Merge branch 'cxgb4-collect-hardware-logs-via-ethtool'

Rahul Lakkireddy says:

====================
cxgb4: collect hardware logs via ethtool

Collect more hardware logs via ethtool --get-dump facility.

Patch 1 collects on-chip memory layout information.

Patch 2 collects on-chip MC memory dumps.

Patch 3 collects HMA memory dump.

Patch 4 evaluates and skips TX and RX payload regions in memory dumps.

Patch 5 collects egress and ingress SGE queue contexts.

Patch 6 collects PCIe configuration logs
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h

@@ -18,17 +18,15 @@
 #ifndef __CUDBG_ENTITY_H__
 #define __CUDBG_ENTITY_H__
 
-#define EDC0_FLAG 3
-#define EDC1_FLAG 4
+#define EDC0_FLAG 0
+#define EDC1_FLAG 1
+#define MC_FLAG 2
+#define MC0_FLAG 3
+#define MC1_FLAG 4
+#define HMA_FLAG 5
 
 #define CUDBG_ENTITY_SIGNATURE 0xCCEDB001
 
-struct card_mem {
-	u16 size_edc0;
-	u16 size_edc1;
-	u16 mem_flag;
-};
-
 struct cudbg_mbox_log {
 	struct mbox_cmd entry;
 	u32 hi[MBOX_LEN / 8];
@@ -87,6 +85,48 @@ struct cudbg_tp_la {
 	u8 data[0];
 };
 
+static const char * const cudbg_region[] = {
+	"DBQ contexts:", "IMSG contexts:", "FLM cache:", "TCBs:",
+	"Pstructs:", "Timers:", "Rx FL:", "Tx FL:", "Pstruct FL:",
+	"Tx payload:", "Rx payload:", "LE hash:", "iSCSI region:",
+	"TDDP region:", "TPT region:", "STAG region:", "RQ region:",
+	"RQUDP region:", "PBL region:", "TXPBL region:",
+	"DBVFIFO region:", "ULPRX state:", "ULPTX state:",
+	"On-chip queues:"
+};
+
+/* Memory region info relative to current memory (i.e. wrt 0). */
+struct cudbg_region_info {
+	bool exist; /* Does region exists in current memory? */
+	u32 start;  /* Start wrt 0 */
+	u32 end;    /* End wrt 0 */
+};
+
+struct cudbg_mem_desc {
+	u32 base;
+	u32 limit;
+	u32 idx;
+};
+
+struct cudbg_meminfo {
+	struct cudbg_mem_desc avail[4];
+	struct cudbg_mem_desc mem[ARRAY_SIZE(cudbg_region) + 3];
+	u32 avail_c;
+	u32 mem_c;
+	u32 up_ram_lo;
+	u32 up_ram_hi;
+	u32 up_extmem2_lo;
+	u32 up_extmem2_hi;
+	u32 rx_pages_data[3];
+	u32 tx_pages_data[4];
+	u32 p_structs;
+	u32 reserved[12];
+	u32 port_used[4];
+	u32 port_alloc[4];
+	u32 loopback_used[NCHAN];
+	u32 loopback_alloc[NCHAN];
+};
+
 struct cudbg_cim_pif_la {
 	int size;
 	u8 data[0];
@@ -145,6 +185,7 @@ struct cudbg_tid_info_region_rev1 {
 	u32 reserved[16];
 };
 
+#define CUDBG_LOWMEM_MAX_CTXT_QIDS 256
 #define CUDBG_MAX_FL_QIDS 1024
 
 struct cudbg_ch_cntxt {
@@ -334,6 +375,25 @@ static const u32 t5_pm_tx_array[][IREG_NUM_ELEM] = {
 	{0x8FF0, 0x8FF4, 0x10021, 0x1D}, /* t5_pm_tx_regs_10021_to_1003c */
 };
 
