethtool.c
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 157cd9efa4be..bb6e498c6e3d 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -121,6 +121,7 @@ tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = {
[ETHTOOL_ID_UNSPEC] = "Unspec",
[ETHTOOL_RX_COPYBREAK] = "rx-copybreak",
[ETHTOOL_TX_COPYBREAK] = "tx-copybreak",
+ [ETHTOOL_PFC_PREVENTION_TOUT] = "pfc-prevention-tout",
};
static const char
@@ -2311,6 +2312,11 @@ static int ethtool_tunable_valid(const struct ethtool_tunable *tuna)
tuna->type_id != ETHTOOL_TUNABLE_U32)
return -EINVAL;
break;
+ case ETHTOOL_PFC_PREVENTION_TOUT:
+ if (tuna->len != sizeof(u16) ||
+ tuna->type_id != ETHTOOL_TUNABLE_U16)
+ return -EINVAL;
+ break;
default:
return -EINVAL;
}
--
2.14.3
^ permalink raw reply related
* [net-next V2 04/15] net/mlx5: Add support for QUERY_VNIC_ENV command
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Moshe Shemesh, Saeed Mahameed
In-Reply-To: <20180326205603.9450-1-saeedm@mellanox.com>
From: Moshe Shemesh <moshe@mellanox.com>
Add support for new FW command QUERY_VNIC_ENV.
The command is used by the driver to query vnic diagnostic statistics
from FW.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 ++
include/linux/mlx5/mlx5_ifc.h | 50 ++++++++++++++++++++++++++-
2 files changed, 51 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e9a1fbcc4adf..fe5428667ad1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -359,6 +359,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_MODIFY_HCA_VPORT_CONTEXT:
case MLX5_CMD_OP_QUERY_HCA_VPORT_GID:
case MLX5_CMD_OP_QUERY_HCA_VPORT_PKEY:
+ case MLX5_CMD_OP_QUERY_VNIC_ENV:
case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
case MLX5_CMD_OP_ALLOC_Q_COUNTER:
case MLX5_CMD_OP_QUERY_Q_COUNTER:
@@ -501,6 +502,7 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(MODIFY_HCA_VPORT_CONTEXT);
MLX5_COMMAND_STR_CASE(QUERY_HCA_VPORT_GID);
MLX5_COMMAND_STR_CASE(QUERY_HCA_VPORT_PKEY);
+ MLX5_COMMAND_STR_CASE(QUERY_VNIC_ENV);
MLX5_COMMAND_STR_CASE(QUERY_VPORT_COUNTER);
MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f3200a9696d6..52e373dd2679 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -143,6 +143,7 @@ enum {
MLX5_CMD_OP_MODIFY_HCA_VPORT_CONTEXT = 0x763,
MLX5_CMD_OP_QUERY_HCA_VPORT_GID = 0x764,
MLX5_CMD_OP_QUERY_HCA_VPORT_PKEY = 0x765,
+ MLX5_CMD_OP_QUERY_VNIC_ENV = 0x76f,
MLX5_CMD_OP_QUERY_VPORT_COUNTER = 0x770,
MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771,
MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772,
@@ -875,7 +876,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 vhca_group_manager[0x1];
u8 ib_virt[0x1];
u8 eth_virt[0x1];
- u8 reserved_at_1a4[0x1];
+ u8 vnic_env_queue_counters[0x1];
u8 ets[0x1];
u8 nic_flow_table[0x1];
u8 eswitch_flow_table[0x1];
@@ -2386,6 +2387,24 @@ struct mlx5_ifc_xrc_srqc_bits {
u8 reserved_at_180[0x80];
};
+struct mlx5_ifc_vnic_diagnostic_statistics_bits {
+ u8 counter_error_queues[0x20];
+
+ u8 total_error_queues[0x20];
+
+ u8 send_queue_priority_update_flow[0x20];
+
+ u8 reserved_at_60[0x20];
