* [PATCH V5 net-next 12/21] net-next/hinic: Add qp resources
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Create the resources for queue pair operations: doorbell area,
consumer index address and producer index address.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
drivers/net/ethernet/huawei/hinic/Makefile | 4 +-
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 1 +
drivers/net/ethernet/huawei/hinic/hinic_hw_io.c | 164 ++++++++++++++-
drivers/net/ethernet/huawei/hinic/hinic_hw_io.h | 27 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c | 266 ++++++++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h | 50 ++++-
6 files changed, 507 insertions(+), 5 deletions(-)
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
index 0575a34..84815f7 100644
--- a/drivers/net/ethernet/huawei/hinic/Makefile
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -1,5 +1,5 @@
obj-$(CONFIG_HINIC) += hinic.o
hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \
- hinic_hw_io.o hinic_hw_wq.o hinic_hw_mgmt.o hinic_hw_api_cmd.o \
- hinic_hw_eqs.o hinic_hw_if.o
+ hinic_hw_io.o hinic_hw_qp.o hinic_hw_wq.o hinic_hw_mgmt.o \
+ hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 2280698..8f59195 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -137,6 +137,7 @@
#define HINIC_IS_PPF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PPF)
#define HINIC_PCI_CFG_REGS_BAR 0
+#define HINIC_PCI_DB_BAR 4
#define HINIC_PCIE_ST_DISABLE 0
#define HINIC_PCIE_AT_DISABLE 0
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
index 1bf944e..ad12cc7 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
@@ -13,11 +13,16 @@
*
*/
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/device.h>
#include <linux/errno.h>
#include <linux/slab.h>
+#include <linux/semaphore.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/err.h>
#include "hinic_hw_if.h"
#include "hinic_hw_wqe.h"
@@ -25,6 +30,76 @@
#include "hinic_hw_qp.h"
#include "hinic_hw_io.h"
+#define CI_Q_ADDR_SIZE sizeof(u32)
+
+#define CI_ADDR(base_addr, q_id) ((base_addr) + \
+ (q_id) * CI_Q_ADDR_SIZE)
+
+#define CI_TABLE_SIZE(num_qps) ((num_qps) * CI_Q_ADDR_SIZE)
+
+#define DB_IDX(db, db_base) \
+ (((unsigned long)(db) - (unsigned long)(db_base)) / HINIC_DB_PAGE_SIZE)
+
+static void init_db_area_idx(struct hinic_free_db_area *free_db_area)
+{
+ int i;
+
+ for (i = 0; i < HINIC_DB_MAX_AREAS; i++)
+ free_db_area->db_idx[i] = i;
+
+ free_db_area->alloc_pos = 0;
+ free_db_area->return_pos = HINIC_DB_MAX_AREAS;
+
+ free_db_area->num_free = HINIC_DB_MAX_AREAS;
+
+ sema_init(&free_db_area->idx_lock, 1);
+}
+
+static void __iomem *get_db_area(struct hinic_func_to_io *func_to_io)
+{
+ struct hinic_free_db_area *free_db_area = &func_to_io->free_db_area;
+ int pos, idx;
+
+ down(&free_db_area->idx_lock);
+
+ free_db_area->num_free--;
+
+ if (free_db_area->num_free < 0) {
+ free_db_area->num_free++;
+ up(&free_db_area->idx_lock);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ pos = free_db_area->alloc_pos++;
+ pos &= HINIC_DB_MAX_AREAS - 1;
+
+ idx = free_db_area->db_idx[pos];
+
+ free_db_area->db_idx[pos] = -1;
+
+ up(&free_db_area->idx_lock);
+
+ return func_to_io->db_base + idx * HINIC_DB_PAGE_SIZE;
+}
+
+static void return_db_area(struct hinic_func_to_io *func_to_io,
+ void __iomem *db_base)
+{
+ struct hinic_free_db_area *free_db_area = &func_to_io->free_db_area;
+ int pos, idx = DB_IDX(db_base, func_to_io->db_base);
+
+ down(&free_db_area->idx_lock);
+
+ pos = free_db_area->return_pos++;
+ pos &= HINIC_DB_MAX_AREAS - 1;
+
+ free_db_area->db_idx[pos] = idx;
+
+ free_db_area->num_free++;
+
+ up(&free_db_area->idx_lock);
+}
+
/**
* init_qp - Initialize a Queue Pair
* @func_to_io: func to io channel that holds the IO components
@@ -42,6 +117,7 @@ static int init_qp(struct hinic_func_to_io *func_to_io,
{
struct hinic_hwif *hwif = func_to_io->hwif;
struct pci_dev *pdev = hwif->pdev;
+ void __iomem *db_base;
int err;
qp->q_id = q_id;
@@ -62,8 +138,42 @@ static int init_qp(struct hinic_func_to_io *func_to_io,
goto err_rq_alloc;
}
+ db_base = get_db_area(func_to_io);
+ if (IS_ERR(db_base)) {
+ dev_err(&pdev->dev, "Failed to get DB area for SQ\n");
+ err = PTR_ERR(db_base);
+ goto err_get_db;
+ }
+
+ func_to_io->sq_db[q_id] = db_base;
+
+ err = hinic_init_sq(&qp->sq, hwif, &func_to_io->sq_wq[q_id],
+ sq_msix_entry,
+ CI_ADDR(func_to_io->ci_addr_base, q_id),
+ CI_ADDR(func_to_io->ci_dma_base, q_id), db_base);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to init SQ\n");
+ goto err_sq_init;
+ }
+
+ err = hinic_init_rq(&qp->rq, hwif, &func_to_io->rq_wq[q_id],
+ rq_msix_entry);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to init RQ\n");
+ goto err_rq_init;
+ }
+
return 0;
+err_rq_init:
+ hinic_clean_sq(&qp->sq);
+
+err_sq_init:
+ return_db_area(func_to_io, db_base);
+
+err_get_db:
+ hinic_wq_free(&func_to_io->wqs, &func_to_io->rq_wq[q_id]);
+
err_rq_alloc:
hinic_wq_free(&func_to_io->wqs, &func_to_io->sq_wq[q_id]);
return err;
@@ -79,6 +189,11 @@ static void destroy_qp(struct hinic_func_to_io *func_to_io,
{
int q_id = qp->q_id;
+ hinic_clean_rq(&qp->rq);
+ hinic_clean_sq(&qp->sq);
+
+ return_db_area(func_to_io, func_to_io->sq_db[q_id]);
+
hinic_wq_free(&func_to_io->wqs, &func_to_io->rq_wq[q_id]);
hinic_wq_free(&func_to_io->wqs, &func_to_io->sq_wq[q_id]);
}
@@ -100,7 +215,8 @@ int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
{
struct hinic_hwif *hwif = func_to_io->hwif;
struct pci_dev *pdev = hwif->pdev;
- size_t qps_size, wq_size;
+ size_t qps_size, wq_size, db_size;
+ void *ci_addr_base;
int i, j, err;
qps_size = num_qps * sizeof(*func_to_io->qps);
@@ -122,6 +238,24 @@ int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
goto err_rq_wq;
}
+ db_size = num_qps * sizeof(*func_to_io->sq_db);
+ func_to_io->sq_db = devm_kzalloc(&pdev->dev, db_size, GFP_KERNEL);
+ if (!func_to_io->sq_db) {
+ err = -ENOMEM;
+ goto err_sq_db;
+ }
+
+ ci_addr_base = dma_zalloc_coherent(&pdev->dev, CI_TABLE_SIZE(num_qps),
+ &func_to_io->ci_dma_base,
+ GFP_KERNEL);
+ if (!ci_addr_base) {
+ dev_err(&pdev->dev, "Failed to allocate CI area\n");
+ err = -ENOMEM;
+ goto err_ci_base;
+ }
+
+ func_to_io->ci_addr_base = ci_addr_base;
+
for (i = 0; i < num_qps; i++) {
err = init_qp(func_to_io, &func_to_io->qps[i], i,
&sq_msix_entries[i], &rq_msix_entries[i]);
@@ -137,6 +271,13 @@ int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
for (j = 0; j < i; j++)
destroy_qp(func_to_io, &func_to_io->qps[j]);
+ dma_free_coherent(&pdev->dev, CI_TABLE_SIZE(num_qps),
+ func_to_io->ci_addr_base, func_to_io->ci_dma_base);
+
+err_ci_base:
+ devm_kfree(&pdev->dev, func_to_io->sq_db);
+
+err_sq_db:
devm_kfree(&pdev->dev, func_to_io->rq_wq);
err_rq_wq:
@@ -156,11 +297,19 @@ void hinic_io_destroy_qps(struct hinic_func_to_io *func_to_io, int num_qps)
{
struct hinic_hwif *hwif = func_to_io->hwif;
struct pci_dev *pdev = hwif->pdev;
+ size_t ci_table_size;
int i;
+ ci_table_size = CI_TABLE_SIZE(num_qps);
+
for (i = 0; i < num_qps; i++)
destroy_qp(func_to_io, &func_to_io->qps[i]);
+ dma_free_coherent(&pdev->dev, ci_table_size, func_to_io->ci_addr_base,
+ func_to_io->ci_dma_base);
+
+ devm_kfree(&pdev->dev, func_to_io->sq_db);
+
devm_kfree(&pdev->dev, func_to_io->rq_wq);
devm_kfree(&pdev->dev, func_to_io->sq_wq);
@@ -194,7 +343,19 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io,
return err;
}
+ func_to_io->db_base = pci_ioremap_bar(pdev, HINIC_PCI_DB_BAR);
+ if (!func_to_io->db_base) {
+ dev_err(&pdev->dev, "Failed to remap IO DB area\n");
+ err = -ENOMEM;
+ goto err_db_ioremap;
+ }
+
+ init_db_area_idx(&func_to_io->free_db_area);
return 0;
+
+err_db_ioremap:
+ hinic_wqs_free(&func_to_io->wqs);
+ return err;
}
/**
@@ -203,5 +364,6 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io,
**/
void hinic_io_free(struct hinic_func_to_io *func_to_io)
{
+ iounmap(func_to_io->db_base);
hinic_wqs_free(&func_to_io->wqs);
}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
index 6cacb8e..2d85a38 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
@@ -18,11 +18,30 @@
#include <linux/types.h>
#include <linux/pci.h>
+#include <linux/semaphore.h>
+#include <linux/sizes.h>
#include "hinic_hw_if.h"
#include "hinic_hw_wq.h"
#include "hinic_hw_qp.h"
+#define HINIC_DB_PAGE_SIZE SZ_4K
+#define HINIC_DB_SIZE SZ_4M
+
+#define HINIC_DB_MAX_AREAS (HINIC_DB_SIZE / HINIC_DB_PAGE_SIZE)
+
+struct hinic_free_db_area {
+ int db_idx[HINIC_DB_MAX_AREAS];
+
+ int alloc_pos;
+ int return_pos;
+
+ int num_free;
+
+ /* Lock for getting db area */
+ struct semaphore idx_lock;
+};
+
struct hinic_func_to_io {
struct hinic_hwif *hwif;
@@ -33,6 +52,14 @@ struct hinic_func_to_io {
struct hinic_qp *qps;
u16 max_qps;
+
+ void __iomem **sq_db;
+ void __iomem *db_base;
+
+ void *ci_addr_base;
+ dma_addr_t ci_dma_base;
+
+ struct hinic_free_db_area free_db_area;
};
int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
new file mode 100644
index 0000000..2b77b59
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -0,0 +1,266 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/errno.h>
+#include <linux/sizes.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_wq.h"
+#include "hinic_hw_qp.h"
+
+#define SQ_DB_OFF SZ_2K
+
+/**
+ * alloc_sq_skb_arr - allocate sq array for saved skb
+ * @sq: HW Send Queue
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int alloc_sq_skb_arr(struct hinic_sq *sq)
+{
+ struct hinic_wq *wq = sq->wq;
+ size_t skb_arr_size;
+
+ skb_arr_size = wq->q_depth * sizeof(*sq->saved_skb);
+ sq->saved_skb = vzalloc(skb_arr_size);
+ if (!sq->saved_skb)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * free_sq_skb_arr - free sq array for saved skb
+ * @sq: HW Send Queue
+ **/
+static void free_sq_skb_arr(struct hinic_sq *sq)
+{
+ vfree(sq->saved_skb);
+}
+
+/**
+ * alloc_rq_skb_arr - allocate rq array for saved skb
+ * @rq: HW Receive Queue
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int alloc_rq_skb_arr(struct hinic_rq *rq)
+{
+ struct hinic_wq *wq = rq->wq;
+ size_t skb_arr_size;
+
+ skb_arr_size = wq->q_depth * sizeof(*rq->saved_skb);
+ rq->saved_skb = vzalloc(skb_arr_size);
+ if (!rq->saved_skb)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * free_rq_skb_arr - free rq array for saved skb
+ * @rq: HW Receive Queue
+ **/
+static void free_rq_skb_arr(struct hinic_rq *rq)
+{
+ vfree(rq->saved_skb);
+}
+
+/**
+ * hinic_init_sq - Initialize HW Send Queue
+ * @sq: HW Send Queue
+ * @hwif: HW Interface for accessing HW
+ * @wq: Work Queue for the data of the SQ
+ * @entry: msix entry for sq
+ * @ci_addr: address for reading the current HW consumer index
+ * @ci_dma_addr: dma address for reading the current HW consumer index
+ * @db_base: doorbell base address
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_init_sq(struct hinic_sq *sq, struct hinic_hwif *hwif,
+ struct hinic_wq *wq, struct msix_entry *entry,
+ void *ci_addr, dma_addr_t ci_dma_addr,
+ void __iomem *db_base)
+{
+ sq->hwif = hwif;
+
+ sq->wq = wq;
+
+ sq->irq = entry->vector;
+ sq->msix_entry = entry->entry;
+
+ sq->hw_ci_addr = ci_addr;
+ sq->hw_ci_dma_addr = ci_dma_addr;
+
+ sq->db_base = db_base + SQ_DB_OFF;
+
+ return alloc_sq_skb_arr(sq);
+}
+
+/**
+ * hinic_clean_sq - Clean HW Send Queue's Resources
+ * @sq: Send Queue
+ **/
+void hinic_clean_sq(struct hinic_sq *sq)
+{
+ free_sq_skb_arr(sq);
+}
+
+/**
+ * alloc_rq_cqe - allocate rq completion queue elements
+ * @rq: HW Receive Queue
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int alloc_rq_cqe(struct hinic_rq *rq)
+{
+ struct hinic_hwif *hwif = rq->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ size_t cqe_dma_size, cqe_size;
+ struct hinic_wq *wq = rq->wq;
+ int j, i;
+
+ cqe_size = wq->q_depth * sizeof(*rq->cqe);
+ rq->cqe = vzalloc(cqe_size);
+ if (!rq->cqe)
+ return -ENOMEM;
+
+ cqe_dma_size = wq->q_depth * sizeof(*rq->cqe_dma);
+ rq->cqe_dma = vzalloc(cqe_dma_size);
+ if (!rq->cqe_dma)
+ goto err_cqe_dma_arr_alloc;
+
+ for (i = 0; i < wq->q_depth; i++) {
+ rq->cqe[i] = dma_zalloc_coherent(&pdev->dev,
+ sizeof(*rq->cqe[i]),
+ &rq->cqe_dma[i], GFP_KERNEL);
+ if (!rq->cqe[i])
+ goto err_cqe_alloc;
+ }
+
+ return 0;
+
+err_cqe_alloc:
+ for (j = 0; j < i; j++)
+ dma_free_coherent(&pdev->dev, sizeof(*rq->cqe[j]), rq->cqe[j],
+ rq->cqe_dma[j]);
+
+ vfree(rq->cqe_dma);
+
+err_cqe_dma_arr_alloc:
+ vfree(rq->cqe);
+ return -ENOMEM;
+}
+
+/**
+ * free_rq_cqe - free rq completion queue elements
+ * @rq: HW Receive Queue
+ **/
+static void free_rq_cqe(struct hinic_rq *rq)
+{
+ struct hinic_hwif *hwif = rq->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_wq *wq = rq->wq;
+ int i;
+
+ for (i = 0; i < wq->q_depth; i++)
+ dma_free_coherent(&pdev->dev, sizeof(*rq->cqe[i]), rq->cqe[i],
+ rq->cqe_dma[i]);
+
+ vfree(rq->cqe_dma);
+ vfree(rq->cqe);
+}
+
+/**
+ * hinic_init_rq - Initialize HW Receive Queue
+ * @rq: HW Receive Queue
+ * @hwif: HW Interface for accessing HW
+ * @wq: Work Queue for the data of the RQ
+ * @entry: msix entry for rq
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_init_rq(struct hinic_rq *rq, struct hinic_hwif *hwif,
+ struct hinic_wq *wq, struct msix_entry *entry)
+{
+ struct pci_dev *pdev = hwif->pdev;
+ size_t pi_size;
+ int err;
+
+ rq->hwif = hwif;
+
+ rq->wq = wq;
+
+ rq->irq = entry->vector;
+ rq->msix_entry = entry->entry;
+
+ rq->buf_sz = HINIC_RX_BUF_SZ;
+
+ err = alloc_rq_skb_arr(rq);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to allocate rq priv data\n");
+ return err;
+ }
+
+ err = alloc_rq_cqe(rq);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to allocate rq cqe\n");
+ goto err_alloc_rq_cqe;
+ }
+
+ /* HW requirements: Must be at least 32 bit */
+ pi_size = ALIGN(sizeof(*rq->pi_virt_addr), sizeof(u32));
+ rq->pi_virt_addr = dma_zalloc_coherent(&pdev->dev, pi_size,
+ &rq->pi_dma_addr, GFP_KERNEL);
+ if (!rq->pi_virt_addr) {
+ dev_err(&pdev->dev, "Failed to allocate PI address\n");
+ err = -ENOMEM;
+ goto err_pi_virt;
+ }
+
+ return 0;
+
+err_pi_virt:
+ free_rq_cqe(rq);
+
+err_alloc_rq_cqe:
+ free_rq_skb_arr(rq);
+ return err;
+}
+
+/**
+ * hinic_clean_rq - Clean HW Receive Queue's Resources
+ * @rq: HW Receive Queue
+ **/
+void hinic_clean_rq(struct hinic_rq *rq)
+{
+ struct hinic_hwif *hwif = rq->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ size_t pi_size;
+
+ pi_size = ALIGN(sizeof(*rq->pi_virt_addr), sizeof(u32));
+ dma_free_coherent(&pdev->dev, pi_size, rq->pi_virt_addr,
+ rq->pi_dma_addr);
+
+ free_rq_cqe(rq);
+ free_rq_skb_arr(rq);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index 4031728..c5ec30d 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -18,6 +18,12 @@
#include <linux/types.h>
#include <linux/sizes.h>
+#include <linux/pci.h>
+#include <linux/skbuff.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_wqe.h"
+#include "hinic_hw_wq.h"
#define HINIC_SQ_WQEBB_SIZE 64
#define HINIC_RQ_WQEBB_SIZE 32
@@ -28,12 +34,41 @@
#define HINIC_SQ_DEPTH SZ_4K
#define HINIC_RQ_DEPTH SZ_4K
+#define HINIC_RX_BUF_SZ 2048
+
struct hinic_sq {
- /* should be implemented */
+ struct hinic_hwif *hwif;
+
+ struct hinic_wq *wq;
+
+ u32 irq;
+ u16 msix_entry;
+
+ void *hw_ci_addr;
+ dma_addr_t hw_ci_dma_addr;
+
+ void __iomem *db_base;
+
+ struct sk_buff **saved_skb;
};
struct hinic_rq {
- /* should be implemented */
+ struct hinic_hwif *hwif;
+
+ struct hinic_wq *wq;
+
+ u32 irq;
+ u16 msix_entry;
+
+ size_t buf_sz;
+
+ struct sk_buff **saved_skb;
+
+ struct hinic_rq_cqe **cqe;
+ dma_addr_t *cqe_dma;
+
+ u16 *pi_virt_addr;
+ dma_addr_t pi_dma_addr;
};
struct hinic_qp {
@@ -43,4 +78,15 @@ struct hinic_qp {
u16 q_id;
};
+int hinic_init_sq(struct hinic_sq *sq, struct hinic_hwif *hwif,
+ struct hinic_wq *wq, struct msix_entry *entry, void *ci_addr,
+ dma_addr_t ci_dma_addr, void __iomem *db_base);
+
+void hinic_clean_sq(struct hinic_sq *sq);
+
+int hinic_init_rq(struct hinic_rq *rq, struct hinic_hwif *hwif,
+ struct hinic_wq *wq, struct msix_entry *entry);
+
+void hinic_clean_rq(struct hinic_rq *rq);
+
#endif
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 10/21] net-next/hinic: Add logical Txq and Rxq
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Create the logical queues of the nic.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
drivers/net/ethernet/huawei/hinic/Makefile | 5 +-
drivers/net/ethernet/huawei/hinic/hinic_dev.h | 5 +
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 131 +++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h | 20 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_io.c | 144 +++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_io.h | 46 ++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h | 32 +++++
drivers/net/ethernet/huawei/hinic/hinic_main.c | 172 ++++++++++++++++++++++-
drivers/net/ethernet/huawei/hinic/hinic_rx.c | 72 ++++++++++
drivers/net/ethernet/huawei/hinic/hinic_rx.h | 46 ++++++
drivers/net/ethernet/huawei/hinic/hinic_tx.c | 75 ++++++++++
drivers/net/ethernet/huawei/hinic/hinic_tx.h | 49 +++++++
12 files changed, 793 insertions(+), 4 deletions(-)
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_rx.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_rx.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_tx.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_tx.h
diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
index dbb1b9d..f60c449 100644
--- a/drivers/net/ethernet/huawei/hinic/Makefile
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -1,4 +1,5 @@
obj-$(CONFIG_HINIC) += hinic.o
-hinic-y := hinic_main.o hinic_port.o hinic_hw_dev.o hinic_hw_mgmt.o \
- hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o
+hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \
+ hinic_hw_io.o hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o \
+ hinic_hw_if.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
index 5c5b4e9..5b8231d 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -23,6 +23,8 @@
#include <linux/bitops.h>
#include "hinic_hw_dev.h"
+#include "hinic_tx.h"
+#include "hinic_rx.h"
#define HINIC_DRV_NAME "hinic"
@@ -49,6 +51,9 @@ struct hinic_dev {
struct hinic_rx_mode_work rx_mode_work;
struct workqueue_struct *workq;
+
+ struct hinic_txq *txqs;
+ struct hinic_rxq *rxqs;
};
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 75fd6d2..d113908 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -25,6 +25,8 @@
#include "hinic_hw_if.h"
#include "hinic_hw_eqs.h"
#include "hinic_hw_mgmt.h"
+#include "hinic_hw_qp.h"
+#include "hinic_hw_io.h"
#include "hinic_hw_dev.h"
#define MAX_IRQS(max_qps, num_aeqs, num_ceqs) \
@@ -230,6 +232,99 @@ int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
}
/**
+ * get_base_qpn - get the first qp number
+ * @hwdev: the NIC HW device
+ * @base_qpn: returned qp number
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn)
+{
+ struct hinic_cmd_base_qpn cmd_base_qpn;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ u16 out_size;
+ int err;
+
+ cmd_base_qpn.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
+
+ err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_GLOBAL_QPN,
+ &cmd_base_qpn, sizeof(cmd_base_qpn),
+ &cmd_base_qpn, &out_size);
+ if (err || (out_size != sizeof(cmd_base_qpn)) || cmd_base_qpn.status) {
+ dev_err(&pdev->dev, "Failed to get base qpn, status = %d\n",
+ cmd_base_qpn.status);
+ return -EFAULT;
+ }
+
+ *base_qpn = cmd_base_qpn.qpn;
+ return 0;
+}
+
+/**
+ * hinic_hwdev_ifup - Preparing the HW for passing IO
+ * @hwdev: the NIC HW device
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_hwdev_ifup(struct hinic_hwdev *hwdev)
+{
+ struct hinic_func_to_io *func_to_io = &hwdev->func_to_io;
+ struct hinic_cap *nic_cap = &hwdev->nic_cap;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ int err, num_aeqs, num_ceqs, num_qps;
+ struct msix_entry *sq_msix_entries;
+ struct msix_entry *rq_msix_entries;
+ struct pci_dev *pdev = hwif->pdev;
+ u16 base_qpn;
+
+ err = get_base_qpn(hwdev, &base_qpn);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to get global base qp number\n");
+ return err;
+ }
+
+ num_aeqs = HINIC_HWIF_NUM_AEQS(hwif);
+ num_ceqs = HINIC_HWIF_NUM_CEQS(hwif);
+ err = hinic_io_init(func_to_io, hwif, nic_cap->max_qps, 0, NULL);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to init IO channel\n");
+ return err;
+ }
+
+ num_qps = nic_cap->num_qps;
+ sq_msix_entries = &hwdev->msix_entries[num_aeqs + num_ceqs];
+ rq_msix_entries = &hwdev->msix_entries[num_aeqs + num_ceqs + num_qps];
+
+ err = hinic_io_create_qps(func_to_io, base_qpn, num_qps,
+ sq_msix_entries, rq_msix_entries);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to create QPs\n");
+ goto err_create_qps;
+ }
+
+ return 0;
+
+err_create_qps:
+ hinic_io_free(func_to_io);
+ return err;
+}
+
+/**
+ * hinic_hwdev_ifdown - Closing the HW for passing IO
+ * @hwdev: the NIC HW device
+ *
+ **/
+void hinic_hwdev_ifdown(struct hinic_hwdev *hwdev)
+{
+ struct hinic_func_to_io *func_to_io = &hwdev->func_to_io;
+ struct hinic_cap *nic_cap = &hwdev->nic_cap;
+
+ hinic_io_destroy_qps(func_to_io, nic_cap->num_qps);
+ hinic_io_free(func_to_io);
+}
+
+/**
* hinic_hwdev_cb_register - register callback handler for MGMT events
* @hwdev: the NIC HW device
* @cmd: the mgmt event
@@ -495,3 +590,39 @@ int hinic_hwdev_num_qps(struct hinic_hwdev *hwdev)
return nic_cap->num_qps;
}
+
+/**
+ * hinic_hwdev_get_sq - get SQ
+ * @hwdev: the NIC HW device
+ * @i: the position of the SQ
+ *
+ * Return: the SQ in the i position
+ **/
+struct hinic_sq *hinic_hwdev_get_sq(struct hinic_hwdev *hwdev, int i)
+{
+ struct hinic_func_to_io *func_to_io = &hwdev->func_to_io;
+ struct hinic_qp *qp = &func_to_io->qps[i];
+
+ if (i >= hinic_hwdev_num_qps(hwdev))
+ return NULL;
+
+ return &qp->sq;
+}
+
+/**
+ * hinic_hwdev_get_sq - get RQ
+ * @hwdev: the NIC HW device
+ * @i: the position of the RQ
+ *
+ * Return: the RQ in the i position
+ **/
+struct hinic_rq *hinic_hwdev_get_rq(struct hinic_hwdev *hwdev, int i)
+{
+ struct hinic_func_to_io *func_to_io = &hwdev->func_to_io;
+ struct hinic_qp *qp = &func_to_io->qps[i];
+
+ if (i >= hinic_hwdev_num_qps(hwdev))
+ return NULL;
+
+ return &qp->rq;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index 1cd8159..81c2c6e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -23,6 +23,8 @@
#include "hinic_hw_if.h"
#include "hinic_hw_eqs.h"
#include "hinic_hw_mgmt.h"
+#include "hinic_hw_qp.h"
+#include "hinic_hw_io.h"
#define HINIC_MAX_QPS 32
@@ -72,11 +74,21 @@ enum hinic_cb_state {
HINIC_CB_RUNNING = BIT(1),
};
+struct hinic_cmd_base_qpn {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 func_idx;
+ u16 qpn;
+};
+
struct hinic_hwdev {
struct hinic_hwif *hwif;
struct msix_entry *msix_entries;
struct hinic_aeqs aeqs;
+ struct hinic_func_to_io func_to_io;
struct hinic_cap nic_cap;
};
@@ -111,10 +123,18 @@ int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
void *buf_in, u16 in_size, void *buf_out,
u16 *out_size);
+int hinic_hwdev_ifup(struct hinic_hwdev *hwdev);
+
+void hinic_hwdev_ifdown(struct hinic_hwdev *hwdev);
+
struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev);
void hinic_free_hwdev(struct hinic_hwdev *hwdev);
int hinic_hwdev_num_qps(struct hinic_hwdev *hwdev);
+struct hinic_sq *hinic_hwdev_get_sq(struct hinic_hwdev *hwdev, int i);
+
+struct hinic_rq *hinic_hwdev_get_rq(struct hinic_hwdev *hwdev, int i);
+
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
new file mode 100644
index 0000000..ebe28ee
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
@@ -0,0 +1,144 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_qp.h"
+#include "hinic_hw_io.h"
+
+/**
+ * init_qp - Initialize a Queue Pair
+ * @func_to_io: func to io channel that holds the IO components
+ * @qp: pointer to the qp to initialize
+ * @q_id: the id of the qp
+ * @sq_msix_entry: msix entry for sq
+ * @rq_msix_entry: msix entry for rq
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int init_qp(struct hinic_func_to_io *func_to_io,
+ struct hinic_qp *qp, int q_id,
+ struct msix_entry *sq_msix_entry,
+ struct msix_entry *rq_msix_entry)
+{
+ /* should be implemented */
+ return 0;
+}
+
+/**
+ * destroy_qp - Clean the resources of a Queue Pair
+ * @func_to_io: func to io channel that holds the IO components
+ * @qp: pointer to the qp to clean
+ **/
+static void destroy_qp(struct hinic_func_to_io *func_to_io,
+ struct hinic_qp *qp)
+{
+ /* should be implemented */
+}
+
+/**
+ * hinic_io_create_qps - Create Queue Pairs
+ * @func_to_io: func to io channel that holds the IO components
+ * @base_qpn: base qp number
+ * @num_qps: number queue pairs to create
+ * @sq_msix_entry: msix entries for sq
+ * @rq_msix_entry: msix entries for rq
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
+ u16 base_qpn, int num_qps,
+ struct msix_entry *sq_msix_entries,
+ struct msix_entry *rq_msix_entries)
+{
+ struct hinic_hwif *hwif = func_to_io->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ size_t qps_size;
+ int i, j, err;
+
+ qps_size = num_qps * sizeof(*func_to_io->qps);
+ func_to_io->qps = devm_kzalloc(&pdev->dev, qps_size, GFP_KERNEL);
+ if (!func_to_io->qps)
+ return -ENOMEM;
+
+ for (i = 0; i < num_qps; i++) {
+ err = init_qp(func_to_io, &func_to_io->qps[i], i,
+ &sq_msix_entries[i], &rq_msix_entries[i]);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to create QP %d\n", i);
+ goto err_init_qp;
+ }
+ }
+
+ return 0;
+
+err_init_qp:
+ for (j = 0; j < i; j++)
+ destroy_qp(func_to_io, &func_to_io->qps[j]);
+
+ devm_kfree(&pdev->dev, func_to_io->qps);
+ return err;
+}
+
+/**
+ * hinic_io_destroy_qps - Destroy the IO Queue Pairs
+ * @func_to_io: func to io channel that holds the IO components
+ * @num_qps: number queue pairs to destroy
+ **/
+void hinic_io_destroy_qps(struct hinic_func_to_io *func_to_io, int num_qps)
+{
+ struct hinic_hwif *hwif = func_to_io->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int i;
+
+ for (i = 0; i < num_qps; i++)
+ destroy_qp(func_to_io, &func_to_io->qps[i]);
+
+ devm_kfree(&pdev->dev, func_to_io->qps);
+}
+
+/**
+ * hinic_io_init - Initialize the IO components
+ * @func_to_io: func to io channel that holds the IO components
+ * @hwif: HW interface for accessing IO
+ * @max_qps: maximum QPs in HW
+ * @num_ceqs: number completion event queues
+ * @ceq_msix_entries: msix entries for ceqs
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_io_init(struct hinic_func_to_io *func_to_io,
+ struct hinic_hwif *hwif, u16 max_qps, int num_ceqs,
+ struct msix_entry *ceq_msix_entries)
+{
+ func_to_io->hwif = hwif;
+ func_to_io->qps = NULL;
+ func_to_io->max_qps = max_qps;
+
+ return 0;
+}
+
+/**
+ * hinic_io_free - Free the IO components
+ * @func_to_io: func to io channel that holds the IO components
+ **/
+void hinic_io_free(struct hinic_func_to_io *func_to_io)
+{
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
new file mode 100644
index 0000000..7cdcffd
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
@@ -0,0 +1,46 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_HW_IO_H
+#define HINIC_HW_IO_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_qp.h"
+
+struct hinic_func_to_io {
+ struct hinic_hwif *hwif;
+
+ struct hinic_qp *qps;
+ u16 max_qps;
+};
+
+int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
+ u16 base_qpn, int num_qps,
+ struct msix_entry *sq_msix_entries,
+ struct msix_entry *rq_msix_entries);
+
+void hinic_io_destroy_qps(struct hinic_func_to_io *func_to_io,
+ int num_qps);
+
+int hinic_io_init(struct hinic_func_to_io *func_to_io,
+ struct hinic_hwif *hwif, u16 max_qps, int num_ceqs,
+ struct msix_entry *ceq_msix_entries);
+
+void hinic_io_free(struct hinic_func_to_io *func_to_io);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
new file mode 100644
index 0000000..64330fb
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -0,0 +1,32 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_HW_QP_H
+#define HINIC_HW_QP_H
+
+struct hinic_sq {
+ /* should be implemented */
+};
+
+struct hinic_rq {
+ /* should be implemented */
+};
+
+struct hinic_qp {
+ struct hinic_sq sq;
+ struct hinic_rq rq;
+};
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 3fe8a6f..914ce52 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -31,8 +31,11 @@
#include <linux/delay.h>
#include <linux/err.h>
+#include "hinic_hw_qp.h"
#include "hinic_hw_dev.h"
#include "hinic_port.h"
+#include "hinic_tx.h"
+#include "hinic_rx.h"
#include "hinic_dev.h"
MODULE_AUTHOR("Huawei Technologies CO., Ltd");
@@ -57,17 +60,164 @@
static int change_mac_addr(struct net_device *netdev, const u8 *addr);
+/**
+ * create_txqs - Create the Logical Tx Queues of specific NIC device
+ * @nic_dev: the specific NIC device
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int create_txqs(struct hinic_dev *nic_dev)
+{
+ int err, i, j, num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+ struct net_device *netdev = nic_dev->netdev;
+ size_t txq_size;
+
+ if (nic_dev->txqs)
+ return -EINVAL;
+
+ txq_size = num_txqs * sizeof(*nic_dev->txqs);
+ nic_dev->txqs = devm_kzalloc(&netdev->dev, txq_size, GFP_KERNEL);
+ if (!nic_dev->txqs)
+ return -ENOMEM;
+
+ for (i = 0; i < num_txqs; i++) {
+ struct hinic_sq *sq = hinic_hwdev_get_sq(nic_dev->hwdev, i);
+
+ err = hinic_init_txq(&nic_dev->txqs[i], sq, netdev);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed to init Txq\n");
+ goto err_init_txq;
+ }
+ }
+
+ return 0;
+
+err_init_txq:
+ for (j = 0; j < i; j++)
+ hinic_clean_txq(&nic_dev->txqs[j]);
+
+ devm_kfree(&netdev->dev, nic_dev->txqs);
+ return err;
+}
+
+/**
+ * free_txqs - Free the Logical Tx Queues of specific NIC device
+ * @nic_dev: the specific NIC device
+ **/
+static void free_txqs(struct hinic_dev *nic_dev)
+{
+ int i, num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+ struct net_device *netdev = nic_dev->netdev;
+
+ if (!nic_dev->txqs)
+ return;
+
+ for (i = 0; i < num_txqs; i++)
+ hinic_clean_txq(&nic_dev->txqs[i]);
+
+ devm_kfree(&netdev->dev, nic_dev->txqs);
+ nic_dev->txqs = NULL;
+}
+
+/**
+ * create_txqs - Create the Logical Rx Queues of specific NIC device
+ * @nic_dev: the specific NIC device
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int create_rxqs(struct hinic_dev *nic_dev)
+{
+ int err, i, j, num_rxqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+ struct net_device *netdev = nic_dev->netdev;
+ size_t rxq_size;
+
+ if (nic_dev->rxqs)
+ return -EINVAL;
+
+ rxq_size = num_rxqs * sizeof(*nic_dev->rxqs);
+ nic_dev->rxqs = devm_kzalloc(&netdev->dev, rxq_size, GFP_KERNEL);
+ if (!nic_dev->rxqs)
+ return -ENOMEM;
+
+ for (i = 0; i < num_rxqs; i++) {
+ struct hinic_rq *rq = hinic_hwdev_get_rq(nic_dev->hwdev, i);
+
+ err = hinic_init_rxq(&nic_dev->rxqs[i], rq, netdev);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed to init rxq\n");
+ goto err_init_rxq;
+ }
+ }
+
+ return 0;
+
+err_init_rxq:
+ for (j = 0; j < i; j++)
+ hinic_clean_rxq(&nic_dev->rxqs[j]);
+
+ devm_kfree(&netdev->dev, nic_dev->rxqs);
+ return err;
+}
+
+/**
+ * free_txqs - Free the Logical Rx Queues of specific NIC device
+ * @nic_dev: the specific NIC device
+ **/
+static void free_rxqs(struct hinic_dev *nic_dev)
+{
+ int i, num_rxqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+ struct net_device *netdev = nic_dev->netdev;
+
+ if (!nic_dev->rxqs)
+ return;
+
+ for (i = 0; i < num_rxqs; i++)
+ hinic_clean_rxq(&nic_dev->rxqs[i]);
+
+ devm_kfree(&netdev->dev, nic_dev->rxqs);
+ nic_dev->rxqs = NULL;
+}
+
static int hinic_open(struct net_device *netdev)
{
struct hinic_dev *nic_dev = netdev_priv(netdev);
enum hinic_port_link_state link_state;
- int err, ret;
+ int err, ret, num_qps;
+
+ if (!(nic_dev->flags & HINIC_INTF_UP)) {
+ err = hinic_hwdev_ifup(nic_dev->hwdev);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed - HW interface up\n");
+ return err;
+ }
+ }
+
+ err = create_txqs(nic_dev);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed to create Tx queues\n");
+ goto err_create_txqs;
+ }
+
+ err = create_rxqs(nic_dev);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed to create Rx queues\n");
+ goto err_create_rxqs;
+ }
+
+ num_qps = hinic_hwdev_num_qps(nic_dev->hwdev);
+ netif_set_real_num_tx_queues(netdev, num_qps);
+ netif_set_real_num_rx_queues(netdev, num_qps);
err = hinic_port_set_state(nic_dev, HINIC_PORT_ENABLE);
if (err) {
netif_err(nic_dev, drv, netdev,
"Failed to set port state\n");
- return err;
+ goto err_port_state;
}
/* Wait up to 3 sec between port enable to link state */
@@ -104,6 +254,16 @@ static int hinic_open(struct net_device *netdev)
if (ret)
netif_warn(nic_dev, drv, netdev,
"Failed to revert port state\n");
+
+err_port_state:
+ free_rxqs(nic_dev);
+
+err_create_rxqs:
+ free_txqs(nic_dev);
+
+err_create_txqs:
+ if (!(nic_dev->flags & HINIC_INTF_UP))
+ hinic_hwdev_ifdown(nic_dev->hwdev);
return err;
}
@@ -130,6 +290,12 @@ static int hinic_close(struct net_device *netdev)
return err;
}
+ free_rxqs(nic_dev);
+ free_txqs(nic_dev);
+
+ if (flags & HINIC_INTF_UP)
+ hinic_hwdev_ifdown(nic_dev->hwdev);
+
netif_info(nic_dev, drv, netdev, "HINIC_INTF is DOWN\n");
return 0;
}
@@ -496,6 +662,8 @@ static int nic_dev_init(struct pci_dev *pdev)
nic_dev->hwdev = hwdev;
nic_dev->msg_enable = MSG_ENABLE_DEFAULT;
nic_dev->flags = 0;
+ nic_dev->txqs = NULL;
+ nic_dev->rxqs = NULL;
sema_init(&nic_dev->mgmt_lock, 1);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
new file mode 100644
index 0000000..173fe8b
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -0,0 +1,72 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <linux/u64_stats_sync.h>
+
+#include "hinic_hw_qp.h"
+#include "hinic_rx.h"
+
+/**
+ * hinic_rxq_clean_stats - Clean the statistics of specific queue
+ * @rxq: Logical Rx Queue
+ **/
+void hinic_rxq_clean_stats(struct hinic_rxq *rxq)
+{
+ struct hinic_rxq_stats *rxq_stats = &rxq->rxq_stats;
+
+ u64_stats_update_begin(&rxq_stats->syncp);
+ rxq_stats->pkts = 0;
+ rxq_stats->bytes = 0;
+ u64_stats_update_end(&rxq_stats->syncp);
+}
+
+/**
+ * rxq_stats_init - Initialize the statistics of specific queue
+ * @rxq: Logical Rx Queue
+ **/
+static void rxq_stats_init(struct hinic_rxq *rxq)
+{
+ struct hinic_rxq_stats *rxq_stats = &rxq->rxq_stats;
+
+ u64_stats_init(&rxq_stats->syncp);
+ hinic_rxq_clean_stats(rxq);
+}
+
+/**
+ * hinic_init_rxq - Initialize the Rx Queue
+ * @rxq: Logical Rx Queue
+ * @rq: Hardware Rx Queue to connect the Logical queue with
+ * @netdev: network device to connect the Logical queue with
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq,
+ struct net_device *netdev)
+{
+ rxq->netdev = netdev;
+ rxq->rq = rq;
+
+ rxq_stats_init(rxq);
+ return 0;
+}
+
+/**
+ * hinic_clean_rxq - Clean the Rx Queue
+ * @rxq: Logical Rx Queue
+ **/
+void hinic_clean_rxq(struct hinic_rxq *rxq)
+{
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.h b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
new file mode 100644
index 0000000..fbd0246
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
@@ -0,0 +1,46 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_RX_H
+#define HINIC_RX_H
+
+#include <linux/types.h>
+#include <linux/netdevice.h>
+#include <linux/u64_stats_sync.h>
+
+#include "hinic_hw_qp.h"
+
+struct hinic_rxq_stats {
+ u64 pkts;
+ u64 bytes;
+
+ struct u64_stats_sync syncp;
+};
+
+struct hinic_rxq {
+ struct net_device *netdev;
+ struct hinic_rq *rq;
+
+ struct hinic_rxq_stats rxq_stats;
+};
+
+void hinic_rxq_clean_stats(struct hinic_rxq *rxq);
+
+int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq,
+ struct net_device *netdev);
+
+void hinic_clean_rxq(struct hinic_rxq *rxq);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
new file mode 100644
index 0000000..9c27fb2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -0,0 +1,75 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <linux/u64_stats_sync.h>
+
+#include "hinic_hw_qp.h"
+#include "hinic_tx.h"
+
+/**
+ * hinic_txq_clean_stats - Clean the statistics of specific queue
+ * @txq: Logical Tx Queue
+ **/
+void hinic_txq_clean_stats(struct hinic_txq *txq)
+{
+ struct hinic_txq_stats *txq_stats = &txq->txq_stats;
+
+ u64_stats_update_begin(&txq_stats->syncp);
+ txq_stats->pkts = 0;
+ txq_stats->bytes = 0;
+ txq_stats->tx_busy = 0;
+ txq_stats->tx_wake = 0;
+ txq_stats->tx_dropped = 0;
+ u64_stats_update_end(&txq_stats->syncp);
+}
+
+/**
+ * txq_stats_init - Initialize the statistics of specific queue
+ * @txq: Logical Tx Queue
+ **/
+static void txq_stats_init(struct hinic_txq *txq)
+{
+ struct hinic_txq_stats *txq_stats = &txq->txq_stats;
+
+ u64_stats_init(&txq_stats->syncp);
+ hinic_txq_clean_stats(txq);
+}
+
+/**
+ * hinic_init_txq - Initialize the Tx Queue
+ * @txq: Logical Tx Queue
+ * @sq: Hardware Tx Queue to connect the Logical queue with
+ * @netdev: network device to connect the Logical queue with
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_init_txq(struct hinic_txq *txq, struct hinic_sq *sq,
+ struct net_device *netdev)
+{
+ txq->netdev = netdev;
+ txq->sq = sq;
+
+ txq_stats_init(txq);
+ return 0;
+}
+
+/**
+ * hinic_clean_txq - Clean the Tx Queue
+ * @txq: Logical Tx Queue
+ **/
+void hinic_clean_txq(struct hinic_txq *txq)
+{
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.h b/drivers/net/ethernet/huawei/hinic/hinic_tx.h
new file mode 100644
index 0000000..bbdb4b6
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.h
@@ -0,0 +1,49 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_TX_H
+#define HINIC_TX_H
+
+#include <linux/types.h>
+#include <linux/netdevice.h>
+#include <linux/u64_stats_sync.h>
+
+#include "hinic_hw_qp.h"
+
+struct hinic_txq_stats {
+ u64 pkts;
+ u64 bytes;
+ u64 tx_busy;
+ u64 tx_wake;
+ u64 tx_dropped;
+
+ struct u64_stats_sync syncp;
+};
+
+struct hinic_txq {
+ struct net_device *netdev;
+ struct hinic_sq *sq;
+
+ struct hinic_txq_stats txq_stats;
+};
+
+void hinic_txq_clean_stats(struct hinic_txq *txq);
+
+int hinic_init_txq(struct hinic_txq *txq, struct hinic_sq *sq,
+ struct net_device *netdev);
+
+void hinic_clean_txq(struct hinic_txq *txq);
+
+#endif
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 09/21] net-next/hinic: Add Rx mode and link event handler
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Add port management message for setting Rx mode in the card,
used for rx_mode netdev operation.
The link event handler is used for getting a notification about the
link state.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
drivers/net/ethernet/huawei/hinic/hinic_dev.h | 17 ++
drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h | 2 +
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 118 +++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h | 37 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.c | 17 ++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 17 ++
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 64 ++++-
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h | 28 +++
drivers/net/ethernet/huawei/hinic/hinic_main.c | 284 ++++++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_port.c | 92 +++++++
drivers/net/ethernet/huawei/hinic/hinic_port.h | 66 +++++
11 files changed, 741 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
index e54a45c..5c5b4e9 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -19,19 +19,36 @@
#include <linux/netdevice.h>
#include <linux/types.h>
#include <linux/semaphore.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
#include "hinic_hw_dev.h"
#define HINIC_DRV_NAME "hinic"
+enum hinic_flags {
+ HINIC_LINK_UP = BIT(0),
+ HINIC_INTF_UP = BIT(1),
+};
+
+struct hinic_rx_mode_work {
+ struct work_struct work;
+ u32 rx_mode;
+};
+
struct hinic_dev {
struct net_device *netdev;
struct hinic_hwdev *hwdev;
u32 msg_enable;
+ unsigned int flags;
+
struct semaphore mgmt_lock;
unsigned long *vlan_bitmap;
+
+ struct hinic_rx_mode_work rx_mode_work;
+ struct workqueue_struct *workq;
};
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
index 52eb89c..1f57301 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
@@ -20,6 +20,8 @@
#define HINIC_CSR_FUNC_ATTR0_ADDR 0x0
#define HINIC_CSR_FUNC_ATTR1_ADDR 0x4
+#define HINIC_CSR_FUNC_ATTR5_ADDR 0x14
+
#define HINIC_DMA_ATTR_BASE 0xC80
#define HINIC_ELECTION_BASE 0x4200
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 6bb6c33..75fd6d2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -230,6 +230,114 @@ int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
}
/**
+ * hinic_hwdev_cb_register - register callback handler for MGMT events
+ * @hwdev: the NIC HW device
+ * @cmd: the mgmt event
+ * @handle: private data for the handler
+ * @handler: event handler
+ **/
+void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev,
+ enum hinic_mgmt_msg_cmd cmd, void *handle,
+ void (*handler)(void *handle, void *buf_in,
+ u16 in_size, void *buf_out,
+ u16 *out_size))
+{
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_pfhwdev *pfhwdev;
+ struct hinic_nic_cb *nic_cb;
+ u8 cmd_cb;
+
+ if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
+ dev_err(&pdev->dev, "unsupported PCI Function type\n");
+ return;
+ }
+
+ pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+ cmd_cb = cmd - HINIC_MGMT_MSG_CMD_BASE;
+ nic_cb = &pfhwdev->nic_cb[cmd_cb];
+
+ nic_cb->handler = handler;
+ nic_cb->handle = handle;
+ nic_cb->cb_state = HINIC_CB_ENABLED;
+}
+
+/**
+ * hinic_hwdev_cb_unregister - unregister callback handler for MGMT events
+ * @hwdev: the NIC HW device
+ * @cmd: the mgmt event
+ **/
+void hinic_hwdev_cb_unregister(struct hinic_hwdev *hwdev,
+ enum hinic_mgmt_msg_cmd cmd)
+{
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_pfhwdev *pfhwdev;
+ struct hinic_nic_cb *nic_cb;
+ u8 cmd_cb;
+
+ if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
+ dev_err(&pdev->dev, "unsupported PCI Function type\n");
+ return;
+ }
+
+ pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+ cmd_cb = cmd - HINIC_MGMT_MSG_CMD_BASE;
+ nic_cb = &pfhwdev->nic_cb[cmd_cb];
+
+ nic_cb->cb_state &= ~HINIC_CB_ENABLED;
+
+ while (nic_cb->cb_state & HINIC_CB_RUNNING)
+ schedule();
+
+ nic_cb->handler = NULL;
+}
+
+/**
+ * nic_mgmt_msg_handler - nic mgmt event handler
+ * @handle: private data for the handler
+ * @buf_in: input buffer
+ * @in_size: input size
+ * @buf_out: output buffer
+ * @out_size: returned output size
+ **/
+static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in,
+ u16 in_size, void *buf_out, u16 *out_size)
+{
+ struct hinic_pfhwdev *pfhwdev = (struct hinic_pfhwdev *)handle;
+ struct hinic_hwdev *hwdev = &pfhwdev->hwdev;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_nic_cb *nic_cb;
+ enum hinic_cb_state cb_state;
+ u8 cmd_cb;
+
+ if ((cmd < HINIC_MGMT_MSG_CMD_BASE) ||
+ (cmd >= HINIC_MGMT_MSG_CMD_MAX)) {
+ dev_err(&pdev->dev, "unknown L2NIC event, cmd = %d\n", cmd);
+ return;
+ }
+
+ cmd_cb = (enum hinic_mgmt_msg_cmd)cmd - HINIC_MGMT_MSG_CMD_BASE;
+
+ nic_cb = &pfhwdev->nic_cb[cmd_cb];
+
+ cb_state = cmpxchg(&nic_cb->cb_state,
+ HINIC_CB_ENABLED,
+ HINIC_CB_ENABLED | HINIC_CB_RUNNING);
+
+ if ((cb_state == HINIC_CB_ENABLED) && (nic_cb->handler))
+ nic_cb->handler(nic_cb->handle, buf_in,
+ in_size, buf_out, out_size);
+ else
+ dev_err(&pdev->dev, "Unhandled NIC Event %d\n", cmd);
+
+ nic_cb->cb_state &= ~HINIC_CB_RUNNING;
+}
+
+/**
* init_pfhwdev - Initialize the extended components of PF
* @pfhwdev: the HW device for PF
*
@@ -248,6 +356,10 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev)
return err;
}
+ hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC,
+ pfhwdev, nic_mgmt_msg_handler);
+
+ hinic_set_pf_action(hwif, HINIC_PF_MGMT_ACTIVE);
return 0;
}
@@ -257,6 +369,12 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev)
**/
static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev)
{
+ struct hinic_hwdev *hwdev = &pfhwdev->hwdev;
+
+ hinic_set_pf_action(hwdev->hwif, HINIC_PF_MGMT_INIT);
+
+ hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC);
+
hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt);
}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index ee9e76a..1cd8159 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -18,6 +18,7 @@
#include <linux/pci.h>
#include <linux/types.h>
+#include <linux/bitops.h>
#include "hinic_hw_if.h"
#include "hinic_hw_eqs.h"
@@ -25,6 +26,9 @@
#define HINIC_MAX_QPS 32
+#define HINIC_MGMT_NUM_MSG_CMD (HINIC_MGMT_MSG_CMD_MAX - \
+ HINIC_MGMT_MSG_CMD_BASE)
+
struct hinic_cap {
u16 max_qps;
u16 num_qps;
@@ -55,6 +59,19 @@ enum hinic_port_cmd {
HINIC_PORT_CMD_GET_CAP = 170,
};
+enum hinic_mgmt_msg_cmd {
+ HINIC_MGMT_MSG_CMD_BASE = 160,
+
+ HINIC_MGMT_MSG_CMD_LINK_STATUS = 160,
+
+ HINIC_MGMT_MSG_CMD_MAX,
+};
+
+enum hinic_cb_state {
+ HINIC_CB_ENABLED = BIT(0),
+ HINIC_CB_RUNNING = BIT(1),
+};
+
struct hinic_hwdev {
struct hinic_hwif *hwif;
struct msix_entry *msix_entries;
@@ -64,12 +81,32 @@ struct hinic_hwdev {
struct hinic_cap nic_cap;
};
+struct hinic_nic_cb {
+ void (*handler)(void *handle, void *buf_in,
+ u16 in_size, void *buf_out,
+ u16 *out_size);
+
+ void *handle;
+ unsigned long cb_state;
+};
+
struct hinic_pfhwdev {
struct hinic_hwdev hwdev;
struct hinic_pf_to_mgmt pf_to_mgmt;
+
+ struct hinic_nic_cb nic_cb[HINIC_MGMT_NUM_MSG_CMD];
};
+void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev,
+ enum hinic_mgmt_msg_cmd cmd, void *handle,
+ void (*handler)(void *handle, void *buf_in,
+ u16 in_size, void *buf_out,
+ u16 *out_size));
+
+void hinic_hwdev_cb_unregister(struct hinic_hwdev *hwdev,
+ enum hinic_mgmt_msg_cmd cmd);
+
int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
void *buf_in, u16 in_size, void *buf_out,
u16 *out_size);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index 2b9410c..d4e6ec4 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -117,6 +117,23 @@ int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index)
}
/**
+ * hinic_set_pf_action - set action on pf channel
+ * @hwif: the HW interface of a pci function device
+ * @action: action on pf channel
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action)
+{
+ u32 attr5 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR);
+
+ attr5 = HINIC_FA5_CLEAR(attr5, PF_ACTION);
+ attr5 |= HINIC_FA5_SET(action, PF_ACTION);
+
+ hinic_hwif_write_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR, attr5);
+}
+
+/**
* hwif_ready - test if the HW is ready for use
* @hwif: the HW interface of a pci function device
*
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 707a046..2280698 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -73,6 +73,15 @@
#define HINIC_FA1_GET(val, member) \
(((val) >> HINIC_FA1_##member##_SHIFT) & HINIC_FA1_##member##_MASK)
+#define HINIC_FA5_PF_ACTION_SHIFT 0
+#define HINIC_FA5_PF_ACTION_MASK 0xFFFF
+
+#define HINIC_FA5_SET(val, member) \
+ (((u32)(val) & HINIC_FA5_##member##_MASK) << HINIC_FA5_##member##_SHIFT)
+
+#define HINIC_FA5_CLEAR(val, member) \
+ ((val) & (~(HINIC_FA5_##member##_MASK << HINIC_FA5_##member##_SHIFT)))
+
#define HINIC_PPF_ELECTION_IDX_SHIFT 0
#define HINIC_PPF_ELECTION_IDX_MASK 0x1F
@@ -166,6 +175,12 @@ enum hinic_node_id {
HINIC_NODE_ID_MGMT = 21,
};
+enum hinic_pf_action {
+ HINIC_PF_MGMT_INIT = 0x0,
+
+ HINIC_PF_MGMT_ACTIVE = 0x11,
+};
+
struct hinic_func_attr {
u16 func_idx;
u8 pf_idx;
@@ -212,6 +227,8 @@ int hinic_msix_attr_get(struct hinic_hwif *hwif, u16 msix_index,
int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index);
+void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action);
+
int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev);
void hinic_free_hwif(struct hinic_hwif *hwif);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 147c404..434e134 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -73,6 +73,46 @@ enum msg_ack_type {
};
/**
+ * hinic_register_mgmt_msg_cb - register msg handler for a msg from a module
+ * @pf_to_mgmt: PF to MGMT channel
+ * @mod: module in the chip that this handler will handle its messages
+ * @handle: private data for the callback
+ * @callback: the handler that will handle messages
+ **/
+void hinic_register_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ enum hinic_mod_type mod,
+ void *handle,
+ void (*callback)(void *handle,
+ u8 cmd, void *buf_in,
+ u16 in_size, void *buf_out,
+ u16 *out_size))
+{
+ struct hinic_mgmt_cb *mgmt_cb = &pf_to_mgmt->mgmt_cb[mod];
+
+ mgmt_cb->cb = callback;
+ mgmt_cb->handle = handle;
+ mgmt_cb->state = HINIC_MGMT_CB_ENABLED;
+}
+
+/**
+ * hinic_unregister_mgmt_msg_cb - unregister msg handler for a msg from a module
+ * @pf_to_mgmt: PF to MGMT channel
+ * @mod: module in the chip that this handler handles its messages
+ **/
+void hinic_unregister_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ enum hinic_mod_type mod)
+{
+ struct hinic_mgmt_cb *mgmt_cb = &pf_to_mgmt->mgmt_cb[mod];
+
+ mgmt_cb->state &= ~HINIC_MGMT_CB_ENABLED;
+
+ while (mgmt_cb->state & HINIC_MGMT_CB_RUNNING)
+ schedule();
+
+ mgmt_cb->cb = NULL;
+}
+
+/**
* prepare_header - prepare the header of the message
* @pf_to_mgmt: PF to MGMT channel
* @msg_len: the length of the message
@@ -337,9 +377,31 @@ static void mgmt_recv_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt,
struct hinic_hwif *hwif = pf_to_mgmt->hwif;
struct pci_dev *pdev = hwif->pdev;
u8 *buf_out = recv_msg->buf_out;
+ struct hinic_mgmt_cb *mgmt_cb;
+ unsigned long cb_state;
u16 out_size = 0;
- dev_err(&pdev->dev, "No MGMT msg handler, mod = %d\n", recv_msg->mod);
+ if (recv_msg->mod >= HINIC_MOD_MAX) {
+ dev_err(&pdev->dev, "Unknown MGMT MSG module = %d\n",
+ recv_msg->mod);
+ return;
+ }
+
+ mgmt_cb = &pf_to_mgmt->mgmt_cb[recv_msg->mod];
+
+ cb_state = cmpxchg(&mgmt_cb->state,
+ HINIC_MGMT_CB_ENABLED,
+ HINIC_MGMT_CB_ENABLED | HINIC_MGMT_CB_RUNNING);
+
+ if ((cb_state == HINIC_MGMT_CB_ENABLED) && (mgmt_cb->cb))
+ mgmt_cb->cb(mgmt_cb->handle, recv_msg->cmd,
+ recv_msg->msg, recv_msg->msg_len,
+ buf_out, &out_size);
+ else
+ dev_err(&pdev->dev, "No MGMT msg handler, mod = %d\n",
+ recv_msg->mod);
+
+ mgmt_cb->state &= ~HINIC_MGMT_CB_RUNNING;
if (!recv_msg->async_mgmt_to_pf)
/* MGMT sent sync msg, send the response */
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
index eca7ad8..8021406 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
@@ -19,6 +19,7 @@
#include <linux/types.h>
#include <linux/semaphore.h>
#include <linux/completion.h>
+#include <linux/bitops.h>
#include "hinic_hw_if.h"
#include "hinic_hw_api_cmd.h"
@@ -67,6 +68,11 @@ enum hinic_cfg_cmd {
HINIC_CFG_NIC_CAP = 0,
};
+enum hinic_mgmt_cb_state {
+ HINIC_MGMT_CB_ENABLED = BIT(0),
+ HINIC_MGMT_CB_RUNNING = BIT(1),
+};
+
struct hinic_recv_msg {
u8 *msg;
u8 *buf_out;
@@ -81,6 +87,15 @@ struct hinic_recv_msg {
u16 msg_id;
};
+struct hinic_mgmt_cb {
+ void (*cb)(void *handle, u8 cmd,
+ void *buf_in, u16 in_size,
+ void *buf_out, u16 *out_size);
+
+ void *handle;
+ unsigned long state;
+};
+
struct hinic_pf_to_mgmt {
struct hinic_hwif *hwif;
@@ -92,8 +107,21 @@ struct hinic_pf_to_mgmt {
struct hinic_recv_msg recv_msg_from_mgmt;
struct hinic_api_cmd_chain *cmd_chain[HINIC_API_CMD_MAX];
+
+ struct hinic_mgmt_cb mgmt_cb[HINIC_MOD_MAX];
};
+void hinic_register_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ enum hinic_mod_type mod,
+ void *handle,
+ void (*callback)(void *handle,
+ u8 cmd, void *buf_in,
+ u16 in_size, void *buf_out,
+ u16 *out_size));
+
+void hinic_unregister_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ enum hinic_mod_type mod);
+
int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
enum hinic_mod_type mod, u8 cmd,
void *buf_in, u16 in_size, void *buf_out, u16 *out_size,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index f46c2bc..3fe8a6f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -24,9 +24,11 @@
#include <linux/slab.h>
#include <linux/if_vlan.h>
#include <linux/semaphore.h>
+#include <linux/workqueue.h>
#include <net/ip.h>
#include <linux/bitops.h>
#include <linux/bitmap.h>
+#include <linux/delay.h>
#include <linux/err.h>
#include "hinic_hw_dev.h"
@@ -39,12 +41,99 @@
#define PCI_DEVICE_ID_HI1822_PF 0x1822
+#define HINIC_WQ_NAME "hinic_dev"
+
#define MSG_ENABLE_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \
NETIF_MSG_IFUP | \
NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR)
#define VLAN_BITMAP_SIZE(nic_dev) (ALIGN(VLAN_N_VID, 8) / 8)
+#define work_to_rx_mode_work(work) \
+ container_of(work, struct hinic_rx_mode_work, work)
+
+#define rx_mode_work_to_nic_dev(rx_mode_work) \
+ container_of(rx_mode_work, struct hinic_dev, rx_mode_work)
+
+static int change_mac_addr(struct net_device *netdev, const u8 *addr);
+
+static int hinic_open(struct net_device *netdev)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ enum hinic_port_link_state link_state;
+ int err, ret;
+
+ err = hinic_port_set_state(nic_dev, HINIC_PORT_ENABLE);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed to set port state\n");
+ return err;
+ }
+
+ /* Wait up to 3 sec between port enable to link state */
+ msleep(3000);
+
+ down(&nic_dev->mgmt_lock);
+
+ err = hinic_port_link_state(nic_dev, &link_state);
+ if (err) {
+ netif_err(nic_dev, drv, netdev, "Failed to get link state\n");
+ goto err_port_link;
+ }
+
+ if (link_state == HINIC_LINK_STATE_UP)
+ nic_dev->flags |= HINIC_LINK_UP;
+
+ nic_dev->flags |= HINIC_INTF_UP;
+
+ if ((nic_dev->flags & (HINIC_LINK_UP | HINIC_INTF_UP)) ==
+ (HINIC_LINK_UP | HINIC_INTF_UP)) {
+ netif_info(nic_dev, drv, netdev, "link + intf UP\n");
+ netif_carrier_on(netdev);
+ netif_tx_wake_all_queues(netdev);
+ }
+
+ up(&nic_dev->mgmt_lock);
+
+ netif_info(nic_dev, drv, netdev, "HINIC_INTF is UP\n");
+ return 0;
+
+err_port_link:
+ up(&nic_dev->mgmt_lock);
+ ret = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
+ if (ret)
+ netif_warn(nic_dev, drv, netdev,
+ "Failed to revert port state\n");
+ return err;
+}
+
+static int hinic_close(struct net_device *netdev)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ unsigned int flags;
+ int err;
+
+ down(&nic_dev->mgmt_lock);
+
+ flags = nic_dev->flags;
+ nic_dev->flags &= ~HINIC_INTF_UP;
+
+ netif_carrier_off(netdev);
+ netif_tx_disable(netdev);
+
+ up(&nic_dev->mgmt_lock);
+
+ err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
+ if (err) {
+ netif_err(nic_dev, drv, netdev, "Failed to set port state\n");
+ nic_dev->flags |= (flags & HINIC_INTF_UP);
+ return err;
+ }
+
+ netif_info(nic_dev, drv, netdev, "HINIC_INTF is DOWN\n");
+ return 0;
+}
+
static int hinic_change_mtu(struct net_device *netdev, int new_mtu)
{
struct hinic_dev *nic_dev = netdev_priv(netdev);
@@ -118,6 +207,77 @@ static int hinic_set_mac_addr(struct net_device *netdev, void *addr)
return err;
}
+/**
+ * add_mac_addr - add mac address to network device
+ * @netdev: network device
+ * @addr: mac address to add
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int add_mac_addr(struct net_device *netdev, const u8 *addr)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ u16 vid = 0;
+ int err;
+
+ if (!is_valid_ether_addr(addr))
+ return -EADDRNOTAVAIL;
+
+ netif_info(nic_dev, drv, netdev, "set mac addr = %02x %02x %02x %02x %02x %02x\n",
+ addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
+
+ down(&nic_dev->mgmt_lock);
+
+ do {
+ err = hinic_port_add_mac(nic_dev, addr, vid);
+ if (err) {
+ netif_err(nic_dev, drv, netdev, "Failed to add mac\n");
+ break;
+ }
+
+ vid = find_next_bit(nic_dev->vlan_bitmap, VLAN_N_VID, vid + 1);
+ } while (vid != VLAN_N_VID);
+
+ up(&nic_dev->mgmt_lock);
+ return err;
+}
+
+/**
+ * remove_mac_addr - remove mac address from network device
+ * @netdev: network device
+ * @addr: mac address to remove
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int remove_mac_addr(struct net_device *netdev, const u8 *addr)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ u16 vid = 0;
+ int err;
+
+ if (!is_valid_ether_addr(addr))
+ return -EADDRNOTAVAIL;
+
+ netif_info(nic_dev, drv, netdev, "remove mac addr = %02x %02x %02x %02x %02x %02x\n",
+ addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
+
+ down(&nic_dev->mgmt_lock);
+
+ do {
+ err = hinic_port_del_mac(nic_dev, addr, vid);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed to delete mac\n");
+ break;
+ }
+
+ vid = find_next_bit(nic_dev->vlan_bitmap, VLAN_N_VID, vid + 1);
+ } while (vid != VLAN_N_VID);
+
+ up(&nic_dev->mgmt_lock);
+ return err;
+}
+
static int hinic_vlan_rx_add_vid(struct net_device *netdev,
__always_unused __be16 proto, u16 vid)
{
@@ -182,12 +342,56 @@ static int hinic_vlan_rx_kill_vid(struct net_device *netdev,
return err;
}
+static void set_rx_mode(struct work_struct *work)
+{
+ struct hinic_rx_mode_work *rx_mode_work = work_to_rx_mode_work(work);
+ struct hinic_dev *nic_dev = rx_mode_work_to_nic_dev(rx_mode_work);
+
+ netif_info(nic_dev, drv, nic_dev->netdev, "set rx mode work\n");
+
+ hinic_port_set_rx_mode(nic_dev, rx_mode_work->rx_mode);
+
+ __dev_uc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
+ __dev_mc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
+}
+
+static void hinic_set_rx_mode(struct net_device *netdev)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ struct hinic_rx_mode_work *rx_mode_work;
+ u32 rx_mode;
+
+ rx_mode_work = &nic_dev->rx_mode_work;
+
+ rx_mode = HINIC_RX_MODE_UC |
+ HINIC_RX_MODE_MC |
+ HINIC_RX_MODE_BC;
+
+ if (netdev->flags & IFF_PROMISC)
+ rx_mode |= HINIC_RX_MODE_PROMISC;
+ else if (netdev->flags & IFF_ALLMULTI)
+ rx_mode |= HINIC_RX_MODE_MC_ALL;
+
+ rx_mode_work->rx_mode = rx_mode;
+
+ queue_work(nic_dev->workq, &rx_mode_work->work);
+}
+
+netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+{
+ return NETDEV_TX_BUSY;
+}
+
static const struct net_device_ops hinic_netdev_ops = {
+ .ndo_open = hinic_open,
+ .ndo_stop = hinic_close,
.ndo_change_mtu = hinic_change_mtu,
.ndo_set_mac_address = hinic_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_vlan_rx_add_vid = hinic_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = hinic_vlan_rx_kill_vid,
+ .ndo_set_rx_mode = hinic_set_rx_mode,
+ .ndo_start_xmit = hinic_xmit_frame,
/* more operations should be filled */
};
@@ -201,6 +405,57 @@ static void netdev_features_init(struct net_device *netdev)
}
/**
+ * link_status_event_handler - link event handler
+ * @handle: nic device for the handler
+ * @buf_in: input buffer
+ * @in_size: input size
+ * @buf_in: output buffer
+ * @out_size: returned output size
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static void link_status_event_handler(void *handle, void *buf_in, u16 in_size,
+ void *buf_out, u16 *out_size)
+{
+ struct hinic_port_link_status *link_status, *ret_link_status;
+ struct hinic_dev *nic_dev = (struct hinic_dev *)handle;
+
+ link_status = buf_in;
+
+ if (link_status->link == HINIC_LINK_STATE_UP) {
+ down(&nic_dev->mgmt_lock);
+
+ nic_dev->flags |= HINIC_LINK_UP;
+
+ if ((nic_dev->flags & (HINIC_LINK_UP | HINIC_INTF_UP)) ==
+ (HINIC_LINK_UP | HINIC_INTF_UP)) {
+ netif_carrier_on(nic_dev->netdev);
+ netif_tx_wake_all_queues(nic_dev->netdev);
+ }
+
+ up(&nic_dev->mgmt_lock);
+
+ netif_info(nic_dev, drv, nic_dev->netdev, "HINIC_Link is UP\n");
+ } else {
+ down(&nic_dev->mgmt_lock);
+
+ nic_dev->flags &= ~HINIC_LINK_UP;
+
+ netif_carrier_off(nic_dev->netdev);
+ netif_tx_disable(nic_dev->netdev);
+
+ up(&nic_dev->mgmt_lock);
+
+ netif_info(nic_dev, drv, nic_dev->netdev, "HINIC_Link is DOWN\n");
+ }
+
+ ret_link_status = buf_out;
+ ret_link_status->status = 0;
+
+ *out_size = sizeof(*ret_link_status);
+}
+
+/**
* nic_dev_init - Initialize the NIC device
* @pdev: the NIC pci device
*
@@ -208,6 +463,7 @@ static void netdev_features_init(struct net_device *netdev)
**/
static int nic_dev_init(struct pci_dev *pdev)
{
+ struct hinic_rx_mode_work *rx_mode_work;
struct hinic_dev *nic_dev;
struct net_device *netdev;
struct hinic_hwdev *hwdev;
@@ -239,6 +495,7 @@ static int nic_dev_init(struct pci_dev *pdev)
nic_dev->netdev = netdev;
nic_dev->hwdev = hwdev;
nic_dev->msg_enable = MSG_ENABLE_DEFAULT;
+ nic_dev->flags = 0;
sema_init(&nic_dev->mgmt_lock, 1);
@@ -250,6 +507,12 @@ static int nic_dev_init(struct pci_dev *pdev)
goto err_vlan_bitmap;
}
+ nic_dev->workq = create_singlethread_workqueue(HINIC_WQ_NAME);
+ if (!nic_dev->workq) {
+ err = -ENOMEM;
+ goto err_workq;
+ }
+
pci_set_drvdata(pdev, netdev);
err = hinic_port_get_mac(nic_dev, netdev->dev_addr);
@@ -268,10 +531,16 @@ static int nic_dev_init(struct pci_dev *pdev)
goto err_set_mtu;
}
+ rx_mode_work = &nic_dev->rx_mode_work;
+ INIT_WORK(&rx_mode_work->work, set_rx_mode);
+
netdev_features_init(netdev);
netif_carrier_off(netdev);
+ hinic_hwdev_cb_register(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS,
+ nic_dev, link_status_event_handler);
+
err = register_netdev(netdev);
if (err) {
dev_err(&pdev->dev, "Failed to register netdev\n");
@@ -281,10 +550,16 @@ static int nic_dev_init(struct pci_dev *pdev)
return 0;
err_reg_netdev:
+ hinic_hwdev_cb_unregister(nic_dev->hwdev,
+ HINIC_MGMT_MSG_CMD_LINK_STATUS);
+ cancel_work_sync(&rx_mode_work->work);
+
err_set_mtu:
err_add_mac:
pci_set_drvdata(pdev, NULL);
+ destroy_workqueue(nic_dev->workq);
+err_workq:
err_vlan_bitmap:
free_netdev(netdev);
@@ -357,11 +632,20 @@ static void hinic_remove(struct pci_dev *pdev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct hinic_dev *nic_dev = netdev_priv(netdev);
+ struct hinic_rx_mode_work *rx_mode_work;
unregister_netdev(netdev);
+ hinic_hwdev_cb_unregister(nic_dev->hwdev,
+ HINIC_MGMT_MSG_CMD_LINK_STATUS);
+
+ rx_mode_work = &nic_dev->rx_mode_work;
+ cancel_work_sync(&rx_mode_work->work);
+
pci_set_drvdata(pdev, NULL);
+ destroy_workqueue(nic_dev->workq);
+
hinic_free_hwdev(nic_dev->hwdev);
free_netdev(netdev);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 5b249e8..0dafede 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -222,3 +222,95 @@ int hinic_port_del_vlan(struct hinic_dev *nic_dev, u16 vlan_id)
&port_vlan_cmd, sizeof(port_vlan_cmd),
NULL, NULL);
}
+
+/**
+ * hinic_port_set_rx_mode - set rx mode in the nic device
+ * @nic_dev: nic device
+ * @rx_mode: the rx mode to set
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_set_rx_mode(struct hinic_dev *nic_dev, u32 rx_mode)
+{
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_port_rx_mode_cmd rx_mode_cmd;
+
+ rx_mode_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+ rx_mode_cmd.rx_mode = rx_mode;
+
+ return hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RX_MODE,
+ &rx_mode_cmd, sizeof(rx_mode_cmd),
+ NULL, NULL);
+}
+
+/**
+ * hinic_port_link_state - get the link state
+ * @nic_dev: nic device
+ * @link_state: the returned link state
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_link_state(struct hinic_dev *nic_dev,
+ enum hinic_port_link_state *link_state)
+{
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct hinic_port_link_cmd link_cmd;
+ struct pci_dev *pdev = hwif->pdev;
+ u16 out_size;
+ int err;
+
+ if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
+ dev_err(&pdev->dev, "unsupported PCI Function type\n");
+ return -EINVAL;
+ }
+
+ link_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
+
+ err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_LINK_STATE,
+ &link_cmd, sizeof(link_cmd),
+ &link_cmd, &out_size);
+ if (err || (out_size != sizeof(link_cmd)) || link_cmd.status) {
+ dev_err(&pdev->dev, "Failed to get link state, ret = %d\n",
+ link_cmd.status);
+ return -EINVAL;
+ }
+
+ *link_state = link_cmd.state;
+ return 0;
+}
+
+/**
+ * hinic_port_set_state - set port state
+ * @nic_dev: nic device
+ * @state: the state to set
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state)
+{
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_port_state_cmd port_state;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ u16 out_size;
+ int err;
+
+ if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
+ dev_err(&pdev->dev, "unsupported PCI Function type\n");
+ return -EINVAL;
+ }
+
+ port_state.state = state;
+
+ err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_PORT_STATE,
+ &port_state, sizeof(port_state),
+ &port_state, &out_size);
+ if (err || (out_size != sizeof(port_state)) || port_state.status) {
+ dev_err(&pdev->dev, "Failed to set port state, ret = %d\n",
+ port_state.status);
+ return -EFAULT;
+ }
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index 4cafb94..3a8da8e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -18,9 +18,28 @@
#include <linux/types.h>
#include <linux/etherdevice.h>
+#include <linux/bitops.h>
#include "hinic_dev.h"
+enum hinic_rx_mode {
+ HINIC_RX_MODE_UC = BIT(0),
+ HINIC_RX_MODE_MC = BIT(1),
+ HINIC_RX_MODE_BC = BIT(2),
+ HINIC_RX_MODE_MC_ALL = BIT(3),
+ HINIC_RX_MODE_PROMISC = BIT(4),
+};
+
+enum hinic_port_link_state {
+ HINIC_LINK_STATE_DOWN,
+ HINIC_LINK_STATE_UP,
+};
+
+enum hinic_port_state {
+ HINIC_PORT_DISABLE = 0,
+ HINIC_PORT_ENABLE = 3,
+};
+
struct hinic_port_mac_cmd {
u8 status;
u8 version;
@@ -51,6 +70,45 @@ struct hinic_port_vlan_cmd {
u16 vlan_id;
};
+struct hinic_port_rx_mode_cmd {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 func_idx;
+ u16 rsvd;
+ u32 rx_mode;
+};
+
+struct hinic_port_link_cmd {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 func_idx;
+ u8 state;
+ u8 rsvd1;
+};
+
+struct hinic_port_state_cmd {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u8 state;
+ u8 rsvd1[3];
+};
+
+struct hinic_port_link_status {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 rsvd1;
+ u8 link;
+ u8 rsvd2;
+};
+
int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
u16 vlan_id);
@@ -65,4 +123,12 @@ int hinic_port_del_mac(struct hinic_dev *nic_dev, const u8 *addr,
int hinic_port_del_vlan(struct hinic_dev *nic_dev, u16 vlan_id);
+int hinic_port_set_rx_mode(struct hinic_dev *nic_dev, u32 rx_mode);
+
+int hinic_port_link_state(struct hinic_dev *nic_dev,
+ enum hinic_port_link_state *link_state);
+
+int hinic_port_set_state(struct hinic_dev *nic_dev,
+ enum hinic_port_state state);
+
#endif
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 08/21] net-next/hinic: Add port management commands
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Add the port management commands that are sent as management messages.
The port management commands are used for netdev operations.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
drivers/net/ethernet/huawei/hinic/Makefile | 4 +-
drivers/net/ethernet/huawei/hinic/hinic_dev.h | 4 +
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 30 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h | 29 +++
drivers/net/ethernet/huawei/hinic/hinic_main.c | 195 +++++++++++++++++++-
drivers/net/ethernet/huawei/hinic/hinic_port.c | 224 +++++++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_port.h | 68 +++++++
7 files changed, 551 insertions(+), 3 deletions(-)
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_port.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_port.h
diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
index beba90a..dbb1b9d 100644
--- a/drivers/net/ethernet/huawei/hinic/Makefile
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -1,4 +1,4 @@
obj-$(CONFIG_HINIC) += hinic.o
-hinic-y := hinic_main.o hinic_hw_dev.o hinic_hw_mgmt.o hinic_hw_api_cmd.o \
- hinic_hw_eqs.o hinic_hw_if.o
+hinic-y := hinic_main.o hinic_port.o hinic_hw_dev.o hinic_hw_mgmt.o \
+ hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
index 6c2c896..e54a45c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -18,6 +18,7 @@
#include <linux/netdevice.h>
#include <linux/types.h>
+#include <linux/semaphore.h>
#include "hinic_hw_dev.h"
@@ -28,6 +29,9 @@ struct hinic_dev {
struct hinic_hwdev *hwdev;
u32 msg_enable;
+
+ struct semaphore mgmt_lock;
+ unsigned long *vlan_bitmap;
};
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index d430e60..6bb6c33 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -200,6 +200,36 @@ static void disable_msix(struct hinic_hwdev *hwdev)
}
/**
+ * hinic_port_msg_cmd - send port msg to mgmt
+ * @hwdev: the NIC HW device
+ * @cmd: the port command
+ * @buf_in: input buffer
+ * @in_size: input size
+ * @buf_out: output buffer
+ * @out_size: returned output size
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
+ void *buf_in, u16 in_size, void *buf_out, u16 *out_size)
+{
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_pfhwdev *pfhwdev;
+
+ if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
+ dev_err(&pdev->dev, "unsupported PCI Function type\n");
+ return -EINVAL;
+ }
+
+ pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+ return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, cmd,
+ buf_in, in_size, buf_out, out_size,
+ HINIC_MGMT_MSG_SYNC);
+}
+
+/**
* init_pfhwdev - Initialize the extended components of PF
* @pfhwdev: the HW device for PF
*
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index feb60138..ee9e76a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -30,6 +30,31 @@ struct hinic_cap {
u16 num_qps;
};
+enum hinic_port_cmd {
+ HINIC_PORT_CMD_CHANGE_MTU = 2,
+
+ HINIC_PORT_CMD_ADD_VLAN = 3,
+ HINIC_PORT_CMD_DEL_VLAN = 4,
+
+ HINIC_PORT_CMD_SET_MAC = 9,
+ HINIC_PORT_CMD_GET_MAC = 10,
+ HINIC_PORT_CMD_DEL_MAC = 11,
+
+ HINIC_PORT_CMD_SET_RX_MODE = 12,
+
+ HINIC_PORT_CMD_GET_LINK_STATE = 24,
+
+ HINIC_PORT_CMD_SET_PORT_STATE = 41,
+
+ HINIC_PORT_CMD_FWCTXT_INIT = 69,
+
+ HINIC_PORT_CMD_SET_FUNC_STATE = 93,
+
+ HINIC_PORT_CMD_GET_GLOBAL_QPN = 102,
+
+ HINIC_PORT_CMD_GET_CAP = 170,
+};
+
struct hinic_hwdev {
struct hinic_hwif *hwif;
struct msix_entry *msix_entries;
@@ -45,6 +70,10 @@ struct hinic_pfhwdev {
struct hinic_pf_to_mgmt pf_to_mgmt;
};
+int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
+ void *buf_in, u16 in_size, void *buf_out,
+ u16 *out_size);
+
struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev);
void hinic_free_hwdev(struct hinic_hwdev *hwdev);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 10df850..f46c2bc 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -13,6 +13,7 @@
*
*/
+#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/device.h>
@@ -20,9 +21,16 @@
#include <linux/types.h>
#include <linux/etherdevice.h>
#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/if_vlan.h>
+#include <linux/semaphore.h>
+#include <net/ip.h>
+#include <linux/bitops.h>
+#include <linux/bitmap.h>
#include <linux/err.h>
#include "hinic_hw_dev.h"
+#include "hinic_port.h"
#include "hinic_dev.h"
MODULE_AUTHOR("Huawei Technologies CO., Ltd");
@@ -35,10 +43,163 @@
NETIF_MSG_IFUP | \
NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR)
+#define VLAN_BITMAP_SIZE(nic_dev) (ALIGN(VLAN_N_VID, 8) / 8)
+
+static int hinic_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ int err;
+
+ netif_info(nic_dev, drv, netdev, "set_mtu = %d\n", new_mtu);
+
+ err = hinic_port_set_mtu(nic_dev, new_mtu);
+ if (err)
+ netif_err(nic_dev, drv, netdev, "Failed to set port mtu\n");
+ else
+ netdev->mtu = new_mtu;
+
+ return err;
+}
+
+/**
+ * change_mac_addr - change the main mac address of network device
+ * @netdev: network device
+ * @addr: mac address to set
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int change_mac_addr(struct net_device *netdev, const u8 *addr)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ u16 vid = 0;
+ int err;
+
+ if (!is_valid_ether_addr(addr))
+ return -EADDRNOTAVAIL;
+
+ netif_info(nic_dev, drv, netdev, "change mac addr = %02x %02x %02x %02x %02x %02x\n",
+ addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
+
+ down(&nic_dev->mgmt_lock);
+
+ do {
+ err = hinic_port_del_mac(nic_dev, netdev->dev_addr, vid);
+ if (err) {
+ netif_err(nic_dev, drv, netdev,
+ "Failed to delete mac\n");
+ break;
+ }
+
+ err = hinic_port_add_mac(nic_dev, addr, vid);
+ if (err) {
+ netif_err(nic_dev, drv, netdev, "Failed to add mac\n");
+ break;
+ }
+
+ vid = find_next_bit(nic_dev->vlan_bitmap, VLAN_N_VID, vid + 1);
+ } while (vid != VLAN_N_VID);
+
+ up(&nic_dev->mgmt_lock);
+ return err;
+}
+
+static int hinic_set_mac_addr(struct net_device *netdev, void *addr)
+{
+ unsigned char new_mac[ETH_ALEN];
+ struct sockaddr *saddr = addr;
+ int err;
+
+ memcpy(new_mac, saddr->sa_data, ETH_ALEN);
+
+ err = change_mac_addr(netdev, new_mac);
+ if (!err)
+ memcpy(netdev->dev_addr, new_mac, ETH_ALEN);
+
+ return err;
+}
+
+static int hinic_vlan_rx_add_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ int ret, err;
+
+ netif_info(nic_dev, drv, netdev, "add vid = %d\n", vid);
+
+ down(&nic_dev->mgmt_lock);
+
+ err = hinic_port_add_vlan(nic_dev, vid);
+ if (err) {
+ netif_err(nic_dev, drv, netdev, "Failed to add vlan\n");
+ goto err_vlan_add;
+ }
+
+ err = hinic_port_add_mac(nic_dev, netdev->dev_addr, vid);
+ if (err) {
+ netif_err(nic_dev, drv, netdev, "Failed to set mac\n");
+ goto err_add_mac;
+ }
+
+ bitmap_set(nic_dev->vlan_bitmap, vid, 1);
+
+ up(&nic_dev->mgmt_lock);
+ return 0;
+
+err_add_mac:
+ ret = hinic_port_del_vlan(nic_dev, vid);
+ if (ret)
+ netif_err(nic_dev, drv, netdev,
+ "Failed to revert by removing vlan\n");
+
+err_vlan_add:
+ up(&nic_dev->mgmt_lock);
+ return err;
+}
+
+static int hinic_vlan_rx_kill_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ int err;
+
+ netif_info(nic_dev, drv, netdev, "remove vid = %d\n", vid);
+
+ down(&nic_dev->mgmt_lock);
+
+ err = hinic_port_del_vlan(nic_dev, vid);
+ if (err) {
+ netif_err(nic_dev, drv, netdev, "Failed to delete vlan\n");
+ goto err_del_vlan;
+ }
+
+ bitmap_clear(nic_dev->vlan_bitmap, vid, 1);
+
+ up(&nic_dev->mgmt_lock);
+ return 0;
+
+err_del_vlan:
+ up(&nic_dev->mgmt_lock);
+ return err;
+}
+
static const struct net_device_ops hinic_netdev_ops = {
- /* Operations are empty, should be filled */
+ .ndo_change_mtu = hinic_change_mtu,
+ .ndo_set_mac_address = hinic_set_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_vlan_rx_add_vid = hinic_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = hinic_vlan_rx_kill_vid,
+ /* more operations should be filled */
};
+static void netdev_features_init(struct net_device *netdev)
+{
+ netdev->hw_features = NETIF_F_SG | NETIF_F_HIGHDMA;
+
+ netdev->vlan_features = netdev->hw_features;
+
+ netdev->features = netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
+}
+
/**
* nic_dev_init - Initialize the NIC device
* @pdev: the NIC pci device
@@ -79,8 +240,36 @@ static int nic_dev_init(struct pci_dev *pdev)
nic_dev->hwdev = hwdev;
nic_dev->msg_enable = MSG_ENABLE_DEFAULT;
+ sema_init(&nic_dev->mgmt_lock, 1);
+
+ nic_dev->vlan_bitmap = devm_kzalloc(&pdev->dev,
+ VLAN_BITMAP_SIZE(nic_dev),
+ GFP_KERNEL);
+ if (!nic_dev->vlan_bitmap) {
+ err = -ENOMEM;
+ goto err_vlan_bitmap;
+ }
+
pci_set_drvdata(pdev, netdev);
+ err = hinic_port_get_mac(nic_dev, netdev->dev_addr);
+ if (err)
+ dev_warn(&pdev->dev, "Failed to get mac address\n");
+
+ err = hinic_port_add_mac(nic_dev, netdev->dev_addr, 0);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to add mac\n");
+ goto err_add_mac;
+ }
+
+ err = hinic_port_set_mtu(nic_dev, netdev->mtu);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to set mtu\n");
+ goto err_set_mtu;
+ }
+
+ netdev_features_init(netdev);
+
netif_carrier_off(netdev);
err = register_netdev(netdev);
@@ -92,7 +281,11 @@ static int nic_dev_init(struct pci_dev *pdev)
return 0;
err_reg_netdev:
+err_set_mtu:
+err_add_mac:
pci_set_drvdata(pdev, NULL);
+
+err_vlan_bitmap:
free_netdev(netdev);
err_alloc_etherdev:
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
new file mode 100644
index 0000000..5b249e8
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -0,0 +1,224 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_dev.h"
+#include "hinic_port.h"
+#include "hinic_dev.h"
+
+#define HINIC_MIN_MTU_SIZE 256
+#define HINIC_MAX_JUMBO_FRAME_SIZE 15872
+
+enum mac_op {
+ MAC_DEL,
+ MAC_SET,
+};
+
+/**
+ * change_mac - change(add or delete) mac address
+ * @nic_dev: nic device
+ * @addr: mac address
+ * @vlan_id: vlan number to set with the mac
+ * @op: add or delete the mac
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int change_mac(struct hinic_dev *nic_dev, const u8 *addr,
+ u16 vlan_id, enum mac_op op)
+{
+ struct net_device *netdev = nic_dev->netdev;
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_port_mac_cmd port_mac_cmd;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ enum hinic_port_cmd cmd;
+ u16 out_size;
+ int err;
+
+ if (vlan_id >= VLAN_N_VID) {
+ netif_err(nic_dev, drv, netdev, "Invalid VLAN number\n");
+ return -EINVAL;
+ }
+
+ if (op == MAC_SET)
+ cmd = HINIC_PORT_CMD_SET_MAC;
+ else
+ cmd = HINIC_PORT_CMD_DEL_MAC;
+
+ port_mac_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
+ port_mac_cmd.vlan_id = vlan_id;
+ memcpy(port_mac_cmd.mac, addr, ETH_ALEN);
+
+ err = hinic_port_msg_cmd(hwdev, cmd, &port_mac_cmd,
+ sizeof(port_mac_cmd),
+ &port_mac_cmd, &out_size);
+ if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) {
+ dev_err(&pdev->dev, "Failed to change MAC, ret = %d\n",
+ port_mac_cmd.status);
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+/**
+ * hinic_port_add_mac - add mac address
+ * @nic_dev: nic device
+ * @addr: mac address
+ * @vlan_id: vlan number to set with the mac
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_add_mac(struct hinic_dev *nic_dev,
+ const u8 *addr, u16 vlan_id)
+{
+ return change_mac(nic_dev, addr, vlan_id, MAC_SET);
+}
+
+/**
+ * hinic_port_del_mac - remove mac address
+ * @nic_dev: nic device
+ * @addr: mac address
+ * @vlan_id: vlan number that is connected to the mac
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_del_mac(struct hinic_dev *nic_dev, const u8 *addr,
+ u16 vlan_id)
+{
+ return change_mac(nic_dev, addr, vlan_id, MAC_DEL);
+}
+
+/**
+ * hinic_port_get_mac - get the mac address of the nic device
+ * @nic_dev: nic device
+ * @addr: returned mac address
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr)
+{
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_port_mac_cmd port_mac_cmd;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ u16 out_size;
+ int err;
+
+ port_mac_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
+
+ err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_MAC,
+ &port_mac_cmd, sizeof(port_mac_cmd),
+ &port_mac_cmd, &out_size);
+ if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) {
+ dev_err(&pdev->dev, "Failed to get mac, ret = %d\n",
+ port_mac_cmd.status);
+ return -EFAULT;
+ }
+
+ memcpy(addr, port_mac_cmd.mac, ETH_ALEN);
+ return 0;
+}
+
+/**
+ * hinic_port_set_mtu - set mtu
+ * @nic_dev: nic device
+ * @new_mtu: new mtu
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu)
+{
+ struct net_device *netdev = nic_dev->netdev;
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_port_mtu_cmd port_mtu_cmd;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int err, max_frame;
+ u16 out_size;
+
+ if (new_mtu < HINIC_MIN_MTU_SIZE) {
+ netif_err(nic_dev, drv, netdev, "mtu < MIN MTU size");
+ return -EINVAL;
+ }
+
+ max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+ if (max_frame > HINIC_MAX_JUMBO_FRAME_SIZE) {
+ netif_err(nic_dev, drv, netdev, "mtu > MAX MTU size");
+ return -EINVAL;
+ }
+
+ port_mtu_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
+ port_mtu_cmd.mtu = new_mtu;
+
+ err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_CHANGE_MTU,
+ &port_mtu_cmd, sizeof(port_mtu_cmd),
+ &port_mtu_cmd, &out_size);
+ if (err || (out_size != sizeof(port_mtu_cmd)) || port_mtu_cmd.status) {
+ dev_err(&pdev->dev, "Failed to set mtu, ret = %d\n",
+ port_mtu_cmd.status);
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+/**
+ * hinic_port_add_vlan - add vlan to the nic device
+ * @nic_dev: nic device
+ * @vlan_id: the vlan number to add
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_add_vlan(struct hinic_dev *nic_dev, u16 vlan_id)
+{
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_port_vlan_cmd port_vlan_cmd;
+
+ port_vlan_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+ port_vlan_cmd.vlan_id = vlan_id;
+
+ return hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_ADD_VLAN,
+ &port_vlan_cmd, sizeof(port_vlan_cmd),
+ NULL, NULL);
+}
+
+/**
+ * hinic_port_del_vlan - delete vlan from the nic device
+ * @nic_dev: nic device
+ * @vlan_id: the vlan number to delete
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_port_del_vlan(struct hinic_dev *nic_dev, u16 vlan_id)
+{
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_port_vlan_cmd port_vlan_cmd;
+
+ port_vlan_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+ port_vlan_cmd.vlan_id = vlan_id;
+
+ return hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_DEL_VLAN,
+ &port_vlan_cmd, sizeof(port_vlan_cmd),
+ NULL, NULL);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
new file mode 100644
index 0000000..4cafb94
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -0,0 +1,68 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_PORT_H
+#define HINIC_PORT_H
+
+#include <linux/types.h>
+#include <linux/etherdevice.h>
+
+#include "hinic_dev.h"
+
+struct hinic_port_mac_cmd {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 func_idx;
+ u16 vlan_id;
+ u16 rsvd1;
+ unsigned char mac[ETH_ALEN];
+};
+
+struct hinic_port_mtu_cmd {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 func_idx;
+ u16 rsvd1;
+ u32 mtu;
+};
+
+struct hinic_port_vlan_cmd {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 func_idx;
+ u16 vlan_id;
+};
+
+int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
+ u16 vlan_id);
+
+int hinic_port_del_mac(struct hinic_dev *nic_dev, const u8 *addr,
+ u16 vlan_id);
+
+int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr);
+
+int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu);
+
+int hinic_port_add_vlan(struct hinic_dev *nic_dev, u16 vlan_id);
+
+int hinic_port_del_vlan(struct hinic_dev *nic_dev, u16 vlan_id);
+
+#endif
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 07/21] net-next/hinic: Add aeqs
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Handle aeq elements that are accumulated on the aeq by calling the
registered handler for the specific event.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h | 49 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c | 464 ++++++++++++++++++++++-
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h | 81 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.c | 91 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 46 +++
5 files changed, 729 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
index ebbf054..52eb89c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
@@ -65,4 +65,53 @@
#define HINIC_CSR_API_CMD_STATUS_ADDR(idx) \
(HINIC_CSR_API_CMD_BASE + 0x30 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+/* MSI-X registers */
+#define HINIC_CSR_MSIX_CTRL_BASE 0x2000
+#define HINIC_CSR_MSIX_CNT_BASE 0x2004
+
+#define HINIC_CSR_MSIX_STRIDE 0x8
+
+#define HINIC_CSR_MSIX_CTRL_ADDR(idx) \
+ (HINIC_CSR_MSIX_CTRL_BASE + (idx) * HINIC_CSR_MSIX_STRIDE)
+
+#define HINIC_CSR_MSIX_CNT_ADDR(idx) \
+ (HINIC_CSR_MSIX_CNT_BASE + (idx) * HINIC_CSR_MSIX_STRIDE)
+
+/* EQ registers */
+#define HINIC_AEQ_MTT_OFF_BASE_ADDR 0x200
+
+#define HINIC_EQ_MTT_OFF_STRIDE 0x40
+
+#define HINIC_CSR_AEQ_MTT_OFF(id) \
+ (HINIC_AEQ_MTT_OFF_BASE_ADDR + (id) * HINIC_EQ_MTT_OFF_STRIDE)
+
+#define HINIC_CSR_EQ_PAGE_OFF_STRIDE 8
+
+#define HINIC_CSR_AEQ_HI_PHYS_ADDR_REG(q_id, pg_num) \
+ (HINIC_CSR_AEQ_MTT_OFF(q_id) + \
+ (pg_num) * HINIC_CSR_EQ_PAGE_OFF_STRIDE)
+
+#define HINIC_CSR_AEQ_LO_PHYS_ADDR_REG(q_id, pg_num) \
+ (HINIC_CSR_AEQ_MTT_OFF(q_id) + \
+ (pg_num) * HINIC_CSR_EQ_PAGE_OFF_STRIDE + 4)
+
+#define HINIC_AEQ_CTRL_0_ADDR_BASE 0xE00
+#define HINIC_AEQ_CTRL_1_ADDR_BASE 0xE04
+#define HINIC_AEQ_CONS_IDX_ADDR_BASE 0xE08
+#define HINIC_AEQ_PROD_IDX_ADDR_BASE 0xE0C
+
+#define HINIC_EQ_OFF_STRIDE 0x80
+
+#define HINIC_CSR_AEQ_CTRL_0_ADDR(idx) \
+ (HINIC_AEQ_CTRL_0_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE)
+
+#define HINIC_CSR_AEQ_CTRL_1_ADDR(idx) \
+ (HINIC_AEQ_CTRL_1_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE)
+
+#define HINIC_CSR_AEQ_CONS_IDX_ADDR(idx) \
+ (HINIC_AEQ_CONS_IDX_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE)
+
+#define HINIC_CSR_AEQ_PROD_IDX_ADDR(idx) \
+ (HINIC_AEQ_PROD_IDX_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE)
+
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index a099d20..a53d5b3 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -13,17 +13,74 @@
*
*/
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/pci.h>
#include <linux/device.h>
#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/log2.h>
+#include <asm/byteorder.h>
+#include <asm/barrier.h>
+#include "hinic_hw_csr.h"
#include "hinic_hw_if.h"
#include "hinic_hw_eqs.h"
#define HINIC_EQS_WQ_NAME "hinic_eqs"
+#define GET_EQ_NUM_PAGES(eq, pg_size) \
+ (ALIGN((eq)->q_len * (eq)->elem_size, pg_size) / (pg_size))
+
+#define GET_EQ_NUM_ELEMS_IN_PG(eq, pg_size) ((pg_size) / (eq)->elem_size)
+
+#define EQ_CONS_IDX_REG_ADDR(eq) HINIC_CSR_AEQ_CONS_IDX_ADDR((eq)->q_id)
+#define EQ_PROD_IDX_REG_ADDR(eq) HINIC_CSR_AEQ_PROD_IDX_ADDR((eq)->q_id)
+
+#define EQ_HI_PHYS_ADDR_REG(eq, pg_num) \
+ HINIC_CSR_AEQ_HI_PHYS_ADDR_REG((eq)->q_id, pg_num)
+
+#define EQ_LO_PHYS_ADDR_REG(eq, pg_num) \
+ HINIC_CSR_AEQ_LO_PHYS_ADDR_REG((eq)->q_id, pg_num)
+
+#define GET_EQ_ELEMENT(eq, idx) \
+ ((eq)->virt_addr[(idx) / (eq)->num_elem_in_pg] + \
+ (((idx) & ((eq)->num_elem_in_pg - 1)) * (eq)->elem_size))
+
+#define GET_AEQ_ELEM(eq, idx) ((struct hinic_aeq_elem *) \
+ GET_EQ_ELEMENT(eq, idx))
+
+#define GET_CURR_AEQ_ELEM(eq) GET_AEQ_ELEM(eq, (eq)->cons_idx)
+
+#define PAGE_IN_4K(page_size) ((page_size) >> 12)
+#define EQ_SET_HW_PAGE_SIZE_VAL(eq) (ilog2(PAGE_IN_4K((eq)->page_size)))
+
+#define ELEMENT_SIZE_IN_32B(eq) (((eq)->elem_size) >> 5)
+#define EQ_SET_HW_ELEM_SIZE_VAL(eq) (ilog2(ELEMENT_SIZE_IN_32B(eq)))
+
+#define EQ_MAX_PAGES 8
+
+#define aeq_to_aeqs(eq) \
+ container_of((eq) - (eq)->q_id, struct hinic_aeqs, aeq[0])
+
+#define work_to_aeq_work(work) \
+ container_of(work, struct hinic_eq_work, work)
+
+#define DMA_ATTR_AEQ_DEFAULT 0
+
+enum eq_int_mode {
+ EQ_INT_MODE_ARMED,
+ EQ_INT_MODE_ALWAYS
+};
+
+enum eq_arm_state {
+ EQ_NOT_ARMED,
+ EQ_ARMED
+};
+
/**
* hinic_aeq_register_hw_cb - register AEQ callback for specific event
* @aeqs: pointer to Async eqs of the chip
@@ -61,6 +118,326 @@ void hinic_aeq_unregister_hw_cb(struct hinic_aeqs *aeqs,
hwe_cb->hwe_handler = NULL;
}
+static u8 eq_cons_idx_checksum_set(u32 val)
+{
+ u8 checksum = 0;
+ int idx;
+
+ for (idx = 0; idx < 32; idx += 4)
+ checksum ^= ((val >> idx) & 0xF);
+
+ return (checksum & 0xF);
+}
+
+/**
+ * eq_update_ci - update the HW cons idx of event queue
+ * @eq: the event queue to update the cons idx for
+ **/
+static void eq_update_ci(struct hinic_eq *eq)
+{
+ u32 val, addr = EQ_CONS_IDX_REG_ADDR(eq);
+
+ /* Read Modify Write */
+ val = hinic_hwif_read_reg(eq->hwif, addr);
+
+ val = HINIC_EQ_CI_CLEAR(val, IDX) &
+ HINIC_EQ_CI_CLEAR(val, WRAPPED) &
+ HINIC_EQ_CI_CLEAR(val, INT_ARMED) &
+ HINIC_EQ_CI_CLEAR(val, XOR_CHKSUM);
+
+ val |= HINIC_EQ_CI_SET(eq->cons_idx, IDX) |
+ HINIC_EQ_CI_SET(eq->wrapped, WRAPPED) |
+ HINIC_EQ_CI_SET(EQ_ARMED, INT_ARMED);
+
+ val |= HINIC_EQ_CI_SET(eq_cons_idx_checksum_set(val), XOR_CHKSUM);
+
+ hinic_hwif_write_reg(eq->hwif, addr, val);
+}
+
+/**
+ * aeq_irq_handler - handler for the AEQ event
+ * @eq: the Async Event Queue that received the event
+ **/
+static void aeq_irq_handler(struct hinic_eq *eq)
+{
+ struct hinic_aeqs *aeqs = aeq_to_aeqs(eq);
+ struct hinic_hwif *hwif = aeqs->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_aeq_elem *aeqe_curr;
+ struct hinic_hw_event_cb *hwe_cb;
+ enum hinic_aeq_type event;
+ unsigned long eqe_state;
+ u32 aeqe_desc;
+ int i, size;
+
+ for (i = 0; i < eq->q_len; i++) {
+ aeqe_curr = GET_CURR_AEQ_ELEM(eq);
+
+ /* Data in HW is in Big endian Format */
+ aeqe_desc = be32_to_cpu(aeqe_curr->desc);
+
+ /* HW toggles the wrapped bit, when it adds eq element */
+ if (HINIC_EQ_ELEM_DESC_GET(aeqe_desc, WRAPPED) == eq->wrapped)
+ break;
+
+ event = HINIC_EQ_ELEM_DESC_GET(aeqe_desc, TYPE);
+ if (event >= HINIC_MAX_AEQ_EVENTS) {
+ dev_err(&pdev->dev, "Unknown AEQ Event %d\n", event);
+ return;
+ }
+
+ if (!HINIC_EQ_ELEM_DESC_GET(aeqe_desc, SRC)) {
+ hwe_cb = &aeqs->hwe_cb[event];
+
+ size = HINIC_EQ_ELEM_DESC_GET(aeqe_desc, SIZE);
+
+ eqe_state = cmpxchg(&hwe_cb->hwe_state,
+ HINIC_EQE_ENABLED,
+ HINIC_EQE_ENABLED |
+ HINIC_EQE_RUNNING);
+ if ((eqe_state == HINIC_EQE_ENABLED) &&
+ (hwe_cb->hwe_handler))
+ hwe_cb->hwe_handler(hwe_cb->handle,
+ aeqe_curr->data, size);
+ else
+ dev_err(&pdev->dev, "Unhandled AEQ Event %d\n",
+ event);
+
+ hwe_cb->hwe_state &= ~HINIC_EQE_RUNNING;
+ }
+
+ eq->cons_idx++;
+
+ if (eq->cons_idx == eq->q_len) {
+ eq->cons_idx = 0;
+ eq->wrapped = !eq->wrapped;
+ }
+ }
+}
+
+/**
+ * eq_irq_handler - handler for the EQ event
+ * @data: the Event Queue that received the event
+ **/
+static void eq_irq_handler(void *data)
+{
+ struct hinic_eq *eq = (struct hinic_eq *)data;
+
+ if (eq->type == HINIC_AEQ)
+ aeq_irq_handler(eq);
+
+ eq_update_ci(eq);
+}
+
+/**
+ * eq_irq_work - the work of the EQ that received the event
+ * @work: the work struct that is associated with the EQ
+ **/
+static void eq_irq_work(struct work_struct *work)
+{
+ struct hinic_eq_work *aeq_work = work_to_aeq_work(work);
+ struct hinic_eq *aeq;
+
+ aeq = (struct hinic_eq *)aeq_work->data;
+ eq_irq_handler(aeq);
+}
+
+/**
+ * aeq_interrupt - aeq interrupt handler
+ * @irq: irq number
+ * @data: the Async Event Queue that collected the event
+ **/
+static irqreturn_t aeq_interrupt(int irq, void *data)
+{
+ struct hinic_eq *aeq = (struct hinic_eq *)data;
+ struct hinic_aeqs *aeqs = aeq_to_aeqs(aeq);
+ struct hinic_eq_work *aeq_work;
+
+ /* clear resend timer cnt register */
+ hinic_msix_attr_cnt_clear(aeq->hwif, aeq->msix_entry.entry);
+
+ aeq_work = &aeq->aeq_work;
+ aeq_work->data = aeq;
+
+ queue_work(aeqs->workq, &aeq_work->work);
+
+ return IRQ_HANDLED;
+}
+
+void set_ctrl0(struct hinic_eq *eq)
+{
+ struct msix_entry *msix_entry = &eq->msix_entry;
+ struct hinic_hwif *hwif = eq->hwif;
+ enum hinic_eq_type type = eq->type;
+ u32 addr, val, ctrl0;
+
+ if (type == HINIC_AEQ) {
+ /* RMW Ctrl0 */
+ addr = HINIC_CSR_AEQ_CTRL_0_ADDR(eq->q_id);
+
+ val = hinic_hwif_read_reg(hwif, addr);
+
+ val = HINIC_AEQ_CTRL_0_CLEAR(val, INT_IDX) &
+ HINIC_AEQ_CTRL_0_CLEAR(val, DMA_ATTR) &
+ HINIC_AEQ_CTRL_0_CLEAR(val, PCI_INTF_IDX) &
+ HINIC_AEQ_CTRL_0_CLEAR(val, INT_MODE);
+
+ ctrl0 = HINIC_AEQ_CTRL_0_SET(msix_entry->entry, INT_IDX) |
+ HINIC_AEQ_CTRL_0_SET(DMA_ATTR_AEQ_DEFAULT, DMA_ATTR) |
+ HINIC_AEQ_CTRL_0_SET(HINIC_HWIF_PCI_INTF(hwif),
+ PCI_INTF_IDX) |
+ HINIC_AEQ_CTRL_0_SET(EQ_INT_MODE_ARMED, INT_MODE);
+
+ val |= ctrl0;
+
+ hinic_hwif_write_reg(hwif, addr, val);
+ }
+}
+
+void set_ctrl1(struct hinic_eq *eq)
+{
+ struct hinic_hwif *hwif = eq->hwif;
+ enum hinic_eq_type type = eq->type;
+ u32 page_size_val, elem_size;
+ u32 addr, val, ctrl1;
+
+ if (type == HINIC_AEQ) {
+ /* RMW Ctrl1 */
+ addr = HINIC_CSR_AEQ_CTRL_1_ADDR(eq->q_id);
+
+ page_size_val = EQ_SET_HW_PAGE_SIZE_VAL(eq);
+ elem_size = EQ_SET_HW_ELEM_SIZE_VAL(eq);
+
+ val = hinic_hwif_read_reg(hwif, addr);
+
+ val = HINIC_AEQ_CTRL_1_CLEAR(val, LEN) &
+ HINIC_AEQ_CTRL_1_CLEAR(val, ELEM_SIZE) &
+ HINIC_AEQ_CTRL_1_CLEAR(val, PAGE_SIZE);
+
+ ctrl1 = HINIC_AEQ_CTRL_1_SET(eq->q_len, LEN) |
+ HINIC_AEQ_CTRL_1_SET(elem_size, ELEM_SIZE) |
+ HINIC_AEQ_CTRL_1_SET(page_size_val, PAGE_SIZE);
+
+ val |= ctrl1;
+
+ hinic_hwif_write_reg(hwif, addr, val);
+ }
+}
+
+/**
+ * set_eq_ctrls - setting eq's ctrl registers
+ * @eq: the Event Queue for setting
+ **/
+static void set_eq_ctrls(struct hinic_eq *eq)
+{
+ set_ctrl0(eq);
+ set_ctrl1(eq);
+}
+
+/**
+ * aeq_elements_init - initialize all the elements in the aeq
+ * @eq: the Async Event Queue
+ * @init_val: value to initialize the elements with it
+ **/
+static void aeq_elements_init(struct hinic_eq *eq, u32 init_val)
+{
+ struct hinic_aeq_elem *aeqe;
+ int i;
+
+ for (i = 0; i < eq->q_len; i++) {
+ aeqe = GET_AEQ_ELEM(eq, i);
+ aeqe->desc = cpu_to_be32(init_val);
+ }
+
+ wmb(); /* Write the initilzation values */
+}
+
+/**
+ * alloc_eq_pages - allocate the pages for the queue
+ * @eq: the event queue
+ *
+ * Return 0 - Success, Negative - Failure
+ **/
+static int alloc_eq_pages(struct hinic_eq *eq)
+{
+ struct hinic_hwif *hwif = eq->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ u32 init_val, addr, val;
+ size_t addr_size;
+ int err, pg;
+
+ addr_size = eq->num_pages * sizeof(*eq->dma_addr);
+ eq->dma_addr = devm_kzalloc(&pdev->dev, addr_size, GFP_KERNEL);
+ if (!eq->dma_addr)
+ return -ENOMEM;
+
+ addr_size = eq->num_pages * sizeof(*eq->virt_addr);
+ eq->virt_addr = devm_kzalloc(&pdev->dev, addr_size, GFP_KERNEL);
+ if (!eq->virt_addr) {
+ err = -ENOMEM;
+ goto err_virt_addr_alloc;
+ }
+
+ for (pg = 0; pg < eq->num_pages; pg++) {
+ eq->virt_addr[pg] = dma_zalloc_coherent(&pdev->dev,
+ eq->page_size,
+ &eq->dma_addr[pg],
+ GFP_KERNEL);
+ if (!eq->virt_addr[pg]) {
+ err = -ENOMEM;
+ goto err_dma_alloc;
+ }
+
+ addr = EQ_HI_PHYS_ADDR_REG(eq, pg);
+ val = upper_32_bits(eq->dma_addr[pg]);
+
+ hinic_hwif_write_reg(hwif, addr, val);
+
+ addr = EQ_LO_PHYS_ADDR_REG(eq, pg);
+ val = lower_32_bits(eq->dma_addr[pg]);
+
+ hinic_hwif_write_reg(hwif, addr, val);
+ }
+
+ init_val = HINIC_EQ_ELEM_DESC_SET(eq->wrapped, WRAPPED);
+
+ if (eq->type == HINIC_AEQ)
+ aeq_elements_init(eq, init_val);
+
+ return 0;
+
+err_dma_alloc:
+ while (--pg >= 0)
+ dma_free_coherent(&pdev->dev, eq->page_size,
+ eq->virt_addr[pg],
+ eq->dma_addr[pg]);
+
+ devm_kfree(&pdev->dev, eq->virt_addr);
+
+err_virt_addr_alloc:
+ devm_kfree(&pdev->dev, eq->dma_addr);
+ return err;
+}
+
+/**
+ * free_eq_pages - free the pages of the queue
+ * @eq: the Event Queue
+ **/
+static void free_eq_pages(struct hinic_eq *eq)
+{
+ struct hinic_hwif *hwif = eq->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int pg;
+
+ for (pg = 0; pg < eq->num_pages; pg++)
+ dma_free_coherent(&pdev->dev, eq->page_size,
+ eq->virt_addr[pg],
+ eq->dma_addr[pg]);
+
+ devm_kfree(&pdev->dev, eq->virt_addr);
+ devm_kfree(&pdev->dev, eq->dma_addr);
+}
+
/**
* init_eq - initialize Event Queue
* @eq: the event queue
@@ -77,8 +454,81 @@ static int init_eq(struct hinic_eq *eq, struct hinic_hwif *hwif,
enum hinic_eq_type type, int q_id, u32 q_len, u32 page_size,
struct msix_entry entry)
{
- /* should be implemented */
+ struct pci_dev *pdev = hwif->pdev;
+ int err;
+
+ eq->hwif = hwif;
+ eq->type = type;
+ eq->q_id = q_id;
+ eq->q_len = q_len;
+ eq->page_size = page_size;
+
+ /* Clear PI and CI, also clear the ARM bit */
+ hinic_hwif_write_reg(eq->hwif, EQ_CONS_IDX_REG_ADDR(eq), 0);
+ hinic_hwif_write_reg(eq->hwif, EQ_PROD_IDX_REG_ADDR(eq), 0);
+
+ eq->cons_idx = 0;
+ eq->wrapped = 0;
+
+ if (type == HINIC_AEQ) {
+ eq->elem_size = HINIC_AEQE_SIZE;
+ } else {
+ dev_err(&pdev->dev, "Invalid EQ type\n");
+ return -EINVAL;
+ }
+
+ eq->num_pages = GET_EQ_NUM_PAGES(eq, page_size);
+ eq->num_elem_in_pg = GET_EQ_NUM_ELEMS_IN_PG(eq, page_size);
+
+ eq->msix_entry = entry;
+
+ if (eq->num_elem_in_pg & (eq->num_elem_in_pg - 1)) {
+ dev_err(&pdev->dev, "num elements in eq page != power of 2\n");
+ return -EINVAL;
+ }
+
+ if (eq->num_pages > EQ_MAX_PAGES) {
+ dev_err(&pdev->dev, "too many pages for eq\n");
+ return -EINVAL;
+ }
+
+ set_eq_ctrls(eq);
+ eq_update_ci(eq);
+
+ err = alloc_eq_pages(eq);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to allocate pages for eq\n");
+ return err;
+ }
+
+ if (type == HINIC_AEQ) {
+ struct hinic_eq_work *aeq_work = &eq->aeq_work;
+
+ INIT_WORK(&aeq_work->work, eq_irq_work);
+ }
+
+ /* set the attributes of the msix entry */
+ hinic_msix_attr_set(eq->hwif, eq->msix_entry.entry,
+ HINIC_EQ_MSIX_PENDING_LIMIT_DEFAULT,
+ HINIC_EQ_MSIX_COALESC_TIMER_DEFAULT,
+ HINIC_EQ_MSIX_LLI_TIMER_DEFAULT,
+ HINIC_EQ_MSIX_LLI_CREDIT_LIMIT_DEFAULT,
+ HINIC_EQ_MSIX_RESEND_TIMER_DEFAULT);
+
+ if (type == HINIC_AEQ)
+ err = request_irq(entry.vector, aeq_interrupt, 0,
+ "hinic_aeq", eq);
+
+ if (err) {
+ dev_err(&pdev->dev, "Failed to request irq for the EQ\n");
+ goto err_req_irq;
+ }
+
return 0;
+
+err_req_irq:
+ free_eq_pages(eq);
+ return err;
}
/**
@@ -87,7 +537,17 @@ static int init_eq(struct hinic_eq *eq, struct hinic_hwif *hwif,
**/
static void remove_eq(struct hinic_eq *eq)
{
- /* should be implemented */
+ struct msix_entry *entry = &eq->msix_entry;
+
+ free_irq(entry->vector, eq);
+
+ if (eq->type == HINIC_AEQ) {
+ struct hinic_eq_work *aeq_work = &eq->aeq_work;
+
+ cancel_work_sync(&aeq_work->work);
+ }
+
+ free_eq_pages(eq);
}
/**
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
index 1580127..7f50b2f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
@@ -24,8 +24,84 @@
#include "hinic_hw_if.h"
+#define HINIC_AEQ_CTRL_0_INT_IDX_SHIFT 0
+#define HINIC_AEQ_CTRL_0_DMA_ATTR_SHIFT 12
+#define HINIC_AEQ_CTRL_0_PCI_INTF_IDX_SHIFT 20
+#define HINIC_AEQ_CTRL_0_INT_MODE_SHIFT 31
+
+#define HINIC_AEQ_CTRL_0_INT_IDX_MASK 0x3FF
+#define HINIC_AEQ_CTRL_0_DMA_ATTR_MASK 0x3F
+#define HINIC_AEQ_CTRL_0_PCI_INTF_IDX_MASK 0x3
+#define HINIC_AEQ_CTRL_0_INT_MODE_MASK 0x1
+
+#define HINIC_AEQ_CTRL_0_SET(val, member) \
+ (((u32)(val) & HINIC_AEQ_CTRL_0_##member##_MASK) << \
+ HINIC_AEQ_CTRL_0_##member##_SHIFT)
+
+#define HINIC_AEQ_CTRL_0_CLEAR(val, member) \
+ ((val) & (~(HINIC_AEQ_CTRL_0_##member##_MASK \
+ << HINIC_AEQ_CTRL_0_##member##_SHIFT)))
+
+#define HINIC_AEQ_CTRL_1_LEN_SHIFT 0
+#define HINIC_AEQ_CTRL_1_ELEM_SIZE_SHIFT 24
+#define HINIC_AEQ_CTRL_1_PAGE_SIZE_SHIFT 28
+
+#define HINIC_AEQ_CTRL_1_LEN_MASK 0x1FFFFF
+#define HINIC_AEQ_CTRL_1_ELEM_SIZE_MASK 0x3
+#define HINIC_AEQ_CTRL_1_PAGE_SIZE_MASK 0xF
+
+#define HINIC_AEQ_CTRL_1_SET(val, member) \
+ (((u32)(val) & HINIC_AEQ_CTRL_1_##member##_MASK) << \
+ HINIC_AEQ_CTRL_1_##member##_SHIFT)
+
+#define HINIC_AEQ_CTRL_1_CLEAR(val, member) \
+ ((val) & (~(HINIC_AEQ_CTRL_1_##member##_MASK \
+ << HINIC_AEQ_CTRL_1_##member##_SHIFT)))
+
+#define HINIC_EQ_ELEM_DESC_TYPE_SHIFT 0
+#define HINIC_EQ_ELEM_DESC_SRC_SHIFT 7
+#define HINIC_EQ_ELEM_DESC_SIZE_SHIFT 8
+#define HINIC_EQ_ELEM_DESC_WRAPPED_SHIFT 31
+
+#define HINIC_EQ_ELEM_DESC_TYPE_MASK 0x7F
+#define HINIC_EQ_ELEM_DESC_SRC_MASK 0x1
+#define HINIC_EQ_ELEM_DESC_SIZE_MASK 0xFF
+#define HINIC_EQ_ELEM_DESC_WRAPPED_MASK 0x1
+
+#define HINIC_EQ_ELEM_DESC_SET(val, member) \
+ (((u32)(val) & HINIC_EQ_ELEM_DESC_##member##_MASK) << \
+ HINIC_EQ_ELEM_DESC_##member##_SHIFT)
+
+#define HINIC_EQ_ELEM_DESC_GET(val, member) \
+ (((val) >> HINIC_EQ_ELEM_DESC_##member##_SHIFT) & \
+ HINIC_EQ_ELEM_DESC_##member##_MASK)
+
+#define HINIC_EQ_CI_IDX_SHIFT 0
+#define HINIC_EQ_CI_WRAPPED_SHIFT 20
+#define HINIC_EQ_CI_XOR_CHKSUM_SHIFT 24
+#define HINIC_EQ_CI_INT_ARMED_SHIFT 31
+
+#define HINIC_EQ_CI_IDX_MASK 0xFFFFF
+#define HINIC_EQ_CI_WRAPPED_MASK 0x1
+#define HINIC_EQ_CI_XOR_CHKSUM_MASK 0xF
+#define HINIC_EQ_CI_INT_ARMED_MASK 0x1
+
+#define HINIC_EQ_CI_SET(val, member) \
+ (((u32)(val) & HINIC_EQ_CI_##member##_MASK) << \
+ HINIC_EQ_CI_##member##_SHIFT)
+
+#define HINIC_EQ_CI_CLEAR(val, member) \
+ ((val) & (~(HINIC_EQ_CI_##member##_MASK \
+ << HINIC_EQ_CI_##member##_SHIFT)))
+
#define HINIC_MAX_AEQS 4
+#define HINIC_AEQE_SIZE 64
+
+#define HINIC_AEQE_DESC_SIZE 4
+#define HINIC_AEQE_DATA_SIZE \
+ (HINIC_AEQE_SIZE - HINIC_AEQE_DESC_SIZE)
+
#define HINIC_DEFAULT_AEQ_LEN 64
#define HINIC_EQ_PAGE_SIZE SZ_4K
@@ -45,6 +121,11 @@ enum hinic_eqe_state {
HINIC_EQE_RUNNING = BIT(1),
};
+struct hinic_aeq_elem {
+ u8 data[HINIC_AEQE_DATA_SIZE];
+ u32 desc;
+};
+
struct hinic_eq_work {
struct work_struct work;
void *data;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index edf1842..2b9410c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -25,6 +25,97 @@
#define PCIE_ATTR_ENTRY 0
+#define VALID_MSIX_IDX(attr, msix_index) ((msix_index) < (attr)->num_irqs)
+
+/**
+ * hinic_msix_attr_set - set message attribute for msix entry
+ * @hwif: the HW interface of a pci function device
+ * @msix_index: msix_index
+ * @pending_limit: the maximum pending interrupt events (unit 8)
+ * @coalesc_timer: coalesc period for interrupt (unit 8 us)
+ * @lli_timer: replenishing period for low latency credit (unit 8 us)
+ * @lli_credit_limit: maximum credits for low latency msix messages (unit 8)
+ * @resend_timer: maximum wait for resending msix (unit coalesc period)
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_msix_attr_set(struct hinic_hwif *hwif, u16 msix_index,
+ u8 pending_limit, u8 coalesc_timer,
+ u8 lli_timer, u8 lli_credit_limit,
+ u8 resend_timer)
+{
+ u32 msix_ctrl, addr;
+
+ if (!VALID_MSIX_IDX(&hwif->attr, msix_index))
+ return -EINVAL;
+
+ msix_ctrl = HINIC_MSIX_ATTR_SET(pending_limit, PENDING_LIMIT) |
+ HINIC_MSIX_ATTR_SET(coalesc_timer, COALESC_TIMER) |
+ HINIC_MSIX_ATTR_SET(lli_timer, LLI_TIMER) |
+ HINIC_MSIX_ATTR_SET(lli_credit_limit, LLI_CREDIT) |
+ HINIC_MSIX_ATTR_SET(resend_timer, RESEND_TIMER);
+
+ addr = HINIC_CSR_MSIX_CTRL_ADDR(msix_index);
+
+ hinic_hwif_write_reg(hwif, addr, msix_ctrl);
+ return 0;
+}
+
+/**
+ * hinic_msix_attr_get - get message attribute of msix entry
+ * @hwif: the HW interface of a pci function device
+ * @msix_index: msix_index
+ * @pending_limit: the maximum pending interrupt events (unit 8)
+ * @coalesc_timer: coalesc period for interrupt (unit 8 us)
+ * @lli_timer: replenishing period for low latency credit (unit 8 us)
+ * @lli_credit_limit: maximum credits for low latency msix messages (unit 8)
+ * @resend_timer: maximum wait for resending msix (unit coalesc period)
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_msix_attr_get(struct hinic_hwif *hwif, u16 msix_index,
+ u8 *pending_limit, u8 *coalesc_timer,
+ u8 *lli_timer, u8 *lli_credit_limit,
+ u8 *resend_timer)
+{
+ u32 addr, val;
+
+ if (!VALID_MSIX_IDX(&hwif->attr, msix_index))
+ return -EINVAL;
+
+ addr = HINIC_CSR_MSIX_CTRL_ADDR(msix_index);
+ val = hinic_hwif_read_reg(hwif, addr);
+
+ *pending_limit = HINIC_MSIX_ATTR_GET(val, PENDING_LIMIT);
+ *coalesc_timer = HINIC_MSIX_ATTR_GET(val, COALESC_TIMER);
+ *lli_timer = HINIC_MSIX_ATTR_GET(val, LLI_TIMER);
+ *lli_credit_limit = HINIC_MSIX_ATTR_GET(val, LLI_CREDIT);
+ *resend_timer = HINIC_MSIX_ATTR_GET(val, RESEND_TIMER);
+ return 0;
+}
+
+/**
+ * hinic_msix_attr_cnt_clear - clear message attribute counters for msix entry
+ * @hwif: the HW interface of a pci function device
+ * @msix_index: msix_index
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index)
+{
+ u32 msix_ctrl, addr;
+
+ if (!VALID_MSIX_IDX(&hwif->attr, msix_index))
+ return -EINVAL;
+
+ msix_ctrl = HINIC_MSIX_CNT_SET(1, RESEND_TIMER);
+
+ addr = HINIC_CSR_MSIX_CNT_ADDR(msix_index);
+
+ hinic_hwif_write_reg(hwif, addr, msix_ctrl);
+ return 0;
+}
+
/**
* hwif_ready - test if the HW is ready for use
* @hwif: the HW interface of a pci function device
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 98623d6..707a046 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -88,6 +88,34 @@
((val) & (~(HINIC_PPF_ELECTION_##member##_MASK \
<< HINIC_PPF_ELECTION_##member##_SHIFT)))
+#define HINIC_MSIX_PENDING_LIMIT_SHIFT 0
+#define HINIC_MSIX_COALESC_TIMER_SHIFT 8
+#define HINIC_MSIX_LLI_TIMER_SHIFT 16
+#define HINIC_MSIX_LLI_CREDIT_SHIFT 24
+#define HINIC_MSIX_RESEND_TIMER_SHIFT 29
+
+#define HINIC_MSIX_PENDING_LIMIT_MASK 0xFF
+#define HINIC_MSIX_COALESC_TIMER_MASK 0xFF
+#define HINIC_MSIX_LLI_TIMER_MASK 0xFF
+#define HINIC_MSIX_LLI_CREDIT_MASK 0x1F
+#define HINIC_MSIX_RESEND_TIMER_MASK 0x7
+
+#define HINIC_MSIX_ATTR_SET(val, member) \
+ (((u32)(val) & HINIC_MSIX_##member##_MASK) << \
+ HINIC_MSIX_##member##_SHIFT)
+
+#define HINIC_MSIX_ATTR_GET(val, member) \
+ (((val) >> HINIC_MSIX_##member##_SHIFT) & \
+ HINIC_MSIX_##member##_MASK)
+
+#define HINIC_MSIX_CNT_RESEND_TIMER_SHIFT 29
+
+#define HINIC_MSIX_CNT_RESEND_TIMER_MASK 0x1
+
+#define HINIC_MSIX_CNT_SET(val, member) \
+ (((u32)(val) & HINIC_MSIX_CNT_##member##_MASK) << \
+ HINIC_MSIX_CNT_##member##_SHIFT)
+
#define HINIC_HWIF_NUM_AEQS(hwif) ((hwif)->attr.num_aeqs)
#define HINIC_HWIF_NUM_CEQS(hwif) ((hwif)->attr.num_ceqs)
#define HINIC_HWIF_NUM_IRQS(hwif) ((hwif)->attr.num_irqs)
@@ -105,6 +133,12 @@
#define HINIC_PCIE_AT_DISABLE 0
#define HINIC_PCIE_PH_DISABLE 0
+#define HINIC_EQ_MSIX_PENDING_LIMIT_DEFAULT 0 /* Disabled */
+#define HINIC_EQ_MSIX_COALESC_TIMER_DEFAULT 0xFF /* max */
+#define HINIC_EQ_MSIX_LLI_TIMER_DEFAULT 0 /* Disabled */
+#define HINIC_EQ_MSIX_LLI_CREDIT_LIMIT_DEFAULT 0 /* Disabled */
+#define HINIC_EQ_MSIX_RESEND_TIMER_DEFAULT 7 /* max */
+
enum hinic_pcie_nosnoop {
HINIC_PCIE_SNOOP = 0,
HINIC_PCIE_NO_SNOOP = 1,
@@ -166,6 +200,18 @@ static inline void hinic_hwif_write_reg(struct hinic_hwif *hwif, u32 reg,
writel(cpu_to_be32(val), hwif->cfg_regs_bar + reg);
}
+int hinic_msix_attr_set(struct hinic_hwif *hwif, u16 msix_index,
+ u8 pending_limit, u8 coalesc_timer,
+ u8 lli_timer_cfg, u8 lli_credit_limit,
+ u8 resend_timer);
+
+int hinic_msix_attr_get(struct hinic_hwif *hwif, u16 msix_index,
+ u8 *pending_limit, u8 *coalesc_timer_cfg,
+ u8 *lli_timer, u8 *lli_credit_limit,
+ u8 *resend_timer);
+
+int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index);
+
int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev);
void hinic_free_hwif(struct hinic_hwif *hwif);
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 06/21] net-next/hinic: Add api cmd commands
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Add the api cmd commands for sending management messages to the nic.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.c | 329 ++++++++++++++++++++-
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.h | 65 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h | 6 +
3 files changed, 398 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
index b44ddf2..d0145c6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
@@ -25,7 +25,9 @@
#include <linux/jiffies.h>
#include <linux/delay.h>
#include <linux/log2.h>
+#include <linux/semaphore.h>
#include <asm/byteorder.h>
+#include <asm/barrier.h>
#include "hinic_hw_csr.h"
#include "hinic_hw_if.h"
@@ -45,14 +47,313 @@
#define API_CMD_BUF_SIZE 2048
+/* Sizes of the members in hinic_api_cmd_cell */
+#define API_CMD_CELL_DESC_SIZE 8
+#define API_CMD_CELL_DATA_ADDR_SIZE 8
+
+#define API_CMD_CELL_ALIGNMENT 8
+
#define API_CMD_TIMEOUT 1000
+#define MASKED_IDX(chain, idx) ((idx) & ((chain)->num_cells - 1))
+
+#define SIZE_8BYTES(size) (ALIGN((size), 8) >> 3)
+#define SIZE_4BYTES(size) (ALIGN((size), 4) >> 2)
+
+#define RD_DMA_ATTR_DEFAULT 0
+#define WR_DMA_ATTR_DEFAULT 0
+
+enum api_cmd_data_format {
+ SGE_DATA = 1, /* cell data is passed by hw address */
+};
+
+enum api_cmd_type {
+ API_CMD_WRITE = 0,
+};
+
+enum api_cmd_bypass {
+ NO_BYPASS = 0,
+ BYPASS = 1,
+};
+
enum api_cmd_xor_chk_level {
XOR_CHK_DIS = 0,
XOR_CHK_ALL = 3,
};
+static u8 xor_chksum_set(void *data)
+{
+ int idx;
+ u8 *val, checksum = 0;
+
+ val = data;
+
+ for (idx = 0; idx < 7; idx++)
+ checksum ^= val[idx];
+
+ return checksum;
+}
+
+static void set_prod_idx(struct hinic_api_cmd_chain *chain)
+{
+ enum hinic_api_cmd_chain_type chain_type = chain->chain_type;
+ struct hinic_hwif *hwif = chain->hwif;
+ u32 hw_prod_idx_addr, prod_idx;
+
+ hw_prod_idx_addr = HINIC_CSR_API_CMD_CHAIN_PI_ADDR(chain_type);
+ prod_idx = hinic_hwif_read_reg(hwif, hw_prod_idx_addr);
+
+ prod_idx = HINIC_API_CMD_PI_CLEAR(prod_idx, IDX);
+
+ prod_idx |= HINIC_API_CMD_PI_SET(chain->prod_idx, IDX);
+
+ hinic_hwif_write_reg(hwif, hw_prod_idx_addr, prod_idx);
+}
+
+static u32 get_hw_cons_idx(struct hinic_api_cmd_chain *chain)
+{
+ u32 addr, val;
+
+ addr = HINIC_CSR_API_CMD_STATUS_ADDR(chain->chain_type);
+ val = hinic_hwif_read_reg(chain->hwif, addr);
+
+ return HINIC_API_CMD_STATUS_GET(val, CONS_IDX);
+}
+
+/**
+ * chain_busy - check if the chain is still processing last requests
+ * @chain: chain to check
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int chain_busy(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ u32 prod_idx;
+
+ switch (chain->chain_type) {
+ case HINIC_API_CMD_WRITE_TO_MGMT_CPU:
+ chain->cons_idx = get_hw_cons_idx(chain);
+ prod_idx = chain->prod_idx;
+
+ /* check for a space for a new command */
+ if (chain->cons_idx == MASKED_IDX(chain, prod_idx + 1)) {
+ dev_err(&pdev->dev, "API CMD chain %d is busy\n",
+ chain->chain_type);
+ return -EBUSY;
+ }
+ break;
+
+ default:
+ dev_err(&pdev->dev, "Unknown API CMD Chain type\n");
+ break;
+ }
+
+ return 0;
+}
+
+/**
+ * get_cell_data_size - get the data size of a specific cell type
+ * @type: chain type
+ *
+ * Return the data(Desc + Address) size in the cell
+ **/
+static u8 get_cell_data_size(enum hinic_api_cmd_chain_type type)
+{
+ u8 cell_data_size = 0;
+
+ switch (type) {
+ case HINIC_API_CMD_WRITE_TO_MGMT_CPU:
+ cell_data_size = ALIGN(API_CMD_CELL_DESC_SIZE +
+ API_CMD_CELL_DATA_ADDR_SIZE,
+ API_CMD_CELL_ALIGNMENT);
+ break;
+ default:
+ break;
+ }
+
+ return cell_data_size;
+}
+
+/**
+ * prepare_cell_ctrl - prepare the ctrl of the cell for the command
+ * @cell_ctrl: the control of the cell to set the control value into it
+ * @data_size: the size of the data in the cell
+ **/
+static void prepare_cell_ctrl(u64 *cell_ctrl, u16 data_size)
+{
+ u8 chksum;
+ u64 ctrl;
+
+ ctrl = HINIC_API_CMD_CELL_CTRL_SET(SIZE_8BYTES(data_size), DATA_SZ) |
+ HINIC_API_CMD_CELL_CTRL_SET(RD_DMA_ATTR_DEFAULT, RD_DMA_ATTR) |
+ HINIC_API_CMD_CELL_CTRL_SET(WR_DMA_ATTR_DEFAULT, WR_DMA_ATTR);
+
+ chksum = xor_chksum_set(&ctrl);
+
+ ctrl |= HINIC_API_CMD_CELL_CTRL_SET(chksum, XOR_CHKSUM);
+
+ /* The data in the HW should be in Big Endian Format */
+ *cell_ctrl = cpu_to_be64(ctrl);
+}
+
+/**
+ * prepare_api_cmd - prepare API CMD command
+ * @chain: chain for the command
+ * @dest: destination node on the card that will receive the command
+ * @cmd: command data
+ * @cmd_size: the command size
+ **/
+static void prepare_api_cmd(struct hinic_api_cmd_chain *chain,
+ enum hinic_node_id dest,
+ void *cmd, u16 cmd_size)
+{
+ struct hinic_api_cmd_cell *cell = chain->curr_node;
+ struct hinic_api_cmd_cell_ctxt *cell_ctxt;
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+
+ cell_ctxt = &chain->cell_ctxt[chain->prod_idx];
+
+ switch (chain->chain_type) {
+ case HINIC_API_CMD_WRITE_TO_MGMT_CPU:
+ cell->desc = HINIC_API_CMD_DESC_SET(SGE_DATA, API_TYPE) |
+ HINIC_API_CMD_DESC_SET(API_CMD_WRITE, RD_WR) |
+ HINIC_API_CMD_DESC_SET(NO_BYPASS, MGMT_BYPASS);
+ break;
+
+ default:
+ dev_err(&pdev->dev, "unknown Chain type\n");
+ return;
+ }
+
+ cell->desc |= HINIC_API_CMD_DESC_SET(dest, DEST) |
+ HINIC_API_CMD_DESC_SET(SIZE_4BYTES(cmd_size), SIZE);
+
+ cell->desc |= HINIC_API_CMD_DESC_SET(xor_chksum_set(&cell->desc),
+ XOR_CHKSUM);
+
+ /* The data in the HW should be in Big Endian Format */
+ cell->desc = cpu_to_be64(cell->desc);
+
+ memcpy(cell_ctxt->api_cmd_vaddr, cmd, cmd_size);
+}
+
+/**
+ * prepare_cell - prepare cell ctrl and cmd in the current cell
+ * @chain: chain for the command
+ * @dest: destination node on the card that will receive the command
+ * @cmd: command data
+ * @cmd_size: the command size
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static void prepare_cell(struct hinic_api_cmd_chain *chain,
+ enum hinic_node_id dest,
+ void *cmd, u16 cmd_size)
+{
+ struct hinic_api_cmd_cell *curr_node = chain->curr_node;
+ u16 data_size = get_cell_data_size(chain->chain_type);
+
+ prepare_cell_ctrl(&curr_node->ctrl, data_size);
+ prepare_api_cmd(chain, dest, cmd, cmd_size);
+}
+
+static inline void cmd_chain_prod_idx_inc(struct hinic_api_cmd_chain *chain)
+{
+ chain->prod_idx = MASKED_IDX(chain, chain->prod_idx + 1);
+}
+
+/**
+ * api_cmd_status_update - update the status in the chain struct
+ * @chain: chain to update
+ **/
+static void api_cmd_status_update(struct hinic_api_cmd_chain *chain)
+{
+ enum hinic_api_cmd_chain_type chain_type;
+ struct hinic_api_cmd_status *wb_status;
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ u64 status_header;
+ u32 status;
+
+ wb_status = chain->wb_status;
+ status_header = be64_to_cpu(wb_status->header);
+
+ status = be32_to_cpu(wb_status->status);
+ if (HINIC_API_CMD_STATUS_GET(status, CHKSUM_ERR)) {
+ dev_err(&pdev->dev, "API CMD status: Xor check error\n");
+ return;
+ }
+
+ chain_type = HINIC_API_CMD_STATUS_HEADER_GET(status_header, CHAIN_ID);
+ if (chain_type >= HINIC_API_CMD_MAX) {
+ dev_err(&pdev->dev, "unknown API CMD Chain %d\n", chain_type);
+ return;
+ }
+
+ chain->cons_idx = HINIC_API_CMD_STATUS_GET(status, CONS_IDX);
+}
+
+/**
+ * wait_for_status_poll - wait for write to api cmd command to complete
+ * @chain: the chain of the command
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int wait_for_status_poll(struct hinic_api_cmd_chain *chain)
+{
+ int err = -ETIMEDOUT;
+ unsigned long end;
+
+ end = jiffies + msecs_to_jiffies(API_CMD_TIMEOUT);
+ do {
+ api_cmd_status_update(chain);
+
+ /* wait for CI to be updated - sign for completion */
+ if (chain->cons_idx == chain->prod_idx) {
+ err = 0;
+ break;
+ }
+
+ msleep(20);
+ } while (time_before(jiffies, end));
+
+ return err;
+}
+
+/**
+ * wait_for_api_cmd_completion - wait for command to complete
+ * @chain: chain for the command
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int wait_for_api_cmd_completion(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int err;
+
+ switch (chain->chain_type) {
+ case HINIC_API_CMD_WRITE_TO_MGMT_CPU:
+ err = wait_for_status_poll(chain);
+ if (err) {
+ dev_err(&pdev->dev, "API CMD Poll status timeout\n");
+ break;
+ }
+ break;
+
+ default:
+ dev_err(&pdev->dev, "unknown API CMD Chain type\n");
+ err = -EINVAL;
+ break;
+ }
+
+ return err;
+}
+
/**
* api_cmd - API CMD command
* @chain: chain for the command
@@ -65,8 +366,30 @@ enum api_cmd_xor_chk_level {
static int api_cmd(struct hinic_api_cmd_chain *chain,
enum hinic_node_id dest, u8 *cmd, u16 cmd_size)
{
- /* should be implemented */
- return -EINVAL;
+ struct hinic_api_cmd_cell_ctxt *ctxt;
+ int err;
+
+ down(&chain->sem);
+ if (chain_busy(chain)) {
+ up(&chain->sem);
+ return -EBUSY;
+ }
+
+ prepare_cell(chain, dest, cmd, cmd_size);
+ cmd_chain_prod_idx_inc(chain);
+
+ wmb(); /* inc pi before issue the command */
+
+ set_prod_idx(chain); /* issue the command */
+
+ ctxt = &chain->cell_ctxt[chain->prod_idx];
+
+ chain->curr_node = ctxt->cell_vaddr;
+
+ err = wait_for_api_cmd_completion(chain);
+
+ up(&chain->sem);
+ return err;
}
/**
@@ -491,6 +814,8 @@ static int api_chain_init(struct hinic_api_cmd_chain *chain,
chain->prod_idx = 0;
chain->cons_idx = 0;
+ sema_init(&chain->sem, 1);
+
cell_ctxt_size = chain->num_cells * sizeof(*chain->cell_ctxt);
chain->cell_ctxt = devm_kzalloc(&pdev->dev, cell_ctxt_size, GFP_KERNEL);
if (!chain->cell_ctxt)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
index e8865d6..31b94d5 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
@@ -17,9 +17,22 @@
#define HINIC_HW_API_CMD_H
#include <linux/types.h>
+#include <linux/semaphore.h>
#include "hinic_hw_if.h"
+#define HINIC_API_CMD_PI_IDX_SHIFT 0
+
+#define HINIC_API_CMD_PI_IDX_MASK 0xFFFFFF
+
+#define HINIC_API_CMD_PI_SET(val, member) \
+ (((u32)(val) & HINIC_API_CMD_PI_##member##_MASK) << \
+ HINIC_API_CMD_PI_##member##_SHIFT)
+
+#define HINIC_API_CMD_PI_CLEAR(val, member) \
+ ((val) & (~(HINIC_API_CMD_PI_##member##_MASK \
+ << HINIC_API_CMD_PI_##member##_SHIFT)))
+
#define HINIC_API_CMD_CHAIN_REQ_RESTART_SHIFT 1
#define HINIC_API_CMD_CHAIN_REQ_RESTART_MASK 0x1
@@ -58,6 +71,56 @@
((val) & (~(HINIC_API_CMD_CHAIN_CTRL_##member##_MASK \
<< HINIC_API_CMD_CHAIN_CTRL_##member##_SHIFT)))
+#define HINIC_API_CMD_CELL_CTRL_DATA_SZ_SHIFT 0
+#define HINIC_API_CMD_CELL_CTRL_RD_DMA_ATTR_SHIFT 16
+#define HINIC_API_CMD_CELL_CTRL_WR_DMA_ATTR_SHIFT 24
+#define HINIC_API_CMD_CELL_CTRL_XOR_CHKSUM_SHIFT 56
+
+#define HINIC_API_CMD_CELL_CTRL_DATA_SZ_MASK 0x3F
+#define HINIC_API_CMD_CELL_CTRL_RD_DMA_ATTR_MASK 0x3F
+#define HINIC_API_CMD_CELL_CTRL_WR_DMA_ATTR_MASK 0x3F
+#define HINIC_API_CMD_CELL_CTRL_XOR_CHKSUM_MASK 0xFF
+
+#define HINIC_API_CMD_CELL_CTRL_SET(val, member) \
+ ((((u64)val) & HINIC_API_CMD_CELL_CTRL_##member##_MASK) << \
+ HINIC_API_CMD_CELL_CTRL_##member##_SHIFT)
+
+#define HINIC_API_CMD_DESC_API_TYPE_SHIFT 0
+#define HINIC_API_CMD_DESC_RD_WR_SHIFT 1
+#define HINIC_API_CMD_DESC_MGMT_BYPASS_SHIFT 2
+#define HINIC_API_CMD_DESC_DEST_SHIFT 32
+#define HINIC_API_CMD_DESC_SIZE_SHIFT 40
+#define HINIC_API_CMD_DESC_XOR_CHKSUM_SHIFT 56
+
+#define HINIC_API_CMD_DESC_API_TYPE_MASK 0x1
+#define HINIC_API_CMD_DESC_RD_WR_MASK 0x1
+#define HINIC_API_CMD_DESC_MGMT_BYPASS_MASK 0x1
+#define HINIC_API_CMD_DESC_DEST_MASK 0x1F
+#define HINIC_API_CMD_DESC_SIZE_MASK 0x7FF
+#define HINIC_API_CMD_DESC_XOR_CHKSUM_MASK 0xFF
+
+#define HINIC_API_CMD_DESC_SET(val, member) \
+ ((((u64)val) & HINIC_API_CMD_DESC_##member##_MASK) << \
+ HINIC_API_CMD_DESC_##member##_SHIFT)
+
+#define HINIC_API_CMD_STATUS_HEADER_CHAIN_ID_SHIFT 16
+
+#define HINIC_API_CMD_STATUS_HEADER_CHAIN_ID_MASK 0xFF
+
+#define HINIC_API_CMD_STATUS_HEADER_GET(val, member) \
+ (((val) >> HINIC_API_CMD_STATUS_HEADER_##member##_SHIFT) & \
+ HINIC_API_CMD_STATUS_HEADER_##member##_MASK)
+
+#define HINIC_API_CMD_STATUS_CONS_IDX_SHIFT 0
+#define HINIC_API_CMD_STATUS_CHKSUM_ERR_SHIFT 28
+
+#define HINIC_API_CMD_STATUS_CONS_IDX_MASK 0xFFFFFF
+#define HINIC_API_CMD_STATUS_CHKSUM_ERR_MASK 0x3
+
+#define HINIC_API_CMD_STATUS_GET(val, member) \
+ (((val) >> HINIC_API_CMD_STATUS_##member##_SHIFT) & \
+ HINIC_API_CMD_STATUS_##member##_MASK)
+
enum hinic_api_cmd_chain_type {
HINIC_API_CMD_WRITE_TO_MGMT_CPU = 2,
@@ -122,6 +185,8 @@ struct hinic_api_cmd_chain {
u32 prod_idx;
u32 cons_idx;
+ struct semaphore sem;
+
struct hinic_api_cmd_cell_ctxt *cell_ctxt;
dma_addr_t wb_status_paddr;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
index a9ece6d..ebbf054 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
@@ -56,7 +56,13 @@
#define HINIC_CSR_API_CMD_CHAIN_CTRL_ADDR(idx) \
(HINIC_CSR_API_CMD_BASE + 0x14 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+#define HINIC_CSR_API_CMD_CHAIN_PI_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x1C + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
#define HINIC_CSR_API_CMD_CHAIN_REQ_ADDR(idx) \
(HINIC_CSR_API_CMD_BASE + 0x20 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+#define HINIC_CSR_API_CMD_STATUS_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x30 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
#endif
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 05/21] net-next/hinic: Add management messages
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Add the management messages for sending to api cmd and add the
asynchronous event handler for the completion of the messages.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.c | 35 ++
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.h | 3 +
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 5 +
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 439 ++++++++++++++++++++-
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h | 59 +++
5 files changed, 538 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
index 234ede9..b44ddf2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
@@ -54,6 +54,41 @@ enum api_cmd_xor_chk_level {
};
/**
+ * api_cmd - API CMD command
+ * @chain: chain for the command
+ * @dest: destination node on the card that will receive the command
+ * @cmd: command data
+ * @size: the command size
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int api_cmd(struct hinic_api_cmd_chain *chain,
+ enum hinic_node_id dest, u8 *cmd, u16 cmd_size)
+{
+ /* should be implemented */
+ return -EINVAL;
+}
+
+/**
+ * hinic_api_cmd_write - Write API CMD command
+ * @chain: chain for write command
+ * @dest: destination node on the card that will receive the command
+ * @cmd: command data
+ * @size: the command size
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_api_cmd_write(struct hinic_api_cmd_chain *chain,
+ enum hinic_node_id dest, u8 *cmd, u16 size)
+{
+ /* Verify the chain type */
+ if (chain->chain_type == HINIC_API_CMD_WRITE_TO_MGMT_CPU)
+ return api_cmd(chain, dest, cmd, size);
+
+ return -EINVAL;
+}
+
+/**
* api_cmd_hw_restart - restart the chain in the HW
* @chain: the API CMD specific chain to restart
*
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
index 0c83b80..e8865d6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
@@ -132,6 +132,9 @@ struct hinic_api_cmd_chain {
struct hinic_api_cmd_cell *curr_node;
};
+int hinic_api_cmd_write(struct hinic_api_cmd_chain *chain,
+ enum hinic_node_id dest, u8 *cmd, u16 size);
+
int hinic_api_cmd_init(struct hinic_api_cmd_chain **chain,
struct hinic_hwif *hwif);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index b6d9850..98623d6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -93,6 +93,7 @@
#define HINIC_HWIF_NUM_IRQS(hwif) ((hwif)->attr.num_irqs)
#define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx)
#define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx)
+#define HINIC_HWIF_PF_IDX(hwif) ((hwif)->attr.pf_idx)
#define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type)
#define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF)
@@ -127,6 +128,10 @@ enum hinic_mod_type {
HINIC_MOD_MAX = 15
};
+enum hinic_node_id {
+ HINIC_NODE_ID_MGMT = 21,
+};
+
struct hinic_func_attr {
u16 func_idx;
u8 pf_idx;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index f914bc7..147c404 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -16,6 +16,12 @@
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/semaphore.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <asm/barrier.h>
#include "hinic_hw_if.h"
#include "hinic_hw_eqs.h"
@@ -23,9 +29,267 @@
#include "hinic_hw_mgmt.h"
#include "hinic_hw_dev.h"
+#define SYNC_MSG_ID_MASK 0x1FF
+
+#define SYNC_MSG_ID(pf_to_mgmt) ((pf_to_mgmt)->sync_msg_id)
+
+#define SYNC_MSG_ID_INC(pf_to_mgmt) (SYNC_MSG_ID(pf_to_mgmt) = \
+ ((SYNC_MSG_ID(pf_to_mgmt) + 1) & \
+ SYNC_MSG_ID_MASK))
+
+#define MSG_SZ_IS_VALID(in_size) ((in_size) <= MAX_MSG_LEN)
+
+#define MGMT_MSG_LEN_MIN 20
+#define MGMT_MSG_LEN_STEP 16
+#define MGMT_MSG_RSVD_FOR_DEV 8
+
+#define SEGMENT_LEN 48
+
+#define MAX_PF_MGMT_BUF_SIZE 2048
+
+/* Data should be SEG LEN size aligned */
+#define MAX_MSG_LEN 2016
+
+#define MSG_NOT_RESP 0xFFFF
+
+#define MGMT_MSG_TIMEOUT 1000
+
#define mgmt_to_pfhwdev(pf_mgmt) \
container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt)
+enum msg_segment_type {
+ NOT_LAST_SEGMENT = 0,
+ LAST_SEGMENT = 1,
+};
+
+enum mgmt_direction_type {
+ MGMT_DIRECT_SEND = 0,
+ MGMT_RESP = 1,
+};
+
+enum msg_ack_type {
+ MSG_ACK = 0,
+ MSG_NO_ACK = 1,
+};
+
+/**
+ * prepare_header - prepare the header of the message
+ * @pf_to_mgmt: PF to MGMT channel
+ * @msg_len: the length of the message
+ * @mod: module in the chip that will get the message
+ * @ack_type: ask for response
+ * @direction: the direction of the message
+ * @cmd: command of the message
+ * @msg_id: message id
+ *
+ * Return the prepared header value
+ **/
+static u64 prepare_header(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ u16 msg_len, enum hinic_mod_type mod,
+ enum msg_ack_type ack_type,
+ enum mgmt_direction_type direction,
+ u16 cmd, u16 msg_id)
+{
+ struct hinic_hwif *hwif = pf_to_mgmt->hwif;
+
+ return HINIC_MSG_HEADER_SET(msg_len, MSG_LEN) |
+ HINIC_MSG_HEADER_SET(mod, MODULE) |
+ HINIC_MSG_HEADER_SET(SEGMENT_LEN, SEG_LEN) |
+ HINIC_MSG_HEADER_SET(ack_type, NO_ACK) |
+ HINIC_MSG_HEADER_SET(0, ASYNC_MGMT_TO_PF) |
+ HINIC_MSG_HEADER_SET(0, SEQID) |
+ HINIC_MSG_HEADER_SET(LAST_SEGMENT, LAST) |
+ HINIC_MSG_HEADER_SET(direction, DIRECTION) |
+ HINIC_MSG_HEADER_SET(cmd, CMD) |
+ HINIC_MSG_HEADER_SET(HINIC_HWIF_PCI_INTF(hwif), PCI_INTF) |
+ HINIC_MSG_HEADER_SET(HINIC_HWIF_PF_IDX(hwif), PF_IDX) |
+ HINIC_MSG_HEADER_SET(msg_id, MSG_ID);
+}
+
+/**
+ * prepare_mgmt_cmd - prepare the mgmt command
+ * @mgmt_cmd: pointer to the command to prepare
+ * @header: pointer of the header for the message
+ * @msg: the data of the message
+ * @msg_len: the length of the message
+ **/
+static void prepare_mgmt_cmd(u8 *mgmt_cmd, u64 *header, u8 *msg, u16 msg_len)
+{
+ memset(mgmt_cmd, 0, MGMT_MSG_RSVD_FOR_DEV);
+
+ mgmt_cmd += MGMT_MSG_RSVD_FOR_DEV;
+ memcpy(mgmt_cmd, header, sizeof(*header));
+
+ mgmt_cmd += sizeof(*header);
+ memcpy(mgmt_cmd, msg, msg_len);
+}
+
+/**
+ * mgmt_msg_len - calculate the total message length
+ * @msg_data_len: the length of the message data
+ *
+ * Return the total message length
+ **/
+static u16 mgmt_msg_len(u16 msg_data_len)
+{
+ /* RSVD + HEADER_SIZE + DATA_LEN */
+ u16 msg_len = MGMT_MSG_RSVD_FOR_DEV + sizeof(u64) + msg_data_len;
+
+ if (msg_len > MGMT_MSG_LEN_MIN)
+ msg_len = MGMT_MSG_LEN_MIN +
+ ALIGN((msg_len - MGMT_MSG_LEN_MIN),
+ MGMT_MSG_LEN_STEP);
+ else
+ msg_len = MGMT_MSG_LEN_MIN;
+
+ return msg_len;
+}
+
+/**
+ * send_msg_to_mgmt - send message to mgmt by API CMD
+ * @pf_to_mgmt: PF to MGMT channel
+ * @mod: module in the chip that will get the message
+ * @cmd: command of the message
+ * @data: the msg data
+ * @data_len: the msg data length
+ * @ack_type: ask for response
+ * @direction: the direction of the original message
+ * @resp_msg_id: msg id to response for
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int send_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ enum hinic_mod_type mod, u8 cmd,
+ u8 *data, u16 data_len,
+ enum msg_ack_type ack_type,
+ enum mgmt_direction_type direction,
+ u16 resp_msg_id)
+{
+ struct hinic_api_cmd_chain *chain;
+ u64 header;
+ u16 msg_id;
+
+ msg_id = SYNC_MSG_ID(pf_to_mgmt);
+
+ if (direction == MGMT_RESP) {
+ header = prepare_header(pf_to_mgmt, data_len, mod, ack_type,
+ direction, cmd, resp_msg_id);
+ } else {
+ SYNC_MSG_ID_INC(pf_to_mgmt);
+ header = prepare_header(pf_to_mgmt, data_len, mod, ack_type,
+ direction, cmd, msg_id);
+ }
+
+ prepare_mgmt_cmd(pf_to_mgmt->sync_msg_buf, &header, data, data_len);
+
+ chain = pf_to_mgmt->cmd_chain[HINIC_API_CMD_WRITE_TO_MGMT_CPU];
+ return hinic_api_cmd_write(chain, HINIC_NODE_ID_MGMT,
+ pf_to_mgmt->sync_msg_buf,
+ mgmt_msg_len(data_len));
+}
+
+/**
+ * msg_to_mgmt_sync - send sync message to mgmt
+ * @pf_to_mgmt: PF to MGMT channel
+ * @mod: module in the chip that will get the message
+ * @cmd: command of the message
+ * @buf_in: the msg data
+ * @in_size: the msg data length
+ * @buf_out: response
+ * @out_size: response length
+ * @direction: the direction of the original message
+ * @resp_msg_id: msg id to response for
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ enum hinic_mod_type mod, u8 cmd,
+ u8 *buf_in, u16 in_size,
+ u8 *buf_out, u16 *out_size,
+ enum mgmt_direction_type direction,
+ u16 resp_msg_id)
+{
+ struct hinic_hwif *hwif = pf_to_mgmt->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_recv_msg *recv_msg;
+ struct completion *recv_done;
+ u16 msg_id;
+ int err;
+
+ /* Lock the sync_msg_buf */
+ down(&pf_to_mgmt->sync_msg_lock);
+
+ recv_msg = &pf_to_mgmt->recv_resp_msg_from_mgmt;
+ recv_done = &recv_msg->recv_done;
+
+ if (resp_msg_id == MSG_NOT_RESP)
+ msg_id = SYNC_MSG_ID(pf_to_mgmt);
+ else
+ msg_id = resp_msg_id;
+
+ init_completion(recv_done);
+
+ err = send_msg_to_mgmt(pf_to_mgmt, mod, cmd, buf_in, in_size,
+ MSG_ACK, direction, resp_msg_id);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to send sync msg to mgmt\n");
+ goto unlock_sync_msg;
+ }
+
+ if (!wait_for_completion_timeout(recv_done, MGMT_MSG_TIMEOUT)) {
+ dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id);
+ err = -ETIMEDOUT;
+ goto unlock_sync_msg;
+ }
+
+ smp_rmb(); /* verify reading after completion */
+
+ if (recv_msg->msg_id != msg_id) {
+ dev_err(&pdev->dev, "incorrect MSG for id = %d\n", msg_id);
+ err = -EFAULT;
+ goto unlock_sync_msg;
+ }
+
+ if ((buf_out) && (recv_msg->msg_len <= MAX_PF_MGMT_BUF_SIZE)) {
+ memcpy(buf_out, recv_msg->msg, recv_msg->msg_len);
+ *out_size = recv_msg->msg_len;
+ }
+
+unlock_sync_msg:
+ up(&pf_to_mgmt->sync_msg_lock);
+ return err;
+}
+
+/**
+ * msg_to_mgmt_async - send message to mgmt without response
+ * @pf_to_mgmt: PF to MGMT channel
+ * @mod: module in the chip that will get the message
+ * @cmd: command of the message
+ * @buf_in: the msg data
+ * @in_size: the msg data length
+ * @direction: the direction of the original message
+ * @resp_msg_id: msg id to response for
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int msg_to_mgmt_async(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ enum hinic_mod_type mod, u8 cmd,
+ u8 *buf_in, u16 in_size,
+ enum mgmt_direction_type direction,
+ u16 resp_msg_id)
+{
+ int err;
+
+ /* Lock the sync_msg_buf */
+ down(&pf_to_mgmt->sync_msg_lock);
+
+ err = send_msg_to_mgmt(pf_to_mgmt, mod, cmd, buf_in, in_size,
+ MSG_NO_ACK, direction, resp_msg_id);
+
+ up(&pf_to_mgmt->sync_msg_lock);
+ return err;
+}
+
/**
* hinic_msg_to_mgmt - send message to mgmt
* @pf_to_mgmt: PF to MGMT channel
@@ -44,8 +308,98 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
void *buf_in, u16 in_size, void *buf_out, u16 *out_size,
enum hinic_mgmt_msg_type sync)
{
- /* should be implemented */
- return -EINVAL;
+ struct hinic_hwif *hwif = pf_to_mgmt->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+
+ if (sync != HINIC_MGMT_MSG_SYNC) {
+ dev_err(&pdev->dev, "Invalid MGMT msg type\n");
+ return -EINVAL;
+ }
+
+ if (!MSG_SZ_IS_VALID(in_size)) {
+ dev_err(&pdev->dev, "Invalid MGMT msg buffer size\n");
+ return -EINVAL;
+ }
+
+ return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
+ buf_out, out_size, MGMT_DIRECT_SEND,
+ MSG_NOT_RESP);
+}
+
+/**
+ * mgmt_recv_msg_handler - handler for message from mgmt cpu
+ * @pf_to_mgmt: PF to MGMT channel
+ * @recv_msg: received message details
+ **/
+static void mgmt_recv_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ struct hinic_recv_msg *recv_msg)
+{
+ struct hinic_hwif *hwif = pf_to_mgmt->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ u8 *buf_out = recv_msg->buf_out;
+ u16 out_size = 0;
+
+ dev_err(&pdev->dev, "No MGMT msg handler, mod = %d\n", recv_msg->mod);
+
+ if (!recv_msg->async_mgmt_to_pf)
+ /* MGMT sent sync msg, send the response */
+ msg_to_mgmt_async(pf_to_mgmt, recv_msg->mod, recv_msg->cmd,
+ buf_out, out_size, MGMT_RESP,
+ recv_msg->msg_id);
+}
+
+/**
+ * mgmt_resp_msg_handler - handler for a response message from mgmt cpu
+ * @pf_to_mgmt: PF to MGMT channel
+ * @recv_msg: received message details
+ **/
+static void mgmt_resp_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ struct hinic_recv_msg *recv_msg)
+{
+ wmb(); /* verify writing all, before reading */
+
+ complete(&recv_msg->recv_done);
+}
+
+/**
+ * recv_mgmt_msg_handler - handler for a message from mgmt cpu
+ * @pf_to_mgmt: PF to MGMT channel
+ * @header: the header of the message
+ * @recv_msg: received message details
+ **/
+static void recv_mgmt_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ u64 *header, struct hinic_recv_msg *recv_msg)
+{
+ struct hinic_hwif *hwif = pf_to_mgmt->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int seq_id, seg_len;
+ u8 *msg_body;
+
+ seq_id = HINIC_MSG_HEADER_GET(*header, SEQID);
+ seg_len = HINIC_MSG_HEADER_GET(*header, SEG_LEN);
+
+ if (seq_id >= (MAX_MSG_LEN / SEGMENT_LEN)) {
+ dev_err(&pdev->dev, "recv big mgmt msg\n");
+ return;
+ }
+
+ msg_body = (u8 *)header + sizeof(*header);
+ memcpy(recv_msg->msg + seq_id * SEGMENT_LEN, msg_body, seg_len);
+
+ if (!HINIC_MSG_HEADER_GET(*header, LAST))
+ return;
+
+ recv_msg->cmd = HINIC_MSG_HEADER_GET(*header, CMD);
+ recv_msg->mod = HINIC_MSG_HEADER_GET(*header, MODULE);
+ recv_msg->async_mgmt_to_pf = HINIC_MSG_HEADER_GET(*header,
+ ASYNC_MGMT_TO_PF);
+ recv_msg->msg_len = HINIC_MSG_HEADER_GET(*header, MSG_LEN);
+ recv_msg->msg_id = HINIC_MSG_HEADER_GET(*header, MSG_ID);
+
+ if (HINIC_MSG_HEADER_GET(*header, DIRECTION) == MGMT_RESP)
+ mgmt_resp_msg_handler(pf_to_mgmt, recv_msg);
+ else
+ mgmt_recv_msg_handler(pf_to_mgmt, recv_msg);
}
/**
@@ -56,7 +410,77 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
**/
static void mgmt_msg_aeqe_handler(void *handle, void *data, u8 size)
{
- /* should be implemented */
+ struct hinic_pf_to_mgmt *pf_to_mgmt = handle;
+ struct hinic_recv_msg *recv_msg;
+ u64 *header = (u64 *)data;
+
+ recv_msg = HINIC_MSG_HEADER_GET(*header, DIRECTION) ==
+ MGMT_DIRECT_SEND ?
+ &pf_to_mgmt->recv_msg_from_mgmt :
+ &pf_to_mgmt->recv_resp_msg_from_mgmt;
+
+ recv_mgmt_msg_handler(pf_to_mgmt, header, recv_msg);
+}
+
+/**
+ * alloc_recv_msg - allocate receive message memory
+ * @pf_to_mgmt: PF to MGMT channel
+ * @recv_msg: pointer that will hold the allocated data
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int alloc_recv_msg(struct hinic_pf_to_mgmt *pf_to_mgmt,
+ struct hinic_recv_msg *recv_msg)
+{
+ struct hinic_hwif *hwif = pf_to_mgmt->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+
+ recv_msg->msg = devm_kzalloc(&pdev->dev, MAX_PF_MGMT_BUF_SIZE,
+ GFP_KERNEL);
+ if (!recv_msg->msg)
+ return -ENOMEM;
+
+ recv_msg->buf_out = devm_kzalloc(&pdev->dev, MAX_PF_MGMT_BUF_SIZE,
+ GFP_KERNEL);
+ if (!recv_msg->buf_out)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * alloc_msg_buf - allocate all the message buffers of PF to MGMT channel
+ * @pf_to_mgmt: PF to MGMT channel
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int alloc_msg_buf(struct hinic_pf_to_mgmt *pf_to_mgmt)
+{
+ struct hinic_hwif *hwif = pf_to_mgmt->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int err;
+
+ err = alloc_recv_msg(pf_to_mgmt,
+ &pf_to_mgmt->recv_msg_from_mgmt);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to allocate recv msg\n");
+ return err;
+ }
+
+ err = alloc_recv_msg(pf_to_mgmt,
+ &pf_to_mgmt->recv_resp_msg_from_mgmt);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to allocate resp recv msg\n");
+ return err;
+ }
+
+ pf_to_mgmt->sync_msg_buf = devm_kzalloc(&pdev->dev,
+ MAX_PF_MGMT_BUF_SIZE,
+ GFP_KERNEL);
+ if (!pf_to_mgmt->sync_msg_buf)
+ return -ENOMEM;
+
+ return 0;
}
/**
@@ -76,6 +500,15 @@ int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt,
pf_to_mgmt->hwif = hwif;
+ sema_init(&pf_to_mgmt->sync_msg_lock, 1);
+ pf_to_mgmt->sync_msg_id = 0;
+
+ err = alloc_msg_buf(pf_to_mgmt);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to allocate msg buffers\n");
+ return err;
+ }
+
err = hinic_api_cmd_init(pf_to_mgmt->cmd_chain, hwif);
if (err) {
dev_err(&pdev->dev, "Failed to initialize cmd chains\n");
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
index dff321c..eca7ad8 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
@@ -17,10 +17,48 @@
#define HINIC_HW_MGMT_H
#include <linux/types.h>
+#include <linux/semaphore.h>
+#include <linux/completion.h>
#include "hinic_hw_if.h"
#include "hinic_hw_api_cmd.h"
+#define HINIC_MSG_HEADER_MSG_LEN_SHIFT 0
+#define HINIC_MSG_HEADER_MODULE_SHIFT 11
+#define HINIC_MSG_HEADER_SEG_LEN_SHIFT 16
+#define HINIC_MSG_HEADER_NO_ACK_SHIFT 22
+#define HINIC_MSG_HEADER_ASYNC_MGMT_TO_PF_SHIFT 23
+#define HINIC_MSG_HEADER_SEQID_SHIFT 24
+#define HINIC_MSG_HEADER_LAST_SHIFT 30
+#define HINIC_MSG_HEADER_DIRECTION_SHIFT 31
+#define HINIC_MSG_HEADER_CMD_SHIFT 32
+#define HINIC_MSG_HEADER_ZEROS_SHIFT 40
+#define HINIC_MSG_HEADER_PCI_INTF_SHIFT 48
+#define HINIC_MSG_HEADER_PF_IDX_SHIFT 50
+#define HINIC_MSG_HEADER_MSG_ID_SHIFT 54
+
+#define HINIC_MSG_HEADER_MSG_LEN_MASK 0x7FF
+#define HINIC_MSG_HEADER_MODULE_MASK 0x1F
+#define HINIC_MSG_HEADER_SEG_LEN_MASK 0x3F
+#define HINIC_MSG_HEADER_NO_ACK_MASK 0x1
+#define HINIC_MSG_HEADER_ASYNC_MGMT_TO_PF_MASK 0x1
+#define HINIC_MSG_HEADER_SEQID_MASK 0x3F
+#define HINIC_MSG_HEADER_LAST_MASK 0x1
+#define HINIC_MSG_HEADER_DIRECTION_MASK 0x1
+#define HINIC_MSG_HEADER_CMD_MASK 0xFF
+#define HINIC_MSG_HEADER_ZEROS_MASK 0xFF
+#define HINIC_MSG_HEADER_PCI_INTF_MASK 0x3
+#define HINIC_MSG_HEADER_PF_IDX_MASK 0xF
+#define HINIC_MSG_HEADER_MSG_ID_MASK 0x3FF
+
+#define HINIC_MSG_HEADER_SET(val, member) \
+ ((u64)((val) & HINIC_MSG_HEADER_##member##_MASK) << \
+ HINIC_MSG_HEADER_##member##_SHIFT)
+
+#define HINIC_MSG_HEADER_GET(val, member) \
+ (((val) >> HINIC_MSG_HEADER_##member##_SHIFT) & \
+ HINIC_MSG_HEADER_##member##_MASK)
+
enum hinic_mgmt_msg_type {
HINIC_MGMT_MSG_SYNC = 1,
};
@@ -29,9 +67,30 @@ enum hinic_cfg_cmd {
HINIC_CFG_NIC_CAP = 0,
};
+struct hinic_recv_msg {
+ u8 *msg;
+ u8 *buf_out;
+
+ struct completion recv_done;
+
+ u16 cmd;
+ enum hinic_mod_type mod;
+ int async_mgmt_to_pf;
+
+ u16 msg_len;
+ u16 msg_id;
+};
+
struct hinic_pf_to_mgmt {
struct hinic_hwif *hwif;
+ struct semaphore sync_msg_lock;
+ u16 sync_msg_id;
+ u8 *sync_msg_buf;
+
+ struct hinic_recv_msg recv_resp_msg_from_mgmt;
+ struct hinic_recv_msg recv_msg_from_mgmt;
+
struct hinic_api_cmd_chain *cmd_chain[HINIC_API_CMD_MAX];
};
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 04/21] net-next/hinic: Initialize api cmd hw
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Update the hardware about api cmd resources and initialize it.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.c | 173 ++++++++++++++++++++-
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.h | 38 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h | 26 ++++
3 files changed, 236 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
index 4291f8e..234ede9 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
@@ -13,6 +13,7 @@
*
*/
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/pci.h>
@@ -21,8 +22,12 @@
#include <linux/dma-mapping.h>
#include <linux/bitops.h>
#include <linux/err.h>
+#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/log2.h>
#include <asm/byteorder.h>
+#include "hinic_hw_csr.h"
#include "hinic_hw_if.h"
#include "hinic_hw_api_cmd.h"
@@ -35,8 +40,157 @@
(((cell_size) >= API_CMD_CELL_SIZE_MIN) ? \
(1 << (fls(cell_size - 1))) : API_CMD_CELL_SIZE_MIN)
+#define API_CMD_CELL_SIZE_VAL(size) \
+ ilog2((size) >> API_CMD_CELL_SIZE_SHIFT)
+
#define API_CMD_BUF_SIZE 2048
+#define API_CMD_TIMEOUT 1000
+
+enum api_cmd_xor_chk_level {
+ XOR_CHK_DIS = 0,
+
+ XOR_CHK_ALL = 3,
+};
+
+/**
+ * api_cmd_hw_restart - restart the chain in the HW
+ * @chain: the API CMD specific chain to restart
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int api_cmd_hw_restart(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ int err = -ETIMEDOUT;
+ unsigned long end;
+ u32 reg_addr, val;
+
+ /* Read Modify Write */
+ reg_addr = HINIC_CSR_API_CMD_CHAIN_REQ_ADDR(chain->chain_type);
+ val = hinic_hwif_read_reg(hwif, reg_addr);
+
+ val = HINIC_API_CMD_CHAIN_REQ_CLEAR(val, RESTART);
+ val |= HINIC_API_CMD_CHAIN_REQ_SET(1, RESTART);
+
+ hinic_hwif_write_reg(hwif, reg_addr, val);
+
+ end = jiffies + msecs_to_jiffies(API_CMD_TIMEOUT);
+ do {
+ val = hinic_hwif_read_reg(hwif, reg_addr);
+
+ if (!HINIC_API_CMD_CHAIN_REQ_GET(val, RESTART)) {
+ err = 0;
+ break;
+ }
+
+ msleep(20);
+ } while (time_before(jiffies, end));
+
+ return err;
+}
+
+/**
+ * api_cmd_ctrl_init - set the control register of a chain
+ * @chain: the API CMD specific chain to set control register for
+ **/
+static void api_cmd_ctrl_init(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ u32 reg_addr, ctrl;
+ u16 cell_size;
+
+ /* Read Modify Write */
+ reg_addr = HINIC_CSR_API_CMD_CHAIN_CTRL_ADDR(chain->chain_type);
+
+ cell_size = API_CMD_CELL_SIZE_VAL(chain->cell_size);
+
+ ctrl = hinic_hwif_read_reg(hwif, reg_addr);
+
+ ctrl = HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, RESTART_WB_STAT) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_ERR) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, AEQE_EN) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_CHK_EN) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, CELL_SIZE);
+
+ ctrl |= HINIC_API_CMD_CHAIN_CTRL_SET(1, XOR_ERR) |
+ HINIC_API_CMD_CHAIN_CTRL_SET(XOR_CHK_ALL, XOR_CHK_EN) |
+ HINIC_API_CMD_CHAIN_CTRL_SET(cell_size, CELL_SIZE);
+
+ hinic_hwif_write_reg(hwif, reg_addr, ctrl);
+}
+
+/**
+ * api_cmd_set_status_addr - set the status address of a chain in the HW
+ * @chain: the API CMD specific chain to set in HW status address for
+ **/
+static void api_cmd_set_status_addr(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ u32 addr, val;
+
+ addr = HINIC_CSR_API_CMD_STATUS_HI_ADDR(chain->chain_type);
+ val = upper_32_bits(chain->wb_status_paddr);
+ hinic_hwif_write_reg(hwif, addr, val);
+
+ addr = HINIC_CSR_API_CMD_STATUS_LO_ADDR(chain->chain_type);
+ val = lower_32_bits(chain->wb_status_paddr);
+ hinic_hwif_write_reg(hwif, addr, val);
+}
+
+/**
+ * api_cmd_set_num_cells - set the number cells of a chain in the HW
+ * @chain: the API CMD specific chain to set in HW the number of cells for
+ **/
+static void api_cmd_set_num_cells(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ u32 addr, val;
+
+ addr = HINIC_CSR_API_CMD_CHAIN_NUM_CELLS_ADDR(chain->chain_type);
+ val = chain->num_cells;
+ hinic_hwif_write_reg(hwif, addr, val);
+}
+
+/**
+ * api_cmd_head_init - set the head of a chain in the HW
+ * @chain: the API CMD specific chain to set in HW the head for
+ **/
+static void api_cmd_head_init(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ u32 addr, val;
+
+ addr = HINIC_CSR_API_CMD_CHAIN_HEAD_HI_ADDR(chain->chain_type);
+ val = upper_32_bits(chain->head_cell_paddr);
+ hinic_hwif_write_reg(hwif, addr, val);
+
+ addr = HINIC_CSR_API_CMD_CHAIN_HEAD_LO_ADDR(chain->chain_type);
+ val = lower_32_bits(chain->head_cell_paddr);
+ hinic_hwif_write_reg(hwif, addr, val);
+}
+
+/**
+ * api_cmd_chain_hw_clean - clean the HW
+ * @chain: the API CMD specific chain
+ **/
+static void api_cmd_chain_hw_clean(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ u32 addr, ctrl;
+
+ addr = HINIC_CSR_API_CMD_CHAIN_CTRL_ADDR(chain->chain_type);
+
+ ctrl = hinic_hwif_read_reg(hwif, addr);
+ ctrl = HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, RESTART_WB_STAT) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_ERR) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, AEQE_EN) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_CHK_EN) &
+ HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, CELL_SIZE);
+
+ hinic_hwif_write_reg(hwif, addr, ctrl);
+}
+
/**
* api_cmd_chain_hw_init - initialize the chain in the HW
* @chain: the API CMD specific chain to initialize in HW
@@ -45,7 +199,23 @@
**/
static int api_cmd_chain_hw_init(struct hinic_api_cmd_chain *chain)
{
- /* should be implemented */
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int err;
+
+ api_cmd_chain_hw_clean(chain);
+
+ api_cmd_set_status_addr(chain);
+
+ err = api_cmd_hw_restart(chain);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to restart API CMD HW\n");
+ return err;
+ }
+
+ api_cmd_ctrl_init(chain);
+ api_cmd_set_num_cells(chain);
+ api_cmd_head_init(chain);
return 0;
}
@@ -373,6 +543,7 @@ static void api_chain_free(struct hinic_api_cmd_chain *chain)
**/
static void api_cmd_destroy_chain(struct hinic_api_cmd_chain *chain)
{
+ api_cmd_chain_hw_clean(chain);
api_cmd_destroy_cells(chain, chain->num_cells);
api_chain_free(chain);
}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
index 9c7d1e5..0c83b80 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
@@ -20,6 +20,44 @@
#include "hinic_hw_if.h"
+#define HINIC_API_CMD_CHAIN_REQ_RESTART_SHIFT 1
+
+#define HINIC_API_CMD_CHAIN_REQ_RESTART_MASK 0x1
+
+#define HINIC_API_CMD_CHAIN_REQ_SET(val, member) \
+ (((u32)(val) & HINIC_API_CMD_CHAIN_REQ_##member##_MASK) << \
+ HINIC_API_CMD_CHAIN_REQ_##member##_SHIFT)
+
+#define HINIC_API_CMD_CHAIN_REQ_GET(val, member) \
+ (((val) >> HINIC_API_CMD_CHAIN_REQ_##member##_SHIFT) & \
+ HINIC_API_CMD_CHAIN_REQ_##member##_MASK)
+
+#define HINIC_API_CMD_CHAIN_REQ_CLEAR(val, member) \
+ ((val) & (~(HINIC_API_CMD_CHAIN_REQ_##member##_MASK \
+ << HINIC_API_CMD_CHAIN_REQ_##member##_SHIFT)))
+
+#define HINIC_API_CMD_CHAIN_CTRL_RESTART_WB_STAT_SHIFT 1
+#define HINIC_API_CMD_CHAIN_CTRL_XOR_ERR_SHIFT 2
+#define HINIC_API_CMD_CHAIN_CTRL_AEQE_EN_SHIFT 4
+#define HINIC_API_CMD_CHAIN_CTRL_AEQ_ID_SHIFT 8
+#define HINIC_API_CMD_CHAIN_CTRL_XOR_CHK_EN_SHIFT 28
+#define HINIC_API_CMD_CHAIN_CTRL_CELL_SIZE_SHIFT 30
+
+#define HINIC_API_CMD_CHAIN_CTRL_RESTART_WB_STAT_MASK 0x1
+#define HINIC_API_CMD_CHAIN_CTRL_XOR_ERR_MASK 0x1
+#define HINIC_API_CMD_CHAIN_CTRL_AEQE_EN_MASK 0x1
+#define HINIC_API_CMD_CHAIN_CTRL_AEQ_ID_MASK 0x3
+#define HINIC_API_CMD_CHAIN_CTRL_XOR_CHK_EN_MASK 0x3
+#define HINIC_API_CMD_CHAIN_CTRL_CELL_SIZE_MASK 0x3
+
+#define HINIC_API_CMD_CHAIN_CTRL_SET(val, member) \
+ (((u32)(val) & HINIC_API_CMD_CHAIN_CTRL_##member##_MASK) << \
+ HINIC_API_CMD_CHAIN_CTRL_##member##_SHIFT)
+
+#define HINIC_API_CMD_CHAIN_CTRL_CLEAR(val, member) \
+ ((val) & (~(HINIC_API_CMD_CHAIN_CTRL_##member##_MASK \
+ << HINIC_API_CMD_CHAIN_CTRL_##member##_SHIFT)))
+
enum hinic_api_cmd_chain_type {
HINIC_API_CMD_WRITE_TO_MGMT_CPU = 2,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
index c3440a9..a9ece6d 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
@@ -33,4 +33,30 @@
#define HINIC_CSR_PPF_ELECTION_ADDR(idx) \
(HINIC_ELECTION_BASE + (idx) * HINIC_PPF_ELECTION_STRIDE)
+/* API CMD registers */
+#define HINIC_CSR_API_CMD_BASE 0xF000
+
+#define HINIC_CSR_API_CMD_STRIDE 0x100
+
+#define HINIC_CSR_API_CMD_CHAIN_HEAD_HI_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x0 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
+#define HINIC_CSR_API_CMD_CHAIN_HEAD_LO_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x4 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
+#define HINIC_CSR_API_CMD_STATUS_HI_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x8 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
+#define HINIC_CSR_API_CMD_STATUS_LO_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0xC + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
+#define HINIC_CSR_API_CMD_CHAIN_NUM_CELLS_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x10 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
+#define HINIC_CSR_API_CMD_CHAIN_CTRL_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x14 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
+#define HINIC_CSR_API_CMD_CHAIN_REQ_ADDR(idx) \
+ (HINIC_CSR_API_CMD_BASE + 0x20 + (idx) * HINIC_CSR_API_CMD_STRIDE)
+
#endif
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 03/21] net-next/hinic: Initialize api cmd resources
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Initialize api cmd resources as part of management initialization.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
drivers/net/ethernet/huawei/hinic/Makefile | 4 +-
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.c | 446 +++++++++++++++++++++
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.h | 102 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 10 +
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h | 3 +
5 files changed, 563 insertions(+), 2 deletions(-)
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
index 717ad71..beba90a 100644
--- a/drivers/net/ethernet/huawei/hinic/Makefile
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -1,4 +1,4 @@
obj-$(CONFIG_HINIC) += hinic.o
-hinic-y := hinic_main.o hinic_hw_dev.o hinic_hw_mgmt.o hinic_hw_eqs.o \
- hinic_hw_if.o
+hinic-y := hinic_main.o hinic_hw_dev.o hinic_hw_mgmt.o hinic_hw_api_cmd.o \
+ hinic_hw_eqs.o hinic_hw_if.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
new file mode 100644
index 0000000..4291f8e
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
@@ -0,0 +1,446 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <asm/byteorder.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_api_cmd.h"
+
+#define API_CHAIN_NUM_CELLS 32
+
+#define API_CMD_CELL_SIZE_SHIFT 6
+#define API_CMD_CELL_SIZE_MIN (BIT(API_CMD_CELL_SIZE_SHIFT))
+
+#define API_CMD_CELL_SIZE(cell_size) \
+ (((cell_size) >= API_CMD_CELL_SIZE_MIN) ? \
+ (1 << (fls(cell_size - 1))) : API_CMD_CELL_SIZE_MIN)
+
+#define API_CMD_BUF_SIZE 2048
+
+/**
+ * api_cmd_chain_hw_init - initialize the chain in the HW
+ * @chain: the API CMD specific chain to initialize in HW
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int api_cmd_chain_hw_init(struct hinic_api_cmd_chain *chain)
+{
+ /* should be implemented */
+ return 0;
+}
+
+/**
+ * free_cmd_buf - free the dma buffer of API CMD command
+ * @chain: the API CMD specific chain of the cmd
+ * @cell_idx: the cell index of the cmd
+ **/
+static void free_cmd_buf(struct hinic_api_cmd_chain *chain, int cell_idx)
+{
+ struct hinic_api_cmd_cell_ctxt *cell_ctxt;
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+
+ cell_ctxt = &chain->cell_ctxt[cell_idx];
+
+ dma_free_coherent(&pdev->dev, API_CMD_BUF_SIZE,
+ cell_ctxt->api_cmd_vaddr,
+ cell_ctxt->api_cmd_paddr);
+}
+
+/**
+ * alloc_cmd_buf - allocate a dma buffer for API CMD command
+ * @chain: the API CMD specific chain for the cmd
+ * @cell: the cell in the HW for the cmd
+ * @cell_idx: the index of the cell
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int alloc_cmd_buf(struct hinic_api_cmd_chain *chain,
+ struct hinic_api_cmd_cell *cell, int cell_idx)
+{
+ struct hinic_api_cmd_cell_ctxt *cell_ctxt;
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ dma_addr_t cmd_paddr;
+ u8 *cmd_vaddr;
+ int err = 0;
+
+ cmd_vaddr = dma_zalloc_coherent(&pdev->dev, API_CMD_BUF_SIZE,
+ &cmd_paddr, GFP_KERNEL);
+ if (!cmd_vaddr) {
+ dev_err(&pdev->dev, "Failed to allocate API CMD DMA memory\n");
+ return -ENOMEM;
+ }
+
+ cell_ctxt = &chain->cell_ctxt[cell_idx];
+
+ cell_ctxt->api_cmd_vaddr = cmd_vaddr;
+ cell_ctxt->api_cmd_paddr = cmd_paddr;
+
+ /* set the cmd DMA address in the cell */
+ switch (chain->chain_type) {
+ case HINIC_API_CMD_WRITE_TO_MGMT_CPU:
+ /* The data in the HW should be in Big Endian Format */
+ cell->write.hw_cmd_paddr = cpu_to_be64(cmd_paddr);
+ break;
+
+ default:
+ dev_err(&pdev->dev, "Unsupported API CMD chain type\n");
+ free_cmd_buf(chain, cell_idx);
+ err = -EINVAL;
+ break;
+ }
+
+ return err;
+}
+
+/**
+ * api_cmd_create_cell - create API CMD cell for specific chain
+ * @chain: the API CMD specific chain to create its cell
+ * @cell_idx: the index of the cell to create
+ * @pre_node: previous cell
+ * @node_vaddr: the returned virt addr of the cell
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int api_cmd_create_cell(struct hinic_api_cmd_chain *chain,
+ int cell_idx,
+ struct hinic_api_cmd_cell *pre_node,
+ struct hinic_api_cmd_cell **node_vaddr)
+{
+ struct hinic_api_cmd_cell_ctxt *cell_ctxt;
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_api_cmd_cell *node;
+ dma_addr_t node_paddr;
+ int err;
+
+ node = dma_zalloc_coherent(&pdev->dev, chain->cell_size,
+ &node_paddr, GFP_KERNEL);
+ if (!node) {
+ dev_err(&pdev->dev, "Failed to allocate dma API CMD cell\n");
+ return -ENOMEM;
+ }
+
+ node->read.hw_wb_resp_paddr = 0;
+
+ cell_ctxt = &chain->cell_ctxt[cell_idx];
+ cell_ctxt->cell_vaddr = node;
+ cell_ctxt->cell_paddr = node_paddr;
+
+ if (!pre_node) {
+ chain->head_cell_paddr = node_paddr;
+ chain->head_node = node;
+ } else {
+ /* The data in the HW should be in Big Endian Format */
+ pre_node->next_cell_paddr = cpu_to_be64(node_paddr);
+ }
+
+ switch (chain->chain_type) {
+ case HINIC_API_CMD_WRITE_TO_MGMT_CPU:
+ err = alloc_cmd_buf(chain, node, cell_idx);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to allocate cmd buffer\n");
+ goto err_alloc_cmd_buf;
+ }
+ break;
+
+ default:
+ dev_err(&pdev->dev, "Unsupported API CMD chain type\n");
+ err = -EINVAL;
+ goto err_alloc_cmd_buf;
+ }
+
+ *node_vaddr = node;
+ return 0;
+
+err_alloc_cmd_buf:
+ dma_free_coherent(&pdev->dev, chain->cell_size, node, node_paddr);
+ return err;
+}
+
+/**
+ * api_cmd_destroy_cell - destroy API CMD cell of specific chain
+ * @chain: the API CMD specific chain to destroy its cell
+ * @cell_idx: the cell to destroy
+ **/
+static void api_cmd_destroy_cell(struct hinic_api_cmd_chain *chain,
+ int cell_idx)
+{
+ struct hinic_api_cmd_cell_ctxt *cell_ctxt;
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_api_cmd_cell *node;
+ dma_addr_t node_paddr;
+ size_t node_size;
+
+ cell_ctxt = &chain->cell_ctxt[cell_idx];
+
+ node = cell_ctxt->cell_vaddr;
+ node_paddr = cell_ctxt->cell_paddr;
+ node_size = chain->cell_size;
+
+ if (cell_ctxt->api_cmd_vaddr) {
+ switch (chain->chain_type) {
+ case HINIC_API_CMD_WRITE_TO_MGMT_CPU:
+ free_cmd_buf(chain, cell_idx);
+ break;
+ default:
+ dev_err(&pdev->dev, "Unsupported API CMD chain type\n");
+ break;
+ }
+
+ dma_free_coherent(&pdev->dev, node_size, node,
+ node_paddr);
+ }
+}
+
+/**
+ * api_cmd_destroy_cells - destroy API CMD cells of specific chain
+ * @chain: the API CMD specific chain to destroy its cells
+ * @num_cells: number of cells to destroy
+ **/
+static void api_cmd_destroy_cells(struct hinic_api_cmd_chain *chain,
+ int num_cells)
+{
+ int cell_idx;
+
+ for (cell_idx = 0; cell_idx < num_cells; cell_idx++)
+ api_cmd_destroy_cell(chain, cell_idx);
+}
+
+/**
+ * api_cmd_create_cells - create API CMD cells for specific chain
+ * @chain: the API CMD specific chain
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int api_cmd_create_cells(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_api_cmd_cell *node = NULL, *pre_node = NULL;
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int err, cell_idx;
+
+ for (cell_idx = 0; cell_idx < chain->num_cells; cell_idx++) {
+ err = api_cmd_create_cell(chain, cell_idx, pre_node, &node);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to create API CMD cell\n");
+ goto err_create_cell;
+ }
+
+ pre_node = node;
+ }
+
+ /* set the Final node to point on the start */
+ node->next_cell_paddr = cpu_to_be64(chain->head_cell_paddr);
+
+ /* set the current node to be the head */
+ chain->curr_node = chain->head_node;
+ return 0;
+
+err_create_cell:
+ api_cmd_destroy_cells(chain, cell_idx);
+ return err;
+}
+
+/**
+ * api_chain_init - initialize API CMD specific chain
+ * @chain: the API CMD specific chain to initialize
+ * @attr: attributes to set in the chain
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int api_chain_init(struct hinic_api_cmd_chain *chain,
+ struct hinic_api_cmd_chain_attr *attr)
+{
+ struct hinic_hwif *hwif = attr->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ size_t cell_ctxt_size;
+
+ chain->hwif = hwif;
+ chain->chain_type = attr->chain_type;
+ chain->num_cells = attr->num_cells;
+ chain->cell_size = attr->cell_size;
+
+ chain->prod_idx = 0;
+ chain->cons_idx = 0;
+
+ cell_ctxt_size = chain->num_cells * sizeof(*chain->cell_ctxt);
+ chain->cell_ctxt = devm_kzalloc(&pdev->dev, cell_ctxt_size, GFP_KERNEL);
+ if (!chain->cell_ctxt)
+ return -ENOMEM;
+
+ chain->wb_status = dma_zalloc_coherent(&pdev->dev,
+ sizeof(*chain->wb_status),
+ &chain->wb_status_paddr,
+ GFP_KERNEL);
+ if (!chain->wb_status) {
+ dev_err(&pdev->dev, "Failed to allocate DMA wb status\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+/**
+ * api_chain_free - free API CMD specific chain
+ * @chain: the API CMD specific chain to free
+ **/
+static void api_chain_free(struct hinic_api_cmd_chain *chain)
+{
+ struct hinic_hwif *hwif = chain->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+
+ dma_free_coherent(&pdev->dev, sizeof(*chain->wb_status),
+ chain->wb_status, chain->wb_status_paddr);
+}
+
+/**
+ * api_cmd_create_chain - create API CMD specific chain
+ * @attr: attributes to set the chain
+ *
+ * Return the created chain
+ **/
+static struct hinic_api_cmd_chain *
+ api_cmd_create_chain(struct hinic_api_cmd_chain_attr *attr)
+{
+ struct hinic_hwif *hwif = attr->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ struct hinic_api_cmd_chain *chain;
+ int err;
+
+ if (attr->num_cells & (attr->num_cells - 1)) {
+ dev_err(&pdev->dev, "Invalid number of cells, must be power of 2\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL);
+ if (!chain)
+ return ERR_PTR(-ENOMEM);
+
+ err = api_chain_init(chain, attr);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to initialize chain\n");
+ return ERR_PTR(err);
+ }
+
+ err = api_cmd_create_cells(chain);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to create cells for API CMD chain\n");
+ goto err_create_cells;
+ }
+
+ err = api_cmd_chain_hw_init(chain);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to initialize chain HW\n");
+ goto err_chain_hw_init;
+ }
+
+ return chain;
+
+err_chain_hw_init:
+ api_cmd_destroy_cells(chain, chain->num_cells);
+
+err_create_cells:
+ api_chain_free(chain);
+ return ERR_PTR(err);
+}
+
+/**
+ * api_cmd_destroy_chain - destroy API CMD specific chain
+ * @chain: the API CMD specific chain to destroy
+ **/
+static void api_cmd_destroy_chain(struct hinic_api_cmd_chain *chain)
+{
+ api_cmd_destroy_cells(chain, chain->num_cells);
+ api_chain_free(chain);
+}
+
+/**
+ * hinic_api_cmd_init - Initialize all the API CMD chains
+ * @chain: the API CMD chains that are initialized
+ * @hwif: the hardware interface of a pci function device
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_api_cmd_init(struct hinic_api_cmd_chain **chain,
+ struct hinic_hwif *hwif)
+{
+ enum hinic_api_cmd_chain_type type, chain_type;
+ struct hinic_api_cmd_chain_attr attr;
+ struct pci_dev *pdev = hwif->pdev;
+ size_t hw_cell_sz;
+ int err;
+
+ hw_cell_sz = sizeof(struct hinic_api_cmd_cell);
+
+ attr.hwif = hwif;
+ attr.num_cells = API_CHAIN_NUM_CELLS;
+ attr.cell_size = API_CMD_CELL_SIZE(hw_cell_sz);
+
+ chain_type = HINIC_API_CMD_WRITE_TO_MGMT_CPU;
+ for ( ; chain_type < HINIC_API_CMD_MAX; chain_type++) {
+ attr.chain_type = chain_type;
+
+ if (chain_type != HINIC_API_CMD_WRITE_TO_MGMT_CPU)
+ continue;
+
+ chain[chain_type] = api_cmd_create_chain(&attr);
+ if (IS_ERR(chain[chain_type])) {
+ dev_err(&pdev->dev, "Failed to create chain %d\n",
+ chain_type);
+ goto err_create_chain;
+ }
+ }
+
+ return 0;
+
+err_create_chain:
+ type = HINIC_API_CMD_WRITE_TO_MGMT_CPU;
+ for ( ; type < chain_type; type++) {
+ if (type != HINIC_API_CMD_WRITE_TO_MGMT_CPU)
+ continue;
+
+ api_cmd_destroy_chain(chain[type]);
+ }
+
+ return err;
+}
+
+/**
+ * hinic_api_cmd_free - free the API CMD chains
+ * @chain: the API CMD chains that are freed
+ **/
+void hinic_api_cmd_free(struct hinic_api_cmd_chain **chain)
+{
+ enum hinic_api_cmd_chain_type chain_type;
+
+ chain_type = HINIC_API_CMD_WRITE_TO_MGMT_CPU;
+ for ( ; chain_type < HINIC_API_CMD_MAX; chain_type++) {
+ if (chain_type != HINIC_API_CMD_WRITE_TO_MGMT_CPU)
+ continue;
+
+ api_cmd_destroy_chain(chain[chain_type]);
+ }
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
new file mode 100644
index 0000000..9c7d1e5
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
@@ -0,0 +1,102 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_HW_API_CMD_H
+#define HINIC_HW_API_CMD_H
+
+#include <linux/types.h>
+
+#include "hinic_hw_if.h"
+
+enum hinic_api_cmd_chain_type {
+ HINIC_API_CMD_WRITE_TO_MGMT_CPU = 2,
+
+ HINIC_API_CMD_MAX,
+};
+
+struct hinic_api_cmd_chain_attr {
+ struct hinic_hwif *hwif;
+ enum hinic_api_cmd_chain_type chain_type;
+
+ u32 num_cells;
+ u16 cell_size;
+};
+
+struct hinic_api_cmd_status {
+ u64 header;
+ u32 status;
+ u32 rsvd0;
+ u32 rsvd1;
+ u32 rsvd2;
+ u64 rsvd3;
+};
+
+/* HW struct */
+struct hinic_api_cmd_cell {
+ u64 ctrl;
+
+ /* address is 64 bit in HW struct */
+ u64 next_cell_paddr;
+
+ u64 desc;
+
+ /* HW struct */
+ union {
+ struct {
+ u64 hw_cmd_paddr;
+ } write;
+
+ struct {
+ u64 hw_wb_resp_paddr;
+ u64 hw_cmd_paddr;
+ } read;
+ };
+};
+
+struct hinic_api_cmd_cell_ctxt {
+ dma_addr_t cell_paddr;
+ struct hinic_api_cmd_cell *cell_vaddr;
+
+ dma_addr_t api_cmd_paddr;
+ u8 *api_cmd_vaddr;
+};
+
+struct hinic_api_cmd_chain {
+ struct hinic_hwif *hwif;
+ enum hinic_api_cmd_chain_type chain_type;
+
+ u32 num_cells;
+ u16 cell_size;
+
+ /* HW members in 24 bit format */
+ u32 prod_idx;
+ u32 cons_idx;
+
+ struct hinic_api_cmd_cell_ctxt *cell_ctxt;
+
+ dma_addr_t wb_status_paddr;
+ struct hinic_api_cmd_status *wb_status;
+
+ dma_addr_t head_cell_paddr;
+ struct hinic_api_cmd_cell *head_node;
+ struct hinic_api_cmd_cell *curr_node;
+};
+
+int hinic_api_cmd_init(struct hinic_api_cmd_chain **chain,
+ struct hinic_hwif *hwif);
+
+void hinic_api_cmd_free(struct hinic_api_cmd_chain **chain);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 8ae8ed9..f914bc7 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -19,6 +19,7 @@
#include "hinic_hw_if.h"
#include "hinic_hw_eqs.h"
+#include "hinic_hw_api_cmd.h"
#include "hinic_hw_mgmt.h"
#include "hinic_hw_dev.h"
@@ -70,9 +71,17 @@ int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt,
{
struct hinic_pfhwdev *pfhwdev = mgmt_to_pfhwdev(pf_to_mgmt);
struct hinic_hwdev *hwdev = &pfhwdev->hwdev;
+ struct pci_dev *pdev = hwif->pdev;
+ int err;
pf_to_mgmt->hwif = hwif;
+ err = hinic_api_cmd_init(pf_to_mgmt->cmd_chain, hwif);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to initialize cmd chains\n");
+ return err;
+ }
+
hinic_aeq_register_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU,
pf_to_mgmt,
mgmt_msg_aeqe_handler);
@@ -89,4 +98,5 @@ void hinic_pf_to_mgmt_free(struct hinic_pf_to_mgmt *pf_to_mgmt)
struct hinic_hwdev *hwdev = &pfhwdev->hwdev;
hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU);
+ hinic_api_cmd_free(pf_to_mgmt->cmd_chain);
}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
index b4b34b7..dff321c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
@@ -19,6 +19,7 @@
#include <linux/types.h>
#include "hinic_hw_if.h"
+#include "hinic_hw_api_cmd.h"
enum hinic_mgmt_msg_type {
HINIC_MGMT_MSG_SYNC = 1,
@@ -30,6 +31,8 @@ enum hinic_cfg_cmd {
struct hinic_pf_to_mgmt {
struct hinic_hwif *hwif;
+
+ struct hinic_api_cmd_chain *cmd_chain[HINIC_API_CMD_MAX];
};
int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 01/21] net-next/hinic: Initialize hw interface
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
In-Reply-To: <cover.1502970631.git.aviad.krawczyk@huawei.com>
Initialize hw interface as part of the nic initialization for accessing hw.
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
Documentation/networking/hinic.txt | 125 ++++++++++++++
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/huawei/Kconfig | 19 +++
drivers/net/ethernet/huawei/Makefile | 5 +
drivers/net/ethernet/huawei/hinic/Kconfig | 13 ++
drivers/net/ethernet/huawei/hinic/Makefile | 3 +
drivers/net/ethernet/huawei/hinic/hinic_dev.h | 33 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h | 36 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 201 ++++++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h | 42 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.c | 208 +++++++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 160 +++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_main.c | 195 +++++++++++++++++++++
14 files changed, 1042 insertions(+)
create mode 100644 Documentation/networking/hinic.txt
create mode 100644 drivers/net/ethernet/huawei/Kconfig
create mode 100644 drivers/net/ethernet/huawei/Makefile
create mode 100644 drivers/net/ethernet/huawei/hinic/Kconfig
create mode 100644 drivers/net/ethernet/huawei/hinic/Makefile
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_dev.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_main.c
diff --git a/Documentation/networking/hinic.txt b/Documentation/networking/hinic.txt
new file mode 100644
index 0000000..989366a
--- /dev/null
+++ b/Documentation/networking/hinic.txt
@@ -0,0 +1,125 @@
+Linux Kernel Driver for Huawei Intelligent NIC(HiNIC) family
+============================================================
+
+Overview:
+=========
+HiNIC is a network interface card for the Data Center Area.
+
+The driver supports a range of link-speed devices (10GbE, 25GbE, 40GbE, etc.).
+The driver supports also a negotiated and extendable feature set.
+
+Some HiNIC devices support SR-IOV. This driver is used for Physical Function
+(PF).
+
+HiNIC devices support MSI-X interrupt vector for each Tx/Rx queue and
+adaptive interrupt moderation.
+
+HiNIC devices support also various offload features such as checksum offload,
+TCP Transmit Segmentation Offload(TSO), Receive-Side Scaling(RSS) and
+LRO(Large Receive Offload).
+
+
+Supported PCI vendor ID/device IDs:
+===================================
+
+19e5:1822 - HiNIC PF
+
+
+Driver Architecture and Source Code:
+====================================
+
+hinic_dev - Implement a Logical Network device that is independent from
+specific HW details about HW data structure formats.
+
+hinic_hwdev - Implement the HW details of the device and include the components
+for accessing the PCI NIC.
+
+hinic_hwdev contains the following components:
+===============================================
+
+HW Interface:
+=============
+
+The interface for accessing the pci device (DMA memory and PCI BARs).
+(hinic_hw_if.c, hinic_hw_if.h)
+
+Configuration Status Registers Area that describes the HW Registers on the
+configuration and status BAR0. (hinic_hw_csr.h)
+
+MGMT components:
+================
+
+Asynchronous Event Queues(AEQs) - The event queues for receiving messages from
+the MGMT modules on the cards. (hinic_hw_eqs.c, hinic_hw_eqs.h)
+
+Application Programmable Interface commands(API CMD) - Interface for sending
+MGMT commands to the card. (hinic_hw_api_cmd.c, hinic_hw_api_cmd.h)
+
+Management (MGMT) - the PF to MGMT channel that uses API CMD for sending MGMT
+commands to the card and receives notifications from the MGMT modules on the
+card by AEQs. Also set the addresses of the IO CMDQs in HW.
+(hinic_hw_mgmt.c, hinic_hw_mgmt.h)
+
+IO components:
+==============
+
+Completion Event Queues(CEQs) - The completion Event Queues that describe IO
+tasks that are finished. (hinic_hw_eqs.c, hinic_hw_eqs.h)
+
+Work Queues(WQ) - Contain the memory and operations for use by CMD queues and
+the Queue Pairs. The WQ is a Memory Block in a Page. The Block contains
+pointers to Memory Areas that are the Memory for the Work Queue Elements(WQEs).
+(hinic_hw_wq.c, hinic_hw_wq.h)
+
+Command Queues(CMDQ) - The queues for sending commands for IO management and is
+used to set the QPs addresses in HW. The commands completion events are
+accumulated on the CEQ that is configured to receive the CMDQ completion events.
+(hinic_hw_cmdq.c, hinic_hw_cmdq.h)
+
+Queue Pairs(QPs) - The HW Receive and Send queues for Receiving and Transmitting
+Data. (hinic_hw_qp.c, hinic_hw_qp.h, hinic_hw_qp_ctxt.h)
+
+IO - de/constructs all the IO components. (hinic_hw_io.c, hinic_hw_io.h)
+
+HW device:
+==========
+
+HW device - de/constructs the HW Interface, the MGMT components on the
+initialization of the driver and the IO components on the case of Interface
+UP/DOWN Events. (hinic_hw_dev.c, hinic_hw_dev.h)
+
+
+hinic_dev contains the following components:
+===============================================
+
+PCI ID table - Contains the supported PCI Vendor/Device IDs.
+(hinic_pci_tbl.h)
+
+Port Commands - Send commands to the HW device for port management
+(MAC, Vlan, MTU, ...). (hinic_port.c, hinic_port.h)
+
+Tx Queues - Logical Tx Queues that use the HW Send Queues for transmit.
+The Logical Tx queue is not dependent on the format of the HW Send Queue.
+(hinic_tx.c, hinic_tx.h)
+
+Rx Queues - Logical Rx Queues that use the HW Receive Queues for receive.
+The Logical Rx queue is not dependent on the format of the HW Receive Queue.
+(hinic_rx.c, hinic_rx.h)
+
+hinic_dev - de/constructs the Logical Tx and Rx Queues.
+(hinic_main.c, hinic_dev.h)
+
+
+Miscellaneous:
+=============
+
+Common functions that are used by HW and Logical Device.
+(hinic_common.c, hinic_common.h)
+
+
+Support
+=======
+
+If an issue is identified with the released source code on the supported kernel
+with a supported adapter, email the specific information related to the issue to
+aviad.krawczyk@huawei.com.
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index edae15ac..c604213 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -78,6 +78,7 @@ source "drivers/net/ethernet/freescale/Kconfig"
source "drivers/net/ethernet/fujitsu/Kconfig"
source "drivers/net/ethernet/hisilicon/Kconfig"
source "drivers/net/ethernet/hp/Kconfig"
+source "drivers/net/ethernet/huawei/Kconfig"
source "drivers/net/ethernet/ibm/Kconfig"
source "drivers/net/ethernet/intel/Kconfig"
source "drivers/net/ethernet/i825xx/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index bf7f450..a0a03d4 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/
obj-$(CONFIG_NET_VENDOR_FUJITSU) += fujitsu/
obj-$(CONFIG_NET_VENDOR_HISILICON) += hisilicon/
obj-$(CONFIG_NET_VENDOR_HP) += hp/
+obj-$(CONFIG_NET_VENDOR_HUAWEI) += huawei/
obj-$(CONFIG_NET_VENDOR_IBM) += ibm/
obj-$(CONFIG_NET_VENDOR_INTEL) += intel/
obj-$(CONFIG_NET_VENDOR_I825XX) += i825xx/
diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig
new file mode 100644
index 0000000..c1a95ae
--- /dev/null
+++ b/drivers/net/ethernet/huawei/Kconfig
@@ -0,0 +1,19 @@
+#
+# Huawei driver configuration
+#
+
+config NET_VENDOR_HUAWEI
+ bool "Huawei devices"
+ default y
+ ---help---
+ If you have a network (Ethernet) card belonging to this class, say Y.
+ Note that the answer to this question doesn't directly affect the
+ kernel: saying N will just cause the configurator to skip all
+ the questions about Huawei cards. If you say Y, you will be asked
+ for your specific card in the following questions.
+
+if NET_VENDOR_HUAWEI
+
+source "drivers/net/ethernet/huawei/hinic/Kconfig"
+
+endif # NET_VENDOR_HUAWEI
diff --git a/drivers/net/ethernet/huawei/Makefile b/drivers/net/ethernet/huawei/Makefile
new file mode 100644
index 0000000..5c37cc8
--- /dev/null
+++ b/drivers/net/ethernet/huawei/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Huawei device drivers.
+#
+
+obj-$(CONFIG_HINIC) += hinic/
diff --git a/drivers/net/ethernet/huawei/hinic/Kconfig b/drivers/net/ethernet/huawei/hinic/Kconfig
new file mode 100644
index 0000000..69f2b1f
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/Kconfig
@@ -0,0 +1,13 @@
+#
+# Huawei driver configuration
+#
+
+config HINIC
+ tristate "Huawei Intelligent PCIE Network Interface Card"
+ depends on (PCI_MSI && X86)
+ default m
+ ---help---
+ This driver supports HiNIC PCIE Ethernet cards.
+ To compile this driver as part of the kernel, choose Y here.
+ If unsure, choose N.
+ The default is compiled as module.
diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
new file mode 100644
index 0000000..353cee0
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_HINIC) += hinic.o
+
+hinic-y := hinic_main.o hinic_hw_dev.o hinic_hw_if.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
new file mode 100644
index 0000000..6c2c896
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -0,0 +1,33 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_DEV_H
+#define HINIC_DEV_H
+
+#include <linux/netdevice.h>
+#include <linux/types.h>
+
+#include "hinic_hw_dev.h"
+
+#define HINIC_DRV_NAME "hinic"
+
+struct hinic_dev {
+ struct net_device *netdev;
+ struct hinic_hwdev *hwdev;
+
+ u32 msg_enable;
+};
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
new file mode 100644
index 0000000..c3440a9
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
@@ -0,0 +1,36 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_HW_CSR_H
+#define HINIC_HW_CSR_H
+
+/* HW interface registers */
+#define HINIC_CSR_FUNC_ATTR0_ADDR 0x0
+#define HINIC_CSR_FUNC_ATTR1_ADDR 0x4
+
+#define HINIC_DMA_ATTR_BASE 0xC80
+#define HINIC_ELECTION_BASE 0x4200
+
+#define HINIC_DMA_ATTR_STRIDE 0x4
+#define HINIC_CSR_DMA_ATTR_ADDR(idx) \
+ (HINIC_DMA_ATTR_BASE + (idx) * HINIC_DMA_ATTR_STRIDE)
+
+#define HINIC_PPF_ELECTION_STRIDE 0x4
+#define HINIC_CSR_MAX_PORTS 4
+
+#define HINIC_CSR_PPF_ELECTION_ADDR(idx) \
+ (HINIC_ELECTION_BASE + (idx) * HINIC_PPF_ELECTION_STRIDE)
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
new file mode 100644
index 0000000..f681846
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -0,0 +1,201 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/bitops.h>
+#include <linux/err.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_dev.h"
+
+#define MAX_IRQS(max_qps, num_aeqs, num_ceqs) \
+ (2 * (max_qps) + (num_aeqs) + (num_ceqs))
+
+/**
+ * init_msix - enable the msix and save the entries
+ * @hwdev: the NIC HW device
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int init_msix(struct hinic_hwdev *hwdev)
+{
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+ int nr_irqs, num_aeqs, num_ceqs;
+ size_t msix_entries_size;
+ int i, err;
+
+ num_aeqs = HINIC_HWIF_NUM_AEQS(hwif);
+ num_ceqs = HINIC_HWIF_NUM_CEQS(hwif);
+ nr_irqs = MAX_IRQS(HINIC_MAX_QPS, num_aeqs, num_ceqs);
+ if (nr_irqs > HINIC_HWIF_NUM_IRQS(hwif))
+ nr_irqs = HINIC_HWIF_NUM_IRQS(hwif);
+
+ msix_entries_size = nr_irqs * sizeof(*hwdev->msix_entries);
+ hwdev->msix_entries = devm_kzalloc(&pdev->dev, msix_entries_size,
+ GFP_KERNEL);
+ if (!hwdev->msix_entries)
+ return -ENOMEM;
+
+ for (i = 0; i < nr_irqs; i++)
+ hwdev->msix_entries[i].entry = i;
+
+ err = pci_enable_msix_exact(pdev, hwdev->msix_entries, nr_irqs);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to enable pci msix\n");
+ return err;
+ }
+
+ return 0;
+}
+
+/**
+ * disable_msix - disable the msix
+ * @hwdev: the NIC HW device
+ **/
+static void disable_msix(struct hinic_hwdev *hwdev)
+{
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct pci_dev *pdev = hwif->pdev;
+
+ pci_disable_msix(pdev);
+}
+
+/**
+ * init_pfhwdev - Initialize the extended components of PF
+ * @pfhwdev: the HW device for PF
+ *
+ * Return 0 - success, negative - failure
+ **/
+static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev)
+{
+ /* Initialize PF HW device extended components */
+ return 0;
+}
+
+/**
+ * free_pfhwdev - Free the extended components of PF
+ * @pfhwdev: the HW device for PF
+ **/
+static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev)
+{
+}
+
+/**
+ * hinic_init_hwdev - Initialize the NIC HW
+ * @pdev: the NIC pci device
+ *
+ * Return initialized NIC HW device
+ *
+ * Initialize the NIC HW device and return a pointer to it
+ **/
+struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev)
+{
+ struct hinic_pfhwdev *pfhwdev;
+ struct hinic_hwdev *hwdev;
+ struct hinic_hwif *hwif;
+ int err;
+
+ hwif = devm_kzalloc(&pdev->dev, sizeof(*hwif), GFP_KERNEL);
+ if (!hwif)
+ return ERR_PTR(-ENOMEM);
+
+ err = hinic_init_hwif(hwif, pdev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to init HW interface\n");
+ return ERR_PTR(err);
+ }
+
+ if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
+ dev_err(&pdev->dev, "Unsupported PCI Function type\n");
+ err = -EFAULT;
+ goto err_func_type;
+ }
+
+ pfhwdev = devm_kzalloc(&pdev->dev, sizeof(*pfhwdev), GFP_KERNEL);
+ if (!pfhwdev) {
+ err = -ENOMEM;
+ goto err_pfhwdev_alloc;
+ }
+
+ hwdev = &pfhwdev->hwdev;
+ hwdev->hwif = hwif;
+
+ err = init_msix(hwdev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to init msix\n");
+ goto err_init_msix;
+ }
+
+ err = init_pfhwdev(pfhwdev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to init PF HW device\n");
+ goto err_init_pfhwdev;
+ }
+
+ return hwdev;
+
+err_init_pfhwdev:
+ disable_msix(hwdev);
+
+err_init_msix:
+err_pfhwdev_alloc:
+err_func_type:
+ hinic_free_hwif(hwif);
+ return ERR_PTR(err);
+}
+
+/**
+ * hinic_free_hwdev - Free the NIC HW device
+ * @hwdev: the NIC HW device
+ **/
+void hinic_free_hwdev(struct hinic_hwdev *hwdev)
+{
+ struct hinic_pfhwdev *pfhwdev = container_of(hwdev,
+ struct hinic_pfhwdev,
+ hwdev);
+
+ free_pfhwdev(pfhwdev);
+
+ disable_msix(hwdev);
+
+ hinic_free_hwif(hwdev->hwif);
+}
+
+/**
+ * hinic_hwdev_num_qps - return the number QPs available for use
+ * @hwdev: the NIC HW device
+ *
+ * Return number QPs available for use
+ **/
+int hinic_hwdev_num_qps(struct hinic_hwdev *hwdev)
+{
+ int num_aeqs, num_ceqs, nr_irqs, num_qps;
+
+ num_aeqs = HINIC_HWIF_NUM_AEQS(hwdev->hwif);
+ num_ceqs = HINIC_HWIF_NUM_CEQS(hwdev->hwif);
+ nr_irqs = HINIC_HWIF_NUM_IRQS(hwdev->hwif);
+
+ /* Each QP has its own (SQ + RQ) interrupt */
+ num_qps = (nr_irqs - (num_aeqs + num_ceqs)) / 2;
+
+ /* num_qps must be power of 2 */
+ return BIT(fls(num_qps) - 1);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
new file mode 100644
index 0000000..b42e0eb
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -0,0 +1,42 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_HW_DEV_H
+#define HINIC_HW_DEV_H
+
+#include <linux/pci.h>
+
+#include "hinic_hw_if.h"
+
+#define HINIC_MAX_QPS 32
+
+struct hinic_hwdev {
+ struct hinic_hwif *hwif;
+ struct msix_entry *msix_entries;
+};
+
+struct hinic_pfhwdev {
+ struct hinic_hwdev hwdev;
+
+ /* PF Extended components should be here */
+};
+
+struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev);
+
+void hinic_free_hwdev(struct hinic_hwdev *hwdev);
+
+int hinic_hwdev_num_qps(struct hinic_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
new file mode 100644
index 0000000..edf1842
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -0,0 +1,208 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+
+#include "hinic_hw_csr.h"
+#include "hinic_hw_if.h"
+
+#define PCIE_ATTR_ENTRY 0
+
+/**
+ * hwif_ready - test if the HW is ready for use
+ * @hwif: the HW interface of a pci function device
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int hwif_ready(struct hinic_hwif *hwif)
+{
+ struct pci_dev *pdev = hwif->pdev;
+ u32 addr, attr1;
+
+ addr = HINIC_CSR_FUNC_ATTR1_ADDR;
+ attr1 = hinic_hwif_read_reg(hwif, addr);
+
+ if (!HINIC_FA1_GET(attr1, INIT_STATUS)) {
+ dev_err(&pdev->dev, "hwif status is not ready\n");
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+/**
+ * set_hwif_attr - set the attributes in the relevant members in hwif
+ * @hwif: the HW interface of a pci function device
+ * @attr0: the first attribute that was read from the hw
+ * @attr1: the second attribute that was read from the hw
+ **/
+static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1)
+{
+ hwif->attr.func_idx = HINIC_FA0_GET(attr0, FUNC_IDX);
+ hwif->attr.pf_idx = HINIC_FA0_GET(attr0, PF_IDX);
+ hwif->attr.pci_intf_idx = HINIC_FA0_GET(attr0, PCI_INTF_IDX);
+ hwif->attr.func_type = HINIC_FA0_GET(attr0, FUNC_TYPE);
+
+ hwif->attr.num_aeqs = BIT(HINIC_FA1_GET(attr1, AEQS_PER_FUNC));
+ hwif->attr.num_ceqs = BIT(HINIC_FA1_GET(attr1, CEQS_PER_FUNC));
+ hwif->attr.num_irqs = BIT(HINIC_FA1_GET(attr1, IRQS_PER_FUNC));
+ hwif->attr.num_dma_attr = BIT(HINIC_FA1_GET(attr1, DMA_ATTR_PER_FUNC));
+}
+
+/**
+ * read_hwif_attr - read the attributes and set members in hwif
+ * @hwif: the HW interface of a pci function device
+ **/
+static void read_hwif_attr(struct hinic_hwif *hwif)
+{
+ u32 addr, attr0, attr1;
+
+ addr = HINIC_CSR_FUNC_ATTR0_ADDR;
+ attr0 = hinic_hwif_read_reg(hwif, addr);
+
+ addr = HINIC_CSR_FUNC_ATTR1_ADDR;
+ attr1 = hinic_hwif_read_reg(hwif, addr);
+
+ set_hwif_attr(hwif, attr0, attr1);
+}
+
+/**
+ * set_ppf - try to set hwif as ppf and set the type of hwif in this case
+ * @hwif: the HW interface of a pci function device
+ **/
+static void set_ppf(struct hinic_hwif *hwif)
+{
+ struct hinic_func_attr *attr = &hwif->attr;
+ u32 addr, val, ppf_election;
+
+ /* Read Modify Write */
+ addr = HINIC_CSR_PPF_ELECTION_ADDR(HINIC_HWIF_PCI_INTF(hwif));
+
+ val = hinic_hwif_read_reg(hwif, addr);
+ val = HINIC_PPF_ELECTION_CLEAR(val, IDX);
+
+ ppf_election = HINIC_PPF_ELECTION_SET(HINIC_HWIF_FUNC_IDX(hwif), IDX);
+
+ val |= ppf_election;
+ hinic_hwif_write_reg(hwif, addr, val);
+
+ /* check PPF */
+ val = hinic_hwif_read_reg(hwif, addr);
+
+ attr->ppf_idx = HINIC_PPF_ELECTION_GET(val, IDX);
+ if (attr->ppf_idx == HINIC_HWIF_FUNC_IDX(hwif))
+ attr->func_type = HINIC_PPF;
+}
+
+/**
+ * set_dma_attr - set the dma attributes in the HW
+ * @hwif: the HW interface of a pci function device
+ * @entry_idx: the entry index in the dma table
+ * @st: PCIE TLP steering tag
+ * @at: PCIE TLP AT field
+ * @ph: PCIE TLP Processing Hint field
+ * @no_snooping: PCIE TLP No snooping
+ * @tph_en: PCIE TLP Processing Hint Enable
+ **/
+static void set_dma_attr(struct hinic_hwif *hwif, u32 entry_idx,
+ u8 st, u8 at, u8 ph,
+ enum hinic_pcie_nosnoop no_snooping,
+ enum hinic_pcie_tph tph_en)
+{
+ u32 addr, val, dma_attr_entry;
+
+ /* Read Modify Write */
+ addr = HINIC_CSR_DMA_ATTR_ADDR(entry_idx);
+
+ val = hinic_hwif_read_reg(hwif, addr);
+ val = HINIC_DMA_ATTR_CLEAR(val, ST) &
+ HINIC_DMA_ATTR_CLEAR(val, AT) &
+ HINIC_DMA_ATTR_CLEAR(val, PH) &
+ HINIC_DMA_ATTR_CLEAR(val, NO_SNOOPING) &
+ HINIC_DMA_ATTR_CLEAR(val, TPH_EN);
+
+ dma_attr_entry = HINIC_DMA_ATTR_SET(st, ST) |
+ HINIC_DMA_ATTR_SET(at, AT) |
+ HINIC_DMA_ATTR_SET(ph, PH) |
+ HINIC_DMA_ATTR_SET(no_snooping, NO_SNOOPING) |
+ HINIC_DMA_ATTR_SET(tph_en, TPH_EN);
+
+ val |= dma_attr_entry;
+ hinic_hwif_write_reg(hwif, addr, val);
+}
+
+/**
+ * dma_attr_table_init - initialize the the default dma attributes
+ * @hwif: the HW interface of a pci function device
+ **/
+static void dma_attr_init(struct hinic_hwif *hwif)
+{
+ set_dma_attr(hwif, PCIE_ATTR_ENTRY, HINIC_PCIE_ST_DISABLE,
+ HINIC_PCIE_AT_DISABLE, HINIC_PCIE_PH_DISABLE,
+ HINIC_PCIE_SNOOP, HINIC_PCIE_TPH_DISABLE);
+}
+
+/**
+ * hinic_init_hwif - initialize the hw interface
+ * @hwif: the HW interface of a pci function device
+ * @pdev: the pci device for acessing PCI resources
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev)
+{
+ int err;
+
+ hwif->pdev = pdev;
+
+ hwif->cfg_regs_bar = pci_ioremap_bar(pdev, HINIC_PCI_CFG_REGS_BAR);
+ if (!hwif->cfg_regs_bar) {
+ dev_err(&pdev->dev, "Failed to map configuration regs\n");
+ return -ENOMEM;
+ }
+
+ err = hwif_ready(hwif);
+ if (err) {
+ dev_err(&pdev->dev, "HW interface is not ready\n");
+ goto err_hwif_ready;
+ }
+
+ read_hwif_attr(hwif);
+
+ if (HINIC_IS_PF(hwif))
+ set_ppf(hwif);
+
+ /* No transactionss before DMA is initialized */
+ dma_attr_init(hwif);
+ return 0;
+
+err_hwif_ready:
+ iounmap(hwif->cfg_regs_bar);
+ return err;
+}
+
+/**
+ * hinic_free_hwif - free the HW interface
+ * @hwif: the HW interface of a pci function device
+ **/
+void hinic_free_hwif(struct hinic_hwif *hwif)
+{
+ iounmap(hwif->cfg_regs_bar);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
new file mode 100644
index 0000000..d1a8fa2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -0,0 +1,160 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef HINIC_HW_IF_H
+#define HINIC_HW_IF_H
+
+#include <linux/pci.h>
+#include <linux/io.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+#define HINIC_DMA_ATTR_ST_SHIFT 0
+#define HINIC_DMA_ATTR_AT_SHIFT 8
+#define HINIC_DMA_ATTR_PH_SHIFT 10
+#define HINIC_DMA_ATTR_NO_SNOOPING_SHIFT 12
+#define HINIC_DMA_ATTR_TPH_EN_SHIFT 13
+
+#define HINIC_DMA_ATTR_ST_MASK 0xFF
+#define HINIC_DMA_ATTR_AT_MASK 0x3
+#define HINIC_DMA_ATTR_PH_MASK 0x3
+#define HINIC_DMA_ATTR_NO_SNOOPING_MASK 0x1
+#define HINIC_DMA_ATTR_TPH_EN_MASK 0x1
+
+#define HINIC_DMA_ATTR_SET(val, member) \
+ (((u32)(val) & HINIC_DMA_ATTR_##member##_MASK) << \
+ HINIC_DMA_ATTR_##member##_SHIFT)
+
+#define HINIC_DMA_ATTR_CLEAR(val, member) \
+ ((val) & (~(HINIC_DMA_ATTR_##member##_MASK \
+ << HINIC_DMA_ATTR_##member##_SHIFT)))
+
+#define HINIC_FA0_FUNC_IDX_SHIFT 0
+#define HINIC_FA0_PF_IDX_SHIFT 10
+#define HINIC_FA0_PCI_INTF_IDX_SHIFT 14
+/* reserved members - off 16 */
+#define HINIC_FA0_FUNC_TYPE_SHIFT 24
+
+#define HINIC_FA0_FUNC_IDX_MASK 0x3FF
+#define HINIC_FA0_PF_IDX_MASK 0xF
+#define HINIC_FA0_PCI_INTF_IDX_MASK 0x3
+#define HINIC_FA0_FUNC_TYPE_MASK 0x1
+
+#define HINIC_FA0_GET(val, member) \
+ (((val) >> HINIC_FA0_##member##_SHIFT) & HINIC_FA0_##member##_MASK)
+
+#define HINIC_FA1_AEQS_PER_FUNC_SHIFT 8
+/* reserved members - off 10 */
+#define HINIC_FA1_CEQS_PER_FUNC_SHIFT 12
+/* reserved members - off 15 */
+#define HINIC_FA1_IRQS_PER_FUNC_SHIFT 20
+#define HINIC_FA1_DMA_ATTR_PER_FUNC_SHIFT 24
+/* reserved members - off 27 */
+#define HINIC_FA1_INIT_STATUS_SHIFT 30
+
+#define HINIC_FA1_AEQS_PER_FUNC_MASK 0x3
+#define HINIC_FA1_CEQS_PER_FUNC_MASK 0x7
+#define HINIC_FA1_IRQS_PER_FUNC_MASK 0xF
+#define HINIC_FA1_DMA_ATTR_PER_FUNC_MASK 0x7
+#define HINIC_FA1_INIT_STATUS_MASK 0x1
+
+#define HINIC_FA1_GET(val, member) \
+ (((val) >> HINIC_FA1_##member##_SHIFT) & HINIC_FA1_##member##_MASK)
+
+#define HINIC_PPF_ELECTION_IDX_SHIFT 0
+#define HINIC_PPF_ELECTION_IDX_MASK 0x1F
+
+#define HINIC_PPF_ELECTION_SET(val, member) \
+ (((u32)(val) & HINIC_PPF_ELECTION_##member##_MASK) << \
+ HINIC_PPF_ELECTION_##member##_SHIFT)
+
+#define HINIC_PPF_ELECTION_GET(val, member) \
+ (((val) >> HINIC_PPF_ELECTION_##member##_SHIFT) & \
+ HINIC_PPF_ELECTION_##member##_MASK)
+
+#define HINIC_PPF_ELECTION_CLEAR(val, member) \
+ ((val) & (~(HINIC_PPF_ELECTION_##member##_MASK \
+ << HINIC_PPF_ELECTION_##member##_SHIFT)))
+
+#define HINIC_HWIF_NUM_AEQS(hwif) ((hwif)->attr.num_aeqs)
+#define HINIC_HWIF_NUM_CEQS(hwif) ((hwif)->attr.num_ceqs)
+#define HINIC_HWIF_NUM_IRQS(hwif) ((hwif)->attr.num_irqs)
+#define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx)
+#define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx)
+
+#define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type)
+#define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF)
+#define HINIC_IS_PPF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PPF)
+
+#define HINIC_PCI_CFG_REGS_BAR 0
+
+#define HINIC_PCIE_ST_DISABLE 0
+#define HINIC_PCIE_AT_DISABLE 0
+#define HINIC_PCIE_PH_DISABLE 0
+
+enum hinic_pcie_nosnoop {
+ HINIC_PCIE_SNOOP = 0,
+ HINIC_PCIE_NO_SNOOP = 1,
+};
+
+enum hinic_pcie_tph {
+ HINIC_PCIE_TPH_DISABLE = 0,
+ HINIC_PCIE_TPH_ENABLE = 1,
+};
+
+enum hinic_func_type {
+ HINIC_PF = 0,
+ HINIC_PPF = 2,
+};
+
+struct hinic_func_attr {
+ u16 func_idx;
+ u8 pf_idx;
+ u8 pci_intf_idx;
+
+ enum hinic_func_type func_type;
+
+ u8 ppf_idx;
+
+ u16 num_irqs;
+ u8 num_aeqs;
+ u8 num_ceqs;
+
+ u8 num_dma_attr;
+};
+
+struct hinic_hwif {
+ struct pci_dev *pdev;
+ void __iomem *cfg_regs_bar;
+
+ struct hinic_func_attr attr;
+};
+
+static inline u32 hinic_hwif_read_reg(struct hinic_hwif *hwif, u32 reg)
+{
+ return be32_to_cpu(readl(hwif->cfg_regs_bar + reg));
+}
+
+static inline void hinic_hwif_write_reg(struct hinic_hwif *hwif, u32 reg,
+ u32 val)
+{
+ writel(cpu_to_be32(val), hwif->cfg_regs_bar + reg);
+}
+
+int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev);
+
+void hinic_free_hwif(struct hinic_hwif *hwif);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
new file mode 100644
index 0000000..10df850
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -0,0 +1,195 @@
+/*
+ * Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+#include <linux/err.h>
+
+#include "hinic_hw_dev.h"
+#include "hinic_dev.h"
+
+MODULE_AUTHOR("Huawei Technologies CO., Ltd");
+MODULE_DESCRIPTION("Huawei Intelligent NIC driver");
+MODULE_LICENSE("GPL");
+
+#define PCI_DEVICE_ID_HI1822_PF 0x1822
+
+#define MSG_ENABLE_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \
+ NETIF_MSG_IFUP | \
+ NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR)
+
+static const struct net_device_ops hinic_netdev_ops = {
+ /* Operations are empty, should be filled */
+};
+
+/**
+ * nic_dev_init - Initialize the NIC device
+ * @pdev: the NIC pci device
+ *
+ * Return 0 - Success, negative - Failure
+ **/
+static int nic_dev_init(struct pci_dev *pdev)
+{
+ struct hinic_dev *nic_dev;
+ struct net_device *netdev;
+ struct hinic_hwdev *hwdev;
+ int err, num_qps;
+
+ hwdev = hinic_init_hwdev(pdev);
+ if (IS_ERR(hwdev)) {
+ dev_err(&pdev->dev, "Failed to initialize HW device\n");
+ return PTR_ERR(hwdev);
+ }
+
+ num_qps = hinic_hwdev_num_qps(hwdev);
+ if (num_qps <= 0) {
+ dev_err(&pdev->dev, "Invalid number of QPS\n");
+ err = -EINVAL;
+ goto err_num_qps;
+ }
+
+ netdev = alloc_etherdev_mq(sizeof(*nic_dev), num_qps);
+ if (!netdev) {
+ dev_err(&pdev->dev, "Failed to allocate Ethernet device\n");
+ err = -ENOMEM;
+ goto err_alloc_etherdev;
+ }
+
+ netdev->netdev_ops = &hinic_netdev_ops;
+
+ nic_dev = (struct hinic_dev *)netdev_priv(netdev);
+ nic_dev->netdev = netdev;
+ nic_dev->hwdev = hwdev;
+ nic_dev->msg_enable = MSG_ENABLE_DEFAULT;
+
+ pci_set_drvdata(pdev, netdev);
+
+ netif_carrier_off(netdev);
+
+ err = register_netdev(netdev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to register netdev\n");
+ goto err_reg_netdev;
+ }
+
+ return 0;
+
+err_reg_netdev:
+ pci_set_drvdata(pdev, NULL);
+ free_netdev(netdev);
+
+err_alloc_etherdev:
+err_num_qps:
+ hinic_free_hwdev(hwdev);
+ return err;
+}
+
+static int hinic_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ int err = pci_enable_device(pdev);
+
+ if (err) {
+ dev_err(&pdev->dev, "Failed to enable PCI device\n");
+ return err;
+ }
+
+ err = pci_request_regions(pdev, HINIC_DRV_NAME);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to request PCI regions\n");
+ goto err_pci_regions;
+ }
+
+ pci_set_master(pdev);
+
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ if (err) {
+ dev_warn(&pdev->dev, "Couldn't set 64-bit DMA mask\n");
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev, "Failed to set DMA mask\n");
+ goto err_dma_mask;
+ }
+ }
+
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+ if (err) {
+ dev_warn(&pdev->dev,
+ "Couldn't set 64-bit consistent DMA mask\n");
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev,
+ "Failed to set consistent DMA mask\n");
+ goto err_dma_consistent_mask;
+ }
+ }
+
+ err = nic_dev_init(pdev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to initialize NIC device\n");
+ goto err_nic_dev_init;
+ }
+
+ dev_info(&pdev->dev, "HiNIC driver - probed\n");
+ return 0;
+
+err_nic_dev_init:
+err_dma_consistent_mask:
+err_dma_mask:
+ pci_release_regions(pdev);
+
+err_pci_regions:
+ pci_disable_device(pdev);
+ return err;
+}
+
+static void hinic_remove(struct pci_dev *pdev)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+
+ unregister_netdev(netdev);
+
+ pci_set_drvdata(pdev, NULL);
+
+ hinic_free_hwdev(nic_dev->hwdev);
+
+ free_netdev(netdev);
+
+ pci_release_regions(pdev);
+ pci_disable_device(pdev);
+
+ dev_info(&pdev->dev, "HiNIC driver - removed\n");
+}
+
+static const struct pci_device_id hinic_pci_table[] = {
+ { PCI_VDEVICE(HUAWEI, PCI_DEVICE_ID_HI1822_PF), 0},
+ { 0, 0}
+};
+MODULE_DEVICE_TABLE(pci, hinic_pci_table);
+
+static struct pci_driver hinic_driver = {
+ .name = HINIC_DRV_NAME,
+ .id_table = hinic_pci_table,
+ .probe = hinic_probe,
+ .remove = hinic_remove,
+};
+
+module_pci_driver(hinic_driver);
--
1.9.1
^ permalink raw reply related
* [PATCH V5 net-next 00/21] Huawei HiNIC Ethernet Driver
From: Aviad Krawczyk @ 2017-08-17 11:52 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, bc.y, victor.gissin, aviad.krawczyk,
zhaochen6, tony.qu
The patch-set contains the support of the HiNIC Ethernet driver for
hinic family of PCIE Network Interface Cards.
The Huawei's PCIE HiNIC card is a new Ethernet card and hence there was
a need of a new driver.
The current driver is meant to be used for the Physical Function and there
would soon be a support for Virtual Function and more features once the
basic PF driver has been accepted.
Changes V4 -> V5:
1. Remove select_queue NOP - David Miller comment
https://lkml.org/lkml/2017/8/16/625
Changes V3 -> V4:
1. Reverse christmas tree order - David Miller comment
https://lkml.org/lkml/2017/8/3/862
Changes V2 -> V3:
1. Replace dev_ functions by netif_ functions - Joe Perches comment
https://lkml.org/lkml/2017/7/19/424
2. Fix the driver directory in MAINTAINERS file - Sergei Shtylyov comment
https://lkml.org/lkml/2017/7/19/615
3. Add a newline at the end of Makefile - David Miller comment
https://lkml.org/lkml/2017/7/19/1345
4. Return a pointer as a val instead of in arg - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
5. Change the error labels to err_xyz - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
6. Remove check of Func Type in free function - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
7. Remove !netdev check in remove function - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
8. Use module_pci_driver - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
9. Move the PCI device ID to the .c file - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
10. Remove void * to avoid passing wrong ptr - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
Changes V1 -> V2:
1. remove driver verstion - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/372
2. replace kzalloc by devm_kzalloc for short clean - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/372
3. replace pr_ functions by dev_ functions - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/375
4. seperate last patch by moving ops to a new patch - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/377
Aviad Krawczyk (21):
net-next/hinic: Initialize hw interface
net-next/hinic: Initialize hw device components
net-next/hinic: Initialize api cmd resources
net-next/hinic: Initialize api cmd hw
net-next/hinic: Add management messages
net-next/hinic: Add api cmd commands
net-next/hinic: Add aeqs
net-next/hinic: Add port management commands
net-next/hinic: Add Rx mode and link event handler
net-next/hinic: Add logical Txq and Rxq
net-next/hinic: Add wq
net-next/hinic: Add qp resources
net-next/hinic: Set qp context
net-next/hinic: Initialize cmdq
net-next/hinic: Add ceqs
net-next/hinic: Add cmdq commands
net-next/hinic: Add cmdq completion handler
net-next/hinic: Add Rx handler
net-next/hinic: Add Tx operation
net-next/hinic: Add ethtool and stats
net-next/hinic: Add netpoll
Documentation/networking/hinic.txt | 125 +++
MAINTAINERS | 7 +
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/huawei/Kconfig | 19 +
drivers/net/ethernet/huawei/Makefile | 5 +
drivers/net/ethernet/huawei/hinic/Kconfig | 13 +
drivers/net/ethernet/huawei/hinic/Makefile | 6 +
drivers/net/ethernet/huawei/hinic/hinic_common.c | 80 ++
drivers/net/ethernet/huawei/hinic/hinic_common.h | 38 +
drivers/net/ethernet/huawei/hinic/hinic_dev.h | 64 ++
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.c | 977 +++++++++++++++++
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.h | 208 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c | 946 +++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h | 187 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h | 149 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 1045 ++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h | 239 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c | 888 ++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h | 265 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.c | 352 +++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 272 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_io.c | 533 ++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_io.h | 97 ++
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 597 +++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h | 153 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c | 892 ++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h | 180 ++++
.../net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h | 214 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c | 879 ++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h | 117 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h | 368 +++++++
drivers/net/ethernet/huawei/hinic/hinic_main.c | 1111 ++++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_port.c | 379 +++++++
drivers/net/ethernet/huawei/hinic/hinic_port.h | 198 ++++
drivers/net/ethernet/huawei/hinic/hinic_rx.c | 510 +++++++++
drivers/net/ethernet/huawei/hinic/hinic_rx.h | 55 +
drivers/net/ethernet/huawei/hinic/hinic_tx.c | 503 +++++++++
drivers/net/ethernet/huawei/hinic/hinic_tx.h | 62 ++
39 files changed, 12735 insertions(+)
create mode 100644 Documentation/networking/hinic.txt
create mode 100644 drivers/net/ethernet/huawei/Kconfig
create mode 100644 drivers/net/ethernet/huawei/Makefile
create mode 100644 drivers/net/ethernet/huawei/hinic/Kconfig
create mode 100644 drivers/net/ethernet/huawei/hinic/Makefile
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_common.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_common.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_dev.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_main.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_port.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_port.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_rx.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_rx.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_tx.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_tx.h
--
1.9.1
^ permalink raw reply
* Re: [PATCH 1/6] bridge: learn dst metadata in FDB
From: Nikolay Aleksandrov @ 2017-08-17 11:51 UTC (permalink / raw)
To: David Lamparter
Cc: netdev, roopa, bridge@lists.linux-foundation.org,
amine.kherbouche
In-Reply-To: <4d4c8d17-1e0b-b78f-983b-e419e153b2bf@cumulusnetworks.com>
On 17/08/17 14:39, Nikolay Aleksandrov wrote:
> On 17/08/17 14:03, David Lamparter wrote:
>> Hi Nikolay,
>>
>>
>> On Wed, Aug 16, 2017 at 11:38:06PM +0300, Nikolay Aleksandrov wrote:
>>> On 16/08/17 20:01, David Lamparter wrote:
>>>> This implements holding dst metadata information in the bridge layer,
>>>> but only for unicast entries in the MAC table. Multicast is still left
>>>> to design and implement.
>>>
>>> Sorry but I do not agree with this change, adding a special case for
>>> VPLS in the bridge code
>>
>> I don't think this is specific to VPLS at all, though you're right that
>> VPLS is the only user currently.
>>
>>> and hitting the fast path for everyone in a few different places for a
>>> feature that the majority will not use does not sound acceptable to
>>> me. We've been trying hard to optimize it, trying to avoid additional
>>> cache lines, removing tests and keeping special cases to a minimum.
>>
>> skb->dst is on the same cacheline as skb->len.
>> fdb->md_dst is on the same cacheline as fdb->dst.
>> Both will be 0 in a lot of cases, so this should be two null checks on
>> data that is hot in the cache. Are you sure this is an actual problem?
>>
>
> Sure - no, I haven't benchmarked it, but I don't see skb->len being on
> the same cache line as _skb_refdst assuming 64 byte cache lines.
I should've been clearer - that obviously depends on the kernel config, but
in order for them to be in the same line you need to disable either one of
conntrack, bridge_netfilter or xfrm, these are almost always enabled (at
least in all major distributions).
> But again any special cases, in my opinion, should be handled on their own,
> it is both about the fast path and the code complexity that they bring in.
>
>>> I understand that you want to use the fdb tables and avoid
>>> duplication, but this is not worth it. There're other similar use
>>> cases and they have their own private fdb tables, that way the user
>>> can opt out and is much cleaner and separated.
>>
>> Sure, this can be done. I think it's a noticeable performance penalty
>> to have the entire fdb copied (multiple times for H-VPLS even), but I
>> understand that it's preferable to have the normal cases faster in
>> exchange. As the previous paragraph notes, I still wonder if that hit
>> to the normal case exists though.
>>
>> I will leave this to Amine, he's paid to work on VPLS while I'm doing
>> this for fun ;)
>>
>> There is however another concern I have here. As I noted in my
>> introductory mail, I'm working on the bridge MDB making similar changes.
>> And there's actually strong use cases for this in both VPLS and the
>> 802.11 code (though I'm not sure I can code the latter one up, it's
>> related to rate control and this is seriously complicated - the goal is
>> to select a multicast rate based on the now-known receiving STAs).
>>
>> I really hope you're not suggesting the entire MDB with IPv4 & IPv6
>> snooping be duplicated into both VPLS and mac80211?
>>
>
> Code can always be shared if there are more users, no need to stuff everything in
> the bridge, but I'm not that familiar with this case, once patches are out I can
> comment further.
>
>>> As you've noted this is only an RFC so I will not point out every issue, but there seems
>>> to be a major problem with br_fdb_update(), note that it runs without any locks except RCU.
>>
>> Right, Thanks! ... I only thought about concurrent access, forgetting
>> about concurrent modification... I'll replace it with an xchg I think.
>> (No need for a lock that way)
>
> I think you can still lose references to a dst that way, what if someone changes the
> dst you read before the xchg and you xchg it ?
>
>>
>> That said, now that I think about it, the skb_dst_set_noref() in the
>> following chunk is probably not safe if the VPLS device has a qdisc on
>> it. I was relying on the fact that br_dev_xmit is holding RCU there,
>> but if the SKB is queued, md_dst might go away in the meantime...
>> ... probably need to change this to dst_hold() + skb_dst_set()...
>>
>>
>> -David
>>
>>>> diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
>>>> index 861ae2a165f4..534cacf02f8d 100644
>>>> --- a/net/bridge/br_device.c
>>>> +++ b/net/bridge/br_device.c
>>>> @@ -81,6 +82,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
>>>> else
>>>> br_flood(br, skb, BR_PKT_MULTICAST, false, true);
>>>> } else if ((dst = br_fdb_find_rcu(br, dest, vid)) != NULL) {
>>>> + struct dst_entry *md_dst = rcu_dereference(dst->md_dst);
>>>> + if (md_dst)
>>>> + skb_dst_set_noref(skb, md_dst);
>>>> br_forward(dst->dst, skb, false, true);
>>>> } else {
>>>> br_flood(br, skb, BR_PKT_UNICAST, false, true);
>>
>>
>>>> diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
>>>> index a79b648aac88..0751fcb89699 100644
>>>> @@ -567,10 +579,15 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
>>>> source->dev->name, addr, vid);
>>>> } else {
>>>> unsigned long now = jiffies;
>>>> + struct dst_entry *ref_md = rcu_access_pointer(fdb->md_dst);
>>>>
>>>> /* fastpath: update of existing entry */
>>>> - if (unlikely(source != fdb->dst)) {
>>>> + if (unlikely(source != fdb->dst ||
>>>> + dst_metadata_cmp(md_dst, ref_md))) {
>>>> fdb->dst = source;
>>>> + dst_release(ref_md);
>>>> + rcu_assign_pointer(fdb->md_dst,
>>>> + dst_clone(md_dst));
>>>> fdb_modified = true;
>>>> /* Take over HW learned entry */
>>>> if (unlikely(fdb->added_by_external_learn))
>
^ permalink raw reply
* Re: [PATCH v2] bpf: Update sysctl documentation to list all supported architectures
From: Daniel Borkmann @ 2017-08-17 11:50 UTC (permalink / raw)
To: Michael Ellerman, ast; +Cc: davem, netdev, linux-kernel
In-Reply-To: <1502965839-23115-1-git-send-email-mpe@ellerman.id.au>
On 08/17/2017 12:30 PM, Michael Ellerman wrote:
> The sysctl documentation states that the JIT is only available on
> x86_64, which is no longer correct.
>
> Update the list, and break it out to indicate which architectures
> support the cBPF JIT (via HAVE_CBPF_JIT) or the eBPF JIT
> (HAVE_EBPF_JIT).
>
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The last paragraph speaking about tcpdump, I can take care of
later, also given the patch is about updating list of archs, so
lgtm, thanks!
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* [PATCH V5 net-next 00/21] Huawei HiNIC Ethernet Driver
From: Aviad Krawczyk @ 2017-08-17 11:47 UTC (permalink / raw)
To: davem, aviad.krawczyk
Cc: linux-kernel, netdev, bc.y, victor.gissin, zhaochen6, tony.qu
The patch-set contains the support of the HiNIC Ethernet driver for
hinic family of PCIE Network Interface Cards.
The Huawei's PCIE HiNIC card is a new Ethernet card and hence there was
a need of a new driver.
The current driver is meant to be used for the Physical Function and there
would soon be a support for Virtual Function and more features once the
basic PF driver has been accepted.
Changes V4 -> V5:
1. Remove select_queue NOP - David Miller comment
https://lkml.org/lkml/2017/8/16/625
Changes V3 -> V4:
1. Reverse christmas tree order - David Miller comment
https://lkml.org/lkml/2017/8/3/862
Changes V2 -> V3:
1. Replace dev_ functions by netif_ functions - Joe Perches comment
https://lkml.org/lkml/2017/7/19/424
2. Fix the driver directory in MAINTAINERS file - Sergei Shtylyov comment
https://lkml.org/lkml/2017/7/19/615
3. Add a newline at the end of Makefile - David Miller comment
https://lkml.org/lkml/2017/7/19/1345
4. Return a pointer as a val instead of in arg - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
5. Change the error labels to err_xyz - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
6. Remove check of Func Type in free function - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
7. Remove !netdev check in remove function - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
8. Use module_pci_driver - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
9. Move the PCI device ID to the .c file - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
10. Remove void * to avoid passing wrong ptr - Francois Romieu comment
https://lkml.org/lkml/2017/7/19/1319
Changes V1 -> V2:
1. remove driver verstion - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/372
2. replace kzalloc by devm_kzalloc for short clean - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/372
3. replace pr_ functions by dev_ functions - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/375
4. seperate last patch by moving ops to a new patch - Andrew Lunn comment
https://lkml.org/lkml/2017/7/12/377
Aviad Krawczyk (21):
net-next/hinic: Initialize hw interface
net-next/hinic: Initialize hw device components
net-next/hinic: Initialize api cmd resources
net-next/hinic: Initialize api cmd hw
net-next/hinic: Add management messages
net-next/hinic: Add api cmd commands
net-next/hinic: Add aeqs
net-next/hinic: Add port management commands
net-next/hinic: Add Rx mode and link event handler
net-next/hinic: Add logical Txq and Rxq
net-next/hinic: Add wq
net-next/hinic: Add qp resources
net-next/hinic: Set qp context
net-next/hinic: Initialize cmdq
net-next/hinic: Add ceqs
net-next/hinic: Add cmdq commands
net-next/hinic: Add cmdq completion handler
net-next/hinic: Add Rx handler
net-next/hinic: Add Tx operation
net-next/hinic: Add ethtool and stats
net-next/hinic: Add netpoll
Documentation/networking/hinic.txt | 125 +++
MAINTAINERS | 7 +
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/huawei/Kconfig | 19 +
drivers/net/ethernet/huawei/Makefile | 5 +
drivers/net/ethernet/huawei/hinic/Kconfig | 13 +
drivers/net/ethernet/huawei/hinic/Makefile | 6 +
drivers/net/ethernet/huawei/hinic/hinic_common.c | 80 ++
drivers/net/ethernet/huawei/hinic/hinic_common.h | 38 +
drivers/net/ethernet/huawei/hinic/hinic_dev.h | 64 ++
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.c | 977 +++++++++++++++++
.../net/ethernet/huawei/hinic/hinic_hw_api_cmd.h | 208 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c | 946 +++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h | 187 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h | 149 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 1045 ++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h | 239 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c | 888 ++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h | 265 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.c | 352 +++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 272 +++++
drivers/net/ethernet/huawei/hinic/hinic_hw_io.c | 533 ++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_io.h | 97 ++
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 597 +++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h | 153 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c | 892 ++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h | 180 ++++
.../net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h | 214 ++++
drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c | 879 ++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h | 117 +++
drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h | 368 +++++++
drivers/net/ethernet/huawei/hinic/hinic_main.c | 1111 ++++++++++++++++++++
drivers/net/ethernet/huawei/hinic/hinic_port.c | 379 +++++++
drivers/net/ethernet/huawei/hinic/hinic_port.h | 198 ++++
drivers/net/ethernet/huawei/hinic/hinic_rx.c | 510 +++++++++
drivers/net/ethernet/huawei/hinic/hinic_rx.h | 55 +
drivers/net/ethernet/huawei/hinic/hinic_tx.c | 503 +++++++++
drivers/net/ethernet/huawei/hinic/hinic_tx.h | 62 ++
39 files changed, 12735 insertions(+)
create mode 100644 Documentation/networking/hinic.txt
create mode 100644 drivers/net/ethernet/huawei/Kconfig
create mode 100644 drivers/net/ethernet/huawei/Makefile
create mode 100644 drivers/net/ethernet/huawei/hinic/Kconfig
create mode 100644 drivers/net/ethernet/huawei/hinic/Makefile
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_common.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_common.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_dev.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_main.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_port.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_port.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_rx.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_rx.h
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_tx.c
create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_tx.h
--
1.9.1
^ permalink raw reply
* Re: [PATCH 1/6] bridge: learn dst metadata in FDB
From: Nikolay Aleksandrov @ 2017-08-17 11:39 UTC (permalink / raw)
To: David Lamparter
Cc: netdev, roopa, bridge@lists.linux-foundation.org,
amine.kherbouche
In-Reply-To: <20170817110324.GK773745@eidolon>
On 17/08/17 14:03, David Lamparter wrote:
> Hi Nikolay,
>
>
> On Wed, Aug 16, 2017 at 11:38:06PM +0300, Nikolay Aleksandrov wrote:
>> On 16/08/17 20:01, David Lamparter wrote:
>>> This implements holding dst metadata information in the bridge layer,
>>> but only for unicast entries in the MAC table. Multicast is still left
>>> to design and implement.
>>
>> Sorry but I do not agree with this change, adding a special case for
>> VPLS in the bridge code
>
> I don't think this is specific to VPLS at all, though you're right that
> VPLS is the only user currently.
>
>> and hitting the fast path for everyone in a few different places for a
>> feature that the majority will not use does not sound acceptable to
>> me. We've been trying hard to optimize it, trying to avoid additional
>> cache lines, removing tests and keeping special cases to a minimum.
>
> skb->dst is on the same cacheline as skb->len.
> fdb->md_dst is on the same cacheline as fdb->dst.
> Both will be 0 in a lot of cases, so this should be two null checks on
> data that is hot in the cache. Are you sure this is an actual problem?
>
Sure - no, I haven't benchmarked it, but I don't see skb->len being on
the same cache line as _skb_refdst assuming 64 byte cache lines.
But again any special cases, in my opinion, should be handled on their own,
it is both about the fast path and the code complexity that they bring in.
>> I understand that you want to use the fdb tables and avoid
>> duplication, but this is not worth it. There're other similar use
>> cases and they have their own private fdb tables, that way the user
>> can opt out and is much cleaner and separated.
>
> Sure, this can be done. I think it's a noticeable performance penalty
> to have the entire fdb copied (multiple times for H-VPLS even), but I
> understand that it's preferable to have the normal cases faster in
> exchange. As the previous paragraph notes, I still wonder if that hit
> to the normal case exists though.
>
> I will leave this to Amine, he's paid to work on VPLS while I'm doing
> this for fun ;)
>
> There is however another concern I have here. As I noted in my
> introductory mail, I'm working on the bridge MDB making similar changes.
> And there's actually strong use cases for this in both VPLS and the
> 802.11 code (though I'm not sure I can code the latter one up, it's
> related to rate control and this is seriously complicated - the goal is
> to select a multicast rate based on the now-known receiving STAs).
>
> I really hope you're not suggesting the entire MDB with IPv4 & IPv6
> snooping be duplicated into both VPLS and mac80211?
>
Code can always be shared if there are more users, no need to stuff everything in
the bridge, but I'm not that familiar with this case, once patches are out I can
comment further.
>> As you've noted this is only an RFC so I will not point out every issue, but there seems
>> to be a major problem with br_fdb_update(), note that it runs without any locks except RCU.
>
> Right, Thanks! ... I only thought about concurrent access, forgetting
> about concurrent modification... I'll replace it with an xchg I think.
> (No need for a lock that way)
I think you can still lose references to a dst that way, what if someone changes the
dst you read before the xchg and you xchg it ?
>
> That said, now that I think about it, the skb_dst_set_noref() in the
> following chunk is probably not safe if the VPLS device has a qdisc on
> it. I was relying on the fact that br_dev_xmit is holding RCU there,
> but if the SKB is queued, md_dst might go away in the meantime...
> ... probably need to change this to dst_hold() + skb_dst_set()...
>
>
> -David
>
>>> diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
>>> index 861ae2a165f4..534cacf02f8d 100644
>>> --- a/net/bridge/br_device.c
>>> +++ b/net/bridge/br_device.c
>>> @@ -81,6 +82,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
>>> else
>>> br_flood(br, skb, BR_PKT_MULTICAST, false, true);
>>> } else if ((dst = br_fdb_find_rcu(br, dest, vid)) != NULL) {
>>> + struct dst_entry *md_dst = rcu_dereference(dst->md_dst);
>>> + if (md_dst)
>>> + skb_dst_set_noref(skb, md_dst);
>>> br_forward(dst->dst, skb, false, true);
>>> } else {
>>> br_flood(br, skb, BR_PKT_UNICAST, false, true);
>
>
>>> diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
>>> index a79b648aac88..0751fcb89699 100644
>>> @@ -567,10 +579,15 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
>>> source->dev->name, addr, vid);
>>> } else {
>>> unsigned long now = jiffies;
>>> + struct dst_entry *ref_md = rcu_access_pointer(fdb->md_dst);
>>>
>>> /* fastpath: update of existing entry */
>>> - if (unlikely(source != fdb->dst)) {
>>> + if (unlikely(source != fdb->dst ||
>>> + dst_metadata_cmp(md_dst, ref_md))) {
>>> fdb->dst = source;
>>> + dst_release(ref_md);
>>> + rcu_assign_pointer(fdb->md_dst,
>>> + dst_clone(md_dst));
>>> fdb_modified = true;
>>> /* Take over HW learned entry */
>>> if (unlikely(fdb->added_by_external_learn))
^ permalink raw reply
* Re: Something hitting my total number of connections to the server
From: Eric Dumazet @ 2017-08-17 11:36 UTC (permalink / raw)
To: Akshat Kakkar; +Cc: netdev
In-Reply-To: <CAA5aLPh0m=ZZp5kcz9h3if8kemg0QRykBpfYAnr6Bd1ptoeKKg@mail.gmail.com>
On Thu, 2017-08-17 at 14:35 +0530, Akshat Kakkar wrote:
> I upgraded to 4.4 but still experiencing same issue.
> Please help.
Still too old kernel, shoot again ;)
^ permalink raw reply
* Re: [PATCH net] net: sched: fix NULL pointer dereference when action calls some targets
From: Xin Long @ 2017-08-17 11:24 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: Cong Wang, network dev, David Miller, netfilter-devel,
Jamal Hadi Salim
In-Reply-To: <20170817103344.GA7568@salvia>
On Thu, Aug 17, 2017 at 10:33 PM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> On Thu, Aug 17, 2017 at 12:02:20PM +0200, Pablo Neira Ayuso wrote:
>> On Wed, Aug 16, 2017 at 08:39:44PM +1200, Xin Long wrote:
>> > On Wed, Aug 9, 2017 at 7:33 AM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
>> > > On Mon, Aug 7, 2017 at 7:33 PM, Xin Long <lucien.xin@gmail.com> wrote:
>> > >> On Tue, Aug 8, 2017 at 9:15 AM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
>> > >>> This looks like a completely API burden?
>> > >> netfilter xt targets are not really compatible with netsched action.
>> > >> I've got to say, the patch is just a way to make checkentry return
>> > >> false and avoid panic. like [1] said
>> > >
>> > > I don't doubt you fix a crash, I am thinking if we can
>> > > "fix" the API instead of fixing the caller.
>> > Hi, Cong,
>> >
>> > For now, I don't think it's possible to change APIs or some of their targets
>> > for the panic caused by action xt calling.
>> >
>> > The common way should be fixed in net_sched side.
>> >
>> > Given that the issue is very easy to triggered,
>> > let's wait for netfilter's replies for another few days,
>> > otherwise I will repost the fix, agree ?
>>
>> Please, post the workaround so the kernel doesn't crash anymore.
>>
>> This is going to be very hard to fix, it's broken since the very
>> beginning...
>
> Wait a second, you could rename par->nft_compat to par->no_entry. From
> net/sched/ you can set this to 1, so the entry checks are ignored.
>
> I'm refering to patch 55917a21d0cc0
par->nft_compat wasn't used to ignore the entry checks, if we rename it
as no_entry, some other targets still needs to update. like the ones in
this patch's changelog:
ECN: ecn_tg_check()
TPROXY: tproxy_tg4_check()
which means these two checks will be ignored for nft as well, that is
not what we want.
As nft has e4.ip.proto and e4.ip.invflags being set which net/sched
gets nothing. they are still different.
^ permalink raw reply
* [PATCH] PCI: Allow PCI express root ports to find themselves
From: Thierry Reding @ 2017-08-17 11:06 UTC (permalink / raw)
To: David Miller, Bjorn Helgaas, Ding Tianhong, Michael Ellerman
Cc: leedom, ashok.raj, werner, ganeshgr, asit.k.mallick,
patrick.j.cramer, Suravee.Suthikulpanit, Bob.Shaw, l.stach, amira,
gabriele.paoloni, David.Laight, jeffrey.t.kirsher,
catalin.marinas, will.deacon, mark.rutland, robin.murphy,
alexander.duyck, eric.dumazet, linux-arm-kernel, netdev,
linux-pci, linux-kernel, linuxarm
In-Reply-To: <1502936730-7368-1-git-send-email-dingtianhong@huawei.com>
From: Thierry Reding <treding@nvidia.com>
If the pci_find_pcie_root_port() function is called on a root port
itself, return the root port rather than NULL.
This effectively reverts commit 0e405232871d6 ("PCI: fix oops when
try to find Root Port for a PCI device") which added an extra check
that would now be redundant.
Fixes: a99b646afa8a ("PCI: Disable PCIe Relaxed Ordering if unsupported")
Fixes: c56d4450eb68 ("PCI: Turn off Request Attributes to avoid Chelsio T5 Completion erratum")
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
This applies on top of and was tested on next-20170817.
Michael, it'd be great if you could test this one again to clarify
whether or not the fix that's already in Linus' tree is still needed, or
whether it's indeed obsoleted by this patch.
drivers/pci/pci.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index b05c587e335a..dd56c1c05614 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -514,7 +514,7 @@ EXPORT_SYMBOL(pci_find_resource);
*/
struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev)
{
- struct pci_dev *bridge, *highest_pcie_bridge = NULL;
+ struct pci_dev *bridge, *highest_pcie_bridge = dev;
bridge = pci_upstream_bridge(dev);
while (bridge && pci_is_pcie(bridge)) {
@@ -522,11 +522,10 @@ struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev)
bridge = pci_upstream_bridge(bridge);
}
- if (highest_pcie_bridge &&
- pci_pcie_type(highest_pcie_bridge) == PCI_EXP_TYPE_ROOT_PORT)
- return highest_pcie_bridge;
+ if (pci_pcie_type(highest_pcie_bridge) != PCI_EXP_TYPE_ROOT_PORT)
+ return NULL;
- return NULL;
+ return highest_pcie_bridge;
}
EXPORT_SYMBOL(pci_find_pcie_root_port);
--
2.13.3
^ permalink raw reply related
* Re: [PATCH 1/6] bridge: learn dst metadata in FDB
From: David Lamparter @ 2017-08-17 11:03 UTC (permalink / raw)
To: Nikolay Aleksandrov
Cc: David Lamparter, netdev, amine.kherbouche, roopa, stephen,
bridge@lists.linux-foundation.org
In-Reply-To: <1fbaa432-6241-fad0-5407-8b87abb965ae@cumulusnetworks.com>
Hi Nikolay,
On Wed, Aug 16, 2017 at 11:38:06PM +0300, Nikolay Aleksandrov wrote:
> On 16/08/17 20:01, David Lamparter wrote:
> > This implements holding dst metadata information in the bridge layer,
> > but only for unicast entries in the MAC table. Multicast is still left
> > to design and implement.
>
> Sorry but I do not agree with this change, adding a special case for
> VPLS in the bridge code
I don't think this is specific to VPLS at all, though you're right that
VPLS is the only user currently.
> and hitting the fast path for everyone in a few different places for a
> feature that the majority will not use does not sound acceptable to
> me. We've been trying hard to optimize it, trying to avoid additional
> cache lines, removing tests and keeping special cases to a minimum.
skb->dst is on the same cacheline as skb->len.
fdb->md_dst is on the same cacheline as fdb->dst.
Both will be 0 in a lot of cases, so this should be two null checks on
data that is hot in the cache. Are you sure this is an actual problem?
> I understand that you want to use the fdb tables and avoid
> duplication, but this is not worth it. There're other similar use
> cases and they have their own private fdb tables, that way the user
> can opt out and is much cleaner and separated.
Sure, this can be done. I think it's a noticeable performance penalty
to have the entire fdb copied (multiple times for H-VPLS even), but I
understand that it's preferable to have the normal cases faster in
exchange. As the previous paragraph notes, I still wonder if that hit
to the normal case exists though.
I will leave this to Amine, he's paid to work on VPLS while I'm doing
this for fun ;)
There is however another concern I have here. As I noted in my
introductory mail, I'm working on the bridge MDB making similar changes.
And there's actually strong use cases for this in both VPLS and the
802.11 code (though I'm not sure I can code the latter one up, it's
related to rate control and this is seriously complicated - the goal is
to select a multicast rate based on the now-known receiving STAs).
I really hope you're not suggesting the entire MDB with IPv4 & IPv6
snooping be duplicated into both VPLS and mac80211?
> As you've noted this is only an RFC so I will not point out every issue, but there seems
> to be a major problem with br_fdb_update(), note that it runs without any locks except RCU.
Right, Thanks! ... I only thought about concurrent access, forgetting
about concurrent modification... I'll replace it with an xchg I think.
(No need for a lock that way)
That said, now that I think about it, the skb_dst_set_noref() in the
following chunk is probably not safe if the VPLS device has a qdisc on
it. I was relying on the fact that br_dev_xmit is holding RCU there,
but if the SKB is queued, md_dst might go away in the meantime...
... probably need to change this to dst_hold() + skb_dst_set()...
-David
> > diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
> > index 861ae2a165f4..534cacf02f8d 100644
> > --- a/net/bridge/br_device.c
> > +++ b/net/bridge/br_device.c
> > @@ -81,6 +82,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
> > else
> > br_flood(br, skb, BR_PKT_MULTICAST, false, true);
> > } else if ((dst = br_fdb_find_rcu(br, dest, vid)) != NULL) {
> > + struct dst_entry *md_dst = rcu_dereference(dst->md_dst);
> > + if (md_dst)
> > + skb_dst_set_noref(skb, md_dst);
> > br_forward(dst->dst, skb, false, true);
> > } else {
> > br_flood(br, skb, BR_PKT_UNICAST, false, true);
> > diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
> > index a79b648aac88..0751fcb89699 100644
> > @@ -567,10 +579,15 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
> > source->dev->name, addr, vid);
> > } else {
> > unsigned long now = jiffies;
> > + struct dst_entry *ref_md = rcu_access_pointer(fdb->md_dst);
> >
> > /* fastpath: update of existing entry */
> > - if (unlikely(source != fdb->dst)) {
> > + if (unlikely(source != fdb->dst ||
> > + dst_metadata_cmp(md_dst, ref_md))) {
> > fdb->dst = source;
> > + dst_release(ref_md);
> > + rcu_assign_pointer(fdb->md_dst,
> > + dst_clone(md_dst));
> > fdb_modified = true;
> > /* Take over HW learned entry */
> > if (unlikely(fdb->added_by_external_learn))
^ permalink raw reply
* Re: [PATCH net] PCI: fix the return value for the pci_find_pcie_root_port()
From: Thierry Reding @ 2017-08-17 10:51 UTC (permalink / raw)
To: Ding Tianhong
Cc: leedom, ashok.raj, bhelgaas, helgaas, werner, ganeshgr,
asit.k.mallick, patrick.j.cramer, Suravee.Suthikulpanit, Bob.Shaw,
l.stach, amira, gabriele.paoloni, David.Laight, jeffrey.t.kirsher,
catalin.marinas, will.deacon, mark.rutland, robin.murphy, davem,
alexander.duyck, eric.dumazet, linux-arm-kernel, netdev,
linux-pci, linux-kernel, linuxarm
In-Reply-To: <1502936730-7368-1-git-send-email-dingtianhong@huawei.com>
[-- Attachment #1: Type: text/plain, Size: 1589 bytes --]
On Thu, Aug 17, 2017 at 10:25:30AM +0800, Ding Tianhong wrote:
> The pci_find_pcie_root_port() would return NULL if the given
> dev is already a Root Port, it looks like unfriendly to the
> PCIe Root Port device, Thierry and Bjorn suggest to let this
> function return the given dev under this circumstances.
>
> Fixes: 0e405232871d6 ("PCI: fix oops when try to find Root Port for a PCI device")
> Suggested-by: Thierry Reding <thierry.reding@gmail.com>
> Suggested-by: Bjorn Helgaas <helgaas@kernel.org>
> Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
> Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
> ---
> drivers/pci/pci.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index 7e2022f..352bb53 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -514,7 +514,7 @@ struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res)
> */
> struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev)
> {
> - struct pci_dev *bridge, *highest_pcie_bridge = NULL;
> + struct pci_dev *bridge, *highest_pcie_bridge = dev;
>
> bridge = pci_upstream_bridge(dev);
> while (bridge && pci_is_pcie(bridge)) {
I think this should actually be this change on top of a revert of commit
0e405232871d6 ("PCI: fix oops when try to find Root Port for a PCI
device"). After the above change, the previous fix will have a redundant
check because highest_pcie_bridge will never be NULL.
Let me send out that version to clarify what I mean.
Thierry
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* [RFC, iproute2 PATCH v2] tc/mirred: Extend the mirred/redirect action to accept additional traffic class parameter
From: Amritha Nambiar @ 2017-08-17 10:39 UTC (permalink / raw)
To: stephen, netdev; +Cc: amritha.nambiar
The Mirred/redirect action is extended to accept a traffic
class on the device in addition to the device's ifindex.
Usage: mirred <DIRECTION> <ACTION> <dev DEVICENAME> <tclass TC_INDEX>
Example:
# tc qdisc add dev eth0 ingress
# tc filter add dev eth0 protocol ip parent ffff: prio 1 flower\
dst_ip 192.168.1.1/32 ip_proto udp dst_port 22\
skip_sw action mirred ingress redirect dev eth0 tclass 1
v2: Renamed the parameter 'tc' to 'tclass'. Replaced atoi with
strtoul and used NEXT_ARG() construct.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
---
include/linux/tc_act/tc_mirred.h | 3 +++
tc/m_mirred.c | 35 +++++++++++++++++++++++++++++++----
2 files changed, 34 insertions(+), 4 deletions(-)
diff --git a/include/linux/tc_act/tc_mirred.h b/include/linux/tc_act/tc_mirred.h
index 3d7a2b3..ea06a47 100644
--- a/include/linux/tc_act/tc_mirred.h
+++ b/include/linux/tc_act/tc_mirred.h
@@ -9,6 +9,8 @@
#define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */
#define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/
#define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */
+
+#define MIRRED_F_TCLASS 0x1
struct tc_mirred {
tc_gen;
@@ -21,6 +23,7 @@ enum {
TCA_MIRRED_TM,
TCA_MIRRED_PARMS,
TCA_MIRRED_PAD,
+ TCA_MIRRED_TCLASS,
__TCA_MIRRED_MAX
};
#define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1)
diff --git a/tc/m_mirred.c b/tc/m_mirred.c
index 2384bda..1cb477a 100644
--- a/tc/m_mirred.c
+++ b/tc/m_mirred.c
@@ -29,12 +29,13 @@
static void
explain(void)
{
- fprintf(stderr, "Usage: mirred <DIRECTION> <ACTION> [index INDEX] <dev DEVICENAME>\n");
+ fprintf(stderr, "Usage: mirred <DIRECTION> <ACTION> [index INDEX] <dev DEVICENAME> [tclass TCINDEX]\n");
fprintf(stderr, "where:\n");
fprintf(stderr, "\tDIRECTION := <ingress | egress>\n");
fprintf(stderr, "\tACTION := <mirror | redirect>\n");
fprintf(stderr, "\tINDEX is the specific policy instance id\n");
fprintf(stderr, "\tDEVICENAME is the devicename\n");
+ fprintf(stderr, "\tTCINDEX is the traffic class index\n");
}
@@ -72,6 +73,9 @@ parse_direction(struct action_util *a, int *argc_p, char ***argv_p,
struct tc_mirred p = {};
struct rtattr *tail;
char d[16] = {};
+ __u32 flags = 0;
+ char *end;
+ __u8 tc;
while (argc > 0) {
@@ -139,9 +143,23 @@ parse_direction(struct action_util *a, int *argc_p, char ***argv_p,
duparg("dev", *argv);
strncpy(d, *argv, sizeof(d)-1);
- argc--;
- argv++;
-
+ NEXT_ARG_FWD();
+
+ if (argc > 0 && matches(*argv, "tclass") == 0) {
+ NEXT_ARG();
+ tc = strtoul(*argv, &end, 0);
+ if (*end) {
+ fprintf(stderr, "Illegal TC index\n");
+ return -1;
+ }
+ if (tc >= TC_QOPT_MAX_QUEUE) {
+ fprintf(stderr, "TC index exceeds max range\n");
+ return -1;
+ }
+ flags |= MIRRED_F_TCLASS;
+ ok++;
+ NEXT_ARG_FWD();
+ }
break;
}
@@ -193,6 +211,9 @@ parse_direction(struct action_util *a, int *argc_p, char ***argv_p,
tail = NLMSG_TAIL(n);
addattr_l(n, MAX_MSG, tca_id, NULL, 0);
addattr_l(n, MAX_MSG, TCA_MIRRED_PARMS, &p, sizeof(p));
+ if (flags & MIRRED_F_TCLASS)
+ addattr_l(n, MAX_MSG, TCA_MIRRED_TCLASS,
+ &tc, sizeof(tc));
tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
*argc_p = argc;
@@ -248,6 +269,7 @@ print_mirred(struct action_util *au, FILE * f, struct rtattr *arg)
struct tc_mirred *p;
struct rtattr *tb[TCA_MIRRED_MAX + 1];
const char *dev;
+ __u8 *tc;
if (arg == NULL)
return -1;
@@ -273,6 +295,11 @@ print_mirred(struct action_util *au, FILE * f, struct rtattr *arg)
fprintf(f, "mirred (%s to device %s)", mirred_n2a(p->eaction), dev);
print_action_control(f, " ", p->action, "");
+ if (tb[TCA_MIRRED_TCLASS]) {
+ tc = RTA_DATA(tb[TCA_MIRRED_TCLASS]);
+ fprintf(f, " tclass %u", *tc);
+ }
+
fprintf(f, "\n ");
fprintf(f, "\tindex %u ref %d bind %d", p->index, p->refcnt,
p->bindcnt);
^ permalink raw reply related
* Re: [PATCH net] net: sched: fix NULL pointer dereference when action calls some targets
From: Pablo Neira Ayuso @ 2017-08-17 10:33 UTC (permalink / raw)
To: Xin Long
Cc: Cong Wang, network dev, David Miller, netfilter-devel,
Jamal Hadi Salim
In-Reply-To: <20170817100220.GC6928@salvia>
On Thu, Aug 17, 2017 at 12:02:20PM +0200, Pablo Neira Ayuso wrote:
> On Wed, Aug 16, 2017 at 08:39:44PM +1200, Xin Long wrote:
> > On Wed, Aug 9, 2017 at 7:33 AM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
> > > On Mon, Aug 7, 2017 at 7:33 PM, Xin Long <lucien.xin@gmail.com> wrote:
> > >> On Tue, Aug 8, 2017 at 9:15 AM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
> > >>> This looks like a completely API burden?
> > >> netfilter xt targets are not really compatible with netsched action.
> > >> I've got to say, the patch is just a way to make checkentry return
> > >> false and avoid panic. like [1] said
> > >
> > > I don't doubt you fix a crash, I am thinking if we can
> > > "fix" the API instead of fixing the caller.
> > Hi, Cong,
> >
> > For now, I don't think it's possible to change APIs or some of their targets
> > for the panic caused by action xt calling.
> >
> > The common way should be fixed in net_sched side.
> >
> > Given that the issue is very easy to triggered,
> > let's wait for netfilter's replies for another few days,
> > otherwise I will repost the fix, agree ?
>
> Please, post the workaround so the kernel doesn't crash anymore.
>
> This is going to be very hard to fix, it's broken since the very
> beginning...
Wait a second, you could rename par->nft_compat to par->no_entry. From
net/sched/ you can set this to 1, so the entry checks are ignored.
I'm refering to patch 55917a21d0cc0
^ permalink raw reply
* Re: [PATCH] bpf: Update sysctl documentation to list all supported architectures
From: Michael Ellerman @ 2017-08-17 10:31 UTC (permalink / raw)
To: Daniel Borkmann, ast; +Cc: davem, netdev, linux-kernel
In-Reply-To: <5994489E.1020806@iogearbox.net>
Daniel Borkmann <daniel@iogearbox.net> writes:
> On 08/16/2017 01:10 PM, Michael Ellerman wrote:
>> Daniel Borkmann <daniel@iogearbox.net> writes:
>>> On 08/16/2017 07:15 AM, Michael Ellerman wrote:
>>>> diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
>>>> index 14db18c970b1..f68356024d09 100644
>>>> --- a/Documentation/sysctl/net.txt
>>>> +++ b/Documentation/sysctl/net.txt
>>>> @@ -36,8 +36,9 @@ bpf_jit_enable
>>>> --------------
>>>>
>>>> This enables Berkeley Packet Filter Just in Time compiler.
>>>> -Currently supported on x86_64 architecture, bpf_jit provides a framework
>>>> -to speed packet filtering, the one used by tcpdump/libpcap for example.
>>>> +Currently supported on arm, arm64, mips, powerpc, s390, sparc and x86_64
>>>> +architectures, bpf_jit provides a framework to speed packet filtering, the one
>>>> +used by tcpdump/libpcap for example.
>>>
>>> Good point, could we actually make that as a bullet list and
>>> differentiate between cBPF and eBPF JITs, so that a user doesn't
>>> need to run git grep HAVE_{E,C}BPF_JIT to figure it out what the
>>> switch enables on the arch used? That would be great.
>>
>> We could.
>>
>> Does a user of the sysctl want/need to know the difference though? Or do
>> they just want to turn on "the JIT"?
>
> They would just turn it on, but I think it would be nice to inform
> them which archs support eBPF (which is a superset of cBPF in term
> of what can be jited), so in case they have some native eBPF programs
> they would see whether these can also be jited.
OK. v2 just sent.
The text could probably use some more tweaking to mention the other
things BPF is used for these days, but I didn't really feel qualified to
do that.
cheers
^ permalink raw reply
* [PATCH v2] bpf: Update sysctl documentation to list all supported architectures
From: Michael Ellerman @ 2017-08-17 10:30 UTC (permalink / raw)
To: ast, daniel; +Cc: davem, netdev, linux-kernel
The sysctl documentation states that the JIT is only available on
x86_64, which is no longer correct.
Update the list, and break it out to indicate which architectures
support the cBPF JIT (via HAVE_CBPF_JIT) or the eBPF JIT
(HAVE_EBPF_JIT).
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
Documentation/sysctl/net.txt | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
v2: Split the list based on cBPF vs eBPF.
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 14db18c970b1..b9c3c6078010 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -36,8 +36,23 @@ bpf_jit_enable
--------------
This enables Berkeley Packet Filter Just in Time compiler.
-Currently supported on x86_64 architecture, bpf_jit provides a framework
-to speed packet filtering, the one used by tcpdump/libpcap for example.
+
+There are two flavors of JIT, the new eBPF JIT supported on:
+ - x86_64
+ - arm64
+ - ppc64
+ - sparc64
+ - mips64
+
+And the older cBPF JIT supported on:
+ - arm
+ - mips
+ - ppc
+ - sparc
+
+The BPF JIT provides a framework to speed packet filtering, the one used by
+tcpdump/libpcap for example.
+
Values :
0 - disable the JIT (default value)
1 - enable the JIT
--
2.7.4
^ permalink raw reply related
* [RFC PATCH v2 6/6] [net-next]net: i40e: Enable cloud filters in i40e via tc flower classifier
From: Amritha Nambiar @ 2017-08-17 10:27 UTC (permalink / raw)
To: intel-wired-lan, jeffrey.t.kirsher
Cc: alexander.h.duyck, kiran.patil, amritha.nambiar, netdev,
mitch.a.williams, alexander.duyck, neerav.parikh,
sridhar.samudrala, carolyn.wyborny
In-Reply-To: <150296538797.16910.13738130623106637990.stgit@anamdev.jf.intel.com>
This patch enables tc-flower based hardware offloads. tc flower
filter provided by the kernel is configured as driver specific
cloud filter. The patch implements functions and admin queue
commands needed to support cloud filters in the driver and
adds cloud filters to configure these tc-flower filters.
The only action supported is to redirect packets to a traffic class
on the same device.
# tc qdisc add dev eth0 ingress
# ethtool -K eth0 hw-tc-offload on
# tc filter add dev eth0 protocol ip parent ffff:\
prio 1 flower dst_mac 3c:fd:fe:a0:d6:70 skip_sw\
action mirred ingress redirect dev eth0 tclass 0
# tc filter add dev eth0 protocol ip parent ffff:\
prio 2 flower dst_ip 192.168.3.5/32\
ip_proto udp dst_port 25 skip_sw\
action mirred ingress redirect dev eth0 tclass 1
# tc filter add dev eth0 protocol ipv6 parent ffff:\
prio 3 flower dst_ip fe8::200:1\
ip_proto udp dst_port 66 skip_sw\
action mirred ingress redirect dev eth0 tclass 2
Delete tc flower filter:
Example:
# tc filter del dev eth0 parent ffff: prio 3 handle 0x1 flower
# tc filter del dev eth0 parent ffff:
Flow Director Sideband is disabled while configuring cloud filters
via tc-flower and until any cloud filter exists.
Unsupported matches when cloud filters are added using enhanced
big buffer cloud filter mode of underlying switch include:
1. source port and source IP
2. Combined MAC address and IP fields.
3. Not specifying L4 port
These filter matches can however be used to redirect traffic to
the main VSI (tc 0) which does not require the enhanced big buffer
cloud filter support.
v2:
1. Moved I40E_SWITCH_MODE_MASK definition to i40e_type.h
2. Moved dev_info for add/deleting cloud filters in else condition
3. Fixed some format specifier in dev_err logs
4. Refactored i40e_get_capabilities to take an additional
list_type parameter and use it to query device and function
level capabilities.
5. Fixed parsing tc redirect action to check for the is_tcf_mirred_tc()
to verify if redirect to a traffic class is supported.
6. Added comments for Geneve fix in cloud filter big buffer AQ
function definitions.
7. Cleaned up setup_tc interface to rebase and work with Jiri's
updates, separate function to process tc cls flower offloads.
8. Changes to make Flow Director Sideband and Cloud filters mutually
exclusive.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e.h | 46 +
drivers/net/ethernet/intel/i40e/i40e_common.c | 190 ++++
drivers/net/ethernet/intel/i40e/i40e_main.c | 975 +++++++++++++++++++++-
drivers/net/ethernet/intel/i40e/i40e_prototype.h | 17
drivers/net/ethernet/intel/i40e/i40e_type.h | 1
5 files changed, 1202 insertions(+), 27 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ac57ab0..dbf4b9d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -55,6 +55,8 @@
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_mirred.h>
#include "i40e_type.h"
#include "i40e_prototype.h"
#include "i40e_client.h"
@@ -252,9 +254,49 @@ struct i40e_fdir_filter {
u32 fd_id;
};
+#define I40E_CLOUD_FIELD_OMAC 0x01
+#define I40E_CLOUD_FIELD_IMAC 0x02
+#define I40E_CLOUD_FIELD_IVLAN 0x04
+#define I40E_CLOUD_FIELD_TEN_ID 0x08
+#define I40E_CLOUD_FIELD_IIP 0x10
+
+#define I40E_CLOUD_FILTER_FLAGS_OMAC I40E_CLOUD_FIELD_OMAC
+#define I40E_CLOUD_FILTER_FLAGS_IMAC I40E_CLOUD_FIELD_IMAC
+#define I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN (I40E_CLOUD_FIELD_IMAC | \
+ I40E_CLOUD_FIELD_IVLAN)
+#define I40E_CLOUD_FILTER_FLAGS_IMAC_TEN_ID (I40E_CLOUD_FIELD_IMAC | \
+ I40E_CLOUD_FIELD_TEN_ID)
+#define I40E_CLOUD_FILTER_FLAGS_OMAC_TEN_ID_IMAC (I40E_CLOUD_FIELD_OMAC | \
+ I40E_CLOUD_FIELD_IMAC | \
+ I40E_CLOUD_FIELD_TEN_ID)
+#define I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN_TEN_ID (I40E_CLOUD_FIELD_IMAC | \
+ I40E_CLOUD_FIELD_IVLAN | \
+ I40E_CLOUD_FIELD_TEN_ID)
+#define I40E_CLOUD_FILTER_FLAGS_IIP I40E_CLOUD_FIELD_IIP
+
struct i40e_cloud_filter {
struct hlist_node cloud_node;
unsigned long cookie;
+ /* cloud filter input set follows */
+ u8 dst_mac[ETH_ALEN];
+ u8 src_mac[ETH_ALEN];
+ __be16 vlan_id;
+ __be32 dst_ip[4];
+ __be32 src_ip[4];
+ u8 dst_ipv6[16];
+ u8 src_ipv6[16];
+ __be16 dst_port;
+ __be16 src_port;
+ bool is_ipv6; /* IPv6 based filtering */
+ u8 ip_proto; /* IPPROTO value */
+ /* L4 port type: src or destination port */
+#define I40E_CLOUD_FILTER_PORT_SRC 0x01
+#define I40E_CLOUD_FILTER_PORT_DEST 0x02
+ u8 port_type;
+ u32 tenant_id;
+ u8 flags;
+#define I40E_CLOUD_TNL_TYPE_NONE 0xff
+ u8 tunnel_type;
u16 seid; /* filter control */
};
@@ -490,6 +532,8 @@ struct i40e_pf {
#define I40E_FLAG_CLIENT_RESET BIT_ULL(26)
#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT_ULL(27)
#define I40E_FLAG_TC_MQPRIO BIT_ULL(28)
+#define I40E_FLAG_FD_SB_INACTIVE BIT_ULL(29)
+#define I40E_FLAG_FD_SB_TO_CLOUD_FILTER BIT_ULL(30)
struct i40e_client_instance *cinst;
bool stat_offsets_loaded;
@@ -572,6 +616,8 @@ struct i40e_pf {
u16 phy_led_val;
u16 override_q_count;
+ u16 last_sw_conf_flags;
+ u16 last_sw_conf_valid_flags;
};
/**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index d0e8138..caeda6e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -5269,5 +5269,195 @@ i40e_add_pinfo_to_list(struct i40e_hw *hw,
status = i40e_aq_write_ppp(hw, (void *)sec, sec->data_end,
track_id, &offset, &info, NULL);
+
+ return status;
+}
+
+/**
+ * i40e_aq_add_cloud_filters
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to add cloud filters from
+ * @filters: Buffer which contains the filters to be added
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Set the cloud filters for a given VSI. The contents of the
+ * i40e_aqc_add_remove_cloud_filters_element_data are filled
+ * in by the caller of the function.
+ *
+ **/
+enum i40e_status_code i40e_aq_add_cloud_filters(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_add_remove_cloud_filters_element_data *filters,
+ u8 filter_count)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_add_remove_cloud_filters *cmd =
+ (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+ enum i40e_status_code status;
+ u16 buff_len;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_add_cloud_filters);
+
+ buff_len = filter_count * sizeof(*filters);
+ desc.datalen = cpu_to_le16(buff_len);
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ cmd->num_filters = filter_count;
+ cmd->seid = cpu_to_le16(seid);
+
+ status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
+ return status;
+}
+
+/**
+ * i40e_aq_add_cloud_filters_big_buffer
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to add cloud filters from
+ * @filters: Buffer which contains the filters in big buffer to be added
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Set the cloud filters for a given VSI. The contents of the
+ * i40e_aqc_add_remove_cloud_filters_element_big_data are filled
+ * in by the caller of the function.
+ *
+ **/
+i40e_status i40e_aq_add_cloud_filters_big_buffer(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_add_remove_cloud_filters_element_big_data *filters,
+ u8 filter_count)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_add_remove_cloud_filters *cmd =
+ (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+ i40e_status status;
+ u16 buff_len;
+ int i;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_add_cloud_filters);
+
+ buff_len = filter_count * sizeof(*filters);
+ desc.datalen = cpu_to_le16(buff_len);
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ cmd->num_filters = filter_count;
+ cmd->seid = cpu_to_le16(seid);
+ cmd->big_buffer_flag = I40E_AQC_ADD_REM_CLOUD_CMD_BIG_BUFFER;
+
+ for (i = 0; i < filter_count; i++) {
+ u16 tnl_type;
+ u32 ti;
+
+ tnl_type = (le16_to_cpu(filters[i].element.flags) &
+ I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >>
+ I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT;
+
+ /* For Geneve, the VNI should be placed in offset shifted by a
+ * byte than the offset for the Tenant ID for rest of the
+ * tunnels.