+#define CUDBG_NUM_PCIE_CONFIG_REGS 0x61
+
+static const u32 t5_pcie_config_array[][2] = {
+	{0x0, 0x34},
+	{0x3c, 0x40},
+	{0x50, 0x64},
+	{0x70, 0x80},
+	{0x94, 0xa0},
+	{0xb0, 0xb8},
+	{0xd0, 0xd4},
+	{0x100, 0x128},
+	{0x140, 0x148},
+	{0x150, 0x164},
+	{0x170, 0x178},
+	{0x180, 0x194},
+	{0x1a0, 0x1b8},
+	{0x1c0, 0x208},
+};
+
 static const u32 t6_ma_ireg_array[][IREG_NUM_ELEM] = {
 	{0x78f8, 0x78fc, 0xa000, 23}, /* t6_ma_regs_a000_to_a016 */
 	{0x78f8, 0x78fc, 0xa400, 30}, /* t6_ma_regs_a400_to_a41e */

drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h

@@ -47,6 +47,8 @@ enum cudbg_dbg_entity_type {
 	CUDBG_CIM_OBQ_NCSI = 17,
 	CUDBG_EDC0 = 18,
 	CUDBG_EDC1 = 19,
+	CUDBG_MC0 = 20,
+	CUDBG_MC1 = 21,
 	CUDBG_RSS = 22,
 	CUDBG_RSS_VF_CONF = 25,
 	CUDBG_PATH_MTU = 27,
@@ -56,6 +58,7 @@ enum cudbg_dbg_entity_type {
 	CUDBG_SGE_INDIRECT = 37,
 	CUDBG_ULPRX_LA = 41,
 	CUDBG_TP_LA = 43,
+	CUDBG_MEMINFO = 44,
 	CUDBG_CIM_PIF_LA = 45,
 	CUDBG_CLK = 46,
 	CUDBG_CIM_OBQ_RXQ0 = 47,
@@ -63,6 +66,7 @@ enum cudbg_dbg_entity_type {
 	CUDBG_PCIE_INDIRECT = 50,
 	CUDBG_PM_INDIRECT = 51,
 	CUDBG_TID_INFO = 54,
+	CUDBG_PCIE_CONFIG = 55,
 	CUDBG_DUMP_CONTEXT = 56,
 	CUDBG_MPS_TCAM = 57,
 	CUDBG_VPD_DATA = 58,
@@ -74,6 +78,7 @@ enum cudbg_dbg_entity_type {
 	CUDBG_PBT_TABLE = 65,
 	CUDBG_MBOX_LOG = 66,
 	CUDBG_HMA_INDIRECT = 67,
+	CUDBG_HMA = 68,
 	CUDBG_MAX_ENTITY = 70,
 };
 

drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h

@@ -75,6 +75,12 @@ int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init,
 int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init,
 			       struct cudbg_buffer *dbg_buff,
 			       struct cudbg_error *cudbg_err);
+int cudbg_collect_mc0_meminfo(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_mc1_meminfo(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
 int cudbg_collect_rss(struct cudbg_init *pdbg_init,
 		      struct cudbg_buffer *dbg_buff,
 		      struct cudbg_error *cudbg_err);
@@ -102,6 +108,9 @@ int cudbg_collect_ulprx_la(struct cudbg_init *pdbg_init,
 int cudbg_collect_tp_la(struct cudbg_init *pdbg_init,
 			struct cudbg_buffer *dbg_buff,
 			struct cudbg_error *cudbg_err);
+int cudbg_collect_meminfo(struct cudbg_init *pdbg_init,
+			  struct cudbg_buffer *dbg_buff,
+			  struct cudbg_error *cudbg_err);
 int cudbg_collect_cim_pif_la(struct cudbg_init *pdbg_init,
 			     struct cudbg_buffer *dbg_buff,
 			     struct cudbg_error *cudbg_err);
@@ -123,6 +132,9 @@ int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init,
 int cudbg_collect_tid(struct cudbg_init *pdbg_init,
 		      struct cudbg_buffer *dbg_buff,
 		      struct cudbg_error *cudbg_err);
+int cudbg_collect_pcie_config(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
 int cudbg_collect_dump_context(struct cudbg_init *pdbg_init,
 			       struct cudbg_buffer *dbg_buff,
 			       struct cudbg_error *cudbg_err);
@@ -156,6 +168,9 @@ int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init,
 int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init,
 			       struct cudbg_buffer *dbg_buff,
 			       struct cudbg_error *cudbg_err);
+int cudbg_collect_hma_meminfo(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
 
 struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i);
 void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff,
@@ -163,7 +178,8 @@ void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff,
 u32 cudbg_cim_obq_size(struct adapter *padap, int qid);
 int cudbg_dump_context_size(struct adapter *padap);
 
-struct cudbg_tcam;
+int cudbg_fill_meminfo(struct adapter *padap,
+		       struct cudbg_meminfo *meminfo_buff);
 void cudbg_fill_le_tcam_info(struct adapter *padap,
 			     struct cudbg_tcam *tcam_region);
 #endif /* __CUDBG_LIB_H__ */

drivers/net/ethernet/chelsio/cxgb4/cxgb4.h

@@ -77,7 +77,8 @@ enum {
 	MEM_EDC1,
 	MEM_MC,
 	MEM_MC0 = MEM_MC,
-	MEM_MC1
+	MEM_MC1,
+	MEM_HMA,
 };
 
 enum {
@@ -1653,7 +1654,7 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int eqid);
 int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int eqid);
-int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox);
+int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type);
 void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl);
 int t4_update_port_info(struct port_info *pi);
 int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,

drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c

@@ -18,11 +18,13 @@
 #include "t4_regs.h"
 #include "cxgb4.h"
 #include "cxgb4_cudbg.h"
-#include "cudbg_entity.h"
 
 static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = {
 	{ CUDBG_EDC0, cudbg_collect_edc0_meminfo },
 	{ CUDBG_EDC1, cudbg_collect_edc1_meminfo },
+	{ CUDBG_MC0, cudbg_collect_mc0_meminfo },
+	{ CUDBG_MC1, cudbg_collect_mc1_meminfo },
+	{ CUDBG_HMA, cudbg_collect_hma_meminfo },
 };
 
 static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = {
@@ -53,6 +55,7 @@ static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = {
 	{ CUDBG_SGE_INDIRECT, cudbg_collect_sge_indirect },
 	{ CUDBG_ULPRX_LA, cudbg_collect_ulprx_la },
 	{ CUDBG_TP_LA, cudbg_collect_tp_la },
+	{ CUDBG_MEMINFO, cudbg_collect_meminfo },
 	{ CUDBG_CIM_PIF_LA, cudbg_collect_cim_pif_la },
 	{ CUDBG_CLK, cudbg_collect_clk_info },
 	{ CUDBG_CIM_OBQ_RXQ0, cudbg_collect_obq_sge_rx_q0 },
@@ -60,6 +63,7 @@ static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = {
 	{ CUDBG_PCIE_INDIRECT, cudbg_collect_pcie_indirect },
 	{ CUDBG_PM_INDIRECT, cudbg_collect_pm_indirect },
 	{ CUDBG_TID_INFO, cudbg_collect_tid },
+	{ CUDBG_PCIE_CONFIG, cudbg_collect_pcie_config },
 	{ CUDBG_DUMP_CONTEXT, cudbg_collect_dump_context },
 	{ CUDBG_MPS_TCAM, cudbg_collect_mps_tcam },
 	{ CUDBG_VPD_DATA, cudbg_collect_vpd_data },
@@ -158,6 +162,22 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 		}
 		len = cudbg_mbytes_to_bytes(len);
 		break;
+	case CUDBG_MC0:
+		value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A);
+		if (value & EXT_MEM0_ENABLE_F) {
+			value = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A);
+			len = EXT_MEM0_SIZE_G(value);
+		}
+		len = cudbg_mbytes_to_bytes(len);
+		break;
+	case CUDBG_MC1:
+		value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A);
+		if (value & EXT_MEM1_ENABLE_F) {
+			value = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
+			len = EXT_MEM1_SIZE_G(value);
+		}
+		len = cudbg_mbytes_to_bytes(len);
+		break;
 	case CUDBG_RSS:
 		len = RSS_NENTRIES * sizeof(u16);
 		break;
@@ -201,6 +221,9 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 	case CUDBG_TP_LA:
 		len = sizeof(struct cudbg_tp_la) + TPLA_SIZE * sizeof(u64);
 		break;
+	case CUDBG_MEMINFO:
+		len = sizeof(struct cudbg_meminfo);
+		break;
 	case CUDBG_CIM_PIF_LA:
 		len = sizeof(struct cudbg_cim_pif_la);
 		len += 2 * CIM_PIFLA_SIZE * 6 * sizeof(u32);
@@ -219,6 +242,9 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 	case CUDBG_TID_INFO:
 		len = sizeof(struct cudbg_tid_info_region_rev1);
 		break;
+	case CUDBG_PCIE_CONFIG:
+		len = sizeof(u32) * CUDBG_NUM_PCIE_CONFIG_REGS;
+		break;
 	case CUDBG_DUMP_CONTEXT:
 		len = cudbg_dump_context_size(adap);
 		break;
@@ -264,6 +290,17 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 			len = sizeof(struct ireg_buf) * n;
 		}
 		break;
+	case CUDBG_HMA:
+		value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A);
+		if (value & HMA_MUX_F) {
+			/* In T6, there's no MC1.  So, HMA shares MC1
+			 * address space.
+			 */
+			value = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
+			len = EXT_MEM1_SIZE_G(value);
+		}
+		len = cudbg_mbytes_to_bytes(len);
+		break;
 	default:
 		break;
 	}

drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h

@@ -20,6 +20,7 @@
 
 #include "cudbg_if.h"
 #include "cudbg_lib_common.h"
+#include "cudbg_entity.h"
 #include "cudbg_lib.h"
 
 typedef int (*cudbg_collect_callback_t)(struct cudbg_init *pdbg_init,

drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c

@@ -45,6 +45,10 @@
 #include "cxgb4_debugfs.h"
 #include "clip_tbl.h"
 #include "l2t.h"
+#include "cudbg_if.h"
+#include "cudbg_lib_common.h"
+#include "cudbg_entity.h"
+#include "cudbg_lib.h"
 
 /* generic seq_file support for showing a table of size rows x width. */
 static void *seq_tab_get_idx(struct seq_tab *tb, loff_t pos)
@@ -2794,18 +2798,6 @@ static const struct file_operations blocked_fl_fops = {
 	.llseek  = generic_file_llseek,
 };
 
-struct mem_desc {
-	unsigned int base;
-	unsigned int limit;
-	unsigned int idx;
-};
-
-static int mem_desc_cmp(const void *a, const void *b)
-{
-	return ((const struct mem_desc *)a)->base -
-	       ((const struct mem_desc *)b)->base;
-}
-
 static void mem_region_show(struct seq_file *seq, const char *name,
 			    unsigned int from, unsigned int to)
 {
@@ -2819,250 +2811,60 @@ static void mem_region_show(struct seq_file *seq, const char *name,
 static int meminfo_show(struct seq_file *seq, void *v)
 {
 	static const char * const memory[] = { "EDC0:", "EDC1:", "MC:",
-					"MC0:", "MC1:"};
-	static const char * const region[] = {
-		"DBQ contexts:", "IMSG contexts:", "FLM cache:", "TCBs:",
-		"Pstructs:", "Timers:", "Rx FL:", "Tx FL:", "Pstruct FL:",
-		"Tx payload:", "Rx payload:", "LE hash:", "iSCSI region:",
-		"TDDP region:", "TPT region:", "STAG region:", "RQ region:",
-		"RQUDP region:", "PBL region:", "TXPBL region:",
-		"DBVFIFO region:", "ULPRX state:", "ULPTX state:",
-		"On-chip queues:"
-	};
-
-	int i, n;
-	u32 lo, hi, used, alloc;
-	struct mem_desc avail[4];
-	struct mem_desc mem[ARRAY_SIZE(region) + 3];      /* up to 3 holes */
-	struct mem_desc *md = mem;
+					       "MC0:", "MC1:", "HMA:"};
 	struct adapter *adap = seq->private;
+	struct cudbg_meminfo meminfo;
+	int i, rc;
 
-	for (i = 0; i < ARRAY_SIZE(mem); i++) {
-		mem[i].limit = 0;
-		mem[i].idx = i;
-	}
-
-	/* Find and sort the populated memory ranges */
-	i = 0;
-	lo = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A);
-	if (lo & EDRAM0_ENABLE_F) {
-		hi = t4_read_reg(adap, MA_EDRAM0_BAR_A);
-		avail[i].base = EDRAM0_BASE_G(hi) << 20;
-		avail[i].limit = avail[i].base + (EDRAM0_SIZE_G(hi) << 20);
-		avail[i].idx = 0;
-		i++;
-	}
-	if (lo & EDRAM1_ENABLE_F) {
-		hi = t4_read_reg(adap, MA_EDRAM1_BAR_A);
-		avail[i].base = EDRAM1_BASE_G(hi) << 20;
-		avail[i].limit = avail[i].base + (EDRAM1_SIZE_G(hi) << 20);
-		avail[i].idx = 1;
-		i++;
-	}
-
-	if (is_t5(adap->params.chip)) {
-		if (lo & EXT_MEM0_ENABLE_F) {
-			hi = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A);
-			avail[i].base = EXT_MEM0_BASE_G(hi) << 20;
-			avail[i].limit =
-				avail[i].base + (EXT_MEM0_SIZE_G(hi) << 20);
-			avail[i].idx = 3;
-			i++;
-		}
-		if (lo & EXT_MEM1_ENABLE_F) {
-			hi = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
-			avail[i].base = EXT_MEM1_BASE_G(hi) << 20;
-			avail[i].limit =
-				avail[i].base + (EXT_MEM1_SIZE_G(hi) << 20);
-			avail[i].idx = 4;
-			i++;
-		}
-	} else {
-		if (lo & EXT_MEM_ENABLE_F) {
-			hi = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A);
-			avail[i].base = EXT_MEM_BASE_G(hi) << 20;
-			avail[i].limit =
-				avail[i].base + (EXT_MEM_SIZE_G(hi) << 20);
-			avail[i].idx = 2;
-			i++;
-		}
-	}
-	if (!i)                                    /* no memory available */
-		return 0;
-	sort(avail, i, sizeof(struct mem_desc), mem_desc_cmp, NULL);
-
-	(md++)->base = t4_read_reg(adap, SGE_DBQ_CTXT_BADDR_A);
-	(md++)->base = t4_read_reg(adap, SGE_IMSG_CTXT_BADDR_A);
-	(md++)->base = t4_read_reg(adap, SGE_FLM_CACHE_BADDR_A);
-	(md++)->base = t4_read_reg(adap, TP_CMM_TCB_BASE_A);
-	(md++)->base = t4_read_reg(adap, TP_CMM_MM_BASE_A);
-	(md++)->base = t4_read_reg(adap, TP_CMM_TIMER_BASE_A);
-	(md++)->base = t4_read_reg(adap, TP_CMM_MM_RX_FLST_BASE_A);
-	(md++)->base = t4_read_reg(adap, TP_CMM_MM_TX_FLST_BASE_A);
-	(md++)->base = t4_read_reg(adap, TP_CMM_MM_PS_FLST_BASE_A);
-
-	/* the next few have explicit upper bounds */
-	md->base = t4_read_reg(adap, TP_PMM_TX_BASE_A);
-	md->limit = md->base - 1 +
-		    t4_read_reg(adap, TP_PMM_TX_PAGE_SIZE_A) *
-		    PMTXMAXPAGE_G(t4_read_reg(adap, TP_PMM_TX_MAX_PAGE_A));
-	md++;
-
-	md->base = t4_read_reg(adap, TP_PMM_RX_BASE_A);
-	md->limit = md->base - 1 +
-		    t4_read_reg(adap, TP_PMM_RX_PAGE_SIZE_A) *
-		    PMRXMAXPAGE_G(t4_read_reg(adap, TP_PMM_RX_MAX_PAGE_A));
-	md++;
-
-	if (t4_read_reg(adap, LE_DB_CONFIG_A) & HASHEN_F) {
-		if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) {
-			hi = t4_read_reg(adap, LE_DB_TID_HASHBASE_A) / 4;
-			md->base = t4_read_reg(adap, LE_DB_HASH_TID_BASE_A);
-		 } else {
-			hi = t4_read_reg(adap, LE_DB_HASH_TID_BASE_A);
-			md->base = t4_read_reg(adap,
-					       LE_DB_HASH_TBL_BASE_ADDR_A);
-		}
-		md->limit = 0;
-	} else {
-		md->base = 0;
-		md->idx = ARRAY_SIZE(region);  /* hide it */
-	}
-	md++;
-
-#define ulp_region(reg) do { \
-	md->base = t4_read_reg(adap, ULP_ ## reg ## _LLIMIT_A);\
-	(md++)->limit = t4_read_reg(adap, ULP_ ## reg ## _ULIMIT_A); \
-} while (0)
-
-	ulp_region(RX_ISCSI);
-	ulp_region(RX_TDDP);
-	ulp_region(TX_TPT);
-	ulp_region(RX_STAG);
-	ulp_region(RX_RQ);
-	ulp_region(RX_RQUDP);
-	ulp_region(RX_PBL);
-	ulp_region(TX_PBL);
-#undef ulp_region
-	md->base = 0;
-	md->idx = ARRAY_SIZE(region);
-	if (!is_t4(adap->params.chip)) {
-		u32 size = 0;
-		u32 sge_ctrl = t4_read_reg(adap, SGE_CONTROL2_A);
-		u32 fifo_size = t4_read_reg(adap, SGE_DBVFIFO_SIZE_A);
-
-		if (is_t5(adap->params.chip)) {
-			if (sge_ctrl & VFIFO_ENABLE_F)
-				size = DBVFIFO_SIZE_G(fifo_size);
-		} else {
-			size = T6_DBVFIFO_SIZE_G(fifo_size);
-		}
-
-		if (size) {
-			md->base = BASEADDR_G(t4_read_reg(adap,
-					SGE_DBVFIFO_BADDR_A));
-			md->limit = md->base + (size << 2) - 1;
-		}
-	}
-
-	md++;
-
-	md->base = t4_read_reg(adap, ULP_RX_CTX_BASE_A);
-	md->limit = 0;
-	md++;
-	md->base = t4_read_reg(adap, ULP_TX_ERR_TABLE_BASE_A);
-	md->limit = 0;
-	md++;
-
-	md->base = adap->vres.ocq.start;
-	if (adap->vres.ocq.size)
-		md->limit = md->base + adap->vres.ocq.size - 1;
-	else
-		md->idx = ARRAY_SIZE(region);  /* hide it */
-	md++;
-
-	/* add any address-space holes, there can be up to 3 */
-	for (n = 0; n < i - 1; n++)
-		if (avail[n].limit < avail[n + 1].base)
-			(md++)->base = avail[n].limit;
-	if (avail[n].limit)
-		(md++)->base = avail[n].limit;
-
-	n = md - mem;
-	sort(mem, n, sizeof(struct mem_desc), mem_desc_cmp, NULL);
+	memset(&meminfo, 0, sizeof(struct cudbg_meminfo));
+	rc = cudbg_fill_meminfo(adap, &meminfo);
+	if (rc)
+		return -ENXIO;
 
