Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 970 insertions, 203 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index d699bf8..557fd8b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -15,18 +15,65 @@
  *
  */
 
+#include <linux/sort.h>
+
 #include "t4_regs.h"
 #include "cxgb4.h"
 #include "cudbg_if.h"
 #include "cudbg_lib_common.h"
-#include "cudbg_lib.h"
 #include "cudbg_entity.h"
+#include "cudbg_lib.h"
+#include "cudbg_zlib.h"
 
-static void cudbg_write_and_release_buff(struct cudbg_buffer *pin_buff,
-					 struct cudbg_buffer *dbg_buff)
+static int cudbg_do_compression(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *pin_buff,
+				struct cudbg_buffer *dbg_buff)
 {
-	cudbg_update_buff(pin_buff, dbg_buff);
-	cudbg_put_buff(pin_buff, dbg_buff);
+	struct cudbg_buffer temp_in_buff = { 0 };
+	int bytes_left, bytes_read, bytes;
+	u32 offset = dbg_buff->offset;
+	int rc;
+
+	temp_in_buff.offset = pin_buff->offset;
+	temp_in_buff.data = pin_buff->data;
+	temp_in_buff.size = pin_buff->size;
+
+	bytes_left = pin_buff->size;
+	bytes_read = 0;
+	while (bytes_left > 0) {
+		/* Do compression in smaller chunks */
+		bytes = min_t(unsigned long, bytes_left,
+			      (unsigned long)CUDBG_CHUNK_SIZE);
+		temp_in_buff.data = (char *)pin_buff->data + bytes_read;
+		temp_in_buff.size = bytes;
+		rc = cudbg_compress_buff(pdbg_init, &temp_in_buff, dbg_buff);
+		if (rc)
+			return rc;
+		bytes_left -= bytes;
+		bytes_read += bytes;
+	}
+
+	pin_buff->size = dbg_buff->offset - offset;
+	return 0;
+}
+
+static int cudbg_write_and_release_buff(struct cudbg_init *pdbg_init,
+					struct cudbg_buffer *pin_buff,
+					struct cudbg_buffer *dbg_buff)
+{
+	int rc = 0;
+
+	if (pdbg_init->compress_type == CUDBG_COMPRESSION_NONE) {
+		cudbg_update_buff(pin_buff, dbg_buff);
+	} else {
+		rc = cudbg_do_compression(pdbg_init, pin_buff, dbg_buff);
+		if (rc)
+			goto out;
+	}
+
+out:
+	cudbg_put_buff(pdbg_init, pin_buff);
+	return rc;
 }
 
 static int is_fw_attached(struct cudbg_init *pdbg_init)
@@ -84,6 +131,277 @@ static int cudbg_read_vpd_reg(struct adapter *padap, u32 addr, u32 len,
 	return 0;
 }
 
