* [PATCH net-next 09/10] net/mlx4: Refactor QUERY_PORT
From: Or Gerlitz @ 2014-12-04 13:13 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Matan Barak, Amir Vadai, Tal Alon, Jack Morgenstein,
Or Gerlitz
In-Reply-To: <1417698835-11050-1-git-send-email-ogerlitz@mellanox.com>
From: Matan Barak <matanb@mellanox.com>
Currently QUERY_PORT is done as a part of QUERY_DEV_CAP firmware command.
Since we would like to use it without querying all device capabilities,
extract this part to be a function of its own.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/fw.c | 141 +++++++++++++++++------------
drivers/net/ethernet/mellanox/mlx4/fw.h | 37 +++++----
drivers/net/ethernet/mellanox/mlx4/main.c | 71 ++++++++++-----
3 files changed, 154 insertions(+), 95 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 4da5aed..e07cb9b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -886,61 +886,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
if (field32 & (1 << 21))
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_80_VFS;
- if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
- for (i = 1; i <= dev_cap->num_ports; ++i) {
- MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
- dev_cap->max_vl[i] = field >> 4;
- MLX4_GET(field, outbox, QUERY_DEV_CAP_MTU_WIDTH_OFFSET);
- dev_cap->ib_mtu[i] = field >> 4;
- dev_cap->max_port_width[i] = field & 0xf;
- MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_GID_OFFSET);
- dev_cap->max_gids[i] = 1 << (field & 0xf);
- MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PKEY_OFFSET);
- dev_cap->max_pkeys[i] = 1 << (field & 0xf);
- }
- } else {
-#define QUERY_PORT_SUPPORTED_TYPE_OFFSET 0x00
-#define QUERY_PORT_MTU_OFFSET 0x01
-#define QUERY_PORT_ETH_MTU_OFFSET 0x02
-#define QUERY_PORT_WIDTH_OFFSET 0x06
-#define QUERY_PORT_MAX_GID_PKEY_OFFSET 0x07
-#define QUERY_PORT_MAX_MACVLAN_OFFSET 0x0a
-#define QUERY_PORT_MAX_VL_OFFSET 0x0b
-#define QUERY_PORT_MAC_OFFSET 0x10
-#define QUERY_PORT_TRANS_VENDOR_OFFSET 0x18
-#define QUERY_PORT_WAVELENGTH_OFFSET 0x1c
-#define QUERY_PORT_TRANS_CODE_OFFSET 0x20
-
- for (i = 1; i <= dev_cap->num_ports; ++i) {
- err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 0, MLX4_CMD_QUERY_PORT,
- MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
- if (err)
- goto out;
-
- MLX4_GET(field, outbox, QUERY_PORT_SUPPORTED_TYPE_OFFSET);
- dev_cap->supported_port_types[i] = field & 3;
- dev_cap->suggested_type[i] = (field >> 3) & 1;
- dev_cap->default_sense[i] = (field >> 4) & 1;
- MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
- dev_cap->ib_mtu[i] = field & 0xf;
- MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
- dev_cap->max_port_width[i] = field & 0xf;
- MLX4_GET(field, outbox, QUERY_PORT_MAX_GID_PKEY_OFFSET);
- dev_cap->max_gids[i] = 1 << (field >> 4);
- dev_cap->max_pkeys[i] = 1 << (field & 0xf);
- MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
- dev_cap->max_vl[i] = field & 0xf;
- MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
- dev_cap->log_max_macs[i] = field & 0xf;
- dev_cap->log_max_vlans[i] = field >> 4;
- MLX4_GET(dev_cap->eth_mtu[i], outbox, QUERY_PORT_ETH_MTU_OFFSET);
- MLX4_GET(dev_cap->def_mac[i], outbox, QUERY_PORT_MAC_OFFSET);
- MLX4_GET(field32, outbox, QUERY_PORT_TRANS_VENDOR_OFFSET);
- dev_cap->trans_type[i] = field32 >> 24;
- dev_cap->vendor_oui[i] = field32 & 0xffffff;
- MLX4_GET(dev_cap->wavelength[i], outbox, QUERY_PORT_WAVELENGTH_OFFSET);
- MLX4_GET(dev_cap->trans_code[i], outbox, QUERY_PORT_TRANS_CODE_OFFSET);
- }
+ for (i = 1; i <= dev_cap->num_ports; i++) {
+ err = mlx4_QUERY_PORT(dev, i, dev_cap->port_cap + i);
+ if (err)
+ goto out;
}
mlx4_dbg(dev, "Base MM extensions: flags %08x, rsvd L_Key %08x\n",
@@ -977,8 +926,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
mlx4_dbg(dev, "Max CQEs: %d, max WQEs: %d, max SRQ WQEs: %d\n",
dev_cap->max_cq_sz, dev_cap->max_qp_sz, dev_cap->max_srq_sz);
mlx4_dbg(dev, "Local CA ACK delay: %d, max MTU: %d, port width cap: %d\n",
- dev_cap->local_ca_ack_delay, 128 << dev_cap->ib_mtu[1],
- dev_cap->max_port_width[1]);
+ dev_cap->local_ca_ack_delay, 128 << dev_cap->port_cap[1].ib_mtu,
+ dev_cap->port_cap[1].max_port_width);
mlx4_dbg(dev, "Max SQ desc size: %d, max SQ S/G: %d\n",
dev_cap->max_sq_desc_sz, dev_cap->max_sq_sg);
mlx4_dbg(dev, "Max RQ desc size: %d, max RQ S/G: %d\n",
@@ -995,6 +944,84 @@ out:
return err;
}
+int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_cap)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ u32 *outbox;
+ u8 field;
+ u32 field32;
+ int err;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ outbox = mailbox->buf;
+
+ if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+ err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+
+ if (err)
+ goto out;
+
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
+ port_cap->max_vl = field >> 4;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_MTU_WIDTH_OFFSET);
+ port_cap->ib_mtu = field >> 4;
+ port_cap->max_port_width = field & 0xf;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_GID_OFFSET);
+ port_cap->max_gids = 1 << (field & 0xf);
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PKEY_OFFSET);
+ port_cap->max_pkeys = 1 << (field & 0xf);
+ } else {
+#define QUERY_PORT_SUPPORTED_TYPE_OFFSET 0x00
+#define QUERY_PORT_MTU_OFFSET 0x01
+#define QUERY_PORT_ETH_MTU_OFFSET 0x02
+#define QUERY_PORT_WIDTH_OFFSET 0x06
+#define QUERY_PORT_MAX_GID_PKEY_OFFSET 0x07
+#define QUERY_PORT_MAX_MACVLAN_OFFSET 0x0a
+#define QUERY_PORT_MAX_VL_OFFSET 0x0b
+#define QUERY_PORT_MAC_OFFSET 0x10
+#define QUERY_PORT_TRANS_VENDOR_OFFSET 0x18
+#define QUERY_PORT_WAVELENGTH_OFFSET 0x1c
+#define QUERY_PORT_TRANS_CODE_OFFSET 0x20
+
+ err = mlx4_cmd_box(dev, 0, mailbox->dma, port, 0, MLX4_CMD_QUERY_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+ if (err)
+ goto out;
+
+ MLX4_GET(field, outbox, QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+ port_cap->supported_port_types = field & 3;
+ port_cap->suggested_type = (field >> 3) & 1;
+ port_cap->default_sense = (field >> 4) & 1;
+ MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
+ port_cap->ib_mtu = field & 0xf;
+ MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
+ port_cap->max_port_width = field & 0xf;
+ MLX4_GET(field, outbox, QUERY_PORT_MAX_GID_PKEY_OFFSET);
+ port_cap->max_gids = 1 << (field >> 4);
+ port_cap->max_pkeys = 1 << (field & 0xf);
+ MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
+ port_cap->max_vl = field & 0xf;
+ MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
+ port_cap->log_max_macs = field & 0xf;
+ port_cap->log_max_vlans = field >> 4;
+ MLX4_GET(port_cap->eth_mtu, outbox, QUERY_PORT_ETH_MTU_OFFSET);
+ MLX4_GET(port_cap->def_mac, outbox, QUERY_PORT_MAC_OFFSET);
+ MLX4_GET(field32, outbox, QUERY_PORT_TRANS_VENDOR_OFFSET);
+ port_cap->trans_type = field32 >> 24;
+ port_cap->vendor_oui = field32 & 0xffffff;
+ MLX4_GET(port_cap->wavelength, outbox, QUERY_PORT_WAVELENGTH_OFFSET);
+ MLX4_GET(port_cap->trans_code, outbox, QUERY_PORT_TRANS_CODE_OFFSET);
+ }
+
+out:
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+
int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 0e910a4..744398b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -43,6 +43,25 @@ struct mlx4_mod_stat_cfg {
u8 log_pg_sz_m;
};
+struct mlx4_port_cap {
+ u8 supported_port_types;
+ u8 suggested_type;
+ u8 default_sense;
+ u8 log_max_macs;
+ u8 log_max_vlans;
+ int ib_mtu;
+ int max_port_width;
+ int max_vl;
+ int max_gids;
+ int max_pkeys;
+ u64 def_mac;
+ u16 eth_mtu;
+ int trans_type;
+ int vendor_oui;
+ u16 wavelength;
+ u64 trans_code;
+};
+
struct mlx4_dev_cap {
int max_srq_sz;
int max_qp_sz;
@@ -67,17 +86,6 @@ struct mlx4_dev_cap {
int local_ca_ack_delay;
int num_ports;
u32 max_msg_sz;
- int ib_mtu[MLX4_MAX_PORTS + 1];
- int max_port_width[MLX4_MAX_PORTS + 1];
- int max_vl[MLX4_MAX_PORTS + 1];
- int max_gids[MLX4_MAX_PORTS + 1];
- int max_pkeys[MLX4_MAX_PORTS + 1];
- u64 def_mac[MLX4_MAX_PORTS + 1];
- u16 eth_mtu[MLX4_MAX_PORTS + 1];
- int trans_type[MLX4_MAX_PORTS + 1];
- int vendor_oui[MLX4_MAX_PORTS + 1];
- u16 wavelength[MLX4_MAX_PORTS + 1];
- u64 trans_code[MLX4_MAX_PORTS + 1];
u16 stat_rate_support;
int fs_log_max_ucast_qp_range_size;
int fs_max_num_qp_per_entry;
@@ -115,12 +123,8 @@ struct mlx4_dev_cap {
u64 max_icm_sz;
int max_gso_sz;
int max_rss_tbl_sz;
- u8 supported_port_types[MLX4_MAX_PORTS + 1];
- u8 suggested_type[MLX4_MAX_PORTS + 1];
- u8 default_sense[MLX4_MAX_PORTS + 1];
- u8 log_max_macs[MLX4_MAX_PORTS + 1];
- u8 log_max_vlans[MLX4_MAX_PORTS + 1];
u32 max_counters;
+ struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
};
struct mlx4_func_cap {
@@ -217,6 +221,7 @@ struct mlx4_set_ib_param {
};
int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap);
+int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_cap);
int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
struct mlx4_func_cap *func_cap);
int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 3bfe90b..6173b80 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -254,6 +254,46 @@ static void mlx4_enable_cqe_eqe_stride(struct mlx4_dev *dev)
}
}
+static int _mlx4_dev_port(struct mlx4_dev *dev, int port,
+ struct mlx4_port_cap *port_cap)
+{
+ dev->caps.vl_cap[port] = port_cap->max_vl;
+ dev->caps.ib_mtu_cap[port] = port_cap->ib_mtu;
+ dev->phys_caps.gid_phys_table_len[port] = port_cap->max_gids;
+ dev->phys_caps.pkey_phys_table_len[port] = port_cap->max_pkeys;
+ /* set gid and pkey table operating lengths by default
+ * to non-sriov values
+ */
+ dev->caps.gid_table_len[port] = port_cap->max_gids;
+ dev->caps.pkey_table_len[port] = port_cap->max_pkeys;
+ dev->caps.port_width_cap[port] = port_cap->max_port_width;
+ dev->caps.eth_mtu_cap[port] = port_cap->eth_mtu;
+ dev->caps.def_mac[port] = port_cap->def_mac;
+ dev->caps.supported_type[port] = port_cap->supported_port_types;
+ dev->caps.suggested_type[port] = port_cap->suggested_type;
+ dev->caps.default_sense[port] = port_cap->default_sense;
+ dev->caps.trans_type[port] = port_cap->trans_type;
+ dev->caps.vendor_oui[port] = port_cap->vendor_oui;
+ dev->caps.wavelength[port] = port_cap->wavelength;
+ dev->caps.trans_code[port] = port_cap->trans_code;
+
+ return 0;
+}
+
+static int mlx4_dev_port(struct mlx4_dev *dev, int port,
+ struct mlx4_port_cap *port_cap)
+{
+ int err = 0;
+
+ err = mlx4_QUERY_PORT(dev, port, port_cap);
+
+ if (err)
+ mlx4_err(dev, "QUERY_PORT command failed.\n");
+
+ return err;
+}
+
+#define MLX4_A0_STEERING_TABLE_SIZE 256
static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
{
int err;
@@ -289,24 +329,11 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev->caps.num_sys_eqs :
MLX4_MAX_EQ_NUM;
for (i = 1; i <= dev->caps.num_ports; ++i) {
- dev->caps.vl_cap[i] = dev_cap->max_vl[i];
- dev->caps.ib_mtu_cap[i] = dev_cap->ib_mtu[i];
- dev->phys_caps.gid_phys_table_len[i] = dev_cap->max_gids[i];
- dev->phys_caps.pkey_phys_table_len[i] = dev_cap->max_pkeys[i];
- /* set gid and pkey table operating lengths by default
- * to non-sriov values */
- dev->caps.gid_table_len[i] = dev_cap->max_gids[i];
- dev->caps.pkey_table_len[i] = dev_cap->max_pkeys[i];
- dev->caps.port_width_cap[i] = dev_cap->max_port_width[i];
- dev->caps.eth_mtu_cap[i] = dev_cap->eth_mtu[i];
- dev->caps.def_mac[i] = dev_cap->def_mac[i];
- dev->caps.supported_type[i] = dev_cap->supported_port_types[i];
- dev->caps.suggested_type[i] = dev_cap->suggested_type[i];
- dev->caps.default_sense[i] = dev_cap->default_sense[i];
- dev->caps.trans_type[i] = dev_cap->trans_type[i];
- dev->caps.vendor_oui[i] = dev_cap->vendor_oui[i];
- dev->caps.wavelength[i] = dev_cap->wavelength[i];
- dev->caps.trans_code[i] = dev_cap->trans_code[i];
+ err = _mlx4_dev_port(dev, i, dev_cap->port_cap + i);
+ if (err) {
+ mlx4_err(dev, "QUERY_PORT command failed, aborting\n");
+ return err;
+ }
}
dev->caps.uar_page_size = PAGE_SIZE;
@@ -415,13 +442,13 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev->caps.possible_type[i] = dev->caps.port_type[i];
}
- if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
- dev->caps.log_num_macs = dev_cap->log_max_macs[i];
+ if (dev->caps.log_num_macs > dev_cap->port_cap[i].log_max_macs) {
+ dev->caps.log_num_macs = dev_cap->port_cap[i].log_max_macs;
mlx4_warn(dev, "Requested number of MACs is too much for port %d, reducing to %d\n",
i, 1 << dev->caps.log_num_macs);
}
- if (dev->caps.log_num_vlans > dev_cap->log_max_vlans[i]) {
- dev->caps.log_num_vlans = dev_cap->log_max_vlans[i];
+ if (dev->caps.log_num_vlans > dev_cap->port_cap[i].log_max_vlans) {
+ dev->caps.log_num_vlans = dev_cap->port_cap[i].log_max_vlans;
mlx4_warn(dev, "Requested number of VLANs is too much for port %d, reducing to %d\n",
i, 1 << dev->caps.log_num_vlans);
}
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 03/10] net/mlx4_core: Use tasklet for user-space CQ completion events
From: Or Gerlitz @ 2014-12-04 13:13 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Matan Barak, Amir Vadai, Tal Alon, Jack Morgenstein,
Or Gerlitz
In-Reply-To: <1417698835-11050-1-git-send-email-ogerlitz@mellanox.com>
From: Matan Barak <matanb@mellanox.com>
Previously, we've fired all our completion callbacks straight from our ISR.