+
+ u8 nic_receive_steering_discard[0x40];
+
+ u8 receive_discard_vport_down[0x40];
+
+ u8 transmit_discard_vport_down[0x40];
+
+ u8 reserved_at_140[0xec0];
+};
+
struct mlx5_ifc_traffic_counter_bits {
u8 packets[0x40];
@@ -3661,6 +3680,35 @@ struct mlx5_ifc_query_vport_state_in_bits {
u8 reserved_at_60[0x20];
};
+struct mlx5_ifc_query_vnic_env_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+
+ struct mlx5_ifc_vnic_diagnostic_statistics_bits vport_env;
+};
+
+enum {
+ MLX5_QUERY_VNIC_ENV_IN_OP_MOD_VPORT_DIAG_STATISTICS = 0x0,
+};
+
+struct mlx5_ifc_query_vnic_env_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 other_vport[0x1];
+ u8 reserved_at_41[0xf];
+ u8 vport_number[0x10];
+
+ u8 reserved_at_60[0x20];
+};
+
struct mlx5_ifc_query_vport_counter_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
--
2.14.3
^ permalink raw reply related
* [net-next V2 05/15] net/mlx5e: Add vnic steering drop statistics
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Moshe Shemesh, Saeed Mahameed
In-Reply-To: <20180326205603.9450-1-saeedm@mellanox.com>
From: Moshe Shemesh <moshe@mellanox.com>
Added the following packets drop counter:
Rx steering missed dropped packets - counts packets which were dropped
due to miss on NIC rx steering rules.
This counter will be shown on ethtool as a new counter called
rx_steer_missed_packets.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 65 ++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 5 ++
include/linux/mlx5/mlx5_ifc.h | 3 +-
3 files changed, 72 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 2553c58dcf1c..552510c03ef2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -211,6 +211,65 @@ static void mlx5e_grp_q_update_stats(struct mlx5e_priv *priv)
qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out, out, out_of_buffer);
}
+#define VNIC_ENV_OFF(c) MLX5_BYTE_OFF(query_vnic_env_out, c)
+static const struct counter_desc vnic_env_stats_desc[] = {
+ { "rx_steer_missed_packets",
+ VNIC_ENV_OFF(vport_env.nic_receive_steering_discard) },
+};
+
+#define NUM_VNIC_ENV_COUNTERS ARRAY_SIZE(vnic_env_stats_desc)
+
+static int mlx5e_grp_vnic_env_get_num_stats(struct mlx5e_priv *priv)
+{
+ return MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard) ?
+ NUM_VNIC_ENV_COUNTERS : 0;
+}
+
+static int mlx5e_grp_vnic_env_fill_strings(struct mlx5e_priv *priv, u8 *data,
+ int idx)
+{
+ int i;
+
+ if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard))
+ return idx;
+
+ for (i = 0; i < NUM_VNIC_ENV_COUNTERS; i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ vnic_env_stats_desc[i].format);
+ return idx;
+}
+
+static int mlx5e_grp_vnic_env_fill_stats(struct mlx5e_priv *priv, u64 *data,
+ int idx)
+{
+ int i;
+
+ if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard))
+ return idx;
+
+ for (i = 0; i < NUM_VNIC_ENV_COUNTERS; i++)
+ data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vnic.query_vnic_env_out,
+ vnic_env_stats_desc, i);
+ return idx;
+}
+
+static void mlx5e_grp_vnic_env_update_stats(struct mlx5e_priv *priv)
