* [PATCH 2.6.30 2/5] cxgb3: sge setup fixes
2009-03-27 2:39 [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded Divy Le Ray
@ 2009-03-27 2:39 ` Divy Le Ray
2009-03-27 7:53 ` David Miller
2009-03-27 2:39 ` [PATCH 2.6.30 3/5] cxgb3: use resource_size_t for mmio declarations Divy Le Ray
` (3 subsequent siblings)
4 siblings, 1 reply; 10+ messages in thread
From: Divy Le Ray @ 2009-03-27 2:39 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, swise
From: Divy Le Ray <divy@chelsio.com>
Enable timestamps, update delayed ack threshold for iSCSI/iWARP traffic
Remove the len flag in Tx requests. It might corrupt offload trace packets.
Update SGE context setup to avoid potential H/W misprogrammation.
Signed-off-by: Divy Le Ray <divy@chelsio.com>
---
drivers/net/cxgb3/sge.c | 2 +-
drivers/net/cxgb3/t3_hw.c | 45 ++++++++++++++++++++++++++++++++++++++-------
2 files changed, 39 insertions(+), 8 deletions(-)
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index fcd1a4f..54667f0 100755
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -1089,7 +1089,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
struct tx_desc *d = &q->desc[pidx];
struct cpl_tx_pkt *cpl = (struct cpl_tx_pkt *)d;
- cpl->len = htonl(skb->len | 0x80000000);
+ cpl->len = htonl(skb->len);
cntrl = V_TXPKT_INTF(pi->port_id);
if (vlan_tx_tag_present(skb) && pi->vlan_grp)
diff --git a/drivers/net/cxgb3/t3_hw.c b/drivers/net/cxgb3/t3_hw.c
old mode 100644
new mode 100755
index ff262a0..7d8fbae
--- a/drivers/net/cxgb3/t3_hw.c
+++ b/drivers/net/cxgb3/t3_hw.c
@@ -2128,16 +2128,40 @@ void t3_port_intr_clear(struct adapter *adapter, int idx)
static int t3_sge_write_context(struct adapter *adapter, unsigned int id,
unsigned int type)
{
- t3_write_reg(adapter, A_SG_CONTEXT_MASK0, 0xffffffff);
- t3_write_reg(adapter, A_SG_CONTEXT_MASK1, 0xffffffff);
- t3_write_reg(adapter, A_SG_CONTEXT_MASK2, 0xffffffff);
- t3_write_reg(adapter, A_SG_CONTEXT_MASK3, 0xffffffff);
+ if (type == F_RESPONSEQ) {
+ /*
+ * Can't write the Response Queue Context bits for
+ * Interrupt Armed or the Reserve bits after the chip
+ * has been initialized out of reset. Writing to these
+ * bits can confuse the hardware.
+ */
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK0, 0xffffffff);
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK1, 0xffffffff);
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK2, 0x17ffffff);
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK3, 0xffffffff);
+ } else {
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK0, 0xffffffff);
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK1, 0xffffffff);
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK2, 0xffffffff);
+ t3_write_reg(adapter, A_SG_CONTEXT_MASK3, 0xffffffff);
+ }
t3_write_reg(adapter, A_SG_CONTEXT_CMD,
V_CONTEXT_CMD_OPCODE(1) | type | V_CONTEXT(id));
return t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
0, SG_CONTEXT_CMD_ATTEMPTS, 1);
}
+/**
+ * clear_sge_ctxt - completely clear an SGE context
+ * @adapter: the adapter
+ * @id: the context id
+ * @type: the context type
+ *
+ * Completely clear an SGE context. Used predominantly at post-reset
+ * initialization. Note in particular that we don't skip writing to any
+ * "sensitive bits" in the contexts the way that t3_sge_write_context()
+ * does ...