+ */
+ if (tnl_type == I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE) {
+ ti = le32_to_cpu(filters[i].element.tenant_id);
+ filters[i].element.tenant_id = cpu_to_le32(ti << 8);
+ }
+ }
+
+ status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
+ return status;
+}
+
+/**
+ * i40e_aq_remove_cloud_filters
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to remove cloud filters from
+ * @filters: Buffer which contains the filters to be removed
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Remove the cloud filters for a given VSI. The contents of the
+ * i40e_aqc_add_remove_cloud_filters_element_data are filled
+ * in by the caller of the function.
+ *
+ **/
+enum i40e_status_code i40e_aq_remove_cloud_filters(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_add_remove_cloud_filters_element_data *filters,
+ u8 filter_count)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_add_remove_cloud_filters *cmd =
+ (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+ enum i40e_status_code status;
+ u16 buff_len;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_remove_cloud_filters);
+
+ buff_len = filter_count * sizeof(*filters);
+ desc.datalen = cpu_to_le16(buff_len);
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ cmd->num_filters = filter_count;
+ cmd->seid = cpu_to_le16(seid);
+
+ status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
+ return status;
+}
+
+/**
+ * i40e_aq_remove_cloud_filters_big_buffer
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to remove cloud filters from
+ * @filters: Buffer which contains the filters in big buffer to be removed
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Remove the cloud filters for a given VSI. The contents of the
+ * i40e_aqc_add_remove_cloud_filters_element_big_data are filled
+ * in by the caller of the function.
+ *
+ **/
+i40e_status i40e_aq_remove_cloud_filters_big_buffer(
+ struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_add_remove_cloud_filters_element_big_data *filters,
+ u8 filter_count)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_add_remove_cloud_filters *cmd =
+ (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+ i40e_status status;
+ u16 buff_len;
+ int i;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_remove_cloud_filters);
+
+ buff_len = filter_count * sizeof(*filters);
+ desc.datalen = cpu_to_le16(buff_len);
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ cmd->num_filters = filter_count;
+ cmd->seid = cpu_to_le16(seid);
+ cmd->big_buffer_flag = I40E_AQC_ADD_REM_CLOUD_CMD_BIG_BUFFER;
+
+ for (i = 0; i < filter_count; i++) {
+ u16 tnl_type;
+ u32 ti;
+
+ tnl_type = (le16_to_cpu(filters[i].element.flags) &
+ I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >>
+ I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT;
+
+ /* For Geneve, the VNI should be placed in offset shifted by a
+ * byte than the offset for the Tenant ID for rest of the
+ * tunnels.
+ */
+ if (tnl_type == I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE) {
+ ti = le32_to_cpu(filters[i].element.tenant_id);
+ filters[i].element.tenant_id = cpu_to_le32(ti << 8);
+ }
+ }
+
+ status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
return status;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 15f0975..0039e4e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -69,6 +69,15 @@ static int i40e_reset(struct i40e_pf *pf);
static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
static void i40e_fdir_sb_setup(struct i40e_pf *pf);
static int i40e_veb_get_bw_info(struct i40e_veb *veb);
+static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
+ struct i40e_cloud_filter *filter,
+ bool add);
+static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
+ struct i40e_cloud_filter *filter,
+ bool add);
+static int i40e_get_capabilities(struct i40e_pf *pf,
+ enum i40e_admin_queue_opc list_type);
+
/* i40e_pci_tbl - PCI Device ID Table
*
@@ -5482,7 +5491,11 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
**/
static void i40e_remove_queue_channels(struct i40e_vsi *vsi)
{
+ enum i40e_admin_queue_err last_aq_status;
+ struct i40e_cloud_filter *cfilter;
struct i40e_channel *ch, *ch_tmp;
+ struct i40e_pf *pf = vsi->back;
+ struct hlist_node *node;
int ret, i;
/* Reset rss size that was stored when reconfiguring rss for
@@ -5523,6 +5536,29 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi)
"Failed to reset tx rate for ch->seid %u\n",
ch->seid);
+ /* delete cloud filters associated with this channel */
+ hlist_for_each_entry_safe(cfilter, node,
+ &pf->cloud_filter_list, cloud_node) {
+ if (cfilter->seid != ch->seid)
+ continue;
+
+ hash_del(&cfilter->cloud_node);
+ if (cfilter->dst_port)
+ ret = i40e_add_del_cloud_filter_big_buf(vsi,
+ cfilter,
+ false);
+ else
+ ret = i40e_add_del_cloud_filter(vsi, cfilter,
+ false);
+ last_aq_status = pf->hw.aq.asq_last_status;
+ if (ret)
+ dev_info(&pf->pdev->dev,
+ "Failed to delete cloud filter, err %s aq_err %s\n",
+ i40e_stat_str(&pf->hw, ret),
+ i40e_aq_str(&pf->hw, last_aq_status));
+ kfree(cfilter);
+ }
+
/* delete VSI from FW */
ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid,
NULL);
@@ -6004,6 +6040,74 @@ static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi,
}
/**
+ * i40e_validate_and_set_switch_mode - sets up switch mode correctly
+ * @vsi: ptr to VSI which has PF backing
+ * @l4type: true for TCP ond false for UDP
+ * @port_type: true if port is destination and false if port is source
+ *
+ * Sets up switch mode correctly if it needs to be changed and perform
+ * what are allowed modes.
+ **/
+static int i40e_validate_and_set_switch_mode(struct i40e_vsi *vsi, bool l4type,
+ bool port_type)
+{
+ u8 mode;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int ret;
+
+ ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_dev_capabilities);
+ if (ret)
+ return -EINVAL;
+
+ if (hw->dev_caps.switch_mode) {
+ /* if switch mode is set, support mode2 (non-tunneled for
+ * cloud filter) for now
+ */
+ u32 switch_mode = hw->dev_caps.switch_mode &
+ I40E_SWITCH_MODE_MASK;
+ if (switch_mode >= I40E_NVM_IMAGE_TYPE_MODE1) {
+ if (switch_mode == I40E_NVM_IMAGE_TYPE_MODE2)
+ return 0;
+ dev_err(&pf->pdev->dev,
+ "Invalid switch_mode (%d), only non-tunneled mode for cloud filter is supported\n",
+ hw->dev_caps.switch_mode);
+ return -EINVAL;
+ }
+ }
+
+ /* port_type: true for destination port and false for source port
+ * For now, supports only destination port type
+ */
+ if (!port_type) {
+ dev_err(&pf->pdev->dev, "src port type not supported\n");
+ return -EINVAL;
+ }
+
+ /* Set Bit 7 to be valid */
+ mode = I40E_AQ_SET_SWITCH_BIT7_VALID;
+
+ /* Set L4type to both TCP and UDP support */
+ mode |= I40E_AQ_SET_SWITCH_L4_TYPE_BOTH;
+
+ /* Set cloud filter mode */
+ mode |= I40E_AQ_SET_SWITCH_MODE_NON_TUNNEL;
+
+ /* Prep mode field for set_switch_config */
+ ret = i40e_aq_set_switch_config(hw, pf->last_sw_conf_flags,
+ pf->last_sw_conf_valid_flags,
+ mode, NULL);
+ if (ret && hw->aq.asq_last_status != I40E_AQ_RC_ESRCH)
+ dev_err(&pf->pdev->dev,
+ "couldn't set switch config bits, err %s aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw,
+ hw->aq.asq_last_status));
+
+ return ret;
+}
+
+/**
* i40e_create_queue_channel - function to create channel
* @vsi: VSI to be configured
* @ch: ptr to channel (it contains channel specific params)
@@ -6777,6 +6881,727 @@ static int i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
return ret;
}
+/**
+ * i40e_set_cld_element - sets cloud filter element data
+ * @filter: cloud filter rule
+ * @cld: ptr to cloud filter element data
+ *
+ * This is helper function to copy data into cloud filter element
+ **/
+static inline void
+i40e_set_cld_element(struct i40e_cloud_filter *filter,
+ struct i40e_aqc_add_remove_cloud_filters_element_data *cld)
+{
+ u8 *dest_ipaddr;
+ u32 ipaddr;
+ int i;
+
+ memset(cld, 0, sizeof(*cld));
+
+ ether_addr_copy(cld->outer_mac, filter->dst_mac);
+ ether_addr_copy(cld->inner_mac, filter->src_mac);
+
+ if (filter->is_ipv6) {
+ dest_ipaddr = (u8 *)&cld->ipaddr.v6.data;
+ for (i = ARRAY_SIZE(filter->dst_ipv6) - 1; i >= 0; i--) {
+ memcpy(dest_ipaddr, &filter->dst_ipv6[i], 1);
+ dest_ipaddr++;
+ }
+ } else {
+ ipaddr = be32_to_cpu(filter->dst_ip[0]);
+ memcpy(&cld->ipaddr.v4.data, &ipaddr, 4);
+ }
+
+ cld->inner_vlan = cpu_to_le16(ntohs(filter->vlan_id));
+ cld->tenant_id = cpu_to_le32(filter->tenant_id);
+}
+
+/**
+ * i40e_add_del_cloud_filter - Add/del cloud filter
+ * @vsi: pointer to VSI
+ * @filter: cloud filter rule
+ * @add: if true, add, if false, delete
+ *
+ * Add or delete a cloud filter for a specific flow spec.
+ * Returns 0 if the filter were successfully added.
+ **/
+static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
+ struct i40e_cloud_filter *filter, bool add)
+{
+ struct i40e_aqc_add_remove_cloud_filters_element_data cld_filter;
+ struct i40e_pf *pf = vsi->back;
+ int ret;
+ static const u16 flag_table[128] = {
+ [I40E_CLOUD_FILTER_FLAGS_OMAC] =
+ I40E_AQC_ADD_CLOUD_FILTER_OMAC,
+ [I40E_CLOUD_FILTER_FLAGS_IMAC] =
+ I40E_AQC_ADD_CLOUD_FILTER_IMAC,
+ [I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN] =
+ I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN,
+ [I40E_CLOUD_FILTER_FLAGS_IMAC_TEN_ID] =
+ I40E_AQC_ADD_CLOUD_FILTER_IMAC_TEN_ID,
+ [I40E_CLOUD_FILTER_FLAGS_OMAC_TEN_ID_IMAC] =
+ I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC,
+ [I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN_TEN_ID] =
+ I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID,
+ [I40E_CLOUD_FILTER_FLAGS_IIP] =
+ I40E_AQC_ADD_CLOUD_FILTER_IIP,
+ };
+
+ if (filter->flags >= ARRAY_SIZE(flag_table))
+ return I40E_ERR_CONFIG;
+
+ /* copy element needed to add cloud filter from filter */
+ i40e_set_cld_element(filter, &cld_filter);
+
+ if (filter->tunnel_type != I40E_CLOUD_TNL_TYPE_NONE)
+ cld_filter.flags = cpu_to_le16(filter->tunnel_type <<
+ I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT);
+
+ if (filter->is_ipv6)
+ cld_filter.flags |= cpu_to_le16(flag_table[filter->flags] |
+ I40E_AQC_ADD_CLOUD_FLAGS_IPV6);
+ else
+ cld_filter.flags |= cpu_to_le16(flag_table[filter->flags] |
+ I40E_AQC_ADD_CLOUD_FLAGS_IPV4);
+
+ if (add)
+ ret = i40e_aq_add_cloud_filters(&pf->hw, filter->seid,
+ &cld_filter, 1);
+ else
+ ret = i40e_aq_remove_cloud_filters(&pf->hw, filter->seid,
+ &cld_filter, 1);
+ if (ret)
+ dev_dbg(&pf->pdev->dev,
+ "Failed to %s cloud filter using l4 port %u, err %d aq_err %d\n",
+ add ? "add" : "delete", filter->dst_port, ret,
+ pf->hw.aq.asq_last_status);
+ else
+ dev_info(&pf->pdev->dev,
+ "%s cloud filter for VSI: %d\n",
+ add ? "Added" : "Deleted", filter->seid);
+ return ret;
+}
+
+/**
+ * i40e_add_del_cloud_filter_big_buf - Add/del cloud filter using big_buf
+ * @vsi: pointer to VSI
+ * @filter: cloud filter rule
+ * @add: if true, add, if false, delete
+ *
+ * Add or delete a cloud filter for a specific flow spec using big buffer.
+ * Returns 0 if the filter were successfully added.
+ **/
+static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
+ struct i40e_cloud_filter *filter,
+ bool add)
+{
+ struct i40e_aqc_add_remove_cloud_filters_element_big_data cld_filter;
+ struct i40e_pf *pf = vsi->back;
+ int ret;
+
+ /* Both (Outer/Inner) valid mac_addr are not supported */
+ if (is_valid_ether_addr(filter->dst_mac) &&
+ is_valid_ether_addr(filter->src_mac))
+ return -EINVAL;
+
+ /* Make sure port is specified, otherwise bail out, for channel
+ * specific cloud filter needs 'L4 port' to be non-zero
+ */
+ if (!filter->dst_port)
+ return -EINVAL;
+
+ /* adding filter using src_port/src_ip is not supported at this stage */
+ if (filter->src_port || filter->src_ip[0])
+ return -EINVAL;
+
+ /* copy element needed to add cloud filter from filter */
+ i40e_set_cld_element(filter, &cld_filter.element);
+
+ if (is_valid_ether_addr(filter->dst_mac) ||
+ is_valid_ether_addr(filter->src_mac) ||
+ is_multicast_ether_addr(filter->dst_mac) ||
+ is_multicast_ether_addr(filter->src_mac)) {
+ /* MAC + IP : unsupported mode */
+ if (filter->dst_ip[0])
+ return -EINVAL;
+
+ /* since we validated that L4 port must be valid before
+ * we get here, start with respective "flags" value
+ * and update if vlan is present or not
+ */
+ cld_filter.element.flags =
+ cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT);
+
+ if (filter->vlan_id) {
+ cld_filter.element.flags =
+ cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT);
+ }
+
+ } else if (filter->dst_ip[0] || filter->is_ipv6) {
+ cld_filter.element.flags =
+ cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_IP_PORT);
+ if (filter->is_ipv6)
+ cld_filter.element.flags |=
+ cpu_to_le16(I40E_AQC_ADD_CLOUD_FLAGS_IPV6);
+ else
+ cld_filter.element.flags |=
+ cpu_to_le16(I40E_AQC_ADD_CLOUD_FLAGS_IPV4);
+ } else {
+ dev_err(&pf->pdev->dev,
+ "either mac or ip has to be valid for cloud filter\n");
+ return -EINVAL;
+ }
+
+ /* Now copy L4 port in Byte 6..7 in general fields */
+ cld_filter.general_fields[I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0] =
+ be16_to_cpu(filter->dst_port);
+
+ if (add) {
+ bool proto_type, port_type;
+
+ proto_type = (filter->ip_proto == IPPROTO_TCP) ? true : false;
+ port_type = (filter->port_type & I40E_CLOUD_FILTER_PORT_DEST) ?
+ true : false;
+
+ /* For now, src port based cloud filter for channel is not
+ * supported
+ */
+ if (!port_type) {
+ dev_err(&pf->pdev->dev,
+ "unsupported port type (src port)\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Validate current device switch mode, change if necessary */
+ ret = i40e_validate_and_set_switch_mode(vsi, proto_type,
+ port_type);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "failed to set switch mode, ret %d\n",
+ ret);
+ return ret;
+ }
+
+ ret = i40e_aq_add_cloud_filters_big_buffer(&pf->hw,
+ filter->seid,
+ &cld_filter, 1);
+ } else {
+ ret = i40e_aq_remove_cloud_filters_big_buffer(&pf->hw,
+ filter->seid,
+ &cld_filter, 1);
+ }
+
+ if (ret)
+ dev_dbg(&pf->pdev->dev,
+ "Failed to %s cloud filter(big buffer) err %d aq_err %d\n",
+ add ? "add" : "delete", ret, pf->hw.aq.asq_last_status);
+ else
+ dev_info(&pf->pdev->dev,
+ "%s cloud filter for VSI: %d, L4 port: %d\n",
+ add ? "add" : "delete", filter->seid,
+ ntohs(filter->dst_port));
+ return ret;
+}
+
+/**
+ * i40e_parse_cls_flower - Parse tc flower filters provided by kernel
+ * @vsi: Pointer to VSI
+ * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @filter: Pointer to cloud filter structure
+ *
+ **/
+static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
+ struct tc_cls_flower_offload *f,
+ struct i40e_cloud_filter *filter)
+{
+ struct i40e_pf *pf = vsi->back;
+ u16 addr_type = 0;
+ u8 field_flags = 0;
+
+ if (f->dissector->used_keys &
+ ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+ BIT(FLOW_DISSECTOR_KEY_BASIC) |
+ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_VLAN) |
+ BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL))) {
+ dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n",
+ f->dissector->used_keys);
+ return -EOPNOTSUPP;
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_dissector_key_keyid *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ f->key);
+
+ struct flow_dissector_key_keyid *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ f->mask);
+
+ if (mask->keyid != 0)
+ field_flags |= I40E_CLOUD_FIELD_TEN_ID;
+
+ filter->tenant_id = be32_to_cpu(key->keyid);
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->key);
+
+ filter->ip_proto = key->ip_proto;
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ struct flow_dissector_key_eth_addrs *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS,
+ f->key);
+
+ struct flow_dissector_key_eth_addrs *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS,
+ f->mask);
+
+ /* use is_broadcast and is_zero to check for all 0xf or 0 */
+ if (!is_zero_ether_addr(mask->dst)) {
+ if (is_broadcast_ether_addr(mask->dst)) {
+ field_flags |= I40E_CLOUD_FIELD_OMAC;
+ } else {
+ dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n",
+ mask->dst);
+ return I40E_ERR_CONFIG;
+ }
+ }
+
+ if (!is_zero_ether_addr(mask->src)) {
+ if (is_broadcast_ether_addr(mask->src)) {
+ field_flags |= I40E_CLOUD_FIELD_IMAC;
+ } else {
+ dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n",
+ mask->src);
+ return I40E_ERR_CONFIG;
+ }
+ }
+ ether_addr_copy(filter->dst_mac, key->dst);
+ ether_addr_copy(filter->src_mac, key->src);
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_dissector_key_vlan *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->key);
+ struct flow_dissector_key_vlan *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->mask);
+
+ if (mask->vlan_id) {
+ if (mask->vlan_id == VLAN_VID_MASK) {
+ field_flags |= I40E_CLOUD_FIELD_IVLAN;
+
+ } else {
+ dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n",
+ mask->vlan_id);
+ return I40E_ERR_CONFIG;
+ }
+ }
+
+ filter->vlan_id = cpu_to_be16(key->vlan_id);
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+ struct flow_dissector_key_control *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_CONTROL,
+ f->key);
+
+ addr_type = key->addr_type;
+ }
+
+ if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+ struct flow_dissector_key_ipv4_addrs *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+ f->key);
+ struct flow_dissector_key_ipv4_addrs *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+ f->mask);
+
+ if (mask->dst) {
+ if (mask->dst == cpu_to_be32(0xffffffff)) {
+ field_flags |= I40E_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&pf->pdev->dev, "Bad ip dst mask 0x%08x\n",
+ be32_to_cpu(mask->dst));
+ return I40E_ERR_CONFIG;
+ }
+ }
+
+ if (mask->src) {
+ if (mask->src == cpu_to_be32(0xffffffff)) {
+ field_flags |= I40E_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&pf->pdev->dev, "Bad ip src mask 0x%08x\n",
+ be32_to_cpu(mask->dst));
+ return I40E_ERR_CONFIG;
+ }
+ }
+
+ if (field_flags & I40E_CLOUD_FIELD_TEN_ID) {
+ dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n");
+ return I40E_ERR_CONFIG;
+ }
+ filter->dst_ip[0] = key->dst;
+ filter->src_ip[0] = key->src;
+ }
+
+ if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+ struct flow_dissector_key_ipv6_addrs *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ f->key);
+ struct flow_dissector_key_ipv6_addrs *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ f->mask);
+
+ /* validate mask, make sure it is not IPV6_ADDR_ANY */
+ if (ipv6_addr_any(&mask->dst)) {
+ dev_err(&pf->pdev->dev, "Bad ipv6 dst mask 0x%02x\n",
+ IPV6_ADDR_ANY);
+ return I40E_ERR_CONFIG;
+ }
+
+ /* validate src and dest IPV6 address, make sure they are not
+ * ANY (0:0:0:0:0:0:0:0) or LOOPBACK (0:0:0:0:0:0:0:1), which
+ * can be represented as ::1
+ */
+ if (ipv6_addr_any(&key->dst) || ipv6_addr_loopback(&key->dst)) {
+ dev_err(&pf->pdev->dev,
+ "Bad ipv6 dst addr is ANY or LOOPBACK\n");
+ return I40E_ERR_CONFIG;
+ }
+ if (ipv6_addr_loopback(&key->src)) {
+ dev_err(&pf->pdev->dev,
+ "Bad ipv6 src addr is ANY or LOOPBACK\n");
+ return I40E_ERR_CONFIG;
+ }
+ memcpy(&filter->src_ipv6, &key->src.s6_addr,
+ ARRAY_SIZE(filter->src_ipv6));
+ memcpy(&filter->dst_ipv6, &key->dst.s6_addr,
+ ARRAY_SIZE(filter->dst_ipv6));
+
+ /* mark it as IPv6 filter, to be used later */
+ filter->is_ipv6 = true;
+
+ /* and it is IP[4|6] filter type */
+ field_flags |= I40E_CLOUD_FIELD_IIP;
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+ struct flow_dissector_key_ports *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_PORTS,
+ f->key);
+ struct flow_dissector_key_ports *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_PORTS,
+ f->mask);
+
+ if (mask->src) {
+ if (mask->src == cpu_to_be16(0xffff)) {
+ field_flags |= I40E_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n",
+ be16_to_cpu(mask->src));
+ return I40E_ERR_CONFIG;
+ }
+ }
+
+ if (mask->dst) {
+ if (mask->dst == cpu_to_be16(0xffff)) {
+ field_flags |= I40E_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n",
+ be16_to_cpu(mask->dst));
+ return I40E_ERR_CONFIG;
+ }
+ }
+
+ filter->dst_port = key->dst;
+ filter->src_port = key->src;
+
+ /* For now, only supports destination port*/
+ filter->port_type |= I40E_CLOUD_FILTER_PORT_DEST;
+
+ switch (filter->ip_proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ break;
+ default:
+ dev_err(&pf->pdev->dev,
+ "Only UDP and TCP transport are supported\n");
+ return -EINVAL;
+ }
+ }
+ filter->flags = field_flags;
+ return 0;
+}
+
+/**
+ * i40e_handle_redirect_action: Forward to a traffic class on the device
+ * @vsi: Pointer to VSI
+ * @ifindex: ifindex of the device to forwared to
+ * @tc: traffic class index on the device
+ * @filter: Pointer to cloud filter structure
+ *
+ **/
+static int i40e_handle_redirect_action(struct i40e_vsi *vsi, int ifindex, u8 tc,
+ struct i40e_cloud_filter *filter)
+{
+ struct i40e_channel *ch, *ch_tmp;
+
+ /* redirect to a traffic class on the same device */
+ if (vsi->netdev->ifindex == ifindex) {
+ if (tc == 0) {
+ filter->seid = vsi->seid;
+ return 0;
+ } else if (vsi->tc_config.enabled_tc & BIT(tc)) {
+ if (!filter->dst_port) {
+ dev_err(&vsi->back->pdev->dev,
+ "Specify destination port to redirect to traffic class that is not default\n");
+ return -EINVAL;
+ }
+ if (list_empty(&vsi->ch_list))
+ return -EINVAL;
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list,
+ list) {
+ if (ch->seid == vsi->tc_seid_map[tc])
+ filter->seid = ch->seid;
+ }
+ return 0;
+ }
+ }
+ return -EINVAL;
+}
+
+/**
+ * i40e_parse_tc_actions - Parse tc actions
+ * @vsi: Pointer to VSI
+ * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @filter: Pointer to cloud filter structure
+ *
+ **/
+static int i40e_parse_tc_actions(struct i40e_vsi *vsi, struct tcf_exts *exts,
+ struct i40e_cloud_filter *filter)
+{
+ const struct tc_action *a;
+ LIST_HEAD(actions);
+ int err;
+
+ if (!tcf_exts_has_actions(exts))
+ return -EINVAL;
+
+ tcf_exts_to_list(exts, &actions);
+ list_for_each_entry(a, &actions, list) {
+ /* Drop action */
+ if (is_tcf_gact_shot(a)) {
+ dev_err(&vsi->back->pdev->dev,
+ "Cloud filters do not support the drop action.\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Redirect to a traffic class on the same device */
+ if (!is_tcf_mirred_egress_redirect(a) && is_tcf_mirred_tc(a)) {
+ int ifindex = tcf_mirred_ifindex(a);
+ u8 tc = tcf_mirred_tc(a);
+
+ err = i40e_handle_redirect_action(vsi, ifindex, tc,
+ filter);
+ if (err == 0)
+ return err;
+ }
+ }
+ return -EINVAL;
+}
+
+/**
+ * i40e_configure_clsflower - Configure tc flower filters
+ * @vsi: Pointer to VSI
+ * @cls_flower: Pointer to struct tc_cls_flower_offload
+ *
+ **/
+static int i40e_configure_clsflower(struct i40e_vsi *vsi,
+ struct tc_cls_flower_offload *cls_flower)
+{
+ struct i40e_cloud_filter *filter = NULL;
+ struct i40e_pf *pf = vsi->back;
+ int err = 0;
+
+ if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+ test_bit(__I40E_RESET_INTR_RECEIVED, pf->state))
+ return -EBUSY;
+
+ if (pf->fdir_pf_active_filters ||
+ (!hlist_empty(&pf->fdir_filter_list))) {
+ dev_err(&vsi->back->pdev->dev,
+ "Flow Director Sideband filters exists, turn ntuple off to configure cloud filters\n");
+ return -EINVAL;
+ }
+
+ if (vsi->back->flags & I40E_FLAG_FD_SB_ENABLED) {
+ dev_err(&vsi->back->pdev->dev,
+ "Disable Flow Director Sideband, configuring Cloud filters via tc-flower\n");
+ vsi->back->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ vsi->back->flags |= I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
+ }
+
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!filter)
+ return -ENOMEM;
+
+ filter->cookie = cls_flower->cookie;
+
+ err = i40e_parse_cls_flower(vsi, cls_flower, filter);
+ if (err < 0)
+ goto err;
+
+ err = i40e_parse_tc_actions(vsi, cls_flower->exts, filter);
+ if (err < 0)
+ goto err;
+
+ /* Add cloud filter */
+ if (filter->dst_port)
+ err = i40e_add_del_cloud_filter_big_buf(vsi, filter, true);
+ else
+ err = i40e_add_del_cloud_filter(vsi, filter, true);
+
+ if (err) {
+ dev_err(&pf->pdev->dev,
+ "Failed to add cloud filter, err %s\n",
+ i40e_stat_str(&pf->hw, err));
+ err = i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status);
+ goto err;
+ }
+
+ /* add filter to the ordered list */
+ INIT_HLIST_NODE(&filter->cloud_node);
+
+ hlist_add_head(&filter->cloud_node, &pf->cloud_filter_list);
+
+ pf->num_cloud_filters++;
+
+ return err;
+err:
+ kfree(filter);
+ return err;
+}
+
+/**
+ * i40e_find_cloud_filter - Find the could filter in the list
+ * @vsi: Pointer to VSI
+ * @cookie: filter specific cookie
+ *
+ **/
+static struct i40e_cloud_filter *i40e_find_cloud_filter(struct i40e_vsi *vsi,
+ unsigned long *cookie)
+{
+ struct i40e_cloud_filter *filter = NULL;
+ struct hlist_node *node2;
+
+ hlist_for_each_entry_safe(filter, node2,
+ &vsi->back->cloud_filter_list, cloud_node)
+ if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie)))
+ return filter;
+ return NULL;
+}
+
+/**
+ * i40e_delete_clsflower - Remove tc flower filters
+ * @vsi: Pointer to VSI
+ * @cls_flower: Pointer to struct tc_cls_flower_offload
+ *
+ **/
+static int i40e_delete_clsflower(struct i40e_vsi *vsi,
+ struct tc_cls_flower_offload *cls_flower)
+{
+ struct i40e_cloud_filter *filter = NULL;
+ struct i40e_pf *pf = vsi->back;
+ int err = 0;
+
+ filter = i40e_find_cloud_filter(vsi, &cls_flower->cookie);
+
+ if (!filter)
+ return -EINVAL;
+
+ hash_del(&filter->cloud_node);
+
+ if (filter->dst_port)
+ err = i40e_add_del_cloud_filter_big_buf(vsi, filter, false);
+ else
+ err = i40e_add_del_cloud_filter(vsi, filter, false);
+ if (err) {
+ kfree(filter);
+ dev_err(&pf->pdev->dev,
+ "Failed to delete cloud filter, err %s\n",
+ i40e_stat_str(&pf->hw, err));
+ return i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status);
+ }
+
+ kfree(filter);
+ pf->num_cloud_filters--;
+
+ if (!pf->num_cloud_filters)
+ if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) &&
+ !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) {
+ pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+ pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
+ pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+ }
+ return 0;
+}
+
+/**
+ * i40e_setup_tc_cls_flower - flower classifier offloads
+ * @netdev: net device to configure
+ * @type_data: offload data
+ **/
+static int i40e_setup_tc_cls_flower(struct net_device *netdev,
+ struct tc_cls_flower_offload *cls_flower)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
+ cls_flower->common.chain_index)
+ return -EOPNOTSUPP;
+
+ switch (cls_flower->command) {
+ case TC_CLSFLOWER_REPLACE:
+ return i40e_configure_clsflower(vsi, cls_flower);
+ case TC_CLSFLOWER_DESTROY:
+ return i40e_delete_clsflower(vsi, cls_flower);
+ case TC_CLSFLOWER_STATS:
+ return -EOPNOTSUPP;
+ default:
+ return -EINVAL;
+ }
+}
+
static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data)
{
@@ -6784,6 +7609,8 @@ static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
case TC_SETUP_MQPRIO:
case TC_SETUP_MQPRIO_EXT:
return i40e_setup_tc(netdev, type, type_data);
+ case TC_SETUP_CLSFLOWER:
+ return i40e_setup_tc_cls_flower(netdev, type_data);
default:
return -EOPNOTSUPP;
}
@@ -6984,6 +7811,13 @@ static void i40e_cloud_filter_exit(struct i40e_pf *pf)
kfree(cfilter);
}
pf->num_cloud_filters = 0;
+
+ if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) &&
+ !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) {
+ pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+ pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
+ pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+ }
}
/**
@@ -8076,7 +8910,8 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
* i40e_get_capabilities - get info about the HW
* @pf: the PF struct
**/
-static int i40e_get_capabilities(struct i40e_pf *pf)
+static int i40e_get_capabilities(struct i40e_pf *pf,
+ enum i40e_admin_queue_opc list_type)
{
struct i40e_aqc_list_capabilities_element_resp *cap_buf;
u16 data_size;
@@ -8091,9 +8926,8 @@ static int i40e_get_capabilities(struct i40e_pf *pf)
/* this loads the data into the hw struct for us */
err = i40e_aq_discover_capabilities(&pf->hw, cap_buf, buf_len,
- &data_size,
- i40e_aqc_opc_list_func_capabilities,
- NULL);
+ &data_size, list_type,
+ NULL);
/* data loaded, buffer no longer needed */
kfree(cap_buf);
@@ -8110,26 +8944,44 @@ static int i40e_get_capabilities(struct i40e_pf *pf)
}
} while (err);
- if (pf->hw.debug_mask & I40E_DEBUG_USER)
- dev_info(&pf->pdev->dev,
- "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n",
- pf->hw.pf_id, pf->hw.func_caps.num_vfs,
- pf->hw.func_caps.num_msix_vectors,
- pf->hw.func_caps.num_msix_vectors_vf,
- pf->hw.func_caps.fd_filters_guaranteed,
- pf->hw.func_caps.fd_filters_best_effort,
- pf->hw.func_caps.num_tx_qp,
- pf->hw.func_caps.num_vsis);
-
+ if (pf->hw.debug_mask & I40E_DEBUG_USER) {
+ if (list_type == i40e_aqc_opc_list_func_capabilities) {
+ dev_info(&pf->pdev->dev,
+ "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n",
+ pf->hw.pf_id, pf->hw.func_caps.num_vfs,
+ pf->hw.func_caps.num_msix_vectors,
+ pf->hw.func_caps.num_msix_vectors_vf,
+ pf->hw.func_caps.fd_filters_guaranteed,
+ pf->hw.func_caps.fd_filters_best_effort,
+ pf->hw.func_caps.num_tx_qp,
+ pf->hw.func_caps.num_vsis);
+ } else if (list_type == i40e_aqc_opc_list_dev_capabilities) {
+ dev_info(&pf->pdev->dev,
+ "switch_mode=0x%04x, function_valid=0x%08x\n",
+ pf->hw.dev_caps.switch_mode,
+ pf->hw.dev_caps.valid_functions);
+ dev_info(&pf->pdev->dev,
+ "SR-IOV=%d, num_vfs for all function=%u\n",
+ pf->hw.dev_caps.sr_iov_1_1,
+ pf->hw.dev_caps.num_vfs);
+ dev_info(&pf->pdev->dev,
+ "num_vsis=%u, num_rx:%u, num_tx=%u\n",
+ pf->hw.dev_caps.num_vsis,
+ pf->hw.dev_caps.num_rx_qp,
+ pf->hw.dev_caps.num_tx_qp);
+ }
+ }
+ if (list_type == i40e_aqc_opc_list_func_capabilities) {
#define DEF_NUM_VSI (1 + (pf->hw.func_caps.fcoe ? 1 : 0) \
+ pf->hw.func_caps.num_vfs)
- if (pf->hw.revision_id == 0 && (DEF_NUM_VSI > pf->hw.func_caps.num_vsis)) {
- dev_info(&pf->pdev->dev,
- "got num_vsis %d, setting num_vsis to %d\n",
- pf->hw.func_caps.num_vsis, DEF_NUM_VSI);
- pf->hw.func_caps.num_vsis = DEF_NUM_VSI;
+ if (pf->hw.revision_id == 0 &&
+ (pf->hw.func_caps.num_vsis < DEF_NUM_VSI)) {
+ dev_info(&pf->pdev->dev,
+ "got num_vsis %d, setting num_vsis to %d\n",
+ pf->hw.func_caps.num_vsis, DEF_NUM_VSI);
+ pf->hw.func_caps.num_vsis = DEF_NUM_VSI;
+ }
}
-
return 0;
}
@@ -8171,6 +9023,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
if (!vsi) {
dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n");
pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
return;
}
}
@@ -8193,6 +9046,48 @@ static void i40e_fdir_teardown(struct i40e_pf *pf)
}
/**
+ * i40e_rebuild_cloud_filters - Rebuilds cloud filters for VSIs
+ * @vsi: PF main vsi
+ * @seid: seid of main or channel VSIs
+ *
+ * Rebuilds cloud filters associated with main VSI and channel VSIs if they
+ * existed before reset
+ **/
+static int i40e_rebuild_cloud_filters(struct i40e_vsi *vsi, u16 seid)
+{
+ struct i40e_cloud_filter *cfilter;
+ struct i40e_pf *pf = vsi->back;
+ struct hlist_node *node;
+ i40e_status ret;
+
+ /* Add cloud filters back if they exist */
+ if (hlist_empty(&pf->cloud_filter_list))
+ return 0;
+
+ hlist_for_each_entry_safe(cfilter, node, &pf->cloud_filter_list,
+ cloud_node) {
+ if (cfilter->seid != seid)
+ continue;
+
+ if (cfilter->dst_port)
+ ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter,
+ true);
+ else
+ ret = i40e_add_del_cloud_filter(vsi, cfilter, true);
+
+ if (ret) {
+ dev_dbg(&pf->pdev->dev,
+ "Failed to rebuild cloud filter, err %s aq_err %s\n",
+ i40e_stat_str(&pf->hw, ret),
+ i40e_aq_str(&pf->hw,
+ pf->hw.aq.asq_last_status));
+ return ret;
+ }
+ }
+ return 0;
+}
+
+/**
* i40e_rebuild_channels - Rebuilds channel VSIs if they existed before reset
* @vsi: PF main vsi
*
@@ -8229,6 +9124,13 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi)
I40E_BW_CREDIT_DIVISOR,
ch->seid);
}
+ ret = i40e_rebuild_cloud_filters(vsi, ch->seid);
+ if (ret) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Failed to rebuild cloud filters for channel VSI %u\n",
+ ch->seid);
+ return ret;
+ }
}
return 0;
}
@@ -8395,7 +9297,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
i40e_verify_eeprom(pf);
i40e_clear_pxe_mode(hw);
- ret = i40e_get_capabilities(pf);
+ ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
if (ret)
goto end_core_reset;
@@ -8512,6 +9414,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
goto end_unlock;
}
+ ret = i40e_rebuild_cloud_filters(vsi, vsi->seid);
+ if (ret)
+ goto end_unlock;
+
/* PF Main VSI is rebuild by now, go ahead and rebuild channel VSIs
* for this main VSI if they exist
*/
@@ -9434,6 +10340,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
(pf->num_fdsb_msix == 0)) {
dev_info(&pf->pdev->dev, "Sideband Flowdir disabled, not enough MSI-X vectors\n");
pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
}
if ((pf->flags & I40E_FLAG_VMDQ_ENABLED) &&
(pf->num_vmdq_msix == 0)) {
@@ -9551,6 +10458,7 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
I40E_FLAG_VMDQ_ENABLED);
+ pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
/* rework the queue expectations without MSIX */
i40e_determine_queue_usage(pf);
@@ -10288,9 +11196,13 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
/* Enable filters and mark for reset */
if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
need_reset = true;
- /* enable FD_SB only if there is MSI-X vector */
- if (pf->num_fdsb_msix > 0)
+ /* enable FD_SB only if there is MSI-X vector and no cloud
+ * filters exist
+ */
+ if (pf->num_fdsb_msix > 0 && !pf->num_cloud_filters) {
pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+ pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+ }
} else {
/* turn off filters, mark for reset and clear SW filter list */
if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
@@ -10299,6 +11211,8 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
}
pf->flags &= ~(I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_SB_AUTO_DISABLED);
+ pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+
/* reset fd counters */
pf->fd_add_err = 0;
pf->fd_atr_cnt = 0;
@@ -10882,7 +11796,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
netdev->hw_features |= NETIF_F_NTUPLE;
hw_features = hw_enc_features |
NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_CTAG_RX;
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_TC;
netdev->hw_features |= hw_features;
@@ -12159,8 +13074,10 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
*/
if ((pf->hw.pf_id == 0) &&
- !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
+ !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
+ pf->last_sw_conf_flags = flags;
+ }
if (pf->hw.pf_id == 0) {
u16 valid_flags;
@@ -12176,6 +13093,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
pf->hw.aq.asq_last_status));
/* not a fatal problem, just keep going */
}
+ pf->last_sw_conf_valid_flags = valid_flags;
}
/* first time setup */
@@ -12273,6 +13191,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
I40E_FLAG_DCB_ENABLED |
I40E_FLAG_SRIOV_ENABLED |
I40E_FLAG_VMDQ_ENABLED);
+ pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
} else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED |
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
@@ -12287,6 +13206,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
I40E_FLAG_FD_ATR_ENABLED |
I40E_FLAG_DCB_ENABLED |
I40E_FLAG_VMDQ_ENABLED);
+ pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
} else {
/* Not enough queues for all TCs */
if ((pf->flags & I40E_FLAG_DCB_CAPABLE) &&
@@ -12310,6 +13230,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
queues_left -= 1; /* save 1 queue for FD */
} else {
pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
dev_info(&pf->pdev->dev, "not enough queues for Flow Director. Flow Director feature is disabled\n");
}
}
@@ -12606,7 +13527,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n");
i40e_clear_pxe_mode(hw);
- err = i40e_get_capabilities(pf);
+ err = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
if (err)
goto err_adminq_setup;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 9142d0d..e24f1ce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -283,6 +283,23 @@ i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw,
struct i40e_asq_cmd_details *cmd_details);
i40e_status i40e_aq_resume_port_tx(struct i40e_hw *hw,
struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_add_cloud_filters_big_buffer(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_add_remove_cloud_filters_element_big_data *filters,
+ u8 filter_count);
+enum i40e_status_code i40e_aq_add_cloud_filters(struct i40e_hw *hw,
+ u16 vsi,
+ struct i40e_aqc_add_remove_cloud_filters_element_data *filters,
+ u8 filter_count);
+
+enum i40e_status_code i40e_aq_remove_cloud_filters(struct i40e_hw *hw,
+ u16 vsi,
+ struct i40e_aqc_add_remove_cloud_filters_element_data *filters,
+ u8 filter_count);
+i40e_status i40e_aq_remove_cloud_filters_big_buffer(
+ struct i40e_hw *hw, u16 seid,
+ struct i40e_aqc_add_remove_cloud_filters_element_big_data *filters,
+ u8 filter_count);
i40e_status i40e_read_lldp_cfg(struct i40e_hw *hw,
struct i40e_lldp_variables *lldp_cfg);
/* i40e_common */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 0cfc89e..41ae91f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -284,6 +284,7 @@ struct i40e_hw_capabilities {
#define I40E_NVM_IMAGE_TYPE_MODE1 0x6
#define I40E_NVM_IMAGE_TYPE_MODE2 0x7
#define I40E_NVM_IMAGE_TYPE_MODE3 0x8
+#define I40E_SWITCH_MODE_MASK 0xF
u32 management_mode;
u32 mng_protocols_over_mctp;
^ 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