+static int cudbg_mem_desc_cmp(const void *a, const void *b)
+{
+	return ((const struct cudbg_mem_desc *)a)->base -
+	       ((const struct cudbg_mem_desc *)b)->base;
+}
+
+int cudbg_fill_meminfo(struct adapter *padap,
+		       struct cudbg_meminfo *meminfo_buff)
+{
+	struct cudbg_mem_desc *md;
+	u32 lo, hi, used, alloc;
+	int n, i;
+
+	memset(meminfo_buff->avail, 0,
+	       ARRAY_SIZE(meminfo_buff->avail) *
+	       sizeof(struct cudbg_mem_desc));
+	memset(meminfo_buff->mem, 0,
+	       (ARRAY_SIZE(cudbg_region) + 3) * sizeof(struct cudbg_mem_desc));
+	md  = meminfo_buff->mem;
+
+	for (i = 0; i < ARRAY_SIZE(meminfo_buff->mem); i++) {
+		meminfo_buff->mem[i].limit = 0;
+		meminfo_buff->mem[i].idx = i;
+	}
+
+	/* Find and sort the populated memory ranges */
+	i = 0;
+	lo = t4_read_reg(padap, MA_TARGET_MEM_ENABLE_A);
+	if (lo & EDRAM0_ENABLE_F) {
+		hi = t4_read_reg(padap, MA_EDRAM0_BAR_A);
+		meminfo_buff->avail[i].base =
+			cudbg_mbytes_to_bytes(EDRAM0_BASE_G(hi));
+		meminfo_buff->avail[i].limit =
+			meminfo_buff->avail[i].base +
+			cudbg_mbytes_to_bytes(EDRAM0_SIZE_G(hi));
+		meminfo_buff->avail[i].idx = 0;
+		i++;
+	}
+
+	if (lo & EDRAM1_ENABLE_F) {
+		hi =  t4_read_reg(padap, MA_EDRAM1_BAR_A);
+		meminfo_buff->avail[i].base =
+			cudbg_mbytes_to_bytes(EDRAM1_BASE_G(hi));
+		meminfo_buff->avail[i].limit =
+			meminfo_buff->avail[i].base +
+			cudbg_mbytes_to_bytes(EDRAM1_SIZE_G(hi));
+		meminfo_buff->avail[i].idx = 1;
+		i++;
+	}
+
+	if (is_t5(padap->params.chip)) {
+		if (lo & EXT_MEM0_ENABLE_F) {
+			hi = t4_read_reg(padap, MA_EXT_MEMORY0_BAR_A);
+			meminfo_buff->avail[i].base =
+				cudbg_mbytes_to_bytes(EXT_MEM_BASE_G(hi));
+			meminfo_buff->avail[i].limit =
+				meminfo_buff->avail[i].base +
+				cudbg_mbytes_to_bytes(EXT_MEM_SIZE_G(hi));
+			meminfo_buff->avail[i].idx = 3;
+			i++;
+		}
+
+		if (lo & EXT_MEM1_ENABLE_F) {
+			hi = t4_read_reg(padap, MA_EXT_MEMORY1_BAR_A);
+			meminfo_buff->avail[i].base =
+				cudbg_mbytes_to_bytes(EXT_MEM1_BASE_G(hi));
+			meminfo_buff->avail[i].limit =
+				meminfo_buff->avail[i].base +
+				cudbg_mbytes_to_bytes(EXT_MEM1_SIZE_G(hi));
+			meminfo_buff->avail[i].idx = 4;
+			i++;
+		}
+	} else {
+		if (lo & EXT_MEM_ENABLE_F) {
+			hi = t4_read_reg(padap, MA_EXT_MEMORY_BAR_A);
+			meminfo_buff->avail[i].base =
+				cudbg_mbytes_to_bytes(EXT_MEM_BASE_G(hi));
+			meminfo_buff->avail[i].limit =
+				meminfo_buff->avail[i].base +
+				cudbg_mbytes_to_bytes(EXT_MEM_SIZE_G(hi));
+			meminfo_buff->avail[i].idx = 2;
+			i++;
+		}
+
+		if (lo & HMA_MUX_F) {
+			hi = t4_read_reg(padap, MA_EXT_MEMORY1_BAR_A);
+			meminfo_buff->avail[i].base =
+				cudbg_mbytes_to_bytes(EXT_MEM1_BASE_G(hi));
+			meminfo_buff->avail[i].limit =
+				meminfo_buff->avail[i].base +