Some of those callbacks were lightweight (for example, mlx4_en's and
IPoIB napi callbacks), but some of them did more work (for example,
the user-space RDMA stack uverbs' completion handler). Besides that,
doing more than the minimal work in ISR is generally considered wrong,
it could even lead to a hard lockup of the system. Since when a lot
of completion events are generated by the hardware, the loop over those
events could be so long, that we'll get into a hard lockup by the system
watchdog.
In order to avoid that, add a new way of invoking completion events
callbacks. In the interrupt itself, we add the CQs which receive completion
event to a per-EQ list and schedule a tasklet. In the tasklet context
we loop over all the CQs in the list and invoke the user callback.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/infiniband/hw/mlx4/cq.c | 5 ++-
drivers/net/ethernet/mellanox/mlx4/cq.c | 49 +++++++++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/eq.c | 16 +++++++++-
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 12 +++++++
include/linux/mlx4/device.h | 5 +++
5 files changed, 85 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 1066eec..a3b70f6 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -233,7 +233,10 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
if (err)
goto err_dbmap;
- cq->mcq.comp = mlx4_ib_cq_comp;
+ if (context)
+ cq->mcq.tasklet_ctx.comp = mlx4_ib_cq_comp;
+ else
+ cq->mcq.comp = mlx4_ib_cq_comp;
cq->mcq.event = mlx4_ib_cq_event;
if (context)
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 56022d6..060ea63 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -52,6 +52,50 @@
#define MLX4_CQ_STATE_ARMED_SOL ( 6 << 8)
#define MLX4_EQ_STATE_FIRED (10 << 8)
+#define TASKLET_THRESHOLD 1000
+
+void mlx4_cq_tasklet_cb(unsigned long data)
+{
+ unsigned long flags;
+ unsigned int i = 0;
+ struct mlx4_eq_tasklet *ctx = (struct mlx4_eq_tasklet *)data;
+ struct mlx4_cq *mcq, *temp;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ list_splice_tail_init(&ctx->list, &ctx->process_list);
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ list_for_each_entry_safe(mcq, temp, &ctx->process_list, tasklet_ctx.list) {
+ list_del_init(&mcq->tasklet_ctx.list);
+ mcq->tasklet_ctx.comp(mcq);
+ if (atomic_dec_and_test(&mcq->refcount))
+ complete(&mcq->free);
+ if (++i == TASKLET_THRESHOLD)
+ break;
+ }
+
+ if (i == TASKLET_THRESHOLD)
+ tasklet_schedule(&ctx->task);
+}
+
+static void mlx4_add_cq_to_tasklet(struct mlx4_cq *cq)
+{
+ unsigned long flags;
+ struct mlx4_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
+
+ spin_lock_irqsave(&tasklet_ctx->lock, flags);
+ /* When migrating CQs between EQs will be implemented, please note
+ * that you need to sync this point. It is possible that
+ * while migrating a CQ, completions on the old EQs could
+ * still arrive.
+ */
+ if (list_empty_careful(&cq->tasklet_ctx.list)) {
+ atomic_inc(&cq->refcount);
+ list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
+ }
+ spin_unlock_irqrestore(&tasklet_ctx->lock, flags);
+}
+
void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
{
struct mlx4_cq *cq;
@@ -292,6 +336,11 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
cq->uar = uar;
atomic_set(&cq->refcount, 1);
init_completion(&cq->free);
+ cq->comp = mlx4_add_cq_to_tasklet;
+ cq->tasklet_ctx.priv =
+ &priv->eq_table.eq[cq->vector].tasklet_ctx;
+ INIT_LIST_HEAD(&cq->tasklet_ctx.list);
+
cq->irq = priv->eq_table.eq[cq->vector].irq;
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index d68b264..3d275fb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -450,7 +450,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_eqe *eqe;
- int cqn;
+ int cqn = -1;
int eqes_found = 0;
int set_ci = 0;
int port;
@@ -758,6 +758,13 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
eq_set_ci(eq, 1);
+ /* cqn is 24bit wide but is initialized such that its higher bits
+ * are ones too. Thus, if we got any event, cqn's high bits should be off
+ * and we need to schedule the tasklet.
+ */
+ if (!(cqn & ~0xffffff))
+ tasklet_schedule(&eq->tasklet_ctx.task);
+
return eqes_found;
}
@@ -971,6 +978,12 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent,
eq->cons_index = 0;
+ INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+ INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+ spin_lock_init(&eq->tasklet_ctx.lock);
+ tasklet_init(&eq->tasklet_ctx.task, mlx4_cq_tasklet_cb,
+ (unsigned long)&eq->tasklet_ctx);
+
return err;
err_out_free_mtt:
@@ -1027,6 +1040,7 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
}
}
synchronize_irq(eq->irq);
+ tasklet_disable(&eq->tasklet_ctx.task);
mlx4_mtt_cleanup(dev, &eq->mtt);
for (i = 0; i < npages; ++i)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index f48e7c3..b67ef48 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -43,6 +43,8 @@
#include <linux/timer.h>
#include <linux/semaphore.h>
#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/driver.h>
@@ -373,6 +375,14 @@ struct mlx4_srq_context {
__be64 db_rec_addr;
};
+struct mlx4_eq_tasklet {
+ struct list_head list;
+ struct list_head process_list;
+ struct tasklet_struct task;
+ /* lock on completion tasklet list */
+ spinlock_t lock;
+};
+
struct mlx4_eq {
struct mlx4_dev *dev;
void __iomem *doorbell;
@@ -383,6 +393,7 @@ struct mlx4_eq {
int nent;
struct mlx4_buf_list *page_list;
struct mlx4_mtt mtt;
+ struct mlx4_eq_tasklet tasklet_ctx;
};
struct mlx4_slave_eqe {
@@ -1146,6 +1157,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev);
int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
unsigned long timeout);
+void mlx4_cq_tasklet_cb(unsigned long data);
void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn);
void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index cf09e65..3951b53 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -621,6 +621,11 @@ struct mlx4_cq {
atomic_t refcount;
struct completion free;
+ struct {
+ struct list_head list;
+ void (*comp)(struct mlx4_cq *);
+ void *priv;
+ } tasklet_ctx;
};
struct mlx4_qp {
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 05/10] net/mlx4: Add a check if there are too many reserved QPs
From: Or Gerlitz @ 2014-12-04 13:13 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Matan Barak, Amir Vadai, Tal Alon, Jack Morgenstein,
Dotan Barak, Or Gerlitz
In-Reply-To: <1417698835-11050-1-git-send-email-ogerlitz@mellanox.com>
From: Dotan Barak <dotanb@dev.mellanox.co.il>
The number of reserved QPs is affected both from the firmware and
from the driver's requirements. This patch adds a check that
validates that this number is indeed feasable.
Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/qp.c | 8 +++++++-
1 files changed, 7 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 40e82ed..8720428 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -478,6 +478,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
int err;
int reserved_from_top = 0;
+ int reserved_from_bot;
int k;
spin_lock_init(&qp_table->lock);
@@ -534,9 +535,14 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
* b. All the proxy SQPs (8 per function)
* c. All the tunnel QPs (8 per function)
*/
+ reserved_from_bot = mlx4_num_reserved_sqps(dev);
+ if (reserved_from_bot + reserved_from_top > dev->caps.num_qps) {
+ mlx4_err(dev, "Number of reserved QPs is higher than number of QPs\n");
+ return -EINVAL;
+ }
err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
- (1 << 23) - 1, mlx4_num_reserved_sqps(dev),
+ (1 << 23) - 1, reserved_from_bot,
reserved_from_top);
if (err)
return err;
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 06/10] net/mlx4: Add mlx4_bitmap zone allocator
From: Or Gerlitz @ 2014-12-04 13:13 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Matan Barak, Amir Vadai, Tal Alon, Jack Morgenstein,
Or Gerlitz
In-Reply-To: <1417698835-11050-1-git-send-email-ogerlitz@mellanox.com>
From: Matan Barak <matanb@mellanox.com>
The zone allocator is a mechanism which manages a few mlx4_bitmaps.