+ */
static int clear_sge_ctxt(struct adapter *adap, unsigned int id,
unsigned int type)
{
@@ -2145,7 +2169,14 @@ static int clear_sge_ctxt(struct adapter *adap, unsigned int id,
t3_write_reg(adap, A_SG_CONTEXT_DATA1, 0);
t3_write_reg(adap, A_SG_CONTEXT_DATA2, 0);
t3_write_reg(adap, A_SG_CONTEXT_DATA3, 0);
- return t3_sge_write_context(adap, id, type);
+ t3_write_reg(adap, A_SG_CONTEXT_MASK0, 0xffffffff);
+ t3_write_reg(adap, A_SG_CONTEXT_MASK1, 0xffffffff);
+ t3_write_reg(adap, A_SG_CONTEXT_MASK2, 0xffffffff);
+ t3_write_reg(adap, A_SG_CONTEXT_MASK3, 0xffffffff);
+ t3_write_reg(adap, A_SG_CONTEXT_CMD,
+ V_CONTEXT_CMD_OPCODE(1) | type | V_CONTEXT(id));
+ return t3_wait_op_done(adap, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
+ 0, SG_CONTEXT_CMD_ATTEMPTS, 1);
}
/**
@@ -2729,10 +2760,10 @@ static void tp_config(struct adapter *adap, const struct tp_params *p)
F_TCPCHECKSUMOFFLOAD | V_IPTTL(64));
t3_write_reg(adap, A_TP_TCP_OPTIONS, V_MTUDEFAULT(576) |
F_MTUENABLE | V_WINDOWSCALEMODE(1) |
- V_TIMESTAMPSMODE(0) | V_SACKMODE(1) | V_SACKRX(1));
+ V_TIMESTAMPSMODE(1) | V_SACKMODE(1) | V_SACKRX(1));
t3_write_reg(adap, A_TP_DACK_CONFIG, V_AUTOSTATE3(1) |
V_AUTOSTATE2(1) | V_AUTOSTATE1(0) |
- V_BYTETHRESHOLD(16384) | V_MSSTHRESHOLD(2) |
+ V_BYTETHRESHOLD(26880) | V_MSSTHRESHOLD(2) |
F_AUTOCAREFUL | F_AUTOENABLE | V_DACK_MODE(1));
t3_set_reg_field(adap, A_TP_IN_CONFIG, F_RXFBARBPRIO | F_TXFBARBPRIO,
F_IPV6ENABLE | F_NICMODE);
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 2.6.30 3/5] cxgb3: use resource_size_t for mmio declarations
2009-03-27 2:39 [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded Divy Le Ray
2009-03-27 2:39 ` [PATCH 2.6.30 2/5] cxgb3: sge setup fixes Divy Le Ray
@ 2009-03-27 2:39 ` Divy Le Ray
2009-03-27 7:53 ` David Miller
2009-03-27 2:39 ` [PATCH 2.6.30 4/5] cxgb3: differentiate portx and Tx channels Divy Le Ray
` (2 subsequent siblings)
4 siblings, 1 reply; 10+ messages in thread
From: Divy Le Ray @ 2009-03-27 2:39 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, swise
From: Divy Le Ray <divy@chelsio.com>
Use resource_size_t to declare mmio start and len variables.
Print PEX error register after EEH resumed.
Signed-off-by: Divy Le Ray <divy@chelsio.com>
---
drivers/net/cxgb3/cxgb3_main.c | 5 ++++-
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c
index 8ad5f32..e2b1193 100755
--- a/drivers/net/cxgb3/cxgb3_main.c
+++ b/drivers/net/cxgb3/cxgb3_main.c
@@ -2871,6 +2871,9 @@ static void t3_io_resume(struct pci_dev *pdev)
{
struct adapter *adapter = pci_get_drvdata(pdev);
+ CH_ALERT(adapter, "adapter recovering, PEX ERR 0x%x\n",
+ t3_read_reg(adapter, A_PCIE_PEX_ERR));
+
t3_resume_ports(adapter);
}
@@ -3003,7 +3006,7 @@ static int __devinit init_one(struct pci_dev *pdev,
static int version_printed;
int i, err, pci_using_dac = 0;
- unsigned long mmio_start, mmio_len;
+ resource_size_t mmio_start, mmio_len;
const struct adapter_info *ai;
struct adapter *adapter = NULL;
struct port_info *pi;
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 2.6.30 4/5] cxgb3: differentiate portx and Tx channels
2009-03-27 2:39 [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded Divy Le Ray
2009-03-27 2:39 ` [PATCH 2.6.30 2/5] cxgb3: sge setup fixes Divy Le Ray
2009-03-27 2:39 ` [PATCH 2.6.30 3/5] cxgb3: use resource_size_t for mmio declarations Divy Le Ray
@ 2009-03-27 2:39 ` Divy Le Ray
2009-03-27 7:53 ` David Miller
2009-03-27 2:39 ` [PATCH 2.6.30 5/5] cxgb3: map entire Rx page, feed map+offset to Rx ring Divy Le Ray
2009-03-27 7:52 ` [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded David Miller
4 siblings, 1 reply; 10+ messages in thread
From: Divy Le Ray @ 2009-03-27 2:39 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, swise
From: Divy Le Ray <divy@chelsio.com>
Separate ports from H/W Tx channels.