+{
+ u32 *out = (u32 *)priv->stats.vnic.query_vnic_env_out;
+ int outlen = MLX5_ST_SZ_BYTES(query_vnic_env_out);
+ u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {0};
+ struct mlx5_core_dev *mdev = priv->mdev;
+
+ if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard))
+ return;
+
+ MLX5_SET(query_vnic_env_in, in, opcode,
+ MLX5_CMD_OP_QUERY_VNIC_ENV);
+ MLX5_SET(query_vnic_env_in, in, op_mod, 0);
+ MLX5_SET(query_vnic_env_in, in, other_vport, 0);
+ mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
+}
+
#define VPORT_COUNTER_OFF(c) MLX5_BYTE_OFF(query_vport_counter_out, c)
static const struct counter_desc vport_stats_desc[] = {
{ "rx_vport_unicast_packets",
@@ -1111,6 +1170,12 @@ const struct mlx5e_stats_grp mlx5e_stats_grps[] = {
.update_stats_mask = MLX5E_NDO_UPDATE_STATS,
.update_stats = mlx5e_grp_q_update_stats,
},
+ {
+ .get_num_stats = mlx5e_grp_vnic_env_get_num_stats,
+ .fill_strings = mlx5e_grp_vnic_env_fill_strings,
+ .fill_stats = mlx5e_grp_vnic_env_fill_stats,
+ .update_stats = mlx5e_grp_vnic_env_update_stats,
+ },
{
.get_num_stats = mlx5e_grp_vport_get_num_stats,
.fill_strings = mlx5e_grp_vport_fill_strings,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 0b3320a2b072..847388ff8ca8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -99,6 +99,10 @@ struct mlx5e_qcounter_stats {
u32 rx_out_of_buffer;
};
+struct mlx5e_vnic_env_stats {
+ __be64 query_vnic_env_out[MLX5_ST_SZ_QW(query_vnic_env_out)];
+};
+
#define VPORT_COUNTER_GET(vstats, c) MLX5_GET64(query_vport_counter_out, \
vstats->query_vport_out, c)
@@ -201,6 +205,7 @@ struct mlx5e_ch_stats {
struct mlx5e_stats {
struct mlx5e_sw_stats sw;
struct mlx5e_qcounter_stats qcnt;
+ struct mlx5e_vnic_env_stats vnic;
struct mlx5e_vport_stats vport;
struct mlx5e_pport_stats pport;
struct rtnl_link_stats64 vf_vport;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 52e373dd2679..9202113f552c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1008,7 +1008,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_330[0xb];
u8 log_max_xrcd[0x5];
- u8 reserved_at_340[0x8];
+ u8 nic_receive_steering_discard[0x1];
+ u8 reserved_at_341[0x7];
u8 log_max_flow_counter_bulk[0x8];
u8 max_flow_counter_15_0[0x10];
--
2.14.3
^ permalink raw reply related
* [net-next V2 06/15] net/mlx5: Add packet dropped while vport down statistics
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Moshe Shemesh, Saeed Mahameed
In-Reply-To: <20180326205603.9450-1-saeedm@mellanox.com>
From: Moshe Shemesh <moshe@mellanox.com>
Added the following packets dropped while vport down statistics:
Rx dropped while vport down - counts packets which were steered by
e-switch to a vport, but dropped since the vport was down. This counter
will be shown on ip link tool as part of the vport rx_dropped counter.
Tx dropped while vport down - counts packets which were transmitted by
a vport, but dropped due to vport logical link down. This counter
will be shown on ip link tool as part of the vport tx_dropped counter.