When allocating a resource, the user indicates the desired zone of
which this resource will be allocated from. If possible, the resource
will be allocated from this zone. Otherwise, the resource will be
allocated from a less-than, equal-to, higher-than priority zone,
according to the desired zone's properties with that respective
allocation order.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/alloc.c | 392 ++++++++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 69 +++++
2 files changed, 461 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index 91a8acc..665e9da 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -149,6 +149,21 @@ u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap)
return bitmap->avail;
}
+static u32 mlx4_bitmap_max(struct mlx4_bitmap *bitmap)
+{
+ return bitmap->max;
+}
+
+static u32 mlx4_bitmap_effective_len(struct mlx4_bitmap *bitmap)
+{
+ return bitmap->effective_len;
+}
+
+static u32 mlx4_bitmap_masked_value(struct mlx4_bitmap *bitmap, u32 obj)
+{
+ return obj & (bitmap->max + bitmap->reserved_top - 1);
+}
+
void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt,
int use_rr)
{
@@ -178,6 +193,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
bitmap->mask = mask;
bitmap->reserved_top = reserved_top;
bitmap->avail = num - reserved_top - reserved_bot;
+ bitmap->effective_len = bitmap->avail;
spin_lock_init(&bitmap->lock);
bitmap->table = kzalloc(BITS_TO_LONGS(bitmap->max) *
sizeof (long), GFP_KERNEL);
@@ -194,6 +210,382 @@ void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap)
kfree(bitmap->table);
}
+struct mlx4_zone_allocator {
+ struct list_head entries;
+ struct list_head prios;
+ u32 last_uid;
+ u32 mask;
+ /* protect the zone_allocator from concurrent accesses */
+ spinlock_t lock;
+ enum mlx4_zone_alloc_flags flags;
+};
+
+struct mlx4_zone_entry {
+ struct list_head list;
+ struct list_head prio_list;
+ u32 uid;
+ struct mlx4_zone_allocator *allocator;
+ struct mlx4_bitmap *bitmap;
+ int use_rr;
+ int priority;
+ int offset;
+ enum mlx4_zone_flags flags;
+};
+
+struct mlx4_zone_allocator *mlx4_zone_allocator_create(enum mlx4_zone_alloc_flags flags)
+{
+ struct mlx4_zone_allocator *zones = kmalloc(sizeof(*zones), GFP_KERNEL);
+
+ if (NULL == zones)
+ return NULL;
+
+ INIT_LIST_HEAD(&zones->entries);
+ INIT_LIST_HEAD(&zones->prios);
+ spin_lock_init(&zones->lock);
+ zones->last_uid = 0;
+ zones->mask = 0;
+ zones->flags = flags;
+
+ return zones;
+}
+
+int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc,
+ struct mlx4_bitmap *bitmap,
+ u32 flags,
+ int priority,
+ int offset,
+ u32 *puid)
+{
+ u32 mask = mlx4_bitmap_masked_value(bitmap, (u32)-1);
+ struct mlx4_zone_entry *it;
+ struct mlx4_zone_entry *zone = kmalloc(sizeof(*zone), GFP_KERNEL);
+
+ if (NULL == zone)
+ return -ENOMEM;
+
+ zone->flags = flags;
+ zone->bitmap = bitmap;
+ zone->use_rr = (flags & MLX4_ZONE_USE_RR) ? MLX4_USE_RR : 0;
+ zone->priority = priority;
+ zone->offset = offset;
+
+ spin_lock(&zone_alloc->lock);
+
+ zone->uid = zone_alloc->last_uid++;
+ zone->allocator = zone_alloc;
+
+ if (zone_alloc->mask < mask)
+ zone_alloc->mask = mask;
+
+ list_for_each_entry(it, &zone_alloc->prios, prio_list)
+ if (it->priority >= priority)
+ break;
+
+ if (&it->prio_list == &zone_alloc->prios || it->priority > priority)
+ list_add_tail(&zone->prio_list, &it->prio_list);
+ list_add_tail(&zone->list, &it->list);
+
+ spin_unlock(&zone_alloc->lock);
+
+ *puid = zone->uid;
+
+ return 0;
+}
+
+/* Should be called under a lock */
+static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry)
+{
+ struct mlx4_zone_allocator *zone_alloc = entry->allocator;
+
+ if (!list_empty(&entry->prio_list)) {
+ /* Check if we need to add an alternative node to the prio list */
+ if (!list_is_last(&entry->list, &zone_alloc->entries)) {
+ struct mlx4_zone_entry *next = list_first_entry(&entry->list,
+ typeof(*next),
+ list);
+
+ if (next->priority == entry->priority)
+ list_add_tail(&next->prio_list, &entry->prio_list);
+ }
+
+ list_del(&entry->prio_list);
+ }
+
+ list_del(&entry->list);
+
+ if (zone_alloc->flags & MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP) {
+ u32 mask = 0;
+ struct mlx4_zone_entry *it;
+
+ list_for_each_entry(it, &zone_alloc->prios, prio_list) {
+ u32 cur_mask = mlx4_bitmap_masked_value(it->bitmap, (u32)-1);
+
+ if (mask < cur_mask)
+ mask = cur_mask;
+ }
+ zone_alloc->mask = mask;
+ }
+
+ return 0;
+}
+
+void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc)
+{
+ struct mlx4_zone_entry *zone, *tmp;
+
+ spin_lock(&zone_alloc->lock);
+
+ list_for_each_entry_safe(zone, tmp, &zone_alloc->entries, list) {
+ list_del(&zone->list);
+ list_del(&zone->prio_list);
+ kfree(zone);
+ }
+
+ spin_unlock(&zone_alloc->lock);
+ kfree(zone_alloc);
+}
+
+/* Should be called under a lock */
+static u32 __mlx4_alloc_from_zone(struct mlx4_zone_entry *zone, int count,
+ int align, u32 skip_mask, u32 *puid)
+{
+ u32 uid;
+ u32 res;
+ struct mlx4_zone_allocator *zone_alloc = zone->allocator;
+ struct mlx4_zone_entry *curr_node;
+
+ res = mlx4_bitmap_alloc_range(zone->bitmap, count,
+ align, skip_mask);
+
+ if (res != (u32)-1) {
+ res += zone->offset;
+ uid = zone->uid;
+ goto out;
+ }
+
+ list_for_each_entry(curr_node, &zone_alloc->prios, prio_list) {
+ if (unlikely(curr_node->priority == zone->priority))
+ break;
+ }
+
+ if (zone->flags & MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO) {
+ struct mlx4_zone_entry *it = curr_node;
+
+ list_for_each_entry_continue_reverse(it, &zone_alloc->entries, list) {
+ res = mlx4_bitmap_alloc_range(it->bitmap, count,
+ align, skip_mask);
+ if (res != (u32)-1) {
+ res += it->offset;
+ uid = it->uid;
+ goto out;
+ }
+ }
+ }
+
+ if (zone->flags & MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO) {
+ struct mlx4_zone_entry *it = curr_node;
+
+ list_for_each_entry_from(it, &zone_alloc->entries, list) {
+ if (unlikely(it == zone))
+ continue;
+
+ if (unlikely(it->priority != curr_node->priority))
+ break;
+
+ res = mlx4_bitmap_alloc_range(it->bitmap, count,
+ align, skip_mask);
+ if (res != (u32)-1) {
+ res += it->offset;
+ uid = it->uid;
+ goto out;
+ }
+ }
+ }
+
+ if (zone->flags & MLX4_ZONE_FALLBACK_TO_HIGHER_PRIO) {
+ if (list_is_last(&curr_node->prio_list, &zone_alloc->prios))
+ goto out;
+
+ curr_node = list_first_entry(&curr_node->prio_list,
+ typeof(*curr_node),
+ prio_list);
+
+ list_for_each_entry_from(curr_node, &zone_alloc->entries, list) {
+ res = mlx4_bitmap_alloc_range(curr_node->bitmap, count,
+ align, skip_mask);
+ if (res != (u32)-1) {
+ res += curr_node->offset;
+ uid = curr_node->uid;
+ goto out;
+ }
+ }
+ }
+
+out:
+ if (NULL != puid && res != (u32)-1)
+ *puid = uid;
+ return res;
+}
+
+/* Should be called under a lock */
+static void __mlx4_free_from_zone(struct mlx4_zone_entry *zone, u32 obj,
+ u32 count)
+{
+ mlx4_bitmap_free_range(zone->bitmap, obj - zone->offset, count, zone->use_rr);
+}
+
+/* Should be called under a lock */
+static struct mlx4_zone_entry *__mlx4_find_zone_by_uid(
+ struct mlx4_zone_allocator *zones, u32 uid)
+{
+ struct mlx4_zone_entry *zone;
+
+ list_for_each_entry(zone, &zones->entries, list) {
+ if (zone->uid == uid)
+ return zone;
+ }
+
+ return NULL;
+}
+
+struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 uid)
+{
+ struct mlx4_zone_entry *zone;
+ struct mlx4_bitmap *bitmap;
+
+ spin_lock(&zones->lock);
+
+ zone = __mlx4_find_zone_by_uid(zones, uid);
+
+ bitmap = zone == NULL ? NULL : zone->bitmap;
+
+ spin_unlock(&zones->lock);
+
+ return bitmap;
+}
+
+int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid)
+{
+ struct mlx4_zone_entry *zone;
+ int res;
+
+ spin_lock(&zones->lock);
+
+ zone = __mlx4_find_zone_by_uid(zones, uid);
+
+ if (NULL == zone) {
+ res = -1;
+ goto out;
+ }
+
+ res = __mlx4_zone_remove_one_entry(zone);
+
+out:
+ spin_unlock(&zones->lock);
+ kfree(zone);
+
+ return res;
+}
+
+/* Should be called under a lock */
+static struct mlx4_zone_entry *__mlx4_find_zone_by_uid_unique(
+ struct mlx4_zone_allocator *zones, u32 obj)
+{
+ struct mlx4_zone_entry *zone, *zone_candidate = NULL;
+ u32 dist = (u32)-1;
+
+ /* Search for the smallest zone that this obj could be
+ * allocated from. This is done in order to handle
+ * situations when small bitmaps are allocated from bigger
+ * bitmaps (and the allocated space is marked as reserved in
+ * the bigger bitmap.
+ */
+ list_for_each_entry(zone, &zones->entries, list) {
+ if (obj >= zone->offset) {
+ u32 mobj = (obj - zone->offset) & zones->mask;
+
+ if (mobj < mlx4_bitmap_max(zone->bitmap)) {
+ u32 curr_dist = mlx4_bitmap_effective_len(zone->bitmap);
+
+ if (curr_dist < dist) {
+ dist = curr_dist;
+ zone_candidate = zone;
+ }
+ }
+ }
+ }
+
+ return zone_candidate;
+}
+
+u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
+ int align, u32 skip_mask, u32 *puid)
+{
+ struct mlx4_zone_entry *zone;
+ int res = -1;
+
+ spin_lock(&zones->lock);
+
+ zone = __mlx4_find_zone_by_uid(zones, uid);
+
+ if (NULL == zone)
+ goto out;
+
+ res = __mlx4_alloc_from_zone(zone, count, align, skip_mask, puid);
+
+out:
+ spin_unlock(&zones->lock);
+
+ return res;
+}
+
+u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones, u32 uid, u32 obj, u32 count)
+{
+ struct mlx4_zone_entry *zone;
+ int res = 0;
+
+ spin_lock(&zones->lock);
+
+ zone = __mlx4_find_zone_by_uid(zones, uid);
+
+ if (NULL == zone) {
+ res = -1;
+ goto out;
+ }
+
+ __mlx4_free_from_zone(zone, obj, count);
+
+out:
+ spin_unlock(&zones->lock);
+
+ return res;
+}
+
+u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count)
+{
+ struct mlx4_zone_entry *zone;
+ int res;
+
+ if (!(zones->flags & MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP))
+ return -EFAULT;
+
+ spin_lock(&zones->lock);
+
+ zone = __mlx4_find_zone_by_uid_unique(zones, obj);
+
+ if (NULL == zone) {
+ res = -1;
+ goto out;
+ }
+
+ __mlx4_free_from_zone(zone, obj, count);
+ res = 0;
+
+out:
+ spin_unlock(&zones->lock);
+
+ return res;
+}
/*
* Handling for queue buffers -- we allocate a bunch of memory and
* register it in a memory region at HCA virtual address 0. If the
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 6834da6..bc1505e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -245,6 +245,7 @@ struct mlx4_bitmap {
u32 reserved_top;
u32 mask;
u32 avail;
+ u32 effective_len;
spinlock_t lock;
unsigned long *table;
};
@@ -1345,4 +1346,72 @@ int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
int mlx4_config_mad_demux(struct mlx4_dev *dev);
+enum mlx4_zone_flags {
+ MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO = 1UL << 0,
+ MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO = 1UL << 1,
+ MLX4_ZONE_FALLBACK_TO_HIGHER_PRIO = 1UL << 2,
+ MLX4_ZONE_USE_RR = 1UL << 3,
+};
+
+enum mlx4_zone_alloc_flags {
+ /* No two objects could overlap between zones. UID
+ * could be left unused. If this flag is given and
+ * two overlapped zones are used, an object will be free'd
+ * from the smallest possible matching zone.
+ */
+ MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP = 1UL << 0,
+};
+
+struct mlx4_zone_allocator;
+
+/* Create a new zone allocator */
+struct mlx4_zone_allocator *mlx4_zone_allocator_create(enum mlx4_zone_alloc_flags flags);
+
+/* Attach a mlx4_bitmap <bitmap> of priority <priority> to the zone allocator
+ * <zone_alloc>. Allocating an object from this zone adds an offset <offset>.
+ * Similarly, when searching for an object to free, this offset it taken into
+ * account. The use_rr mlx4_ib parameter for allocating objects from this <bitmap>
+ * is given through the MLX4_ZONE_USE_RR flag in <flags>.
+ * When an allocation fails, <zone_alloc> tries to allocate from other zones
+ * according to the policy set by <flags>. <puid> is the unique identifier
+ * received to this zone.
+ */
+int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc,
+ struct mlx4_bitmap *bitmap,
+ u32 flags,
+ int priority,
+ int offset,
+ u32 *puid);
+
+/* Remove bitmap indicated by <uid> from <zone_alloc> */
+int mlx4_zone_remove_one(struct mlx4_zone_allocator *zone_alloc, u32 uid);
+
+/* Delete the zone allocator <zone_alloc. This function doesn't destroy
+ * the attached bitmaps.
+ */
+void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc);
+
+/* Allocate <count> objects with align <align> and skip_mask <skip_mask>
+ * from the mlx4_bitmap whose uid is <uid>. The bitmap which we actually
+ * allocated from is returned in <puid>. If the allocation fails, a negative
+ * number is returned. Otherwise, the offset of the first object is returned.
+ */
+u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
+ int align, u32 skip_mask, u32 *puid);
+
+/* Free <count> objects, start from <obj> of the uid <uid> from zone_allocator
+ * <zones>.
+ */
+u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones,
+ u32 uid, u32 obj, u32 count);
+
+/* If <zones> was allocated with MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP, instead of
+ * specifying the uid when freeing an object, zone allocator could figure it by
+ * itself. Other parameters are similar to mlx4_zone_free.
+ */
+u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count);
+
+/* Returns a pointer to mlx4_bitmap that was attached to <zones> with <uid> */
+struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 uid);
+
#endif /* MLX4_H */
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 10/10] net/mlx4: Add support for A0 steering
From: Or Gerlitz @ 2014-12-04 13:13 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Matan Barak, Amir Vadai, Tal Alon, Jack Morgenstein,
Or Gerlitz
In-Reply-To: <1417698835-11050-1-git-send-email-ogerlitz@mellanox.com>
From: Matan Barak <matanb@mellanox.com>
Add the required firmware commands for A0 steering and a way to enable
that. The firmware support focuses on INIT_HCA, QUERY_HCA, QUERY_PORT,
QUERY_DEV_CAP and QUERY_FUNC_CAP commands. Those commands are used
to configure and query the device.
The different A0 DMFS (steering) modes are:
Static - optimized performance, but flow steering rules are
limited. This mode should be choosed explicitly by the user
in order to be used.
Dynamic - this mode should be explicitly choosed by the user.
In this mode, the FW works in optimized steering mode as long as
it can and afterwards automatically drops to classic (full) DMFS.
Disable - this mode should be explicitly choosed by the user.
The user instructs the system not to use optimized steering, even if
the FW supports Dynamic A0 DMFS (and thus will be able to use optimized
steering in Default A0 DMFS mode).
Default - this mode is implicitly choosed. In this mode, if the FW
supports Dynamic A0 DMFS, it'll work in this mode. Otherwise, it'll
work at Disable A0 DMFS mode.
In order to enable A0 steering, we use log_num_mgm_entry_size param.
If the value of the parameter is not positive, we treat the absolute
value of log_num_mgm_entry_size as a bit field. Setting bit 2 of this
bit field enables static A0 steering.
issue: 387689
Change-Id: I52f21ab5eeaa108f555fe157c07daa65dfe8c322
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 3 +-
drivers/net/ethernet/mellanox/mlx4/fw.c | 48 ++++++++-
drivers/net/ethernet/mellanox/mlx4/fw.h | 4 +
drivers/net/ethernet/mellanox/mlx4/main.c | 131 ++++++++++++++++++++++--
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 -
drivers/net/ethernet/mellanox/mlx4/qp.c | 4 +-
include/linux/mlx4/device.h | 17 +++-
7 files changed, 190 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 5701115..08aa6f8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2594,7 +2594,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
if (mdev->dev->caps.steering_mode ==
- MLX4_STEERING_MODE_DEVICE_MANAGED)
+ MLX4_STEERING_MODE_DEVICE_MANAGED &&
+ mdev->dev->caps.dmfs_high_steer_mode != MLX4_STEERING_DMFS_A0_STATIC)
dev->hw_features |= NETIF_F_NTUPLE;
if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index e07cb9b..b303b34 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -144,7 +144,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
[15] = "Ethernet Backplane autoneg support",
[16] = "CONFIG DEV support",
[17] = "Asymmetric EQs support",
- [18] = "More than 80 VFs support"
+ [18] = "More than 80 VFs support",
+ [19] = "Performance optimized for limited rule configuration flow steering support"
};
int i;
@@ -680,6 +681,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
#define QUERY_DEV_CAP_FW_REASSIGN_MAC 0x9d
#define QUERY_DEV_CAP_VXLAN 0x9e
#define QUERY_DEV_CAP_MAD_DEMUX_OFFSET 0xb0
+#define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET 0xa8
+#define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET 0xac
dev_cap->flags2 = 0;
mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -876,6 +879,13 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
if (field32 & (1 << 0))
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_MAD_DEMUX;
+ MLX4_GET(dev_cap->dmfs_high_rate_qpn_base, outbox,
+ QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET);
+ dev_cap->dmfs_high_rate_qpn_base &= MGM_QPN_MASK;
+ MLX4_GET(dev_cap->dmfs_high_rate_qpn_range, outbox,
+ QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET);
+ dev_cap->dmfs_high_rate_qpn_range &= MGM_QPN_MASK;
+
MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
if (field32 & (1 << 16))
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
@@ -935,6 +945,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
mlx4_dbg(dev, "Max GSO size: %d\n", dev_cap->max_gso_sz);
mlx4_dbg(dev, "Max counters: %d\n", dev_cap->max_counters);
mlx4_dbg(dev, "Max RSS Table size: %d\n", dev_cap->max_rss_tbl_sz);
+ mlx4_dbg(dev, "DMFS high rate steer QPn base: %d\n",
+ dev_cap->dmfs_high_rate_qpn_base);
+ mlx4_dbg(dev, "DMFS high rate steer QPn range: %d\n",
+ dev_cap->dmfs_high_rate_qpn_range);
dump_dev_cap_flags(dev, dev_cap->flags);
dump_dev_cap_flags2(dev, dev_cap->flags2);
@@ -996,6 +1010,7 @@ int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_c
port_cap->supported_port_types = field & 3;
port_cap->suggested_type = (field >> 3) & 1;
port_cap->default_sense = (field >> 4) & 1;
+ port_cap->dmfs_optimized_state = (field >> 5) & 1;
MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
port_cap->ib_mtu = field & 0xf;
MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
@@ -1525,6 +1540,12 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
struct mlx4_cmd_mailbox *mailbox;
__be32 *inbox;
int err;
+ static const u8 a0_dmfs_hw_steering[] = {
+ [MLX4_STEERING_DMFS_A0_DEFAULT] = 0,
+ [MLX4_STEERING_DMFS_A0_DYNAMIC] = 1,
+ [MLX4_STEERING_DMFS_A0_STATIC] = 2,
+ [MLX4_STEERING_DMFS_A0_DISABLE] = 3
+ };
#define INIT_HCA_IN_SIZE 0x200
#define INIT_HCA_VERSION_OFFSET 0x000
@@ -1558,6 +1579,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
#define INIT_HCA_FS_PARAM_OFFSET 0x1d0
#define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00)
#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12)
+#define INIT_HCA_FS_A0_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x18)
#define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b)
#define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21)
#define INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x22)
@@ -1668,8 +1690,11 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
/* Enable Ethernet flow steering
* with udp unicast and tcp unicast
*/
- MLX4_PUT(inbox, (u8) (MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN),
- INIT_HCA_FS_ETH_BITS_OFFSET);
+ if (dev->caps.dmfs_high_steer_mode !=
+ MLX4_STEERING_DMFS_A0_STATIC)
+ MLX4_PUT(inbox,
+ (u8)(MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN),
+ INIT_HCA_FS_ETH_BITS_OFFSET);
MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET);
/* Enable IPoIB flow steering
@@ -1679,6 +1704,13 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
INIT_HCA_FS_IB_BITS_OFFSET);
MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
INIT_HCA_FS_IB_NUM_ADDRS_OFFSET);
+
+ if (dev->caps.dmfs_high_steer_mode !=
+ MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+ MLX4_PUT(inbox,
+ ((u8)(a0_dmfs_hw_steering[dev->caps.dmfs_high_steer_mode]
+ << 6)),
+ INIT_HCA_FS_A0_OFFSET);
} else {
MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET);
MLX4_PUT(inbox, param->log_mc_entry_sz,
@@ -1729,6 +1761,12 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
u32 dword_field;
int err;
u8 byte_field;
+ static const u8 a0_dmfs_query_hw_steering[] = {
+ [0] = MLX4_STEERING_DMFS_A0_DEFAULT,
+ [1] = MLX4_STEERING_DMFS_A0_DYNAMIC,
+ [2] = MLX4_STEERING_DMFS_A0_STATIC,
+ [3] = MLX4_STEERING_DMFS_A0_DISABLE
+ };
#define QUERY_HCA_GLOBAL_CAPS_OFFSET 0x04
#define QUERY_HCA_CORE_CLOCK_OFFSET 0x0c
@@ -1781,6 +1819,10 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
MLX4_GET(param->log_mc_table_sz, outbox,
INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+ MLX4_GET(byte_field, outbox,
+ INIT_HCA_FS_A0_OFFSET);
+ param->dmfs_high_steer_mode =
+ a0_dmfs_query_hw_steering[(byte_field >> 6) & 3];
} else {
MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
MLX4_GET(param->log_mc_entry_sz, outbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 744398b..794e282 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -60,6 +60,7 @@ struct mlx4_port_cap {
int vendor_oui;
u16 wavelength;
u64 trans_code;
+ u8 dmfs_optimized_state;
};
struct mlx4_dev_cap {
@@ -124,6 +125,8 @@ struct mlx4_dev_cap {
int max_gso_sz;
int max_rss_tbl_sz;
u32 max_counters;
+ u32 dmfs_high_rate_qpn_base;
+ u32 dmfs_high_rate_qpn_range;
struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
};
@@ -194,6 +197,7 @@ struct mlx4_init_hca_param {
u8 mw_enabled; /* Enable memory windows */
u8 uar_page_sz; /* log pg sz in 4k chunks */
u8 steering_mode; /* for QUERY_HCA */
+ u8 dmfs_high_steer_mode; /* for QUERY_HCA */
u64 dev_cap_enabled;
u16 cqe_size; /* For use only when CQE stride feature enabled */
u16 eqe_size; /* For use only when EQE stride feature enabled */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6173b80..3845fe8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -105,7 +105,8 @@ MODULE_PARM_DESC(enable_64b_cqe_eqe,
"Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
#define PF_CONTEXT_BEHAVIOUR_MASK (MLX4_FUNC_CAP_64B_EQE_CQE | \
- MLX4_FUNC_CAP_EQE_CQE_STRIDE)
+ MLX4_FUNC_CAP_EQE_CQE_STRIDE | \
+ MLX4_FUNC_CAP_DMFS_A0_STATIC)
static char mlx4_version[] =
DRV_NAME ": Mellanox ConnectX core driver v"
@@ -463,8 +464,28 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
(1 << dev->caps.log_num_vlans) *
dev->caps.num_ports;
dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;
+
+ if (dev_cap->dmfs_high_rate_qpn_base > 0 &&
+ dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN)
+ dev->caps.dmfs_high_rate_qpn_base = dev_cap->dmfs_high_rate_qpn_base;
+ else
+ dev->caps.dmfs_high_rate_qpn_base =
+ dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+
+ if (dev_cap->dmfs_high_rate_qpn_range > 0 &&
+ dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
+ dev->caps.dmfs_high_rate_qpn_range = dev_cap->dmfs_high_rate_qpn_range;
+ dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DEFAULT;
+ dev->caps.flags2 |= MLX4_DEV_CAP_FLAG2_FS_A0;
+ } else {
+ dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_NOT_SUPPORTED;
+ dev->caps.dmfs_high_rate_qpn_base =
+ dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+ dev->caps.dmfs_high_rate_qpn_range = MLX4_A0_STEERING_TABLE_SIZE;
+ }
+
dev->caps.reserved_qps_cnt[MLX4_QP_REGION_RSS_RAW_ETH] =
- MLX4_A0_STEERING_TABLE_SIZE;
+ dev->caps.dmfs_high_rate_qpn_range;
dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
@@ -753,7 +774,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) !=
PF_CONTEXT_BEHAVIOUR_MASK) {
- mlx4_err(dev, "Unknown pf context behaviour\n");
+ mlx4_err(dev, "Unknown pf context behaviour %x\n", func_cap.pf_context_behaviour);
return -ENOSYS;
}
@@ -1640,10 +1661,46 @@ static int choose_log_fs_mgm_entry_size(int qp_per_entry)
return (i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE) ? i : -1;
}
+static const char *dmfs_high_rate_steering_mode_str(int dmfs_high_steer_mode)
+{
+ switch (dmfs_high_steer_mode) {
+ case MLX4_STEERING_DMFS_A0_DEFAULT:
+ return "default performance";
+
+ case MLX4_STEERING_DMFS_A0_DYNAMIC:
+ return "dynamic hybrid mode";
+
+ case MLX4_STEERING_DMFS_A0_STATIC:
+ return "performance optimized for limited rule configuration (static)";
+
+ case MLX4_STEERING_DMFS_A0_DISABLE:
+ return "disabled performance optimized steering";
+
+ case MLX4_STEERING_DMFS_A0_NOT_SUPPORTED:
+ return "performance optimized steering not supported";
+
+ default:
+ return "Unrecognized mode";
+ }
+}
+
+#define MLX4_DMFS_A0_STEERING (1UL << 2)
+
static void choose_steering_mode(struct mlx4_dev *dev,
struct mlx4_dev_cap *dev_cap)
{
- if (mlx4_log_num_mgm_entry_size == -1 &&
+ if (mlx4_log_num_mgm_entry_size <= 0) {
+ if ((-mlx4_log_num_mgm_entry_size) & MLX4_DMFS_A0_STEERING) {
+ if (dev->caps.dmfs_high_steer_mode ==
+ MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+ mlx4_err(dev, "DMFS high rate mode not supported\n");
+ else
+ dev->caps.dmfs_high_steer_mode =
+ MLX4_STEERING_DMFS_A0_STATIC;
+ }
+ }
+
+ if (mlx4_log_num_mgm_entry_size <= 0 &&
dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
(!mlx4_is_mfunc(dev) ||
(dev_cap->fs_max_num_qp_per_entry >= (dev->num_vfs + 1))) &&
@@ -1656,6 +1713,9 @@ static void choose_steering_mode(struct mlx4_dev *dev,
dev->caps.fs_log_max_ucast_qp_range_size =
dev_cap->fs_log_max_ucast_qp_range_size;
} else {
+ if (dev->caps.dmfs_high_steer_mode !=
+ MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+ dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DISABLE;
if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
@@ -1682,7 +1742,8 @@ static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
struct mlx4_dev_cap *dev_cap)
{
if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED &&
- dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
+ dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS &&
+ dev->caps.dmfs_high_steer_mode != MLX4_STEERING_DMFS_A0_STATIC)
dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_VXLAN;
else
dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_NONE;
@@ -1691,6 +1752,35 @@ static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
== MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) ? "vxlan" : "none");
}
+static int mlx4_validate_optimized_steering(struct mlx4_dev *dev)
+{
+ int i;
+ struct mlx4_port_cap port_cap;
+
+ if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+ return -EINVAL;
+
+ for (i = 1; i <= dev->caps.num_ports; i++) {
+ if (mlx4_dev_port(dev, i, &port_cap)) {
+ mlx4_err(dev,
+ "QUERY_DEV_CAP command failed, can't veify DMFS high rate steering.\n");
+ } else if ((dev->caps.dmfs_high_steer_mode !=
+ MLX4_STEERING_DMFS_A0_DEFAULT) &&
+ (port_cap.dmfs_optimized_state ==
+ !!(dev->caps.dmfs_high_steer_mode ==
+ MLX4_STEERING_DMFS_A0_DISABLE))) {
+ mlx4_err(dev,
+ "DMFS high rate steer mode differ, driver requested %s but %s in FW.\n",
+ dmfs_high_rate_steering_mode_str(
+ dev->caps.dmfs_high_steer_mode),
+ (port_cap.dmfs_optimized_state ?
+ "enabled" : "disabled"));
+ }
+ }
+
+ return 0;
+}
+
static int mlx4_init_fw(struct mlx4_dev *dev)
{
struct mlx4_mod_stat_cfg mlx4_cfg;
@@ -1743,6 +1833,10 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
choose_steering_mode(dev, &dev_cap);
choose_tunnel_offload_mode(dev, &dev_cap);
+ if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC &&
+ mlx4_is_master(dev))
+ dev->caps.function_caps |= MLX4_FUNC_CAP_DMFS_A0_STATIC;
+
err = mlx4_get_phys_port_id(dev);
if (err)
mlx4_err(dev, "Fail to get physical port id\n");
@@ -1829,6 +1923,24 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported\n");
}
}
+
+ if (dev->caps.dmfs_high_steer_mode !=
+ MLX4_STEERING_DMFS_A0_NOT_SUPPORTED) {
+ if (mlx4_validate_optimized_steering(dev))
+ mlx4_warn(dev, "Optimized steering validation failed\n");
+
+ if (dev->caps.dmfs_high_steer_mode ==
+ MLX4_STEERING_DMFS_A0_DISABLE) {
+ dev->caps.dmfs_high_rate_qpn_base =
+ dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+ dev->caps.dmfs_high_rate_qpn_range =
+ MLX4_A0_STEERING_TABLE_SIZE;
+ }
+
+ mlx4_dbg(dev, "DMFS high rate steer mode is: %s\n",
+ dmfs_high_rate_steering_mode_str(
+ dev->caps.dmfs_high_steer_mode));
+ }
} else {
err = mlx4_init_slave(dev);
if (err) {
@@ -3201,10 +3313,11 @@ static int __init mlx4_verify_params(void)
port_type_array[0] = true;
}
- if (mlx4_log_num_mgm_entry_size != -1 &&
- (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
- mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) {
- pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-1 or %d..%d)\n",
+ if (mlx4_log_num_mgm_entry_size < -7 ||
+ (mlx4_log_num_mgm_entry_size > 0 &&
+ (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
+ mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE))) {
+ pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-7..0 or %d..%d)\n",
mlx4_log_num_mgm_entry_size,
MLX4_MIN_MGM_LOG_ENTRY_SIZE,
MLX4_MAX_MGM_LOG_ENTRY_SIZE);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index cebd118..bdd4eea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -689,8 +689,6 @@ enum mlx4_qp_table_zones {
MLX4_QP_TABLE_ZONE_NUM
};
-#define MLX4_A0_STEERING_TABLE_SIZE 256
-
struct mlx4_qp_table {
struct mlx4_bitmap *bitmap_gen;
struct mlx4_zone_allocator *zones;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index d8d040c..1586ecc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -712,8 +712,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
int k;
int fixed_reserved_from_bot_rv = 0;
int bottom_reserved_for_rss_bitmap;
- u32 max_table_offset = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
- MLX4_A0_STEERING_TABLE_SIZE;
+ u32 max_table_offset = dev->caps.dmfs_high_rate_qpn_base +
+ dev->caps.dmfs_high_rate_qpn_range;
spin_lock_init(&qp_table->lock);
INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 39890cd..25c791e 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -117,6 +117,14 @@ enum {
MLX4_STEERING_MODE_DEVICE_MANAGED
};
+enum {
+ MLX4_STEERING_DMFS_A0_DEFAULT,
+ MLX4_STEERING_DMFS_A0_DYNAMIC,
+ MLX4_STEERING_DMFS_A0_STATIC,
+ MLX4_STEERING_DMFS_A0_DISABLE,
+ MLX4_STEERING_DMFS_A0_NOT_SUPPORTED
+};
+
static inline const char *mlx4_steering_mode_str(int steering_mode)
{
switch (steering_mode) {
@@ -191,7 +199,8 @@ enum {
MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP = 1LL << 15,
MLX4_DEV_CAP_FLAG2_CONFIG_DEV = 1LL << 16,
MLX4_DEV_CAP_FLAG2_SYS_EQS = 1LL << 17,
- MLX4_DEV_CAP_FLAG2_80_VFS = 1LL << 18
+ MLX4_DEV_CAP_FLAG2_80_VFS = 1LL << 18,
+ MLX4_DEV_CAP_FLAG2_FS_A0 = 1LL << 19
};
enum {
@@ -225,7 +234,8 @@ enum {
enum {
MLX4_FUNC_CAP_64B_EQE_CQE = 1L << 0,
- MLX4_FUNC_CAP_EQE_CQE_STRIDE = 1L << 1
+ MLX4_FUNC_CAP_EQE_CQE_STRIDE = 1L << 1,
+ MLX4_FUNC_CAP_DMFS_A0_STATIC = 1L << 2
};
@@ -482,6 +492,7 @@ struct mlx4_caps {
int reserved_mcgs;
int num_qp_per_mgm;
int steering_mode;
+ int dmfs_high_steer_mode;
int fs_log_max_ucast_qp_range_size;
int num_pds;
int reserved_pds;
@@ -522,6 +533,8 @@ struct mlx4_caps {
int tunnel_offload_mode;
u8 rx_checksum_flags_port[MLX4_MAX_PORTS + 1];
u8 alloc_res_qp_mask;
+ u32 dmfs_high_rate_qpn_base;
+ u32 dmfs_high_rate_qpn_range;
};
struct mlx4_buf_list {
--
1.7.1
^ permalink raw reply related
* Re: Where exactly will arch_fast_hash be used
From: Daniel Borkmann @ 2014-12-04 13:14 UTC (permalink / raw)
To: Hannes Frederic Sowa
Cc: Herbert Xu, Thomas Graf, David S. Miller, Theodore Ts'o,
netdev, Linux Kernel Mailing List, fusco
In-Reply-To: <1417696468.5386.23.camel@localhost>
On 12/04/2014 01:34 PM, Hannes Frederic Sowa wrote:
> On Do, 2014-12-04 at 16:11 +0800, Herbert Xu wrote:
>> While working on rhashtable it came to me that this whole concept
>> of arch_fast_hash is flawed. CRCs are linear functions so it's
>> fairly easy for an attacker to identify collisions or at least
>> eliminate a large amount of search space (e.g., controlling the
>> last bit of the hash result is almost trivial, even when you add
>> a random seed).
>>
>> So what exactly are we going to use arch_fast_hash for? Presumably
>> it's places where security is never goint to be an issue, right?
The original proposal [1] targeted ovs-only as a closed-door user in
order to speed up the worst case of calculating a hash over the extracted
flow key, that is, struct sw_flow_key (which nowadays consumes up to
7 cachelines on x86_64 ...).
[1] http://thread.gmane.org/gmane.linux.network/293981/
>> Even if security wasn't an issue, straight CRC32 has really poor
>> lower-order bit distribution, which makes it a terrible choice for
>> a hash table that simply uses the lower-order bits.
>
> I wondered the same while trying to use arch_fast_hash in a lot more
> places (I did a new implementation in assembler I'll send later on, it
> is mostly optimized to deal with ovs flow keys).
>
> While the uniformity of crc32 does actually look good and IMHO this even
> holds for the lower bits of the hash, I totally agree on the linearity
> matters.
>
> The easiest way to make arch_fast_hash non-linear would be to build up
> on the crc32 instruction like e.g. the cityhash function family does and
> it seems not too hard to do that by combining two crc32c outputs of the
> original and cyclic shifted input data. I have doubts if this is faster
> than jhash in the end. There are proposals from Intel to do so, but they
> are patent encumbered. :/
>
> For most consumers in the networking stack, security and DoS resistence
> is an issue. OVS, for which this was designed at first does do rehashing
> from time to time, but still there is a possible DoS attack vector with
> this hashing algorithm.
^ permalink raw reply
* [PATCH net-next 08/10] net/mlx4_core: Add explicit error message when rule doesn't meet configuration
From: Or Gerlitz @ 2014-12-04 13:13 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Matan Barak, Amir Vadai, Tal Alon, Jack Morgenstein,
Or Gerlitz
In-Reply-To: <1417698835-11050-1-git-send-email-ogerlitz@mellanox.com>
From: Matan Barak <matanb@mellanox.com>
When a given flow steering rule is invalid in respect to the current
steering configuration, print the correct error message to the system log.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/mcg.c | 21 ++++++++++++++++++---
1 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 8728431..a3867e7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -999,12 +999,27 @@ int mlx4_flow_attach(struct mlx4_dev *dev,
}
ret = mlx4_QP_FLOW_STEERING_ATTACH(dev, mailbox, size >> 2, reg_id);
- if (ret == -ENOMEM)
+ if (ret == -ENOMEM) {
mlx4_err_rule(dev,
"mcg table is full. Fail to register network rule\n",
rule);
- else if (ret)
- mlx4_err_rule(dev, "Fail to register network rule\n", rule);
+ } else if (ret) {
+ if (ret == -ENXIO) {
+ if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED)
+ mlx4_err_rule(dev,
+ "DMFS is not enabled, "
+ "failed to register network rule.\n",
+ rule);
+ else
+ mlx4_err_rule(dev,
+ "Rule exceeds the dmfs_high_rate_mode limitations, "
+ "failed to register network rule.\n",
+ rule);
+
+ } else {
+ mlx4_err_rule(dev, "Fail to register network rule.\n", rule);
+ }
+ }
mlx4_free_cmd_mailbox(dev, mailbox);
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 04/10] net/mlx4: Change QP allocation scheme
From: Or Gerlitz @ 2014-12-04 13:13 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Matan Barak, Amir Vadai, Tal Alon, Jack Morgenstein,
Eugenia Emantayev, Or Gerlitz
In-Reply-To: <1417698835-11050-1-git-send-email-ogerlitz@mellanox.com>
From: Eugenia Emantayev <eugenia@mellanox.co.il>
When using BF (Blue-Flame), the QPN overrides the VLAN, CV, and SV fields
in the WQE. Thus, BF may only be used for QPNs with bits 6,7 unset.
The current Ethernet driver code reserves a Tx QP range with 256b alignment.
This is wrong because if there are more than 64 Tx QPs in use,
QPNs >= base + 65 will have bits 6/7 set.
This problem is not specific for the Ethernet driver, any entity that
tries to reserve more than 64 BF-enabled QPs should fail. Also, using
ranges is not necessary here and is wasteful.
The new mechanism introduced here will support reservation for
"Eth QPs eligible for BF" for all drivers: bare-metal, multi-PF, and VFs
(when hypervisors support WC in VMs). The flow we use is:
1. In mlx4_en, allocate Tx QPs one by one instead of a range allocation,
and request "BF enabled QPs" if BF is supported for the function
2. In the ALLOC_RES FW command, change param1 to:
a. param1[23:0] - number of QPs
b. param1[31-24] - flags controlling QPs reservation
Bit 31 refers to Eth blueflame supported QPs. Those QPs must have
bits 6 and 7 unset in order to be used in Ethernet.
Bits 24-30 of the flags are currently reserved.
When a function tries to allocate a QP, it states the required attributes
for this QP. Those attributes are considered "best-effort". If an attribute,
such as Ethernet BF enabled QP, is a must-have attribute, the function has
to check that attribute is supported before trying to do the allocation.
In a lower layer of the code, mlx4_qp_reserve_range masks out the bits
which are unsupported. If SRIOV is used, the PF validates those attirubtes
and masks out unsupported attributes as well. In order to notify VFs which
attirbutes are supported, the VF uses QUERY_FUNC_CAP command. This command's
mailbox is filled by the PF, which notifies which QP allocation attributes
it supports.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/infiniband/hw/mlx4/main.c | 2 +-
drivers/infiniband/hw/mlx4/qp.c | 11 +++--
drivers/net/ethernet/mellanox/mlx4/alloc.c | 43 +++++++++++++++++---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 10 +----
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 4 +-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 14 +++++-
drivers/net/ethernet/mellanox/mlx4/fw.c | 20 +++++++++-
drivers/net/ethernet/mellanox/mlx4/fw.h | 1 +
drivers/net/ethernet/mellanox/mlx4/main.c | 11 +++++-
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 5 +-
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +-
drivers/net/ethernet/mellanox/mlx4/qp.c | 24 +++++++++--
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 7 +++-
include/linux/mlx4/device.h | 21 +++++++++-
14 files changed, 137 insertions(+), 38 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 0c33755..57ecc5b 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2227,7 +2227,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
MLX4_IB_UC_STEER_QPN_ALIGN,
- &ibdev->steer_qpn_base);
+ &ibdev->steer_qpn_base, 0);
if (err)
goto err_counter;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 9c5150c..506d1bd 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -802,16 +802,19 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
}
}
} else {
- /* Raw packet QPNs must be aligned to 8 bits. If not, the WQE
- * BlueFlame setup flow wrongly causes VLAN insertion. */
+ /* Raw packet QPNs may not have bits 6,7 set in their qp_num;
+ * otherwise, the WQE BlueFlame setup flow wrongly causes
+ * VLAN insertion. */
if (init_attr->qp_type == IB_QPT_RAW_PACKET)
- err = mlx4_qp_reserve_range(dev->dev, 1, 1 << 8, &qpn);
+ err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn,
+ init_attr->cap.max_send_wr ?
+ MLX4_RESERVE_ETH_BF_QP : 0);
else
if (qp->flags & MLX4_IB_QP_NETIF)
err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
else
err = mlx4_qp_reserve_range(dev->dev, 1, 1,
- &qpn);
+ &qpn, 0);
if (err)
goto err_proxy;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index b0297da..91a8acc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -76,22 +76,53 @@ void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr)
mlx4_bitmap_free_range(bitmap, obj, 1, use_rr);
}
-u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
+static unsigned long find_aligned_range(unsigned long *bitmap,
+ u32 start, u32 nbits,
+ int len, int align, u32 skip_mask)
+{
+ unsigned long end, i;
+
+again:
+ start = ALIGN(start, align);
+
+ while ((start < nbits) && (test_bit(start, bitmap) ||
+ (start & skip_mask)))
+ start += align;
+
+ if (start >= nbits)
+ return -1;
+
+ end = start+len;
+ if (end > nbits)
+ return -1;
+
+ for (i = start + 1; i < end; i++) {
+ if (test_bit(i, bitmap) || ((u32)i & skip_mask)) {
+ start = i + 1;
+ goto again;
+ }
+ }
+
+ return start;
+}
+
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt,
+ int align, u32 skip_mask)
{
u32 obj;
- if (likely(cnt == 1 && align == 1))
+ if (likely(cnt == 1 && align == 1 && !skip_mask))
return mlx4_bitmap_alloc(bitmap);
spin_lock(&bitmap->lock);
- obj = bitmap_find_next_zero_area(bitmap->table, bitmap->max,
- bitmap->last, cnt, align - 1);
+ obj = find_aligned_range(bitmap->table, bitmap->last,
+ bitmap->max, cnt, align, skip_mask);
if (obj >= bitmap->max) {
bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
& bitmap->mask;
- obj = bitmap_find_next_zero_area(bitmap->table, bitmap->max,
- 0, cnt, align - 1);
+ obj = find_aligned_range(bitmap->table, 0, bitmap->max,
+ cnt, align, skip_mask);
}
if (obj < bitmap->max) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index b7c9978..6537631 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -595,7 +595,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
return 0;
}
- err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+ err = mlx4_qp_reserve_range(dev, 1, 1, qpn, 0);
en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
if (err) {
en_err(priv, "Failed to reserve qp for mac registration\n");
@@ -1974,15 +1974,8 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
{
struct mlx4_en_port_profile *prof = priv->prof;
int i;
- int err;
int node;
- err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
- if (err) {
- en_err(priv, "failed reserving range for TX rings\n");
- return err;
- }
-
/* Create tx Rings */
for (i = 0; i < priv->tx_ring_num; i++) {
node = cpu_to_node(i % num_online_cpus());
@@ -1991,7 +1984,6 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
goto err;
if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
- priv->base_tx_qpn + i,
prof->tx_ring_size, TXBB_SIZE,
node, i))
goto err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 3a9f9bf..4862552 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1132,7 +1132,7 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv)
int err;
u32 qpn;
- err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn);
+ err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn, 0);
if (err) {
en_err(priv, "Failed reserving drop qpn\n");
return err;
@@ -1175,7 +1175,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
en_dbg(DRV, priv, "Configuring rss steering\n");
err = mlx4_qp_reserve_range(mdev->dev, priv->rx_ring_num,
priv->rx_ring_num,
- &rss_map->base_qpn);
+ &rss_map->base_qpn, 0);
if (err) {
en_err(priv, "Failed reserving %d qps\n", priv->rx_ring_num);
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index d0cecbd..a308d41 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -46,7 +46,7 @@
#include "mlx4_en.h"
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
- struct mlx4_en_tx_ring **pring, int qpn, u32 size,
+ struct mlx4_en_tx_ring **pring, u32 size,
u16 stride, int node, int queue_index)
{
struct mlx4_en_dev *mdev = priv->mdev;
@@ -112,11 +112,17 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring, ring->buf, ring->size, ring->buf_size,
(unsigned long long) ring->wqres.buf.direct.map);
- ring->qpn = qpn;
+ err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &ring->qpn,
+ MLX4_RESERVE_ETH_BF_QP);
+ if (err) {
+ en_err(priv, "failed reserving qp for TX ring\n");
+ goto err_map;
+ }
+
err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->qp, GFP_KERNEL);
if (err) {
en_err(priv, "Failed allocating qp %d\n", ring->qpn);
- goto err_map;
+ goto err_reserve;
}
ring->qp.event = mlx4_en_sqp_event;
@@ -143,6 +149,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
*pring = ring;
return 0;
+err_reserve:
+ mlx4_qp_release_range(mdev->dev, ring->qpn, 1);
err_map:
mlx4_en_unmap_buffer(&ring->wqres.buf);
err_hwq_res:
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 8c9ea70..745deb7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -266,10 +266,15 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
#define QUERY_FUNC_CAP_MTT_QUOTA_OFFSET 0x64
#define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET 0x68
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET 0x6c
+
#define QUERY_FUNC_CAP_FMR_FLAG 0x80
#define QUERY_FUNC_CAP_FLAG_RDMA 0x40
#define QUERY_FUNC_CAP_FLAG_ETH 0x80
#define QUERY_FUNC_CAP_FLAG_QUOTAS 0x10
+#define QUERY_FUNC_CAP_FLAG_VALID_MAILBOX 0x04
+
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG (1UL << 31)
/* when opcode modifier = 1 */
#define QUERY_FUNC_CAP_PHYS_PORT_OFFSET 0x3
@@ -339,7 +344,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
mlx4_get_active_ports(dev, slave);
/* enable rdma and ethernet interfaces, and new quota locations */
field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA |
- QUERY_FUNC_CAP_FLAG_QUOTAS);
+ QUERY_FUNC_CAP_FLAG_QUOTAS | QUERY_FUNC_CAP_FLAG_VALID_MAILBOX);
MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS_OFFSET);
field = min(
@@ -401,6 +406,8 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET_DEP);
+ size = QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
} else
err = -EINVAL;
@@ -493,6 +500,17 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
MLX4_GET(size, outbox, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
func_cap->reserved_eq = size & 0xFFFFFF;
+ func_cap->extra_flags = 0;
+
+ /* Mailbox data from 0x6c and onward should only be treated if
+ * QUERY_FUNC_CAP_FLAG_VALID_MAILBOX is set in func_cap->flags
+ */
+ if (func_cap->flags & QUERY_FUNC_CAP_FLAG_VALID_MAILBOX) {
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
+ if (size & QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG)
+ func_cap->extra_flags |= MLX4_QUERY_FUNC_FLAGS_BF_RES_QP;
+ }
+
goto out;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 475215e..0e910a4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -144,6 +144,7 @@ struct mlx4_func_cap {
u8 port_flags;
u8 flags1;
u64 phys_port_id;
+ u32 extra_flags;
};
struct mlx4_func {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 3044f9e..6a9a941 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -466,8 +466,13 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
mlx4_is_master(dev))
dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE;
- if (!mlx4_is_slave(dev))
+ if (!mlx4_is_slave(dev)) {
mlx4_enable_cqe_eqe_stride(dev);
+ dev->caps.alloc_res_qp_mask =
+ (dev->caps.bf_reg_size ? MLX4_RESERVE_ETH_BF_QP : 0);
+ } else {
+ dev->caps.alloc_res_qp_mask = 0;
+ }
return 0;
}
@@ -817,6 +822,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
slave_adjust_steering_mode(dev, &dev_cap, &hca_param);
+ if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_BF_RES_QP &&
+ dev->caps.bf_reg_size)
+ dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_ETH_BF_QP;
+
return 0;
err_mem:
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index b67ef48..6834da6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -884,7 +884,8 @@ extern struct workqueue_struct *mlx4_wq;
u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr);
-u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt,
+ int align, u32 skip_mask);
void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt,
int use_rr);
u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap);
@@ -970,7 +971,7 @@ int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
- int *base);
+ int *base, u8 flags);
void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index aaa7efb..576dd07 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -778,7 +778,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring **pring,
- int qpn, u32 size, u16 stride,
+ u32 size, u16 stride,
int node, int queue_index);
void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring **pring);
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 2301365..40e82ed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -42,6 +42,10 @@
#include "mlx4.h"
#include "icm.h"
+/* QP to support BF should have bits 6,7 cleared */
+#define MLX4_BF_QP_SKIP_MASK 0xc0
+#define MLX4_MAX_BF_QP_RANGE 0x40
+
void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
{
struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
@@ -207,26 +211,36 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
EXPORT_SYMBOL_GPL(mlx4_qp_modify);
int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
- int *base)
+ int *base, u8 flags)
{
+ int bf_qp = !!(flags & (u8)MLX4_RESERVE_ETH_BF_QP);
+
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
- *base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
+ if (cnt > MLX4_MAX_BF_QP_RANGE && bf_qp)
+ return -ENOMEM;
+
+ *base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align,
+ bf_qp ? MLX4_BF_QP_SKIP_MASK : 0);
if (*base == -1)
return -ENOMEM;
return 0;
}
-int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+ int *base, u8 flags)
{
u64 in_param = 0;
u64 out_param;
int err;
+ /* Turn off all unsupported QP allocation flags */
+ flags &= dev->caps.alloc_res_qp_mask;
+
if (mlx4_is_mfunc(dev)) {
- set_param_l(&in_param, cnt);
+ set_param_l(&in_param, (((u32)flags) << 24) | (u32)cnt);
set_param_h(&in_param, align);
err = mlx4_cmd_imm(dev, in_param, &out_param,
RES_QP, RES_OP_RESERVE,
@@ -238,7 +252,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
*base = get_param_l(&out_param);
return 0;
}
- return __mlx4_qp_reserve_range(dev, cnt, align, base);
+ return __mlx4_qp_reserve_range(dev, cnt, align, base, flags);
}
EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 16f617b..4efbd1e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1543,16 +1543,21 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
int align;
int base;
int qpn;
+ u8 flags;
switch (op) {
case RES_OP_RESERVE:
count = get_param_l(&in_param) & 0xffffff;
+ /* Turn off all unsupported QP allocation flags that the
+ * slave tries to set.
+ */
+ flags = (get_param_l(&in_param) >> 24) & dev->caps.alloc_res_qp_mask;
align = get_param_h(&in_param);
err = mlx4_grant_resource(dev, slave, RES_QP, count, 0);
if (err)
return err;
- err = __mlx4_qp_reserve_range(dev, count, align, &base);
+ err = __mlx4_qp_reserve_range(dev, count, align, &base, flags);
if (err) {
mlx4_release_resource(dev, slave, RES_QP, count, 0);
return err;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 3951b53..272aa25 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -195,6 +195,22 @@ enum {
};
enum {
+ MLX4_QUERY_FUNC_FLAGS_BF_RES_QP = 1LL << 0
+};
+
+/* bit enums for an 8-bit flags field indicating special use
+ * QPs which require special handling in qp_reserve_range.
+ * Currently, this only includes QPs used by the ETH interface,
+ * where we expect to use blueflame. These QPs must not have
+ * bits 6 and 7 set in their qp number.
+ *
+ * This enum may use only bits 0..7.
+ */
+enum {
+ MLX4_RESERVE_ETH_BF_QP = 1 << 7,
+};
+
+enum {
MLX4_DEV_CAP_64B_EQE_ENABLED = 1LL << 0,
MLX4_DEV_CAP_64B_CQE_ENABLED = 1LL << 1,
MLX4_DEV_CAP_CQE_STRIDE_ENABLED = 1LL << 2,
@@ -501,6 +517,7 @@ struct mlx4_caps {
u64 phys_port_id[MLX4_MAX_PORTS + 1];
int tunnel_offload_mode;
u8 rx_checksum_flags_port[MLX4_MAX_PORTS + 1];
+ u8 alloc_res_qp_mask;
};
struct mlx4_buf_list {
@@ -950,8 +967,8 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
unsigned vector, int collapsed, int timestamp_en);
void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
-
-int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base);
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+ int *base, u8 flags);
void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp,
--
1.7.1
^ permalink raw reply related
* Re: [patch iproute2 0/6] iproute2: add changes for switchdev
From: Jamal Hadi Salim @ 2014-12-04 13:16 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, sfeldma, f.fainelli, roopa, linville,
jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a, buytenh,
aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, gospo, bcrl,
hemal
In-Reply-To: <1417683438-10935-1-git-send-email-jiri@resnulli.us>
General comment:
iproute2 patches need to be addressed to the maintainer
stephen@networkplumber.org
And are we mainstream enough now we can drop the 1000 people on the
To: list? I doubt most of these people are even following the discussion
(I planted an easter egg for Aviad and didnt see him
reacting) ;->
cheers,
jamal
On 12/04/14 03:57, Jiri Pirko wrote:
> Jiri Pirko (1):
> iproute2: ipa: show switch id
>
> Scott Feldman (5):
> bridge/fdb: fix statistics output spacing
> bridge/fdb: add flag/indication for FDB entry synced from offload
> device
> bridge/link: add new offload hwmode swdev
> link: add missing IFLA_BRPORT_PROXYARP
> bridge/link: add learning_sync policy flag
>
> bridge/fdb.c | 4 +++-
> bridge/link.c | 17 +++++++++++++++--
> include/linux/if_bridge.h | 1 +
> include/linux/if_link.h | 3 +++
> include/linux/neighbour.h | 1 +
> ip/ipaddress.c | 8 ++++++++
> man/man8/bridge.8 | 19 ++++++++++++++-----
> 7 files changed, 45 insertions(+), 8 deletions(-)
>
^ permalink raw reply
* Re: [patch iproute2 1/6] iproute2: ipa: show switch id
From: Jamal Hadi Salim @ 2014-12-04 13:17 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, sfeldma, f.fainelli, roopa, linville,
jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a, buytenh,
aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, gospo, bcrl,
hemal
In-Reply-To: <1417683438-10935-2-git-send-email-jiri@resnulli.us>
On 12/04/14 03:57, Jiri Pirko wrote:
> Signed-off-by: Jiri Pirko <jiri@resnulli.us>
> ---
> include/linux/if_link.h | 1 +
> ip/ipaddress.c | 8 ++++++++
> 2 files changed, 9 insertions(+)
>
> diff --git a/include/linux/if_link.h b/include/linux/if_link.h
> index 4732063..a6e2594 100644
> --- a/include/linux/if_link.h
> +++ b/include/linux/if_link.h
> @@ -145,6 +145,7 @@ enum {
> IFLA_CARRIER,
> IFLA_PHYS_PORT_ID,
> IFLA_CARRIER_CHANGES,
> + IFLA_PHYS_SWITCH_ID,
> __IFLA_MAX
> };
>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
cheers,
jamal
^ permalink raw reply
* Re: [patch iproute2 3/6] bridge/fdb: add flag/indication for FDB entry synced from offload device
From: Jamal Hadi Salim @ 2014-12-04 13:19 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, sfeldma, f.fainelli, roopa, linville,
jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a, buytenh,
aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, gospo, bcrl,
hemal
In-Reply-To: <1417683438-10935-4-git-send-email-jiri@resnulli.us>
On 12/04/14 03:57, Jiri Pirko wrote:
> From: Scott Feldman <sfeldma@gmail.com>
>
Did i say i like it already?;->
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
cheers,
jamal
^ permalink raw reply
* Re: [patch iproute2 4/6] bridge/link: add new offload hwmode swdev
From: Jamal Hadi Salim @ 2014-12-04 13:23 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, sfeldma, f.fainelli, roopa, linville,
jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a, buytenh,
aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, gospo, bcrl,
hemal
In-Reply-To: <1417683438-10935-5-git-send-email-jiri@resnulli.us>
On 12/04/14 03:57, Jiri Pirko wrote:
> From: Scott Feldman <sfeldma@gmail.com>
>
> To support full-featured switch devices offloading bridge funtionality,
> add new hwmode 'swdev'. Like 'vepa' and 'veb', 'swdev' indicated bridge
> port functionality is being offloaded to hardware.
>
Unhappy with the name swdev ..
Ok, go ahead and beat up on me.
cheers,
jamal
^ permalink raw reply
* Re: [patch iproute2 6/6] bridge/link: add learning_sync policy flag
From: Jamal Hadi Salim @ 2014-12-04 13:26 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, sfeldma, f.fainelli, roopa, linville,
jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a, buytenh,
aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, gospo, bcrl,
hemal
In-Reply-To: <1417683438-10935-7-git-send-email-jiri@resnulli.us>
On 12/04/14 03:57, Jiri Pirko wrote:
> From: Scott Feldman <sfeldma@gmail.com>
>
> Add 'learned_sync' flag to turn on/off syncing of learned FDB entries from
> offload device to bridge's FDB. Flag would be set/cleared in on SELF using
> hwmode qualifier 'swdev'. E.g.:
>
> $ sudo bridge link set dev swp1 hwmode swdev learning_sync on
>
> $ bridge -d link show dev swp1
> 2: swp1 state UNKNOWN : <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 master br0 state forwarding priority 32 cost 2
> hairpin off guard off root_block off fastleave off learning off flood off
> 2: swp1 state UNKNOWN : <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 master br0
> learning on learning_sync on hwmode swdev
>
> Adds new IFLA_BRPORT_LEARNING_SYNC attribute for IFLA_PROTINFO on the SELF
> brport.
>
> Signed-off-by: Scott Feldman <sfeldma@gmail.com>
> Signed-off-by: Jiri Pirko <jiri@resnulli.us>
I actually dont think any of these patches needed an ack because they
are off. My ack is just to show support (despite the noun challenges).
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
cheers,
jamal
^ permalink raw reply
* Re: [PATCH net] net: sctp: use MAX_HEADER for headroom reserve in output path
From: Neil Horman @ 2014-12-04 13:41 UTC (permalink / raw)
To: Daniel Borkmann; +Cc: davem, linux-sctp, netdev, robert
In-Reply-To: <1417605238-9936-1-git-send-email-dborkman@redhat.com>
On Wed, Dec 03, 2014 at 12:13:58PM +0100, Daniel Borkmann wrote:
> To accomodate for enough headroom for tunnels, use MAX_HEADER instead
> of LL_MAX_HEADER. Robert reported that he has hit after roughly 40hrs
> of trinity an skb_under_panic() via SCTP output path (see reference).
> I couldn't reproduce it from here, but not using MAX_HEADER as elsewhere
> in other protocols might be one possible cause for this.
>
> In any case, it looks like accounting on chunks themself seems to look
> good as the skb already passed the SCTP output path and did not hit
> any skb_over_panic(). Given tunneling was enabled in his .config, the
> headroom would have been expanded by MAX_HEADER in this case.
>
> Reported-by: Robert Święcki <robert@swiecki.net>
> Reference: https://lkml.org/lkml/2014/12/1/507
> Fixes: 594ccc14dfe4d ("[SCTP] Replace incorrect use of dev_alloc_skb with alloc_skb in sctp_packet_transmit().")
> Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
> ---
> net/sctp/output.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/net/sctp/output.c b/net/sctp/output.c
> index 42dffd4..fc5e45b 100644
> --- a/net/sctp/output.c
> +++ b/net/sctp/output.c
> @@ -401,12 +401,12 @@ int sctp_packet_transmit(struct sctp_packet *packet)
> sk = chunk->skb->sk;
>
> /* Allocate the new skb. */
> - nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC);
> + nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC);
> if (!nskb)
> goto nomem;
>
> /* Make sure the outbound skb has enough header room reserved. */
> - skb_reserve(nskb, packet->overhead + LL_MAX_HEADER);
> + skb_reserve(nskb, packet->overhead + MAX_HEADER);
>
> /* Set the owning socket so that we know where to get the
> * destination IP address.
> --
> 1.7.11.7
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-sctp" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
^ permalink raw reply
* Re: [patch iproute2 0/6] iproute2: add changes for switchdev
From: Andy Gospodarek @ 2014-12-04 13:56 UTC (permalink / raw)
To: Jamal Hadi Salim
Cc: Jiri Pirko, netdev, davem, nhorman, andy, tgraf, dborkman,
ogerlitz, jesse, pshelar, azhou, ben, stephen, jeffrey.t.kirsher,
vyasevic, xiyou.wangcong, john.r.fastabend, edumazet, sfeldma,
f.fainelli, roopa, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, simon.horman, alexander.h.duyck, john.ronciak,
mleitner, shrijeet, bcrl, hemal@
In-Reply-To: <54805EB6.2010901@mojatatu.com>
On Thu, Dec 04, 2014 at 08:16:38AM -0500, Jamal Hadi Salim wrote:
>
> General comment:
> iproute2 patches need to be addressed to the maintainer
> stephen@networkplumber.org
> And are we mainstream enough now we can drop the 1000 people on the
> To: list? I doubt most of these people are even following the discussion (I
> planted an easter egg for Aviad and didnt see him
> reacting) ;->
I actually don't mind them coming here since it is a change to netlink.
Thanks for sending them to netdev, Jiri.
>
> cheers,
> jamal
>
> On 12/04/14 03:57, Jiri Pirko wrote:
> >Jiri Pirko (1):
> > iproute2: ipa: show switch id
> >
> >Scott Feldman (5):
> > bridge/fdb: fix statistics output spacing
> > bridge/fdb: add flag/indication for FDB entry synced from offload
> > device
> > bridge/link: add new offload hwmode swdev
> > link: add missing IFLA_BRPORT_PROXYARP
> > bridge/link: add learning_sync policy flag
> >
> > bridge/fdb.c | 4 +++-
> > bridge/link.c | 17 +++++++++++++++--
> > include/linux/if_bridge.h | 1 +
> > include/linux/if_link.h | 3 +++
> > include/linux/neighbour.h | 1 +
> > ip/ipaddress.c | 8 ++++++++
> > man/man8/bridge.8 | 19 ++++++++++++++-----
> > 7 files changed, 45 insertions(+), 8 deletions(-)
> >
>
^ permalink raw reply
* Re: FIXME in solos-pci.c
From: chas williams - CONTRACTOR @ 2014-12-04 14:05 UTC (permalink / raw)
To: nick, Guy Ellis; +Cc: linux-atm-general, netdev, linux-kernel
In-Reply-To: <547FDBF6.5020008@gmail.com>
The last I heard on this topic was from Guy Ellis,
From: Guy Ellis <guy@traverse.com.au>
To: linux-atm-general@lists.sourceforge.net
Subject: Re: [Linux-ATM-General] solos-pci.c: Fix me
Date: Tue, 22 Jul 2014 07:34:30 +1000
Hi Chas/Nick,
I think the FIXME is reminder to deal correctly with an unknown command.
At the moment an unknown command is treated as a PKT_COMMAND which is
incorrect.
I think the correct behaviour would be to ignore unknown commands and
just free the skb.
That said I doubt this condition ever occurs, which is probably why it
has been this way since day 1.
Nathan is on vacation at the moment, when he gets back in August I'll
ask him to tidy this up.
So perhaps, Guy could let us know if he had a chance for Nathan to
look at removing this FIXME.
On Wed, 03 Dec 2014 22:58:46 -0500
nick <xerofoify@gmail.com> wrote:
> Greetings Chas,
> I am wondering if there is any reason for the FIXME message in the below code. This is due to after reading the other parts of the function the code and logical seem similar and correct unless I am missing something about the hardware.
> Cheers Nick
> case PKT_COMMAND:
> default: /* FIXME: Not really, surely? */
> if (process_command(card, port, skb))
> break;
> spin_lock(&card->cli_queue_lock);
> if (skb_queue_len(&card->cli_queue[port]) > 10) {
> if (net_ratelimit())
> dev_warn(&card->dev->dev, "Dropping console response on port %d\n",
> port);
> dev_kfree_skb_any(skb);
> } else
> skb_queue_tail(&card->cli_queue[port], skb);
> spin_unlock(&card->cli_queue_lock);
> break;
> }
>
>
^ permalink raw reply
* Re: [patch iproute2 6/6] bridge/link: add learning_sync policy flag
From: Jamal Hadi Salim @ 2014-12-04 14:15 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, sfeldma, f.fainelli, roopa, linville,
jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a, buytenh,
aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, gospo, bcrl,
hemal
In-Reply-To: <54806115.9080008@mojatatu.com>
On 12/04/14 08:26, Jamal Hadi Salim wrote:
> I actually dont think any of these patches needed an ack because they
> are off.
^^^ meant ok ;-> or obvious.
cheers,
jamal
^ permalink raw reply
* Re: [patch iproute2 1/6] iproute2: ipa: show switch id
From: Andy Gospodarek @ 2014-12-04 14:20 UTC (permalink / raw)
To: Jiri Pirko
Cc: netdev, davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse,
pshelar, azhou, ben, stephen, jeffrey.t.kirsher, vyasevic,
xiyou.wangcong, john.r.fastabend, edumazet, jhs, sfeldma,
f.fainelli, roopa, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, simon.horman, alexander.h.duyck, john.ronciak,
mleitner, shrijeet, bcrl, hemal
In-Reply-To: <1417683438-10935-2-git-send-email-jiri@resnulli.us>
On Thu, Dec 04, 2014 at 09:57:13AM +0100, Jiri Pirko wrote:
> Signed-off-by: Jiri Pirko <jiri@resnulli.us>
> ---
> include/linux/if_link.h | 1 +
> ip/ipaddress.c | 8 ++++++++
> 2 files changed, 9 insertions(+)
>
> diff --git a/include/linux/if_link.h b/include/linux/if_link.h
> index 4732063..a6e2594 100644
> --- a/include/linux/if_link.h
> +++ b/include/linux/if_link.h
> @@ -145,6 +145,7 @@ enum {
> IFLA_CARRIER,
> IFLA_PHYS_PORT_ID,
> IFLA_CARRIER_CHANGES,
> + IFLA_PHYS_SWITCH_ID,
Serious question for Stephen et al, once we take this to iproute2 are we
going to be able to change the name but the string diplayed if needed?
I had a patch that called this IFLA_PARENT_ID that I was using with the
older github tree used by Jiri and Scott before these were in net-next.
I wanted to submit that as a change to what became
82f2841291cfaf4d225aa1766424280254d3e3b2, but was waiting for things to
be accepted and the dust settled.
I like the parent/child/sibling nomenclature better for 4 reasons:
- Most did not seem to like the term 'offload' since that term would be
confusing with, GRO, GSO, etc.
- A *significant* use case for many of the high-end ASICs in datacenters
is routing.
- switchid does not make sense in the OVS/flow case because it is all
about flows, not switches or routers, and parent made sense there.
- I wanted to combine this for use with SR-IOV use case, so one can more
easily map PF->VF using this.
Can you give me a bit (a day) to clean-up that patch and submit an
alternative proposal to these?
> __IFLA_MAX
> };
>
> diff --git a/ip/ipaddress.c b/ip/ipaddress.c
> index 4d99324..bd36a07 100644
> --- a/ip/ipaddress.c
> +++ b/ip/ipaddress.c
> @@ -589,6 +589,14 @@ int print_linkinfo(const struct sockaddr_nl *who,
> b1, sizeof(b1)));
> }
>
> + if (tb[IFLA_PHYS_SWITCH_ID]) {
> + SPRINT_BUF(b1);
> + fprintf(fp, "switchid %s ",
> + hexstring_n2a(RTA_DATA(tb[IFLA_PHYS_SWITCH_ID]),
> + RTA_PAYLOAD(tb[IFLA_PHYS_SWITCH_ID]),
> + b1, sizeof(b1)));
> + }
> +
> if (tb[IFLA_OPERSTATE])
> print_operstate(fp, rta_getattr_u8(tb[IFLA_OPERSTATE]));
>
> --
> 1.9.3
>
^ permalink raw reply
* Re: [patch iproute2 0/6] iproute2: add changes for switchdev
From: Roopa Prabhu @ 2014-12-04 14:22 UTC (permalink / raw)
To: Andy Gospodarek
Cc: Jamal Hadi Salim, Jiri Pirko, netdev, davem, nhorman, andy, tgraf,
dborkman, ogerlitz, jesse, pshelar, azhou, ben, stephen,
jeffrey.t.kirsher, vyasevic, xiyou.wangcong, john.r.fastabend,
edumazet, sfeldma, f.fainelli, linville, jasowang, ebiederm,
nicolas.dichtel, ryazanov.s.a, buytenh, aviadr, nbd,
alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, bcrl
In-Reply-To: <20141204135621.GQ27416@gospo.rtplab.test>
On 12/4/14, 5:56 AM, Andy Gospodarek wrote:
> On Thu, Dec 04, 2014 at 08:16:38AM -0500, Jamal Hadi Salim wrote:
>> General comment:
>> iproute2 patches need to be addressed to the maintainer
>> stephen@networkplumber.org
>> And are we mainstream enough now we can drop the 1000 people on the
>> To: list? I doubt most of these people are even following the discussion (I
>> planted an easter egg for Aviad and didnt see him
>> reacting) ;->
> I actually don't mind them coming here since it is a change to netlink.
> Thanks for sending them to netdev, Jiri.
I think jamal meant the people in the cc (not netdev).
I actually like the cc, but that probably cant last long because it is a
lot of people.
>
>> cheers,
>> jamal
>>
>> On 12/04/14 03:57, Jiri Pirko wrote:
>>> Jiri Pirko (1):
>>> iproute2: ipa: show switch id
>>>
>>> Scott Feldman (5):
>>> bridge/fdb: fix statistics output spacing
>>> bridge/fdb: add flag/indication for FDB entry synced from offload
>>> device
>>> bridge/link: add new offload hwmode swdev
>>> link: add missing IFLA_BRPORT_PROXYARP
>>> bridge/link: add learning_sync policy flag
>>>
>>> bridge/fdb.c | 4 +++-
>>> bridge/link.c | 17 +++++++++++++++--
>>> include/linux/if_bridge.h | 1 +
>>> include/linux/if_link.h | 3 +++
>>> include/linux/neighbour.h | 1 +
>>> ip/ipaddress.c | 8 ++++++++
>>> man/man8/bridge.8 | 19 ++++++++++++++-----
>>> 7 files changed, 45 insertions(+), 8 deletions(-)
>>>
^ permalink raw reply
* Re: [patch iproute2 0/6] iproute2: add changes for switchdev
From: Roopa Prabhu @ 2014-12-04 14:26 UTC (permalink / raw)
To: Jiri Pirko
Cc: netdev, davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse,
pshelar, azhou, ben, stephen, jeffrey.t.kirsher, vyasevic,
xiyou.wangcong, john.r.fastabend, edumazet, jhs, sfeldma,
f.fainelli, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, simon.horman, alexander.h.duyck, john.ronciak,
mleitner, shrijeet, gospo, bcrl, hemal
In-Reply-To: <1417683438-10935-1-git-send-email-jiri@resnulli.us>
On 12/4/14, 12:57 AM, Jiri Pirko wrote:
> Jiri Pirko (1):
> iproute2: ipa: show switch id
>
> Scott Feldman (5):
> bridge/fdb: fix statistics output spacing
> bridge/fdb: add flag/indication for FDB entry synced from offload
> device
> bridge/link: add new offload hwmode swdev
Ack to most patches but nack on this one. The todo list still has a note
to revist the flag to indicate switchdev offloads.
Exposing this to userspace does not help that.
> link: add missing IFLA_BRPORT_PROXYARP
> bridge/link: add learning_sync policy flag
>
> bridge/fdb.c | 4 +++-
> bridge/link.c | 17 +++++++++++++++--
> include/linux/if_bridge.h | 1 +
> include/linux/if_link.h | 3 +++
> include/linux/neighbour.h | 1 +
> ip/ipaddress.c | 8 ++++++++
> man/man8/bridge.8 | 19 ++++++++++++++-----
> 7 files changed, 45 insertions(+), 8 deletions(-)
>
^ permalink raw reply
* Re: [patch iproute2 1/6] iproute2: ipa: show switch id
From: Roopa Prabhu @ 2014-12-04 14:29 UTC (permalink / raw)
To: Andy Gospodarek
Cc: Jiri Pirko, netdev, davem, nhorman, andy, tgraf, dborkman,
ogerlitz, jesse, pshelar, azhou, ben, stephen, jeffrey.t.kirsher,
vyasevic, xiyou.wangcong, john.r.fastabend, edumazet, jhs,
sfeldma, f.fainelli, linville, jasowang, ebiederm,
nicolas.dichtel, ryazanov.s.a, buytenh, aviadr, nbd,
alexei.starovoitov, Neil.Jerram, ronye, simon.horman,
alexander.h.duyck, john.ronciak, mleitner, shrijeet, bcrl, hemal
In-Reply-To: <20141204142015.GR27416@gospo.rtplab.test>
On 12/4/14, 6:20 AM, Andy Gospodarek wrote:
> On Thu, Dec 04, 2014 at 09:57:13AM +0100, Jiri Pirko wrote:
>> Signed-off-by: Jiri Pirko <jiri@resnulli.us>
>> ---
>> include/linux/if_link.h | 1 +
>> ip/ipaddress.c | 8 ++++++++
>> 2 files changed, 9 insertions(+)
>>
>> diff --git a/include/linux/if_link.h b/include/linux/if_link.h
>> index 4732063..a6e2594 100644
>> --- a/include/linux/if_link.h
>> +++ b/include/linux/if_link.h
>> @@ -145,6 +145,7 @@ enum {
>> IFLA_CARRIER,
>> IFLA_PHYS_PORT_ID,
>> IFLA_CARRIER_CHANGES,
>> + IFLA_PHYS_SWITCH_ID,
> Serious question for Stephen et al, once we take this to iproute2 are we
> going to be able to change the name but the string diplayed if needed?
>
> I had a patch that called this IFLA_PARENT_ID that I was using with the
> older github tree used by Jiri and Scott before these were in net-next.
> I wanted to submit that as a change to what became
> 82f2841291cfaf4d225aa1766424280254d3e3b2, but was waiting for things to
> be accepted and the dust settled.
>
> I like the parent/child/sibling nomenclature better for 4 reasons:
>
> - Most did not seem to like the term 'offload' since that term would be
> confusing with, GRO, GSO, etc.
> - A *significant* use case for many of the high-end ASICs in datacenters
> is routing.
> - switchid does not make sense in the OVS/flow case because it is all
> about flows, not switches or routers, and parent made sense there.
> - I wanted to combine this for use with SR-IOV use case, so one can more
> easily map PF->VF using this.
ack.., I have voted for calling it a generic parent id in the past.
>
> Can you give me a bit (a day) to clean-up that patch and submit an
> alternative proposal to these?
>
>> __IFLA_MAX
>> };
>>
>> diff --git a/ip/ipaddress.c b/ip/ipaddress.c
>> index 4d99324..bd36a07 100644
>> --- a/ip/ipaddress.c
>> +++ b/ip/ipaddress.c
>> @@ -589,6 +589,14 @@ int print_linkinfo(const struct sockaddr_nl *who,
>> b1, sizeof(b1)));
>> }
>>
>> + if (tb[IFLA_PHYS_SWITCH_ID]) {
>> + SPRINT_BUF(b1);
>> + fprintf(fp, "switchid %s ",
>> + hexstring_n2a(RTA_DATA(tb[IFLA_PHYS_SWITCH_ID]),
>> + RTA_PAYLOAD(tb[IFLA_PHYS_SWITCH_ID]),
>> + b1, sizeof(b1)));
>> + }
>> +
>> if (tb[IFLA_OPERSTATE])
>> print_operstate(fp, rta_getattr_u8(tb[IFLA_OPERSTATE]));
>>
>> --
>> 1.9.3
>>
^ permalink raw reply
* Re: [patch iproute2 0/6] iproute2: add changes for switchdev
From: Jamal Hadi Salim @ 2014-12-04 14:31 UTC (permalink / raw)
To: Roopa Prabhu, Andy Gospodarek
Cc: Jiri Pirko, netdev, davem, nhorman, andy, tgraf, dborkman,
ogerlitz, jesse, pshelar, azhou, ben, stephen, jeffrey.t.kirsher,
vyasevic, xiyou.wangcong, john.r.fastabend, edumazet, sfeldma,
f.fainelli, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, simon.horman, alexander.h.duyck, john.ronciak,
mleitner, shrijeet, bcrl, hemal
In-Reply-To: <54806E1B.5010402@cumulusnetworks.com>
On 12/04/14 09:22, Roopa Prabhu wrote:
> On 12/4/14, 5:56 AM, Andy Gospodarek wrote:
> I think jamal meant the people in the cc (not netdev).
> I actually like the cc, but that probably cant last long because it is a
> lot of people.
There are 34 people on that list. I support copying all stake holders
but it is too large.
cheers,
jamal
^ permalink raw reply
* Re: [patch iproute2 1/6] iproute2: ipa: show switch id
From: Jiri Pirko @ 2014-12-04 14:33 UTC (permalink / raw)
To: Andy Gospodarek
Cc: netdev, davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse,
pshelar, azhou, ben, stephen, jeffrey.t.kirsher, vyasevic,
xiyou.wangcong, john.r.fastabend, edumazet, jhs, sfeldma,
f.fainelli, roopa, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, simon.horman, alexander.h.duyck, john.ronciak,
mleitner, shrijeet, bcrl, hemal
In-Reply-To: <20141204142015.GR27416@gospo.rtplab.test>
Thu, Dec 04, 2014 at 03:20:15PM CET, gospo@cumulusnetworks.com wrote:
>On Thu, Dec 04, 2014 at 09:57:13AM +0100, Jiri Pirko wrote:
>> Signed-off-by: Jiri Pirko <jiri@resnulli.us>
>> ---
>> include/linux/if_link.h | 1 +
>> ip/ipaddress.c | 8 ++++++++
>> 2 files changed, 9 insertions(+)
>>
>> diff --git a/include/linux/if_link.h b/include/linux/if_link.h
>> index 4732063..a6e2594 100644
>> --- a/include/linux/if_link.h
>> +++ b/include/linux/if_link.h
>> @@ -145,6 +145,7 @@ enum {
>> IFLA_CARRIER,
>> IFLA_PHYS_PORT_ID,
>> IFLA_CARRIER_CHANGES,
>> + IFLA_PHYS_SWITCH_ID,
>
>Serious question for Stephen et al, once we take this to iproute2 are we
>going to be able to change the name but the string diplayed if needed?
>
>I had a patch that called this IFLA_PARENT_ID that I was using with the
>older github tree used by Jiri and Scott before these were in net-next.
>I wanted to submit that as a change to what became
>82f2841291cfaf4d225aa1766424280254d3e3b2, but was waiting for things to
>be accepted and the dust settled.
>
>I like the parent/child/sibling nomenclature better for 4 reasons:
>
>- Most did not seem to like the term 'offload' since that term would be
> confusing with, GRO, GSO, etc.
>- A *significant* use case for many of the high-end ASICs in datacenters
> is routing.
>- switchid does not make sense in the OVS/flow case because it is all
> about flows, not switches or routers, and parent made sense there.
well ovs is all about flows and has the "switch" word in the name. I
believe that people are talking about "switches" in case of these "flow
devices" as well. I see nothing wrong in that. I think that "switch"
became generic name for "packet forwarding machines".
"parent" is very generic and may mean 100 things...
>- I wanted to combine this for use with SR-IOV use case, so one can more
> easily map PF->VF using this.
Ugh, please don't mix this up with pf, vf. That is completely different
thing.
pf vf mapping is done in sysfs. In netlink, physportid is used for that
purpose. We can expose this phys port id for pf as well (as a different
attr) and we are done.
>
>Can you give me a bit (a day) to clean-up that patch and submit an
>alternative proposal to these?
>
>> __IFLA_MAX
>> };
>>
>> diff --git a/ip/ipaddress.c b/ip/ipaddress.c
>> index 4d99324..bd36a07 100644
>> --- a/ip/ipaddress.c
>> +++ b/ip/ipaddress.c
>> @@ -589,6 +589,14 @@ int print_linkinfo(const struct sockaddr_nl *who,
>> b1, sizeof(b1)));
>> }
>>
>> + if (tb[IFLA_PHYS_SWITCH_ID]) {
>> + SPRINT_BUF(b1);
>> + fprintf(fp, "switchid %s ",
>> + hexstring_n2a(RTA_DATA(tb[IFLA_PHYS_SWITCH_ID]),
>> + RTA_PAYLOAD(tb[IFLA_PHYS_SWITCH_ID]),
>> + b1, sizeof(b1)));
>> + }
>> +
>> if (tb[IFLA_OPERSTATE])
>> print_operstate(fp, rta_getattr_u8(tb[IFLA_OPERSTATE]));
>>
>> --
>> 1.9.3
>>
^ permalink raw reply
* Re: [patch iproute2 0/6] iproute2: add changes for switchdev
From: Jiri Pirko @ 2014-12-04 14:34 UTC (permalink / raw)
To: Roopa Prabhu
Cc: netdev, davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse,
pshelar, azhou, ben, stephen, jeffrey.t.kirsher, vyasevic,
xiyou.wangcong, john.r.fastabend, edumazet, jhs, sfeldma,
f.fainelli, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, simon.horman, alexander.h.duyck, john.ronciak,
mleitner, shrijeet, gospo, bcrl, hemal
In-Reply-To: <54806F2A.2050109@cumulusnetworks.com>
Thu, Dec 04, 2014 at 03:26:50PM CET, roopa@cumulusnetworks.com wrote:
>On 12/4/14, 12:57 AM, Jiri Pirko wrote:
>>Jiri Pirko (1):
>> iproute2: ipa: show switch id
>>
>>Scott Feldman (5):
>> bridge/fdb: fix statistics output spacing
>> bridge/fdb: add flag/indication for FDB entry synced from offload
>> device
>> bridge/link: add new offload hwmode swdev
>Ack to most patches but nack on this one. The todo list still has a note to
>revist the flag to indicate switchdev offloads.
>Exposing this to userspace does not help that.
Hmm, note that this is already exposed to userspace, this patchset is
for iproute2 (userspace tool).
>
>> link: add missing IFLA_BRPORT_PROXYARP
>> bridge/link: add learning_sync policy flag
>>
>> bridge/fdb.c | 4 +++-
>> bridge/link.c | 17 +++++++++++++++--
>> include/linux/if_bridge.h | 1 +
>> include/linux/if_link.h | 3 +++
>> include/linux/neighbour.h | 1 +
>> ip/ipaddress.c | 8 ++++++++
>> man/man8/bridge.8 | 19 ++++++++++++++-----
>> 7 files changed, 45 insertions(+), 8 deletions(-)
>>
>
^ permalink raw reply
* Re: [patch iproute2 0/6] iproute2: add changes for switchdev
From: Roopa Prabhu @ 2014-12-04 14:45 UTC (permalink / raw)
To: Jiri Pirko
Cc: netdev, davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse,
pshelar, azhou, ben, stephen, jeffrey.t.kirsher, vyasevic,
xiyou.wangcong, john.r.fastabend, edumazet, jhs, sfeldma,
f.fainelli, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, simon.horman, alexander.h.duyck, john.ronciak,
mleitner, shrijeet, gospo, bcrl, hemal
In-Reply-To: <20141204143400.GC1861@nanopsycho.orion>
On 12/4/14, 6:34 AM, Jiri Pirko wrote:
> Thu, Dec 04, 2014 at 03:26:50PM CET, roopa@cumulusnetworks.com wrote:
>> On 12/4/14, 12:57 AM, Jiri Pirko wrote:
>>> Jiri Pirko (1):
>>> iproute2: ipa: show switch id
>>>
>>> Scott Feldman (5):
>>> bridge/fdb: fix statistics output spacing
>>> bridge/fdb: add flag/indication for FDB entry synced from offload
>>> device
>>> bridge/link: add new offload hwmode swdev
>> Ack to most patches but nack on this one. The todo list still has a note to
>> revist the flag to indicate switchdev offloads.
>> Exposing this to userspace does not help that.
> Hmm, note that this is already exposed to userspace, this patchset is
> for iproute2 (userspace tool).
hmmm, all feedback on the switchdev patches seemed to indicate we can
change this later.
I don't see swdev mode being used in the kernel anywhere today.
I will send a patch to remove it. Its still in net-next and so can be
changed ?.
I was going to resend my patch to introduce a common offload flag for
all link objects.
It would be nice if all of them had a consistent flag to indicate hw
offload and iproute2 could display the same flag for all.
Including bonds and vxlan's.
>
>>> link: add missing IFLA_BRPORT_PROXYARP
>>> bridge/link: add learning_sync policy flag
>>>
>>> bridge/fdb.c | 4 +++-
>>> bridge/link.c | 17 +++++++++++++++--
>>> include/linux/if_bridge.h | 1 +
>>> include/linux/if_link.h | 3 +++
>>> include/linux/neighbour.h | 1 +
>>> ip/ipaddress.c | 8 ++++++++
>>> man/man8/bridge.8 | 19 ++++++++++++++-----
>>> 7 files changed, 45 insertions(+), 8 deletions(-)
>>>
^ permalink raw reply
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