Signed-off-by: Divy Le Ray <divy@chelsio.com>
---
drivers/net/cxgb3/common.h | 4 +++-
drivers/net/cxgb3/cxgb3_main.c | 4 ++--
drivers/net/cxgb3/t3_hw.c | 35 +++++++++++++++++++----------------
3 files changed, 24 insertions(+), 19 deletions(-)
diff --git a/drivers/net/cxgb3/common.h b/drivers/net/cxgb3/common.h
index 9ee021e..e508dc3 100644
--- a/drivers/net/cxgb3/common.h
+++ b/drivers/net/cxgb3/common.h
@@ -191,7 +191,8 @@ struct mdio_ops {
};
struct adapter_info {
- unsigned char nports; /* # of ports */
+ unsigned char nports0; /* # of ports on channel 0 */
+ unsigned char nports1; /* # of ports on channel 1 */
unsigned char phy_base_addr; /* MDIO PHY base address */
unsigned int gpio_out; /* GPIO output settings */
unsigned char gpio_intr[MAX_NPORTS]; /* GPIO PHY IRQ pins */
@@ -422,6 +423,7 @@ struct adapter_params {
unsigned short b_wnd[NCCTRL_WIN];
unsigned int nports; /* # of ethernet ports */
+ unsigned int chan_map; /* bitmap of in-use Tx channels */
unsigned int stats_update_period; /* MAC stats accumulation period */
unsigned int linkpoll_period; /* link poll period in 0.1s */
unsigned int rev; /* chip revision */
diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c
old mode 100755
new mode 100644
index e2b1193..2c2aaa7
--- a/drivers/net/cxgb3/cxgb3_main.c
+++ b/drivers/net/cxgb3/cxgb3_main.c
@@ -3086,7 +3086,7 @@ static int __devinit init_one(struct pci_dev *pdev,
INIT_WORK(&adapter->fatal_error_handler_task, fatal_error_task);
INIT_DELAYED_WORK(&adapter->adap_check_task, t3_adap_check_task);
- for (i = 0; i < ai->nports; ++i) {
+ for (i = 0; i < ai->nports0 + ai->nports1; ++i) {
struct net_device *netdev;
netdev = alloc_etherdev_mq(sizeof(struct port_info), SGE_QSETS);
@@ -3176,7 +3176,7 @@ static int __devinit init_one(struct pci_dev *pdev,
out_free_dev:
iounmap(adapter->regs);
- for (i = ai->nports - 1; i >= 0; --i)
+ for (i = ai->nports0 + ai->nports1 - 1; i >= 0; --i)
if (adapter->port[i])
free_netdev(adapter->port[i]);
diff --git a/drivers/net/cxgb3/t3_hw.c b/drivers/net/cxgb3/t3_hw.c
old mode 100755
new mode 100644
index 7d8fbae..31ed31a
--- a/drivers/net/cxgb3/t3_hw.c
+++ b/drivers/net/cxgb3/t3_hw.c
@@ -493,20 +493,20 @@ int t3_phy_lasi_intr_handler(struct cphy *phy)
}
static const struct adapter_info t3_adap_info[] = {
- {2, 0,
+ {1, 1, 0,
F_GPIO2_OEN | F_GPIO4_OEN |
F_GPIO2_OUT_VAL | F_GPIO4_OUT_VAL, { S_GPIO3, S_GPIO5 }, 0,
&mi1_mdio_ops, "Chelsio PE9000"},
- {2, 0,
+ {1, 1, 0,
F_GPIO2_OEN | F_GPIO4_OEN |
F_GPIO2_OUT_VAL | F_GPIO4_OUT_VAL, { S_GPIO3, S_GPIO5 }, 0,
&mi1_mdio_ops, "Chelsio T302"},
- {1, 0,
+ {1, 0, 0,
F_GPIO1_OEN | F_GPIO6_OEN | F_GPIO7_OEN | F_GPIO10_OEN |
F_GPIO11_OEN | F_GPIO1_OUT_VAL | F_GPIO6_OUT_VAL | F_GPIO10_OUT_VAL,
{ 0 }, SUPPORTED_10000baseT_Full | SUPPORTED_AUI,
&mi1_mdio_ext_ops, "Chelsio T310"},
- {2, 0,
+ {1, 1, 0,
F_GPIO1_OEN | F_GPIO2_OEN | F_GPIO4_OEN | F_GPIO5_OEN | F_GPIO6_OEN |
F_GPIO7_OEN | F_GPIO10_OEN | F_GPIO11_OEN | F_GPIO1_OUT_VAL |