The counters are read from FW by command QUERY_VNIC_ENV.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 31 +++++++++++++++++++----
drivers/net/ethernet/mellanox/mlx5/core/vport.c | 26 +++++++++++++++++++
include/linux/mlx5/mlx5_ifc.h | 4 ++-
include/linux/mlx5/vport.h | 3 +++
4 files changed, 58 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 77b7272eaaa8..332bc56306bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2096,17 +2096,19 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, int vport,
return err;
}
-static void mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
- int vport_idx,
- struct mlx5_vport_drop_stats *stats)
+static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
+ int vport_idx,
+ struct mlx5_vport_drop_stats *stats)
{
struct mlx5_eswitch *esw = dev->priv.eswitch;
struct mlx5_vport *vport = &esw->vports[vport_idx];
+ u64 rx_discard_vport_down, tx_discard_vport_down;
u64 bytes = 0;
u16 idx = 0;
+ int err = 0;
if (!vport->enabled || esw->mode != SRIOV_LEGACY)
- return;
+ return 0;
if (vport->egress.drop_counter) {
idx = vport->egress.drop_counter->id;
@@ -2117,6 +2119,23 @@ static void mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
idx = vport->ingress.drop_counter->id;
mlx5_fc_query(dev, idx, &stats->tx_dropped, &bytes);
}
+
+ if (!MLX5_CAP_GEN(dev, receive_discard_vport_down) &&
+ !MLX5_CAP_GEN(dev, transmit_discard_vport_down))
+ return 0;
+
+ err = mlx5_query_vport_down_stats(dev, vport_idx,
+ &rx_discard_vport_down,
+ &tx_discard_vport_down);
+ if (err)
+ return err;
+
+ if (MLX5_CAP_GEN(dev, receive_discard_vport_down))
+ stats->rx_dropped += rx_discard_vport_down;
+ if (MLX5_CAP_GEN(dev, transmit_discard_vport_down))
+ stats->tx_dropped += tx_discard_vport_down;
+
+ return 0;
}
int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
@@ -2180,7 +2199,9 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
vf_stats->broadcast =
MLX5_GET_CTR(out, received_eth_broadcast.packets);
- mlx5_eswitch_query_vport_drop_stats(esw->dev, vport, &stats);
+ err = mlx5_eswitch_query_vport_drop_stats(esw->dev, vport, &stats);
+ if (err)
+ goto free_out;
vf_stats->rx_dropped = stats.rx_dropped;
vf_stats->tx_dropped = stats.tx_dropped;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index dfe36cf6fbea..177e076b8d17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -1070,6 +1070,32 @@ int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport,
}
EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter);
+int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
+ u64 *rx_discard_vport_down,
+ u64 *tx_discard_vport_down)
+{
+ u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {0};
+ u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {0};
+ int err;
+
+ MLX5_SET(query_vnic_env_in, in, opcode,
+ MLX5_CMD_OP_QUERY_VNIC_ENV);
+ MLX5_SET(query_vnic_env_in, in, op_mod, 0);
+ MLX5_SET(query_vnic_env_in, in, vport_number, vport);
+ if (vport)
+ MLX5_SET(query_vnic_env_in, in, other_vport, 1);
+
+ err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ *rx_discard_vport_down = MLX5_GET64(query_vnic_env_out, out,
+ vport_env.receive_discard_vport_down);
+ *tx_discard_vport_down = MLX5_GET64(query_vnic_env_out, out,
+ vport_env.transmit_discard_vport_down);
+ return 0;
+}
+
int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
u8 other_vport, u8 port_num,
int vf,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9202113f552c..1f3483d40055 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1009,7 +1009,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 log_max_xrcd[0x5];
u8 nic_receive_steering_discard[0x1];
- u8 reserved_at_341[0x7];
+ u8 receive_discard_vport_down[0x1];
+ u8 transmit_discard_vport_down[0x1];
+ u8 reserved_at_343[0x5];
u8 log_max_flow_counter_bulk[0x8];
u8 max_flow_counter_15_0[0x10];
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 64e193e87394..9208cb8809ac 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -107,6 +107,9 @@ int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev,
int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev);
int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev);
+int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
+ u64 *rx_discard_vport_down,
+ u64 *tx_discard_vport_down);
int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport,
int vf, u8 port_num, void *out,
size_t out_sz);
--
2.14.3
^ permalink raw reply related
* [net-next V2 07/15] net/mlx5e: Add interface down dropped packets statistics
From: Saeed Mahameed @ 2018-03-26 20:55 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Moshe Shemesh, Saeed Mahameed
In-Reply-To: <20180326205603.9450-1-saeedm@mellanox.com>
From: Moshe Shemesh <moshe@mellanox.com>
Added the following packets drop counter:
Rx interface down dropped packets - counts packets which were received
while the ETH interface was down.
