Skip to contentSkip to conversation

e1000e: use hardware writeback batching

PATCH Applied Jeff Kirsher 2 participants 7 messages Sep 30, 2010 – Oct 1, 2010

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/3 e1000e: use hardware writeback batching

From: Jesse Brandeburg <[email protected]>

Most e1000e parts support batching writebacks. The problem with this is that when some of the TADV or TIDV timers are not set, Tx can sit forever.

This is solved in this patch with write flushes using the Flush Partial Descriptors (FPD) bit in TIDV and RDTR.

This improves bus utilization and removes partial writes on e1000e, particularly from 82571 parts in S5500 chipset based machines.

Only ES2LAN and 82571/2 parts are included in this optimization, to reduce testing load.

---

 drivers/net/e1000e/82571.c   |    6 +++--
 drivers/net/e1000e/defines.h |    2 ++
 drivers/net/e1000e/e1000.h   |   28 ++++++++++++++++++++++
 drivers/net/e1000e/es2lan.c  |    1 +
 drivers/net/e1000e/netdev.c  |   53 ++++++++++++++++++++++++++++++++++++++++++
 drivers/net/e1000e/param.c   |    2 --
 6 files changed, 88 insertions(+), 4 deletions(-)
drivers/net/e1000e/82571.c +4 -2
index d3d4a57..ca663f1 100644
@@ -1801,7 +1801,8 @@ struct e1000_info e1000_82571_info = {
 				  | FLAG_RESET_OVERWRITES_LAA /* errata */
 				  | FLAG_TARC_SPEED_MODE_BIT /* errata */
 				  | FLAG_APME_CHECK_PORT_B,
-	.flags2			= FLAG2_DISABLE_ASPM_L1, /* errata 13 */
+	.flags2			= FLAG2_DISABLE_ASPM_L1 /* errata 13 */
+				  | FLAG2_DMA_BURST,
 	.pba			= 38,
 	.max_hw_frame_size	= DEFAULT_JUMBO,
 	.get_variants		= e1000_get_variants_82571,
@@ -1819,7 +1820,8 @@ struct e1000_info e1000_82572_info = {
 				  | FLAG_RX_CSUM_ENABLED
 				  | FLAG_HAS_CTRLEXT_ON_LOAD
 				  | FLAG_TARC_SPEED_MODE_BIT, /* errata */
-	.flags2			= FLAG2_DISABLE_ASPM_L1, /* errata 13 */
+	.flags2			= FLAG2_DISABLE_ASPM_L1 /* errata 13 */
+				  | FLAG2_DMA_BURST,
 	.pba			= 38,
 	.max_hw_frame_size	= DEFAULT_JUMBO,
 	.get_variants		= e1000_get_variants_82571,
drivers/net/e1000e/defines.h +2 -0
index 93b3bed..d3f7a9c 100644
@@ -446,7 +446,9 @@
 
 /* Transmit Descriptor Control */
 #define E1000_TXDCTL_PTHRESH 0x0000003F /* TXDCTL Prefetch Threshold */
+#define E1000_TXDCTL_HTHRESH 0x00003F00 /* TXDCTL Host Threshold */
 #define E1000_TXDCTL_WTHRESH 0x003F0000 /* TXDCTL Writeback Threshold */
+#define E1000_TXDCTL_GRAN    0x01000000 /* TXDCTL Granularity */
 #define E1000_TXDCTL_FULL_TX_DESC_WB 0x01010000 /* GRAN=1, WTHRESH=1 */
 #define E1000_TXDCTL_MAX_TX_DESC_PREFETCH 0x0100001F /* GRAN=1, PTHRESH=31 */
 /* Enable the counting of desc. still to be processed. */
drivers/net/e1000e/e1000.h +28 -0
index f9a31c8..5ec0af5 100644
@@ -153,6 +153,33 @@ struct e1000_info;
 /* Time to wait before putting the device into D3 if there's no link (in ms). */
 #define LINK_TIMEOUT		100
 