-	for (lo = 0; lo < i; lo++)
-		mem_region_show(seq, memory[avail[lo].idx], avail[lo].base,
-				avail[lo].limit - 1);
+	for (i = 0; i < meminfo.avail_c; i++)
+		mem_region_show(seq, memory[meminfo.avail[i].idx],
+				meminfo.avail[i].base,
+				meminfo.avail[i].limit - 1);
 
 	seq_putc(seq, '\n');
-	for (i = 0; i < n; i++) {
-		if (mem[i].idx >= ARRAY_SIZE(region))
+	for (i = 0; i < meminfo.mem_c; i++) {
+		if (meminfo.mem[i].idx >= ARRAY_SIZE(cudbg_region))
 			continue;                        /* skip holes */
-		if (!mem[i].limit)
-			mem[i].limit = i < n - 1 ? mem[i + 1].base - 1 : ~0;
-		mem_region_show(seq, region[mem[i].idx], mem[i].base,
-				mem[i].limit);
+		if (!meminfo.mem[i].limit)
+			meminfo.mem[i].limit =
+				i < meminfo.mem_c - 1 ?
+				meminfo.mem[i + 1].base - 1 : ~0;
+		mem_region_show(seq, cudbg_region[meminfo.mem[i].idx],
+				meminfo.mem[i].base, meminfo.mem[i].limit);
 	}
 
 	seq_putc(seq, '\n');
-	lo = t4_read_reg(adap, CIM_SDRAM_BASE_ADDR_A);
-	hi = t4_read_reg(adap, CIM_SDRAM_ADDR_SIZE_A) + lo - 1;
-	mem_region_show(seq, "uP RAM:", lo, hi);
-
-	lo = t4_read_reg(adap, CIM_EXTMEM2_BASE_ADDR_A);
-	hi = t4_read_reg(adap, CIM_EXTMEM2_ADDR_SIZE_A) + lo - 1;
-	mem_region_show(seq, "uP Extmem2:", lo, hi);
+	mem_region_show(seq, "uP RAM:", meminfo.up_ram_lo, meminfo.up_ram_hi);
+	mem_region_show(seq, "uP Extmem2:", meminfo.up_extmem2_lo,
+			meminfo.up_extmem2_hi);
 
-	lo = t4_read_reg(adap, TP_PMM_RX_MAX_PAGE_A);
 	seq_printf(seq, "\n%u Rx pages of size %uKiB for %u channels\n",
-		   PMRXMAXPAGE_G(lo),
-		   t4_read_reg(adap, TP_PMM_RX_PAGE_SIZE_A) >> 10,
-		   (lo & PMRXNUMCHN_F) ? 2 : 1);
+		   meminfo.rx_pages_data[0], meminfo.rx_pages_data[1],
+		   meminfo.rx_pages_data[2]);
 
-	lo = t4_read_reg(adap, TP_PMM_TX_MAX_PAGE_A);
-	hi = t4_read_reg(adap, TP_PMM_TX_PAGE_SIZE_A);
 	seq_printf(seq, "%u Tx pages of size %u%ciB for %u channels\n",
-		   PMTXMAXPAGE_G(lo),
-		   hi >= (1 << 20) ? (hi >> 20) : (hi >> 10),
-		   hi >= (1 << 20) ? 'M' : 'K', 1 << PMTXNUMCHN_G(lo));
-	seq_printf(seq, "%u p-structs\n\n",
-		   t4_read_reg(adap, TP_CMM_MM_MAX_PSTRUCT_A));
-
-	for (i = 0; i < 4; i++) {
-		if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5)
-			lo = t4_read_reg(adap, MPS_RX_MAC_BG_PG_CNT0_A + i * 4);
-		else
-			lo = t4_read_reg(adap, MPS_RX_PG_RSV0_A + i * 4);
-		if (is_t5(adap->params.chip)) {
-			used = T5_USED_G(lo);
-			alloc = T5_ALLOC_G(lo);
-		} else {
-			used = USED_G(lo);
-			alloc = ALLOC_G(lo);
-		}
+		   meminfo.tx_pages_data[0], meminfo.tx_pages_data[1],
+		   meminfo.tx_pages_data[2], meminfo.tx_pages_data[3]);
+
+	seq_printf(seq, "%u p-structs\n\n", meminfo.p_structs);
+
+	for (i = 0; i < 4; i++)
 		/* For T6 these are MAC buffer groups */
 		seq_printf(seq, "Port %d using %u pages out of %u allocated\n",
-			   i, used, alloc);
-	}
-	for (i = 0; i < adap->params.arch.nchan; i++) {
-		if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5)
-			lo = t4_read_reg(adap,
-					 MPS_RX_LPBK_BG_PG_CNT0_A + i * 4);
-		else
-			lo = t4_read_reg(adap, MPS_RX_PG_RSV4_A + i * 4);
-		if (is_t5(adap->params.chip)) {
-			used = T5_USED_G(lo);
-			alloc = T5_ALLOC_G(lo);
-		} else {
-			used = USED_G(lo);
-			alloc = ALLOC_G(lo);
-		}
+			   i, meminfo.port_used[i], meminfo.port_alloc[i]);
+
+	for (i = 0; i < adap->params.arch.nchan; i++)
 		/* For T6 these are MAC buffer groups */
 		seq_printf(seq,
 			   "Loopback %d using %u pages out of %u allocated\n",
-			   i, used, alloc);
-	}
+			   i, meminfo.loopback_used[i],
+			   meminfo.loopback_alloc[i]);
+
 	return 0;
 }
 

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -1673,7 +1673,7 @@ int cxgb4_flush_eq_cache(struct net_device *dev)
 {
 	struct adapter *adap = netdev2adap(dev);
 
-	return t4_sge_ctxt_flush(adap, adap->mbox);
+	return t4_sge_ctxt_flush(adap, adap->mbox, CTXT_EGRESS);
 }
 EXPORT_SYMBOL(cxgb4_flush_eq_cache);
 

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c

@@ -524,11 +524,14 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
 	 * MEM_EDC1 = 1
 	 * MEM_MC   = 2 -- MEM_MC for chips with only 1 memory controller
 	 * MEM_MC1  = 3 -- for chips with 2 memory controllers (e.g. T5)
+	 * MEM_HMA  = 4
 	 */
 	edc_size  = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A));
-	if (mtype != MEM_MC1)
+	if (mtype == MEM_HMA) {
+		memoffset = 2 * (edc_size * 1024 * 1024);
+	} else if (mtype != MEM_MC1) {
 		memoffset = (mtype * (edc_size * 1024 * 1024));
-	else {
+	} else {
 		mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap,
 						      MA_EXT_MEMORY0_BAR_A));
 		memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024;
@@ -6527,18 +6530,21 @@ void t4_sge_decode_idma_state(struct adapter *adapter, int state)
  *      t4_sge_ctxt_flush - flush the SGE context cache
  *      @adap: the adapter
  *      @mbox: mailbox to use for the FW command
+ *      @ctx_type: Egress or Ingress
  *
  *      Issues a FW command through the given mailbox to flush the
  *      SGE context cache.
  */
-int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox)
+int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type)
 {
 	int ret;
 	u32 ldst_addrspace;
 	struct fw_ldst_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_SGE_EGRC);
+	ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(ctxt_type == CTXT_EGRESS ?
+						 FW_LDST_ADDRSPC_SGE_EGRC :
+						 FW_LDST_ADDRSPC_SGE_INGC);
 	c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
 					FW_CMD_REQUEST_F | FW_CMD_READ_F |
 					ldst_addrspace);

drivers/net/ethernet/chelsio/cxgb4/t4_hw.h

@@ -70,7 +70,9 @@ enum {
 
 /* SGE context types */
 enum ctxt_type {
-	CTXT_FLM = 2,
+	CTXT_EGRESS,
+	CTXT_INGRESS,
+	CTXT_FLM,
 	CTXT_CNM,
 };
 

drivers/net/ethernet/chelsio/cxgb4/t4_regs.h

@@ -961,6 +961,10 @@
 
 #define MA_EXT_MEMORY1_BAR_A 0x7808
 
+#define HMA_MUX_S    5
+#define HMA_MUX_V(x) ((x) << HMA_MUX_S)
+#define HMA_MUX_F    HMA_MUX_V(1U)
+
 #define EXT_MEM1_BASE_S    16
 #define EXT_MEM1_BASE_M    0xfffU
 #define EXT_MEM1_BASE_G(x) (((x) >> EXT_MEM1_BASE_S) & EXT_MEM1_BASE_M)