This counter will be shown on ethtool as a new counter called
rx_if_down_packets.
The implementation allocates a q_counter for drop rq which gets all the
received traffic while the interface is down.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 +-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 46 +++++++++++++--------
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 48 ++++++++++++++++------
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 1 +
4 files changed, 69 insertions(+), 29 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 4c9360b25532..48e0b2a747d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -781,7 +781,8 @@ struct mlx5e_priv {
struct net_device *netdev;
struct mlx5e_stats stats;
struct hwtstamp_config tstamp;
- u16 q_counter;
+ u16 q_counter;
+ u16 drop_rq_q_counter;
#ifdef CONFIG_MLX5_CORE_EN_DCB
struct mlx5e_dcbx dcbx;
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index da94c8cba5ee..f8bc3bcdf046 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -615,8 +615,7 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq,
static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
int next_state)
{
- struct mlx5e_channel *c = rq->channel;
- struct mlx5_core_dev *mdev = c->mdev;
+ struct mlx5_core_dev *mdev = rq->mdev;
void *in;
void *rqc;
@@ -1768,14 +1767,16 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
param->wq.linear = 1;
}
-static void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
+static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
struct mlx5e_rq_param *param)
{
+ struct mlx5_core_dev *mdev = priv->mdev;
void *rqc = param->rqc;
void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe)));
+ MLX5_SET(rqc, rqc, counter_set_id, priv->drop_rq_q_counter);
param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
}
@@ -2643,15 +2644,16 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
return mlx5e_alloc_cq_common(mdev, param, cq);
}
-static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
+static int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
struct mlx5e_rq *drop_rq)
{
+ struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_cq_param cq_param = {};
struct mlx5e_rq_param rq_param = {};
struct mlx5e_cq *cq = &drop_rq->cq;
int err;
- mlx5e_build_drop_rq_param(mdev, &rq_param);
+ mlx5e_build_drop_rq_param(priv, &rq_param);
err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param);
if (err)
@@ -2669,6 +2671,10 @@ static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
if (err)
goto err_free_rq;
+ err = mlx5e_modify_rq_state(drop_rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
+ if (err)
+ mlx5_core_warn(priv->mdev, "modify_rq_state failed, rx_if_down_packets won't be counted %d\n", err);
+
return 0;
err_free_rq:
@@ -4183,7 +4189,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
mlx5e_ipsec_build_netdev(priv);
}
-static void mlx5e_create_q_counter(struct mlx5e_priv *priv)
+static void mlx5e_create_q_counters(struct mlx5e_priv *priv)
{
struct mlx5_core_dev *mdev = priv->mdev;
int err;
@@ -4193,14 +4199,21 @@ static void mlx5e_create_q_counter(struct mlx5e_priv *priv)
mlx5_core_warn(mdev, "alloc queue counter failed, %d\n", err);
priv->q_counter = 0;
}
+
+ err = mlx5_core_alloc_q_counter(mdev, &priv->drop_rq_q_counter);
+ if (err) {
+ mlx5_core_warn(mdev, "alloc drop RQ counter failed, %d\n", err);
+ priv->drop_rq_q_counter = 0;
+ }
}
-static void mlx5e_destroy_q_counter(struct mlx5e_priv *priv)
+static void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
{
- if (!priv->q_counter)
- return;
+ if (priv->q_counter)
+ mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter);
- mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter);
+ if (priv->drop_rq_q_counter)
+ mlx5_core_dealloc_q_counter(priv->mdev, priv->drop_rq_q_counter);
}
static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
@@ -4439,18 +4452,18 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
if (err)
goto out;