+#define DEFAULT_RDTR			0
+#define DEFAULT_RADV			8
+#define BURST_RDTR			0x20
+#define BURST_RADV			0x20
+
+/*
+ * in the case of WTHRESH, it appears at least the 82571/2 hardware
+ * writes back 4 descriptors when WTHRESH=5, and 3 descriptors when
+ * WTHRESH=4, and since we want 64 bytes at a time written back, set
+ * it to 5
+ */
+#define E1000_TXDCTL_DMA_BURST_ENABLE                          \
+	(E1000_TXDCTL_GRAN | /* set descriptor granularity */  \
+	 E1000_TXDCTL_COUNT_DESC |                             \
+	 (5 << 16) | /* wthresh must be +1 more than desired */\
+	 (1 << 8)  | /* hthresh */                             \
+	 0x1f)       /* pthresh */
+
+#define E1000_RXDCTL_DMA_BURST_ENABLE                          \
+	(0x01000000 | /* set descriptor granularity */         \
+	 (4 << 16)  | /* set writeback threshold    */         \
+	 (4 << 8)   | /* set prefetch threshold     */         \
+	 0x20)        /* set hthresh                */
+
+#define E1000_TIDV_FPD (1 << 31)
+#define E1000_RDTR_FPD (1 << 31)
+
 enum e1000_boards {
 	board_82571,
 	board_82572,
@@ -425,6 +452,7 @@ struct e1000_info {
 #define FLAG2_DISABLE_ASPM_L1             (1 << 3)
 #define FLAG2_HAS_PHY_STATS               (1 << 4)
 #define FLAG2_HAS_EEE                     (1 << 5)
+#define FLAG2_DMA_BURST                   (1 << 6)
 
 #define E1000_RX_DESC_PS(R, i)	    \
 	(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
drivers/net/e1000e/es2lan.c +1 -0
index 45aebb4..24f8ac9 100644
@@ -1494,6 +1494,7 @@ struct e1000_info e1000_es2_info = {
 				  | FLAG_APME_CHECK_PORT_B
 				  | FLAG_DISABLE_FC_PAUSE_TIME /* errata */
 				  | FLAG_TIPG_MEDIUM_FOR_80003ESLAN,
+	.flags2			= FLAG2_DMA_BURST,
 	.pba			= 38,
 	.max_hw_frame_size	= DEFAULT_JUMBO,
 	.get_variants		= e1000_get_variants_80003es2lan,
drivers/net/e1000e/netdev.c +53 -0

71 lines not on this page · raw message

drivers/net/e1000e/param.c +0 -2
index 34aeec1..3d36911 100644
@@ -91,7 +91,6 @@ E1000_PARAM(TxAbsIntDelay, "Transmit Absolute Interrupt Delay");
  * Valid Range: 0-65535
  */
 E1000_PARAM(RxIntDelay, "Receive Interrupt Delay");
-#define DEFAULT_RDTR 0
 #define MAX_RXDELAY 0xFFFF
 #define MIN_RXDELAY 0
 
@@ -101,7 +100,6 @@ E1000_PARAM(RxIntDelay, "Receive Interrupt Delay");
  * Valid Range: 0-65535
  */
 E1000_PARAM(RxAbsIntDelay, "Receive Absolute Interrupt Delay");
-#define DEFAULT_RADV 8
 #define MAX_RXABSDELAY 0xFFFF
 #define MIN_RXABSDELAY 0
 
#1 lore raw

PATCH 2/3 e1000e: reset PHY after errors detected on 82574 Si

From: Carolyn Wyborny <[email protected]>

Some errors can be induced in the PHY via environmental testing (specifically extreme temperature changes and electro static discharge testing), and in the case of the PHY hanging due to this input, this detects the problem and resets to continue. This issue only applies to 82574 silicon.

---

 drivers/net/e1000e/82571.c  |   40 +++++++++++++++++++++++++++++++++++++++-
 drivers/net/e1000e/e1000.h  |    3 +++
 drivers/net/e1000e/netdev.c |   25 +++++++++++++++++++++++++
 3 files changed, 67 insertions(+), 1 deletions(-)
drivers/net/e1000e/82571.c +39 -1
index ca663f1..db5ef6e 100644
@@ -52,6 +52,10 @@
 			      (ID_LED_DEF1_DEF2))
 
 #define E1000_GCR_L1_ACT_WITHOUT_L0S_RX 0x08000000
+#define E1000_BASE1000T_STATUS          10
+#define E1000_IDLE_ERROR_COUNT_MASK     0xFF
+#define E1000_RECEIVE_ERROR_COUNTER     21
+#define E1000_RECEIVE_ERROR_MAX         0xFFFF
 
 #define E1000_NVM_INIT_CTRL2_MNGM 0x6000 /* Manageability Operation Mode mask */
 
@@ -1243,6 +1247,39 @@ static s32 e1000_led_on_82574(struct e1000_hw *hw)
 }
 
 /**
+ *  e1000_check_phy_82574 - check 82574 phy hung state
+ *  @hw: pointer to the HW structure
+ *
+ *  Returns whether phy is hung or not
+ **/
+bool e1000_check_phy_82574(struct e1000_hw *hw)
+{
+	u16 status_1kbt = 0;
+	u16 receive_errors = 0;
+	bool phy_hung = false;
+	s32 ret_val = 0;
+
+	/*
+	 * Read PHY Receive Error counter first, if its is max - all F's then
+	 * read the Base1000T status register If both are max then PHY is hung.
+	 */
+	ret_val = e1e_rphy(hw, E1000_RECEIVE_ERROR_COUNTER, &receive_errors);
+
+	if (ret_val)
+		goto out;
+	if (receive_errors == E1000_RECEIVE_ERROR_MAX)  {
+		ret_val = e1e_rphy(hw, E1000_BASE1000T_STATUS, &status_1kbt);
+		if (ret_val)
+			goto out;
+		if ((status_1kbt & E1000_IDLE_ERROR_COUNT_MASK) ==
+		    E1000_IDLE_ERROR_COUNT_MASK)
+			phy_hung = true;
+	}
+out:
+	return phy_hung;
+}
+
+/**
  *  e1000_setup_link_82571 - Setup flow control and link settings
  *  @hw: pointer to the HW structure
  *
@@ -1858,7 +1895,8 @@ struct e1000_info e1000_82574_info = {
 				  | FLAG_RX_CSUM_ENABLED
 				  | FLAG_HAS_SMART_POWER_DOWN
 				  | FLAG_HAS_AMT
-				  | FLAG_HAS_CTRLEXT_ON_LOAD,
+				  | FLAG_HAS_CTRLEXT_ON_LOAD
+				  | FLAG2_CHECK_PHY_HANG,
 	.pba			= 36,
 	.max_hw_frame_size	= DEFAULT_JUMBO,
 	.get_variants		= e1000_get_variants_82571,
drivers/net/e1000e/e1000.h +3 -0
index 5ec0af5..da3b82f 100644
@@ -397,6 +397,7 @@ struct e1000_adapter {
 	struct work_struct print_hang_task;
 
 	bool idle_check;
+	int phy_hang_count;
 };
 
 struct e1000_info {
@@ -453,6 +454,7 @@ struct e1000_info {
 #define FLAG2_HAS_PHY_STATS               (1 << 4)
 #define FLAG2_HAS_EEE                     (1 << 5)
 #define FLAG2_DMA_BURST                   (1 << 6)
+#define FLAG2_CHECK_PHY_HANG              (1 << 7)
 
 #define E1000_RX_DESC_PS(R, i)	    \
 	(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
@@ -630,6 +632,7 @@ extern s32 e1000_get_phy_info_ife(struct e1000_hw *hw);
 extern s32 e1000_check_polarity_ife(struct e1000_hw *hw);
 extern s32 e1000_phy_force_speed_duplex_ife(struct e1000_hw *hw);
 extern s32 e1000_check_polarity_igp(struct e1000_hw *hw);
+extern bool e1000_check_phy_82574(struct e1000_hw *hw);
 
 static inline s32 e1000_phy_hw_reset(struct e1000_hw *hw)
 {
drivers/net/e1000e/netdev.c +25 -0
index 1aa4228..a8b55ab 100644
@@ -4060,6 +4060,28 @@ static void e1000e_enable_receives(struct e1000_adapter *adapter)
 	}
 }
 
+static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+
+	if (!(adapter->flags2 & FLAG2_CHECK_PHY_HANG))
+		return;
+
+	/*
+	 * With 82574 controllers, PHY needs to be checked periodically
+	 * for hung state and reset, if two calls return true
+	 */
+	if (e1000_check_phy_82574(hw))
+		adapter->phy_hang_count++;
+	else
+		adapter->phy_hang_count = 0;
+
+	if (adapter->phy_hang_count > 1) {
+		adapter->phy_hang_count = 0;
+		schedule_work(&adapter->reset_task);
+	}
+}
+
 /**
  * e1000_watchdog - Timer Call-back
  * @data: pointer to adapter cast into an unsigned long
@@ -4295,6 +4317,9 @@ link_up:
 	if (e1000e_get_laa_state_82571(hw))
 		e1000e_rar_set(hw, adapter->hw.mac.addr, 0);
 
+	if (adapter->flags2 & FLAG2_CHECK_PHY_HANG)
+		e1000e_check_82574_phy_workaround(adapter);
+
 	/* Reset the timer */
 	if (!test_bit(__E1000_DOWN, &adapter->state))
 		mod_timer(&adapter->watchdog_timer,
#2 lore raw

Re: [net-next-2.6 PATCH 2/3] e1000e: reset PHY after errors detected on 82574 Si

Quoted 12 lines · Jeff Kirsher

From: Carolyn Wyborny <[email protected]>

Some errors can be induced in the PHY via environmental testing (specifically extreme temperature changes and electro static discharge testing), and in the case of the PHY hanging due to this input, this detects the problem and resets to continue. This issue only applies to 82574 silicon.

Quoted 7 lines

---

 drivers/net/e1000e/82571.c  |   40 +++++++++++++++++++++++++++++++++++++++- drivers/net/e1000e/e1000.h  |    3 +++ drivers/net/e1000e/netdev.c |   25 +++++++++++++++++++++++++

 3 files changed, 67 insertions(+), 1 deletions(-)

Dave - please ignore this patch. An issue was found with this patch.

Signature · 2 lines
Cheers,
Jeff
maintainer
#3 lore raw

Re: [net-next-2.6 PATCH 2/3] e1000e: reset PHY after errors detected on 82574 Si

From: Jeff Kirsher <[email protected]>
Date: Thu, 30 Sep 2010 16:00:47 -0700

Quoted 1 line

Dave - please ignore this patch. An issue was found with this patch.

Ok.

#4 lore raw

PATCH 3/3 e1000e: 82579 performance improvements

In reply to Jeff Kirsher

From: Bruce Allan <[email protected]>

The initial support for 82579 was tuned poorly for performance. Adjust the packet buffer allocation appropriately for both standard and jumbo frames; and for jumbo frames increase the receive descriptor pre-fetch, disable adaptive interrupt moderation and set the DMA latency tolerance.

---

 drivers/net/e1000e/e1000.h   |    1 +
 drivers/net/e1000e/ich8lan.c |    2 +-
 drivers/net/e1000e/netdev.c  |   50 +++++++++++++++++++++++++++++++++++++-----
 3 files changed, 46 insertions(+), 7 deletions(-)
drivers/net/e1000e/e1000.h +1 -0
index da3b82f..8a79bbd 100644
@@ -455,6 +455,7 @@ struct e1000_info {
 #define FLAG2_HAS_EEE                     (1 << 5)
 #define FLAG2_DMA_BURST                   (1 << 6)
 #define FLAG2_CHECK_PHY_HANG              (1 << 7)
+#define FLAG2_DISABLE_AIM                 (1 << 8)
 
 #define E1000_RX_DESC_PS(R, i)	    \
 	(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
drivers/net/e1000e/ich8lan.c +1 -1
index 57b5435..e3374d9 100644
@@ -3986,7 +3986,7 @@ struct e1000_info e1000_pch2_info = {
 				  | FLAG_APME_IN_WUC,
 	.flags2			= FLAG2_HAS_PHY_STATS
 				  | FLAG2_HAS_EEE,
-	.pba			= 18,
+	.pba			= 26,
 	.max_hw_frame_size	= DEFAULT_JUMBO,
 	.get_variants		= e1000_get_variants_ich8lan,
 	.mac_ops		= &ich8_mac_ops,
drivers/net/e1000e/netdev.c +44 -6

98 lines not on this page · raw message

maintainer Applied
#5 lore raw

Re: [net-next-2.6 PATCH 3/3] e1000e: 82579 performance improvements

From: Jeff Kirsher <[email protected]>
Date: Thu, 30 Sep 2010 00:39:37 -0700

Quoted 10 lines

From: Bruce Allan <[email protected]>

The initial support for 82579 was tuned poorly for performance. Adjust the packet buffer allocation appropriately for both standard and jumbo frames; and for jumbo frames increase the receive descriptor pre-fetch, disable adaptive interrupt moderation and set the DMA latency tolerance.

Applied.

maintainer Applied
#6 lore raw
In reply to Jeff Kirsher

From: Jeff Kirsher <[email protected]>
Date: Thu, 30 Sep 2010 00:38:49 -0700

Quoted 11 lines

From: Jesse Brandeburg <[email protected]>

Most e1000e parts support batching writebacks. The problem with this is that when some of the TADV or TIDV timers are not set, Tx can sit forever.

This is solved in this patch with write flushes using the Flush Partial Descriptors (FPD) bit in TIDV and RDTR.

This improves bus utilization and removes partial writes on e1000e, particularly from 82571 parts in S5500 chipset based machines.

Quoted 6 lines

Only ES2LAN and 82571/2 parts are included in this optimization, to reduce testing load.

Applied.