[PATCH v7 1/6] baseband/acc100: update companion PF configure function

[Nicolas Chautru <nicolas.chautru@intel.com>]

Update of the device configuration function from PF used for bbdev-test
to latest sequence for ACC199 PRQ device and matching version in
pf_bb_config 22.03.

Fixes: b17d70922d5d ("baseband/acc100: add configure function")
Cc: stable@dpdk.org

Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
---
 drivers/baseband/acc100/acc100_pf_enum.h |  18 ++++
 drivers/baseband/acc100/rte_acc100_pmd.c | 163 +++++++++++++++++++++++--------
 drivers/baseband/acc100/rte_acc100_pmd.h |  20 +++-
 3 files changed, 153 insertions(+), 48 deletions(-)

diff --git a/drivers/baseband/acc100/acc100_pf_enum.h b/drivers/baseband/acc100/acc100_pf_enum.h
index a1ee416..2fba667 100644
--- a/drivers/baseband/acc100/acc100_pf_enum.h
+++ b/drivers/baseband/acc100/acc100_pf_enum.h
@@ -238,6 +238,24 @@ enum {
 	HWPfPermonBTotalLatLowBusMon          =  0x00BAC504,
 	HWPfPermonBTotalLatUpperBusMon        =  0x00BAC508,
 	HWPfPermonBTotalReqCntBusMon          =  0x00BAC50C,
+	HwPfFabI2MArbCntrlReg                 =  0x00BB0000,
+	HWPfFabricMode                        =  0x00BB1000,
+	HwPfFabI2MGrp0DebugReg                =  0x00BBF000,
+	HwPfFabI2MGrp1DebugReg                =  0x00BBF004,
+	HwPfFabI2MGrp2DebugReg                =  0x00BBF008,
+	HwPfFabI2MGrp3DebugReg                =  0x00BBF00C,
+	HwPfFabI2MBuf0DebugReg                =  0x00BBF010,
+	HwPfFabI2MBuf1DebugReg                =  0x00BBF014,
+	HwPfFabI2MBuf2DebugReg                =  0x00BBF018,
+	HwPfFabI2MBuf3DebugReg                =  0x00BBF01C,
+	HwPfFabM2IBuf0Grp0DebugReg            =  0x00BBF020,
+	HwPfFabM2IBuf1Grp0DebugReg            =  0x00BBF024,
+	HwPfFabM2IBuf0Grp1DebugReg            =  0x00BBF028,
+	HwPfFabM2IBuf1Grp1DebugReg            =  0x00BBF02C,
+	HwPfFabM2IBuf0Grp2DebugReg            =  0x00BBF030,
+	HwPfFabM2IBuf1Grp2DebugReg            =  0x00BBF034,
+	HwPfFabM2IBuf0Grp3DebugReg            =  0x00BBF038,
+	HwPfFabM2IBuf1Grp3DebugReg            =  0x00BBF03C,
 	HWPfFecUl5gCntrlReg                   =  0x00BC0000,
 	HWPfFecUl5gI2MThreshReg               =  0x00BC0004,
 	HWPfFecUl5gVersionReg                 =  0x00BC0100,
diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c b/drivers/baseband/acc100/rte_acc100_pmd.c
index de7e4bc..79bee43 100644
--- a/drivers/baseband/acc100/rte_acc100_pmd.c
+++ b/drivers/baseband/acc100/rte_acc100_pmd.c
@@ -141,8 +141,8 @@
 	int acc_enum = accFromQgid(qg_idx, acc100_conf);
 	qtopFromAcc(&q_top, acc_enum, acc100_conf);
 	if (unlikely(q_top == NULL))
-		return 0;
-	return q_top->aq_depth_log2;
+		return 1;
+	return RTE_MAX(1, q_top->aq_depth_log2);
 }
 
 /* Return the AQ depth for a Queue Group Index */
@@ -4411,7 +4411,7 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 {
 	rte_bbdev_log(INFO, "rte_acc100_configure");
 	uint32_t value, address, status;
-	int qg_idx, template_idx, vf_idx, acc, i;
+	int qg_idx, template_idx, vf_idx, acc, i, j;
 	struct rte_bbdev *bbdev = rte_bbdev_get_named_dev(dev_name);
 