- err = mlx5e_open_drop_rq(mdev, &priv->drop_rq);
+ mlx5e_create_q_counters(priv);
+
+ err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
if (err) {
mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
- goto err_cleanup_tx;
+ goto err_destroy_q_counters;
}
err = profile->init_rx(priv);
if (err)
goto err_close_drop_rq;
- mlx5e_create_q_counter(priv);
-
if (profile->enable)
profile->enable(priv);
@@ -4459,7 +4472,8 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
err_close_drop_rq:
mlx5e_close_drop_rq(&priv->drop_rq);
-err_cleanup_tx:
+err_destroy_q_counters:
+ mlx5e_destroy_q_counters(priv);
profile->cleanup_tx(priv);
out:
@@ -4476,9 +4490,9 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv)
profile->disable(priv);
flush_workqueue(priv->wq);
- mlx5e_destroy_q_counter(priv);
profile->cleanup_rx(priv);
mlx5e_close_drop_rq(&priv->drop_rq);
+ mlx5e_destroy_q_counters(priv);
profile->cleanup_tx(priv);
cancel_delayed_work_sync(&priv->update_stats_work);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 552510c03ef2..c0dab9a8969e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -170,11 +170,24 @@ static const struct counter_desc q_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_qcounter_stats, rx_out_of_buffer) },
};
+static const struct counter_desc drop_rq_stats_desc[] = {
+ { MLX5E_DECLARE_STAT(struct mlx5e_qcounter_stats, rx_if_down_packets) },
+};
+
#define NUM_Q_COUNTERS ARRAY_SIZE(q_stats_desc)
+#define NUM_DROP_RQ_COUNTERS ARRAY_SIZE(drop_rq_stats_desc)
static int mlx5e_grp_q_get_num_stats(struct mlx5e_priv *priv)
{
- return priv->q_counter ? NUM_Q_COUNTERS : 0;
+ int num_stats = 0;
+
+ if (priv->q_counter)
+ num_stats += NUM_Q_COUNTERS;
+
+ if (priv->drop_rq_q_counter)
+ num_stats += NUM_DROP_RQ_COUNTERS;
+
+ return num_stats;
}
static int mlx5e_grp_q_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
@@ -182,7 +195,13 @@ static int mlx5e_grp_q_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
int i;
for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
- strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format);
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ q_stats_desc[i].format);
+
+ for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ drop_rq_stats_desc[i].format);
+
return idx;
}
@@ -191,7 +210,11 @@ static int mlx5e_grp_q_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
int i;
for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
- data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt, q_stats_desc, i);
+ data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
+ q_stats_desc, i);
+ for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++)
+ data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
+ drop_rq_stats_desc, i);
return idx;
}
@@ -199,16 +222,17 @@ static void mlx5e_grp_q_update_stats(struct mlx5e_priv *priv)
{
struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
u32 out[MLX5_ST_SZ_DW(query_q_counter_out)];
- int err;
-
- if (!priv->q_counter)
- return;
-
- err = mlx5_core_query_q_counter(priv->mdev, priv->q_counter, 0, out, sizeof(out));
- if (err)
- return;
- qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out, out, out_of_buffer);
+ if (priv->q_counter &&
+ !mlx5_core_query_q_counter(priv->mdev, priv->q_counter, 0, out,
+ sizeof(out)))
+ qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out,
+ out, out_of_buffer);
+ if (priv->drop_rq_q_counter &&
+ !mlx5_core_query_q_counter(priv->mdev, priv->drop_rq_q_counter, 0,
+ out, sizeof(out)))
+ qcnt->rx_if_down_packets = MLX5_GET(query_q_counter_out, out,
+ out_of_buffer);
}
#define VNIC_ENV_OFF(c) MLX5_BYTE_OFF(query_vnic_env_out, c)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 847388ff8ca8..43a72efa28c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -97,6 +97,7 @@ struct mlx5e_sw_stats {
struct mlx5e_qcounter_stats {
u32 rx_out_of_buffer;
+ u32 rx_if_down_packets;
};
struct mlx5e_vnic_env_stats {
--
2.14.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox