diff mbox

[dpdk-dev,v2] i40e: workaround for XL710 performance

Message ID 82F45D86ADE5454A95A89742C8D1410E01CBD050@shsmsx102.ccr.corp.intel.com (mailing list archive)
State Not Applicable, archived
Headers show

Commit Message

Xu, Qian Q Feb. 10, 2015, 9:06 a.m. UTC
Tested-by: Qian Xu <qian.q.xu@intel.com>

- Tested Commit: 2250cc5a191906c914221ff4f0da7b5d699b4175
- OS: Fedora20 3.18.0
- GCC: gcc version 4.8.3 20140911
- CPU: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz
- NIC: Intel Ethernet Controller XL710 for 40GbE QSFP+ [8086:1583]
- Default x86_64-native-linuxapp-gcc configuration
- Total 1 case, 1 passed, 0 failed

- Case: l3fwd_2port_perf
  Description: Check l3fwd of 2port on different card can achieve hardware limitation rate.
 Command / instruction:
    Bind 40G port to igb_uio
		./<dpdk>/tools/dpdk_nic_bind.py --bind=igb_uio 82:00.1 85:00.1
	Run l3fwd 
		./l3fwd -c 0x3fc0000 -n 4 -w 82:00.1 -w 85:00.1 -- -p 0x3 --config '(0,0,18),(0,1,19),(1,0,20),(1,1,21)'
    Ixia send packets with IP
   Expected test result:
	Ixia can receive the packet with maximum hardware limitation rate. 

-----Original Message-----
From: Zhang, Helin 
Sent: Monday, December 29, 2014 9:41 AM
To: dev@dpdk.org
Cc: nhorman@tuxdriver.com; Xu, Qian Q; Cao, Waterman; Lu, Patrick; Liu, Jijiang; Wu, Jingjing; Zhang, Helin
Subject: [PATCH v2] i40e: workaround for XL710 performance

On XL710, performance number is far from the expectation on recent firmware versions, if promiscuous mode is disabled, or promiscuous mode is enabled and port MAC address is equal to the packet destination MAC address. The fix for this issue may not be integrated in the following firmware version. So the workaround in software driver is needed. For XL710, it needs to modify the initial values of 3 internal only registers, which are the same as X710.
Note that the values for X710 and XL710 registers could be different, and the workaround can be removed when it is fixed in firmware in the future.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
---
 lib/librte_pmd_i40e/i40e_ethdev.c | 44 ++++++++++++++++++++++++++-------------
 1 file changed, 30 insertions(+), 14 deletions(-)

v2 changes:
* Supported modifying the address of 0x269FBC of XL710 during
  initialization, to fix the minor performance gap to expectation.
  That means XL710 can meet the performance expectation with this
  workaround.
diff mbox

Patch

diff --git a/lib/librte_pmd_i40e/i40e_ethdev.c b/lib/librte_pmd_i40e/i40e_ethdev.c
index b47a3d2..8982920 100644
--- a/lib/librte_pmd_i40e/i40e_ethdev.c
+++ b/lib/librte_pmd_i40e/i40e_ethdev.c
@@ -5327,38 +5327,54 @@  i40e_debug_read_register(struct i40e_hw *hw, uint32_t addr, uint64_t *val)
 
 /*
  * On X710, performance number is far from the expectation on recent firmware
- * versions. The fix for this issue may not be integrated in the following
+ * versions; on XL710, performance number is also far from the 
+ expectation on
+ * recent firmware versions, if promiscuous mode is disabled, or 
+ promiscuous
+ * mode is enabled and port MAC address is equal to the packet 
+ destination MAC
+ * address. The fix for this issue may not be integrated in the 
+ following
  * firmware version. So the workaround in software driver is needed. It needs
- * to modify the initial values of 3 internal only registers. Note that the
+ * to modify the initial values of 3 internal only registers for both 
+ X710 and
+ * XL710. Note that the values for X710 or XL710 could be different, 
+ and the
  * workaround can be removed when it is fixed in firmware in the future.
  */
-static void
-i40e_configure_registers(struct i40e_hw *hw) -{
+
+/* For both X710 and XL710 */
+#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200
 #define I40E_GL_SWR_PRI_JOIN_MAP_0       0x26CE00
+
+#define I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
 #define I40E_GL_SWR_PRI_JOIN_MAP_2       0x26CE08
+
+/* For X710 */
+#define I40E_GL_SWR_PM_UP_THR_EF_VALUE   0x03030303
+/* For XL710 */
+#define I40E_GL_SWR_PM_UP_THR_SF_VALUE   0x06060606
 #define I40E_GL_SWR_PM_UP_THR            0x269FBC
-#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200 -#define I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
-#define I40E_GL_SWR_PM_UP_THR_VALUE      0x03030303
 
-	static const struct {
+static void
+i40e_configure_registers(struct i40e_hw *hw) {
+	static struct {
 		uint32_t addr;
 		uint64_t val;
 	} reg_table[] = {
 		{I40E_GL_SWR_PRI_JOIN_MAP_0, I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE},
 		{I40E_GL_SWR_PRI_JOIN_MAP_2, I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE},
-		{I40E_GL_SWR_PM_UP_THR, I40E_GL_SWR_PM_UP_THR_VALUE},
+		{I40E_GL_SWR_PM_UP_THR, 0}, /* Compute value dynamically */
 	};
 	uint64_t reg;
 	uint32_t i;
 	int ret;
 
-	/* Below fix is for X710 only */
-	if (i40e_is_40G_device(hw->device_id))
-		return;
-
 	for (i = 0; i < RTE_DIM(reg_table); i++) {
+		if (reg_table[i].addr == I40E_GL_SWR_PM_UP_THR) {
+			if (i40e_is_40G_device(hw->device_id)) /* For XL710 */
+				reg_table[i].val =
+					I40E_GL_SWR_PM_UP_THR_SF_VALUE;
+			else /* For X710 */
+				reg_table[i].val =
+					I40E_GL_SWR_PM_UP_THR_EF_VALUE;
+		}
+
 		ret = i40e_debug_read_register(hw, reg_table[i].addr, &reg);
 		if (ret < 0) {
 			PMD_DRV_LOG(ERR, "Failed to read from 0x%"PRIx32,
--
1.9.3