 	/* Compile time checks */
@@ -4431,6 +4431,9 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	/* Store configuration */
 	rte_memcpy(&d->acc100_conf, conf, sizeof(d->acc100_conf));
 
+	value = acc100_reg_read(d, HwPfPcieGpexBridgeControl);
+	bool firstCfg = (value != ACC100_CFG_PCI_BRIDGE);
+
 	/* PCIe Bridge configuration */
 	acc100_reg_write(d, HwPfPcieGpexBridgeControl, ACC100_CFG_PCI_BRIDGE);
 	for (i = 1; i < ACC100_GPEX_AXIMAP_NUM; i++)
@@ -4451,20 +4454,9 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	value = 1;
 	acc100_reg_write(d, address, value);
 
-	/* DDR Configuration */
-	address = HWPfDdrBcTim6;
-	value = acc100_reg_read(d, address);
-	value &= 0xFFFFFFFB; /* Bit 2 */
-#ifdef ACC100_DDR_ECC_ENABLE
-	value |= 0x4;
-#endif
-	acc100_reg_write(d, address, value);
-	address = HWPfDdrPhyDqsCountNum;
-#ifdef ACC100_DDR_ECC_ENABLE
-	value = 9;
-#else
-	value = 8;
-#endif
+	/* Enable granular dynamic clock gating */
+	address = HWPfHiClkGateHystReg;
+	value = ACC100_CLOCK_GATING_EN;
 	acc100_reg_write(d, address, value);
 
 	/* Set default descriptor signature */
@@ -4482,6 +4474,17 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	address = HWPfDmaAxcacheReg;
 	acc100_reg_write(d, address, value);
 
+	/* Adjust PCIe Lane adaptation */
+	for (i = 0; i < ACC100_QUAD_NUMS; i++)
+		for (j = 0; j < ACC100_LANES_PER_QUAD; j++)
+			acc100_reg_write(d, HwPfPcieLnAdaptctrl + i * ACC100_PCIE_QUAD_OFFSET
+					+ j * ACC100_PCIE_LANE_OFFSET, ACC100_ADAPT);
+
+	/* Enable PCIe live adaptation */
+	for (i = 0; i < ACC100_QUAD_NUMS; i++)
+		acc100_reg_write(d, HwPfPciePcsEqControl +
+				i * ACC100_PCIE_QUAD_OFFSET, ACC100_PCS_EQ);
+
 	/* Default DMA Configuration (Qmgr Enabled) */
 	address = HWPfDmaConfig0Reg;
 	value = 0;
@@ -4500,6 +4503,11 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	value = HWPfQmgrEgressQueuesTemplate;
 	acc100_reg_write(d, address, value);
 
+	/* Default Fabric Mode */
+	address = HWPfFabricMode;
+	value = ACC100_FABRIC_MODE;
+	acc100_reg_write(d, address, value);
+
 	/* ===== Qmgr Configuration ===== */
 	/* Configuration of the AQueue Depth QMGR_GRP_0_DEPTH_LOG2 for UL */
 	int totalQgs = conf->q_ul_4g.num_qgroups +
@@ -4518,22 +4526,17 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	}
 
 	/* Template Priority in incremental order */
-	for (template_idx = 0; template_idx < ACC100_NUM_TMPL;
-			template_idx++) {
-		address = HWPfQmgrGrpTmplateReg0Indx +
-		ACC100_BYTES_IN_WORD * (template_idx % 8);
+	for (template_idx = 0; template_idx < ACC100_NUM_TMPL; template_idx++) {
+		address = HWPfQmgrGrpTmplateReg0Indx + ACC100_BYTES_IN_WORD * template_idx;
 		value = ACC100_TMPL_PRI_0;
 		acc100_reg_write(d, address, value);
-		address = HWPfQmgrGrpTmplateReg1Indx +
-		ACC100_BYTES_IN_WORD * (template_idx % 8);
+		address = HWPfQmgrGrpTmplateReg1Indx + ACC100_BYTES_IN_WORD * template_idx;
 		value = ACC100_TMPL_PRI_1;
 		acc100_reg_write(d, address, value);
-		address = HWPfQmgrGrpTmplateReg2indx +
-		ACC100_BYTES_IN_WORD * (template_idx % 8);
+		address = HWPfQmgrGrpTmplateReg2indx + ACC100_BYTES_IN_WORD * template_idx;
 		value = ACC100_TMPL_PRI_2;
 		acc100_reg_write(d, address, value);
-		address = HWPfQmgrGrpTmplateReg3Indx +
-		ACC100_BYTES_IN_WORD * (template_idx % 8);
+		address = HWPfQmgrGrpTmplateReg3Indx + ACC100_BYTES_IN_WORD * template_idx;
 		value = ACC100_TMPL_PRI_3;
 		acc100_reg_write(d, address, value);
 	}
@@ -4584,9 +4587,6 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 			numEngines++;
 		} else
 			acc100_reg_write(d, address, 0);
-#if RTE_ACC100_SINGLE_FEC == 1
-		value = 0;
-#endif
 	}
 	printf("Number of 5GUL engines %d\n", numEngines);
 	/* 4GDL */
@@ -4601,9 +4601,6 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 		address = HWPfQmgrGrpTmplateReg4Indx
 				+ ACC100_BYTES_IN_WORD * template_idx;
 		acc100_reg_write(d, address, value);
-#if RTE_ACC100_SINGLE_FEC == 1
-			value = 0;
-#endif
 	}
 	/* 5GDL */
 	numQqsAcc += numQgs;
@@ -4617,13 +4614,10 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 		address = HWPfQmgrGrpTmplateReg4Indx
 				+ ACC100_BYTES_IN_WORD * template_idx;
 		acc100_reg_write(d, address, value);
-#if RTE_ACC100_SINGLE_FEC == 1
-		value = 0;
-#endif
 	}
 
 	/* Queue Group Function mapping */
-	int qman_func_id[5] = {0, 2, 1, 3, 4};
+	int qman_func_id[8] = {0, 2, 1, 3, 4, 0, 0, 0};
 	address = HWPfQmgrGrpFunction0;
 	value = 0;
 	for (qg_idx = 0; qg_idx < 8; qg_idx++) {
@@ -4654,7 +4648,7 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 		}
 	}
 
-	/* This pointer to ARAM (256kB) is shifted by 2 (4B per register) */
+	/* This pointer to ARAM (128kB) is shifted by 2 (4B per register) */
 	uint32_t aram_address = 0;
 	for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
 		for (vf_idx = 0; vf_idx < conf->num_vf_bundles; vf_idx++) {
@@ -4679,6 +4673,11 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 
 	/* ==== HI Configuration ==== */
 
+	/* No Info Ring/MSI by default */
+	acc100_reg_write(d, HWPfHiInfoRingIntWrEnRegPf, 0);
+	acc100_reg_write(d, HWPfHiInfoRingVf2pfLoWrEnReg, 0);
+	acc100_reg_write(d, HWPfHiCfgMsiIntWrEnRegPf, 0xFFFFFFFF);
+	acc100_reg_write(d, HWPfHiCfgMsiVf2pfLoWrEnReg, 0xFFFFFFFF);
 	/* Prevent Block on Transmit Error */
 	address = HWPfHiBlockTransmitOnErrorEn;
 	value = 0;
@@ -4691,10 +4690,6 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	address = HWPfHiPfMode;
 	value = (conf->pf_mode_en) ? ACC100_PF_VAL : 0;
 	acc100_reg_write(d, address, value);
-	/* Enable Error Detection in HW */
-	address = HWPfDmaErrorDetectionEn;
-	value = 0x3D7;
-	acc100_reg_write(d, address, value);
 
 	/* QoS overflow init */
 	value = 1;
@@ -4704,7 +4699,7 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	acc100_reg_write(d, address, value);
 
 	/* HARQ DDR Configuration */
-	unsigned int ddrSizeInMb = 512; /* Fixed to 512 MB per VF for now */
+	unsigned int ddrSizeInMb = ACC100_HARQ_DDR;
 	for (vf_idx = 0; vf_idx < conf->num_vf_bundles; vf_idx++) {
 		address = HWPfDmaVfDdrBaseRw + vf_idx
 				* 0x10;
@@ -4718,6 +4713,88 @@ static int acc100_pci_remove(struct rte_pci_device *pci_dev)
 	if (numEngines < (ACC100_SIG_UL_5G_LAST + 1))
 		poweron_cleanup(bbdev, d, conf);
 