+				cudbg_mbytes_to_bytes(EXT_MEM1_SIZE_G(hi));
+			meminfo_buff->avail[i].idx = 5;
+			i++;
+		}
+	}
+
+	if (!i) /* no memory available */
+		return CUDBG_STATUS_ENTITY_NOT_FOUND;
+
+	meminfo_buff->avail_c = i;
+	sort(meminfo_buff->avail, i, sizeof(struct cudbg_mem_desc),
+	     cudbg_mem_desc_cmp, NULL);
+	(md++)->base = t4_read_reg(padap, SGE_DBQ_CTXT_BADDR_A);
+	(md++)->base = t4_read_reg(padap, SGE_IMSG_CTXT_BADDR_A);
+	(md++)->base = t4_read_reg(padap, SGE_FLM_CACHE_BADDR_A);
+	(md++)->base = t4_read_reg(padap, TP_CMM_TCB_BASE_A);
+	(md++)->base = t4_read_reg(padap, TP_CMM_MM_BASE_A);
+	(md++)->base = t4_read_reg(padap, TP_CMM_TIMER_BASE_A);
+	(md++)->base = t4_read_reg(padap, TP_CMM_MM_RX_FLST_BASE_A);
+	(md++)->base = t4_read_reg(padap, TP_CMM_MM_TX_FLST_BASE_A);
+	(md++)->base = t4_read_reg(padap, TP_CMM_MM_PS_FLST_BASE_A);
+
+	/* the next few have explicit upper bounds */
+	md->base = t4_read_reg(padap, TP_PMM_TX_BASE_A);
+	md->limit = md->base - 1 +
+		    t4_read_reg(padap, TP_PMM_TX_PAGE_SIZE_A) *
+		    PMTXMAXPAGE_G(t4_read_reg(padap, TP_PMM_TX_MAX_PAGE_A));
+	md++;
+
+	md->base = t4_read_reg(padap, TP_PMM_RX_BASE_A);
+	md->limit = md->base - 1 +
+		    t4_read_reg(padap, TP_PMM_RX_PAGE_SIZE_A) *
+		    PMRXMAXPAGE_G(t4_read_reg(padap, TP_PMM_RX_MAX_PAGE_A));
+	md++;
+
+	if (t4_read_reg(padap, LE_DB_CONFIG_A) & HASHEN_F) {
+		if (CHELSIO_CHIP_VERSION(padap->params.chip) <= CHELSIO_T5) {
+			hi = t4_read_reg(padap, LE_DB_TID_HASHBASE_A) / 4;
+			md->base = t4_read_reg(padap, LE_DB_HASH_TID_BASE_A);
+		} else {
+			hi = t4_read_reg(padap, LE_DB_HASH_TID_BASE_A);
+			md->base = t4_read_reg(padap,
+					       LE_DB_HASH_TBL_BASE_ADDR_A);
+		}
+		md->limit = 0;
+	} else {
+		md->base = 0;
+		md->idx = ARRAY_SIZE(cudbg_region);  /* hide it */
+	}
+	md++;
+
+#define ulp_region(reg) do { \
+	md->base = t4_read_reg(padap, ULP_ ## reg ## _LLIMIT_A);\
+	(md++)->limit = t4_read_reg(padap, 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(cudbg_region);
+	if (!is_t4(padap->params.chip)) {
+		u32 fifo_size = t4_read_reg(padap, SGE_DBVFIFO_SIZE_A);
+		u32 sge_ctrl = t4_read_reg(padap, SGE_CONTROL2_A);
+		u32 size = 0;
+
+		if (is_t5(padap->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(padap,
+							  SGE_DBVFIFO_BADDR_A));
+			md->limit = md->base + (size << 2) - 1;
+		}
+	}
+
+	md++;
+
+	md->base = t4_read_reg(padap, ULP_RX_CTX_BASE_A);
+	md->limit = 0;
+	md++;
+	md->base = t4_read_reg(padap, ULP_TX_ERR_TABLE_BASE_A);
+	md->limit = 0;
+	md++;
+
+	md->base = padap->vres.ocq.start;
+	if (padap->vres.ocq.size)
+		md->limit = md->base + padap->vres.ocq.size - 1;
+	else
+		md->idx = ARRAY_SIZE(cudbg_region);  /* hide it */
+	md++;
+
+	/* add any address-space holes, there can be up to 3 */
+	for (n = 0; n < i - 1; n++)
+		if (meminfo_buff->avail[n].limit <
+		    meminfo_buff->avail[n + 1].base)
+			(md++)->base = meminfo_buff->avail[n].limit;
+
+	if (meminfo_buff->avail[n].limit)
+		(md++)->base = meminfo_buff->avail[n].limit;
+
+	n = md - meminfo_buff->mem;
+	meminfo_buff->mem_c = n;
+
+	sort(meminfo_buff->mem, n, sizeof(struct cudbg_mem_desc),
+	     cudbg_mem_desc_cmp, NULL);
+
+	lo = t4_read_reg(padap, CIM_SDRAM_BASE_ADDR_A);
+	hi = t4_read_reg(padap, CIM_SDRAM_ADDR_SIZE_A) + lo - 1;
+	meminfo_buff->up_ram_lo = lo;
+	meminfo_buff->up_ram_hi = hi;
+
+	lo = t4_read_reg(padap, CIM_EXTMEM2_BASE_ADDR_A);
+	hi = t4_read_reg(padap, CIM_EXTMEM2_ADDR_SIZE_A) + lo - 1;
+	meminfo_buff->up_extmem2_lo = lo;
+	meminfo_buff->up_extmem2_hi = hi;
+
+	lo = t4_read_reg(padap, TP_PMM_RX_MAX_PAGE_A);
+	meminfo_buff->rx_pages_data[0] =  PMRXMAXPAGE_G(lo);
+	meminfo_buff->rx_pages_data[1] =
+		t4_read_reg(padap, TP_PMM_RX_PAGE_SIZE_A) >> 10;
+	meminfo_buff->rx_pages_data[2] = (lo & PMRXNUMCHN_F) ? 2 : 1;
+
+	lo = t4_read_reg(padap, TP_PMM_TX_MAX_PAGE_A);
+	hi = t4_read_reg(padap, TP_PMM_TX_PAGE_SIZE_A);
+	meminfo_buff->tx_pages_data[0] = PMTXMAXPAGE_G(lo);
+	meminfo_buff->tx_pages_data[1] =
+		hi >= (1 << 20) ? (hi >> 20) : (hi >> 10);
+	meminfo_buff->tx_pages_data[2] =
+		hi >= (1 << 20) ? 'M' : 'K';
+	meminfo_buff->tx_pages_data[3] = 1 << PMTXNUMCHN_G(lo);
+
+	meminfo_buff->p_structs = t4_read_reg(padap, TP_CMM_MM_MAX_PSTRUCT_A);
+
+	for (i = 0; i < 4; i++) {
+		if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5)
+			lo = t4_read_reg(padap,
+					 MPS_RX_MAC_BG_PG_CNT0_A + i * 4);
+		else
+			lo = t4_read_reg(padap, MPS_RX_PG_RSV0_A + i * 4);
+		if (is_t5(padap->params.chip)) {
+			used = T5_USED_G(lo);
+			alloc = T5_ALLOC_G(lo);
+		} else {
+			used = USED_G(lo);
+			alloc = ALLOC_G(lo);
+		}
+		meminfo_buff->port_used[i] = used;
+		meminfo_buff->port_alloc[i] = alloc;
+	}
+
+	for (i = 0; i < padap->params.arch.nchan; i++) {
+		if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5)
+			lo = t4_read_reg(padap,
+					 MPS_RX_LPBK_BG_PG_CNT0_A + i * 4);
+		else
+			lo = t4_read_reg(padap, MPS_RX_PG_RSV4_A + i * 4);
+		if (is_t5(padap->params.chip)) {
+			used = T5_USED_G(lo);
+			alloc = T5_ALLOC_G(lo);
+		} else {
+			used = USED_G(lo);
+			alloc = ALLOC_G(lo);
+		}
+		meminfo_buff->loopback_used[i] = used;
+		meminfo_buff->loopback_alloc[i] = alloc;
+	}
+
+	return 0;
+}
+
 int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init,
 			   struct cudbg_buffer *dbg_buff,
 			   struct cudbg_error *cudbg_err)
@@ -98,12 +416,11 @@ int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init,
 	else if (is_t5(padap->params.chip) || is_t6(padap->params.chip))
 		buf_size = T5_REGMAP_SIZE;
 
-	rc = cudbg_get_buff(dbg_buff, buf_size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, buf_size, &temp_buff);
 	if (rc)
 		return rc;
 	t4_get_regs(padap, (void *)temp_buff.data, temp_buff.size);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init,
@@ -122,7 +439,7 @@ int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init,
 	}
 
 	dparams = &padap->params.devlog;
-	rc = cudbg_get_buff(dbg_buff, dparams->size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, dparams->size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -137,12 +454,11 @@ int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init,
 		spin_unlock(&padap->win0_lock);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_cim_la(struct cudbg_init *pdbg_init,
@@ -163,14 +479,14 @@ int cudbg_collect_cim_la(struct cudbg_init *pdbg_init,
 	}
 
 	size += sizeof(cfg);
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
 	rc = t4_cim_read(padap, UP_UP_DBG_LA_CFG_A, 1, &cfg);
 	if (rc) {
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
 
@@ -180,11 +496,10 @@ int cudbg_collect_cim_la(struct cudbg_init *pdbg_init,
 			    NULL);
 	if (rc < 0) {
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_cim_ma_la(struct cudbg_init *pdbg_init,
@@ -196,7 +511,7 @@ int cudbg_collect_cim_ma_la(struct cudbg_init *pdbg_init,
 	int size, rc;
 
 	size = 2 * CIM_MALA_SIZE * 5 * sizeof(u32);
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -204,8 +519,7 @@ int cudbg_collect_cim_ma_la(struct cudbg_init *pdbg_init,
 			  (u32 *)temp_buff.data,
 			  (u32 *)((char *)temp_buff.data +
 				  5 * CIM_MALA_SIZE));
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_cim_qcfg(struct cudbg_init *pdbg_init,
@@ -217,7 +531,7 @@ int cudbg_collect_cim_qcfg(struct cudbg_init *pdbg_init,
 	struct cudbg_cim_qcfg *cim_qcfg_data;
 	int rc;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_cim_qcfg),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_cim_qcfg),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -228,7 +542,7 @@ int cudbg_collect_cim_qcfg(struct cudbg_init *pdbg_init,
 			 ARRAY_SIZE(cim_qcfg_data->stat), cim_qcfg_data->stat);
 	if (rc) {
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
 
@@ -237,14 +551,13 @@ int cudbg_collect_cim_qcfg(struct cudbg_init *pdbg_init,
 			 cim_qcfg_data->obq_wr);
 	if (rc) {
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
 
 	t4_read_cimq_cfg(padap, cim_qcfg_data->base, cim_qcfg_data->size,
 			 cim_qcfg_data->thres);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 static int cudbg_read_cim_ibq(struct cudbg_init *pdbg_init,
@@ -258,7 +571,7 @@ static int cudbg_read_cim_ibq(struct cudbg_init *pdbg_init,
 
 	/* collect CIM IBQ */
 	qsize = CIM_IBQ_SIZE * 4 * sizeof(u32);
-	rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, qsize, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -272,11 +585,10 @@ static int cudbg_read_cim_ibq(struct cudbg_init *pdbg_init,
 		else
 			rc = no_of_read_words;
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_cim_ibq_tp0(struct cudbg_init *pdbg_init,
@@ -343,7 +655,7 @@ static int cudbg_read_cim_obq(struct cudbg_init *pdbg_init,
 
 	/* collect CIM OBQ */
 	qsize =  cudbg_cim_obq_size(padap, qid);
-	rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, qsize, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -357,11 +669,10 @@ static int cudbg_read_cim_obq(struct cudbg_init *pdbg_init,
 		else
 			rc = no_of_read_words;
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_cim_obq_ulp0(struct cudbg_init *pdbg_init,
@@ -420,23 +731,211 @@ int cudbg_collect_obq_sge_rx_q1(struct cudbg_init *pdbg_init,
 	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 7);
 }
 