F_GPIO5_OUT_VAL | F_GPIO6_OUT_VAL | F_GPIO10_OUT_VAL,
@@ -514,7 +514,7 @@ static const struct adapter_info t3_adap_info[] = {
&mi1_mdio_ext_ops, "Chelsio T320"},
{},
{},
- {1, 0,
+ {1, 0, 0,
F_GPIO1_OEN | F_GPIO2_OEN | F_GPIO4_OEN | F_GPIO6_OEN | F_GPIO7_OEN |
F_GPIO10_OEN | F_GPIO1_OUT_VAL | F_GPIO6_OUT_VAL | F_GPIO10_OUT_VAL,
{ S_GPIO9 }, SUPPORTED_10000baseT_Full | SUPPORTED_AUI,
@@ -3227,20 +3227,22 @@ int t3_mps_set_active_ports(struct adapter *adap, unsigned int port_mask)
}
/*
- * Perform the bits of HW initialization that are dependent on the number
- * of available ports.
+ * Perform the bits of HW initialization that are dependent on the Tx
+ * channels being used.
*/
-static void init_hw_for_avail_ports(struct adapter *adap, int nports)
+static void chan_init_hw(struct adapter *adap, unsigned int chan_map)
{
int i;
- if (nports == 1) {
+ if (chan_map != 3) { /* one channel */
t3_set_reg_field(adap, A_ULPRX_CTL, F_ROUND_ROBIN, 0);
t3_set_reg_field(adap, A_ULPTX_CONFIG, F_CFG_RR_ARB, 0);
- t3_write_reg(adap, A_MPS_CFG, F_TPRXPORTEN | F_TPTXPORT0EN |
- F_PORT0ACTIVE | F_ENFORCEPKT);
- t3_write_reg(adap, A_PM1_TX_CFG, 0xffffffff);
- } else {
+ t3_write_reg(adap, A_MPS_CFG, F_TPRXPORTEN | F_ENFORCEPKT |
+ (chan_map == 1 ? F_TPTXPORT0EN | F_PORT0ACTIVE :
+ F_TPTXPORT1EN | F_PORT1ACTIVE));
+ t3_write_reg(adap, A_PM1_TX_CFG,
+ chan_map == 1 ? 0xffffffff : 0);
+ } else { /* two channels */
t3_set_reg_field(adap, A_ULPRX_CTL, 0, F_ROUND_ROBIN);
t3_set_reg_field(adap, A_ULPTX_CONFIG, 0, F_CFG_RR_ARB);
t3_write_reg(adap, A_ULPTX_DMA_WEIGHT,
@@ -3548,7 +3550,7 @@ int t3_init_hw(struct adapter *adapter, u32 fw_params)
t3_write_reg(adapter, A_PM1_RX_CFG, 0xffffffff);
t3_write_reg(adapter, A_PM1_RX_MODE, 0);
t3_write_reg(adapter, A_PM1_TX_MODE, 0);
- init_hw_for_avail_ports(adapter, adapter->params.nports);
+ chan_init_hw(adapter, adapter->params.chan_map);
t3_sge_init(adapter, &adapter->params.sge);
t3_write_reg(adapter, A_T3DBG_GPIO_ACT_LOW, calc_gpio_intr(adapter));
@@ -3785,7 +3787,8 @@ int t3_prep_adapter(struct adapter *adapter, const struct adapter_info *ai,
get_pci_mode(adapter, &adapter->params.pci);
adapter->params.info = ai;
- adapter->params.nports = ai->nports;
+ adapter->params.nports = ai->nports0 + ai->nports1;
+ adapter->params.chan_map = !!ai->nports0 | (!!ai->nports1 << 1);
adapter->params.rev = t3_read_reg(adapter, A_PL_REV);
/*
* We used to only run the "adapter check task" once a second if
@@ -3816,7 +3819,7 @@ int t3_prep_adapter(struct adapter *adapter, const struct adapter_info *ai,
mc7_prep(adapter, &adapter->pmtx, MC7_PMTX_BASE_ADDR, "PMTX");
mc7_prep(adapter, &adapter->cm, MC7_CM_BASE_ADDR, "CM");
- p->nchan = ai->nports;
+ p->nchan = adapter->params.chan_map == 3 ? 2 : 1;
p->pmrx_size = t3_mc7_size(&adapter->pmrx);
p->pmtx_size = t3_mc7_size(&adapter->pmtx);
p->cm_size = t3_mc7_size(&adapter->cm);
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 2.6.30 5/5] cxgb3: map entire Rx page, feed map+offset to Rx ring.
2009-03-27 2:39 [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded Divy Le Ray
` (2 preceding siblings ...)
2009-03-27 2:39 ` [PATCH 2.6.30 4/5] cxgb3: differentiate portx and Tx channels Divy Le Ray
@ 2009-03-27 2:39 ` Divy Le Ray
2009-03-27 7:53 ` David Miller
2009-03-27 7:52 ` [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded David Miller
4 siblings, 1 reply; 10+ messages in thread
From: Divy Le Ray @ 2009-03-27 2:39 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, swise
From: Divy Le Ray <divy@chelsio.com>
DMA mapping can be expensive in the presence of iommus.
Reduce the Rx iommu activity by mapping an entire page, and provide the H/W
the mapped address + offset of the current page chunk.
Reserve bits at the end of the page to track mapping references, so the page
can be unmapped.
Signed-off-by: Divy Le Ray <divy@chelsio.com>
---
drivers/net/cxgb3/adapter.h | 3 +
drivers/net/cxgb3/sge.c | 138 ++++++++++++++++++++++++++++++++-----------
2 files changed, 106 insertions(+), 35 deletions(-)
diff --git a/drivers/net/cxgb3/adapter.h b/drivers/net/cxgb3/adapter.h
index 2cf6c92..714df2b 100644
--- a/drivers/net/cxgb3/adapter.h
+++ b/drivers/net/cxgb3/adapter.h
@@ -85,6 +85,8 @@ struct fl_pg_chunk {
struct page *page;
void *va;
unsigned int offset;
+ u64 *p_cnt;
+ DECLARE_PCI_UNMAP_ADDR(mapping);
};
struct rx_desc;
@@ -101,6 +103,7 @@ struct sge_fl { /* SGE per free-buffer list state */
struct fl_pg_chunk pg_chunk;/* page chunk cache */
unsigned int use_pages; /* whether FL uses pages or sk_buffs */
unsigned int order; /* order of page allocations */
+ unsigned int alloc_size; /* size of allocated buffer */
struct rx_desc *desc; /* address of HW Rx descriptor ring */
struct rx_sw_desc *sdesc; /* address of SW Rx descriptor ring */
dma_addr_t phys_addr; /* physical address of HW ring start */
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
old mode 100755
new mode 100644
index 54667f0..26d3587
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -50,6 +50,7 @@
#define SGE_RX_COPY_THRES 256
#define SGE_RX_PULL_LEN 128
+#define SGE_PG_RSVD SMP_CACHE_BYTES
/*
* Page chunk size for FL0 buffers if FL0 is to be populated with page chunks.
* It must be a divisor of PAGE_SIZE. If set to 0 FL0 will use sk_buffs
@@ -57,8 +58,10 @@
*/
#define FL0_PG_CHUNK_SIZE 2048
#define FL0_PG_ORDER 0
+#define FL0_PG_ALLOC_SIZE (PAGE_SIZE << FL0_PG_ORDER)
#define FL1_PG_CHUNK_SIZE (PAGE_SIZE > 8192 ? 16384 : 8192)
#define FL1_PG_ORDER (PAGE_SIZE > 8192 ? 0 : 1)
+#define FL1_PG_ALLOC_SIZE (PAGE_SIZE << FL1_PG_ORDER)
#define SGE_RX_DROP_THRES 16
#define RX_RECLAIM_PERIOD (HZ/4)
@@ -345,13 +348,21 @@ static inline int should_restart_tx(const struct sge_txq *q)
return q->in_use - r < (q->size >> 1);
}
-static void clear_rx_desc(const struct sge_fl *q, struct rx_sw_desc *d)
+static void clear_rx_desc(struct pci_dev *pdev, const struct sge_fl *q,
+ struct rx_sw_desc *d)
{
- if (q->use_pages) {
- if (d->pg_chunk.page)
- put_page(d->pg_chunk.page);
+ if (q->use_pages && d->pg_chunk.page) {
+ (*d->pg_chunk.p_cnt)--;
+ if (!*d->pg_chunk.p_cnt)
+ pci_unmap_page(pdev,
+ pci_unmap_addr(&d->pg_chunk, mapping),
+ q->alloc_size, PCI_DMA_FROMDEVICE);
+
+ put_page(d->pg_chunk.page);
d->pg_chunk.page = NULL;
} else {
+ pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr),
+ q->buf_size, PCI_DMA_FROMDEVICE);
kfree_skb(d->skb);
d->skb = NULL;
}
@@ -372,9 +383,8 @@ static void free_rx_bufs(struct pci_dev *pdev, struct sge_fl *q)
while (q->credits--) {
struct rx_sw_desc *d = &q->sdesc[cidx];
- pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr),
- q->buf_size, PCI_DMA_FROMDEVICE);
- clear_rx_desc(q, d);
+
+ clear_rx_desc(pdev, q, d);
if (++cidx == q->size)
cidx = 0;
}
@@ -417,18 +427,39 @@ static inline int add_one_rx_buf(void *va, unsigned int len,
return 0;
}
-static int alloc_pg_chunk(struct sge_fl *q, struct rx_sw_desc *sd, gfp_t gfp,
+static inline int add_one_rx_chunk(dma_addr_t mapping, struct rx_desc *d,
+ unsigned int gen)
+{
+ d->addr_lo = cpu_to_be32(mapping);
+ d->addr_hi = cpu_to_be32((u64) mapping >> 32);
+ wmb();
+ d->len_gen = cpu_to_be32(V_FLD_GEN1(gen));
+ d->gen2 = cpu_to_be32(V_FLD_GEN2(gen));
+ return 0;
+}
+
+static int alloc_pg_chunk(struct adapter *adapter, struct sge_fl *q,
+ struct rx_sw_desc *sd, gfp_t gfp,
unsigned int order)
{
if (!q->pg_chunk.page) {
+ dma_addr_t mapping;
+
q->pg_chunk.page = alloc_pages(gfp, order);
if (unlikely(!q->pg_chunk.page))
return -ENOMEM;
q->pg_chunk.va = page_address(q->pg_chunk.page);
+ q->pg_chunk.p_cnt = q->pg_chunk.va + (PAGE_SIZE << order) -
+ SGE_PG_RSVD;
q->pg_chunk.offset = 0;
+ mapping = pci_map_page(adapter->pdev, q->pg_chunk.page,
+ 0, q->alloc_size, PCI_DMA_FROMDEVICE);
+ pci_unmap_addr_set(&q->pg_chunk, mapping, mapping);
}
sd->pg_chunk = q->pg_chunk;
+ prefetch(sd->pg_chunk.p_cnt);
+
q->pg_chunk.offset += q->buf_size;
if (q->pg_chunk.offset == (PAGE_SIZE << order))
q->pg_chunk.page = NULL;
@@ -436,6 +467,12 @@ static int alloc_pg_chunk(struct sge_fl *q, struct rx_sw_desc *sd, gfp_t gfp,
q->pg_chunk.va += q->buf_size;
get_page(q->pg_chunk.page);
}
+
+ if (sd->pg_chunk.offset == 0)
+ *sd->pg_chunk.p_cnt = 1;
+ else
+ *sd->pg_chunk.p_cnt += 1;
+
return 0;
}
@@ -460,35 +497,43 @@ static inline void ring_fl_db(struct adapter *adap, struct sge_fl *q)
*/
static int refill_fl(struct adapter *adap, struct sge_fl *q, int n, gfp_t gfp)
{
- void *buf_start;
struct rx_sw_desc *sd = &q->sdesc[q->pidx];
struct rx_desc *d = &q->desc[q->pidx];
unsigned int count = 0;
while (n--) {
+ dma_addr_t mapping;
int err;
if (q->use_pages) {
- if (unlikely(alloc_pg_chunk(q, sd, gfp, q->order))) {
+ if (unlikely(alloc_pg_chunk(adap, q, sd, gfp,
+ q->order))) {
nomem: q->alloc_failed++;
break;
}
- buf_start = sd->pg_chunk.va;
+ mapping = pci_unmap_addr(&sd->pg_chunk, mapping) +
+ sd->pg_chunk.offset;
+ pci_unmap_addr_set(sd, dma_addr, mapping);
+
+ add_one_rx_chunk(mapping, d, q->gen);
+ pci_dma_sync_single_for_device(adap->pdev, mapping,
+ q->buf_size - SGE_PG_RSVD,
+ PCI_DMA_FROMDEVICE);
} else {
- struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
+ void *buf_start;
+ struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
if (!skb)
goto nomem;
sd->skb = skb;
buf_start = skb->data;
- }
-
- err = add_one_rx_buf(buf_start, q->buf_size, d, sd, q->gen,
- adap->pdev);
- if (unlikely(err)) {
- clear_rx_desc(q, sd);
- break;
+ err = add_one_rx_buf(buf_start, q->buf_size, d, sd,
+ q->gen, adap->pdev);
+ if (unlikely(err)) {
+ clear_rx_desc(adap->pdev, q, sd);
+ break;
+ }
}
d++;
@@ -795,19 +840,19 @@ static struct sk_buff *get_packet_pg(struct adapter *adap, struct sge_fl *fl,
struct sk_buff *newskb, *skb;
struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
- newskb = skb = q->pg_skb;
+ dma_addr_t dma_addr = pci_unmap_addr(sd, dma_addr);
+ newskb = skb = q->pg_skb;
if (!skb && (len <= SGE_RX_COPY_THRES)) {
newskb = alloc_skb(len, GFP_ATOMIC);
if (likely(newskb != NULL)) {
__skb_put(newskb, len);
- pci_dma_sync_single_for_cpu(adap->pdev,
- pci_unmap_addr(sd, dma_addr), len,
+ pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len,
PCI_DMA_FROMDEVICE);
memcpy(newskb->data, sd->pg_chunk.va, len);
- pci_dma_sync_single_for_device(adap->pdev,
- pci_unmap_addr(sd, dma_addr), len,
- PCI_DMA_FROMDEVICE);
+ pci_dma_sync_single_for_device(adap->pdev, dma_addr,
+ len,
+ PCI_DMA_FROMDEVICE);
} else if (!drop_thres)
return NULL;
recycle:
@@ -820,16 +865,25 @@ recycle:
if (unlikely(q->rx_recycle_buf || (!skb && fl->credits <= drop_thres)))
goto recycle;
+ prefetch(sd->pg_chunk.p_cnt);
+
if (!skb)
newskb = alloc_skb(SGE_RX_PULL_LEN, GFP_ATOMIC);
+
if (unlikely(!newskb)) {
if (!drop_thres)
return NULL;
goto recycle;
}
- pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
- fl->buf_size, PCI_DMA_FROMDEVICE);
+ pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len,
+ PCI_DMA_FROMDEVICE);
+ (*sd->pg_chunk.p_cnt)--;
+ if (!*sd->pg_chunk.p_cnt)
+ pci_unmap_page(adap->pdev,
+ pci_unmap_addr(&sd->pg_chunk, mapping),
+ fl->alloc_size,
+ PCI_DMA_FROMDEVICE);
if (!skb) {
__skb_put(newskb, SGE_RX_PULL_LEN);
memcpy(newskb->data, sd->pg_chunk.va, SGE_RX_PULL_LEN);
@@ -1958,8 +2012,8 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq,
skb_pull(skb, sizeof(*p) + pad);
skb->protocol = eth_type_trans(skb, adap->port[p->iff]);
pi = netdev_priv(skb->dev);
- if ((pi->rx_offload & T3_RX_CSUM) && p->csum_valid && p->csum == htons(0xffff) &&
- !p->fragment) {
+ if ((pi->rx_offload & T3_RX_CSUM) && p->csum_valid &&
+ p->csum == htons(0xffff) && !p->fragment) {
qs->port_stats[SGE_PSTAT_RX_CSUM_GOOD]++;
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else
@@ -2034,10 +2088,19 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
fl->credits--;
len -= offset;
- pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
- fl->buf_size, PCI_DMA_FROMDEVICE);
+ pci_dma_sync_single_for_cpu(adap->pdev,
+ pci_unmap_addr(sd, dma_addr),
+ fl->buf_size - SGE_PG_RSVD,
+ PCI_DMA_FROMDEVICE);
+
+ (*sd->pg_chunk.p_cnt)--;
+ if (!*sd->pg_chunk.p_cnt)
+ pci_unmap_page(adap->pdev,
+ pci_unmap_addr(&sd->pg_chunk, mapping),
+ fl->alloc_size,
+ PCI_DMA_FROMDEVICE);
- prefetch(&qs->lro_frag_tbl);
+ prefetch(qs->lro_va);
rx_frag += nr_frags;
rx_frag->page = sd->pg_chunk.page;
@@ -2047,6 +2110,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
qs->lro_frag_tbl.nr_frags++;
qs->lro_frag_tbl.len = frag_len;
+
if (!complete)
return;
@@ -2236,6 +2300,8 @@ no_mem:
if (fl->use_pages) {
void *addr = fl->sdesc[fl->cidx].pg_chunk.va;
+ prefetch(&qs->lro_frag_tbl);
+
prefetch(addr);
#if L1_CACHE_BYTES < 128
prefetch(addr + L1_CACHE_BYTES);
@@ -2972,21 +3038,23 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
q->fl[1].use_pages = FL1_PG_CHUNK_SIZE > 0;
q->fl[0].order = FL0_PG_ORDER;
q->fl[1].order = FL1_PG_ORDER;
+ q->fl[0].alloc_size = FL0_PG_ALLOC_SIZE;
+ q->fl[1].alloc_size = FL1_PG_ALLOC_SIZE;
spin_lock_irq(&adapter->sge.reg_lock);
/* FL threshold comparison uses < */
ret = t3_sge_init_rspcntxt(adapter, q->rspq.cntxt_id, irq_vec_idx,
q->rspq.phys_addr, q->rspq.size,
- q->fl[0].buf_size, 1, 0);
+ q->fl[0].buf_size - SGE_PG_RSVD, 1, 0);
if (ret)
goto err_unlock;
for (i = 0; i < SGE_RXQ_PER_SET; ++i) {
ret = t3_sge_init_flcntxt(adapter, q->fl[i].cntxt_id, 0,
q->fl[i].phys_addr, q->fl[i].size,
- q->fl[i].buf_size, p->cong_thres, 1,
- 0);
+ q->fl[i].buf_size - SGE_PG_RSVD,
+ p->cong_thres, 1, 0);
if (ret)
goto err_unlock;
}
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded
2009-03-27 2:39 [PATCH 2.6.30 1/5] cxgb3: start qset timers when setup succeeded Divy Le Ray
` (3 preceding siblings ...)
2009-03-27 2:39 ` [PATCH 2.6.30 5/5] cxgb3: map entire Rx page, feed map+offset to Rx ring Divy Le Ray
@ 2009-03-27 7:52 ` David Miller
4 siblings, 0 replies; 10+ messages in thread
From: David Miller @ 2009-03-27 7:52 UTC (permalink / raw)
To: divy; +Cc: netdev, linux-kernel, swise
From: Divy Le Ray <divy@chelsio.com>
Date: Thu, 26 Mar 2009 19:39:09 -0700
> From: Divy Le Ray <divy@chelsio.com>
>
> Start queue set reclaim timers after the queue sets have been
> allocated successfully.
>
> Signed-off-by: Divy Le Ray <divy@chelsio.com>
Applied.
^ permalink raw reply [flat|nested] 10+ messages in thread