+	uint32_t version = 0;
+	for (i = 0; i < 4; i++)
+		version += acc100_reg_read(d,
+				HWPfDdrPhyIdtmFwVersion + 4 * i) << (8 * i);
+	if (version != ACC100_PRQ_DDR_VER) {
+		printf("* Note: Not on DDR PRQ version %8x != %08x\n",
+				version, ACC100_PRQ_DDR_VER);
+	} else if (firstCfg) {
+		/* ---- DDR configuration at boot up --- */
+		/* Read Clear Ddr training status */
+		acc100_reg_read(d, HWPfChaDdrStDoneStatus);
+		/* Reset PHY/IDTM/UMMC */
+		acc100_reg_write(d, HWPfChaDdrWbRstCfg, 3);
+		acc100_reg_write(d, HWPfChaDdrApbRstCfg, 2);
+		acc100_reg_write(d, HWPfChaDdrPhyRstCfg, 2);
+		acc100_reg_write(d, HWPfChaDdrCpuRstCfg, 3);
+		acc100_reg_write(d, HWPfChaDdrSifRstCfg, 2);
+		usleep(ACC100_MS_IN_US);
+		/* Reset WB and APB resets */
+		acc100_reg_write(d, HWPfChaDdrWbRstCfg, 2);
+		acc100_reg_write(d, HWPfChaDdrApbRstCfg, 3);
+		/* Configure PHY-IDTM */
+		acc100_reg_write(d, HWPfDdrPhyIdletimeout, 0x3e8);
+		/* IDTM timing registers */
+		acc100_reg_write(d, HWPfDdrPhyRdLatency, 0x13);
+		acc100_reg_write(d, HWPfDdrPhyRdLatencyDbi, 0x15);
+		acc100_reg_write(d, HWPfDdrPhyWrLatency, 0x10011);
+		/* Configure SDRAM MRS registers */
+		acc100_reg_write(d, HWPfDdrPhyMr01Dimm, 0x3030b70);
+		acc100_reg_write(d, HWPfDdrPhyMr01DimmDbi, 0x3030b50);
+		acc100_reg_write(d, HWPfDdrPhyMr23Dimm, 0x30);
+		acc100_reg_write(d, HWPfDdrPhyMr67Dimm, 0xc00);
+		acc100_reg_write(d, HWPfDdrPhyMr45Dimm, 0x4000000);
+		/* Configure active lanes */
+		acc100_reg_write(d, HWPfDdrPhyDqsCountMax, 0x9);
+		acc100_reg_write(d, HWPfDdrPhyDqsCountNum, 0x9);
+		/* Configure WR/RD leveling timing registers */
+		acc100_reg_write(d, HWPfDdrPhyWrlvlWwRdlvlRr, 0x101212);
+		/* Configure what trainings to execute */
+		acc100_reg_write(d, HWPfDdrPhyTrngType, 0x2d3c);
+		/* Releasing PHY reset */
+		acc100_reg_write(d, HWPfChaDdrPhyRstCfg, 3);
+		/* Configure Memory Controller registers */
+		acc100_reg_write(d, HWPfDdrMemInitPhyTrng0, 0x3);
+		acc100_reg_write(d, HWPfDdrBcDram, 0x3c232003);
+		acc100_reg_write(d, HWPfDdrBcAddrMap, 0x31);
+		/* Configure UMMC BC timing registers */
+		acc100_reg_write(d, HWPfDdrBcRef, 0xa22);
+		acc100_reg_write(d, HWPfDdrBcTim0, 0x4050501);
+		acc100_reg_write(d, HWPfDdrBcTim1, 0xf0b0476);
+		acc100_reg_write(d, HWPfDdrBcTim2, 0x103);
+		acc100_reg_write(d, HWPfDdrBcTim3, 0x144050a1);
+		acc100_reg_write(d, HWPfDdrBcTim4, 0x23300);
+		acc100_reg_write(d, HWPfDdrBcTim5, 0x4230276);
+		acc100_reg_write(d, HWPfDdrBcTim6, 0x857914);
+		acc100_reg_write(d, HWPfDdrBcTim7, 0x79100232);
+		acc100_reg_write(d, HWPfDdrBcTim8, 0x100007ce);
+		acc100_reg_write(d, HWPfDdrBcTim9, 0x50020);
+		acc100_reg_write(d, HWPfDdrBcTim10, 0x40ee);
+		/* Configure UMMC DFI timing registers */
+		acc100_reg_write(d, HWPfDdrDfiInit, 0x5000);
+		acc100_reg_write(d, HWPfDdrDfiTim0, 0x15030006);
+		acc100_reg_write(d, HWPfDdrDfiTim1, 0x11305);
+		acc100_reg_write(d, HWPfDdrDfiPhyUpdEn, 0x1);
+		acc100_reg_write(d, HWPfDdrUmmcIntEn, 0x1f);
+		/* Release IDTM CPU out of reset */
+		acc100_reg_write(d, HWPfChaDdrCpuRstCfg, 0x2);
+		/* Wait PHY-IDTM to finish static training */
+		for (i = 0; i < ACC100_DDR_TRAINING_MAX; i++) {
+			usleep(ACC100_MS_IN_US);
+			value = acc100_reg_read(d,
+					HWPfChaDdrStDoneStatus);
+			if (value & 1)
+				break;
+		}
+		printf("DDR Training completed in %d ms", i);
+		/* Enable Memory Controller */
+		acc100_reg_write(d, HWPfDdrUmmcCtrl, 0x401);
+		/* Release AXI interface reset */
+		acc100_reg_write(d, HWPfChaDdrSifRstCfg, 3);
+	}
+
 	rte_bbdev_log_debug("PF Tip configuration complete for %s", dev_name);
 	return 0;
 }
diff --git a/drivers/baseband/acc100/rte_acc100_pmd.h b/drivers/baseband/acc100/rte_acc100_pmd.h
index cbcece2..071b37c 100644
--- a/drivers/baseband/acc100/rte_acc100_pmd.h
+++ b/drivers/baseband/acc100/rte_acc100_pmd.h
@@ -31,11 +31,6 @@
 #define RTE_ACC100_PF_DEVICE_ID        (0x0d5c)
 #define RTE_ACC100_VF_DEVICE_ID        (0x0d5d)
 
-/* Define as 1 to use only a single FEC engine */
-#ifndef RTE_ACC100_SINGLE_FEC
-#define RTE_ACC100_SINGLE_FEC 0
-#endif
-
 /* Values used in filling in descriptors */
 #define ACC100_DMA_DESC_TYPE           2
 #define ACC100_DMA_CODE_BLK_MODE       0
@@ -153,6 +148,12 @@
 #define ACC100_CFG_QMGR_HI_P    0x0F0F
 #define ACC100_CFG_PCI_AXI      0xC003
 #define ACC100_CFG_PCI_BRIDGE   0x40006033
+#define ACC100_QUAD_NUMS        4
+#define ACC100_LANES_PER_QUAD   4
+#define ACC100_PCIE_LANE_OFFSET 0x200
+#define ACC100_PCIE_QUAD_OFFSET 0x2000
+#define ACC100_PCS_EQ           0x6007
+#define ACC100_ADAPT            0x8400
 #define ACC100_ENGINE_OFFSET    0x1000
 #define ACC100_RESET_HI         0x20100
 #define ACC100_RESET_LO         0x20000
@@ -160,6 +161,15 @@
 #define ACC100_ENGINES_MAX      9
 #define ACC100_LONG_WAIT        1000
 #define ACC100_GPEX_AXIMAP_NUM  17
+#define ACC100_CLOCK_GATING_EN  0x30000
+#define ACC100_FABRIC_MODE      0xB
+/* DDR Size per VF - 512MB by default
+ * Can be increased up to 4 GB with single PF/VF
+ */
+#define ACC100_HARQ_DDR         (512 * 1)
+#define ACC100_PRQ_DDR_VER       0x10092020
+#define ACC100_MS_IN_US         (1000)
+#define ACC100_DDR_TRAINING_MAX (5000)
 
 /* ACC100 DMA Descriptor triplet */
 struct acc100_dma_triplet {
-- 
1.8.3.1