+static int cudbg_meminfo_get_mem_index(struct adapter *padap,
+				       struct cudbg_meminfo *mem_info,
+				       u8 mem_type, u8 *idx)
+{
+	u8 i, flag;
+
+	switch (mem_type) {
+	case MEM_EDC0:
+		flag = EDC0_FLAG;
+		break;
+	case MEM_EDC1:
+		flag = EDC1_FLAG;
+		break;
+	case MEM_MC0:
+		/* Some T5 cards have both MC0 and MC1. */
+		flag = is_t5(padap->params.chip) ? MC0_FLAG : MC_FLAG;
+		break;
+	case MEM_MC1:
+		flag = MC1_FLAG;
+		break;
+	case MEM_HMA:
+		flag = HMA_FLAG;
+		break;
+	default:
+		return CUDBG_STATUS_ENTITY_NOT_FOUND;
+	}
+
+	for (i = 0; i < mem_info->avail_c; i++) {
+		if (mem_info->avail[i].idx == flag) {
+			*idx = i;
+			return 0;
+		}
+	}
+
+	return CUDBG_STATUS_ENTITY_NOT_FOUND;
+}
+
+/* Fetch the @region_name's start and end from @meminfo. */
+static int cudbg_get_mem_region(struct adapter *padap,
+				struct cudbg_meminfo *meminfo,
+				u8 mem_type, const char *region_name,
+				struct cudbg_mem_desc *mem_desc)
+{
+	u8 mc, found = 0;
+	u32 i, idx = 0;
+	int rc;
+
+	rc = cudbg_meminfo_get_mem_index(padap, meminfo, mem_type, &mc);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < ARRAY_SIZE(cudbg_region); i++) {
+		if (!strcmp(cudbg_region[i], region_name)) {
+			found = 1;
+			idx = i;
+			break;
+		}
+	}
+	if (!found)
+		return -EINVAL;
+
+	found = 0;
+	for (i = 0; i < meminfo->mem_c; i++) {
+		if (meminfo->mem[i].idx >= ARRAY_SIZE(cudbg_region))
+			continue; /* Skip holes */
+
+		if (!(meminfo->mem[i].limit))
+			meminfo->mem[i].limit =
+				i < meminfo->mem_c - 1 ?
+				meminfo->mem[i + 1].base - 1 : ~0;
+
+		if (meminfo->mem[i].idx == idx) {
+			/* Check if the region exists in @mem_type memory */
+			if (meminfo->mem[i].base < meminfo->avail[mc].base &&
+			    meminfo->mem[i].limit < meminfo->avail[mc].base)
+				return -EINVAL;
+
+			if (meminfo->mem[i].base > meminfo->avail[mc].limit)
+				return -EINVAL;
+
+			memcpy(mem_desc, &meminfo->mem[i],
+			       sizeof(struct cudbg_mem_desc));
+			found = 1;
+			break;
+		}
+	}
+	if (!found)
+		return -EINVAL;
+
+	return 0;
+}
+
+/* Fetch and update the start and end of the requested memory region w.r.t 0
+ * in the corresponding EDC/MC/HMA.
+ */
+static int cudbg_get_mem_relative(struct adapter *padap,
+				  struct cudbg_meminfo *meminfo,
+				  u8 mem_type, u32 *out_base, u32 *out_end)
+{
+	u8 mc_idx;
+	int rc;
+
+	rc = cudbg_meminfo_get_mem_index(padap, meminfo, mem_type, &mc_idx);
+	if (rc)
+		return rc;
+
+	if (*out_base < meminfo->avail[mc_idx].base)
+		*out_base = 0;
+	else
+		*out_base -= meminfo->avail[mc_idx].base;
+
+	if (*out_end > meminfo->avail[mc_idx].limit)
+		*out_end = meminfo->avail[mc_idx].limit;
+	else
+		*out_end -= meminfo->avail[mc_idx].base;
+
+	return 0;
+}
+
+/* Get TX and RX Payload region */
+static int cudbg_get_payload_range(struct adapter *padap, u8 mem_type,
+				   const char *region_name,
+				   struct cudbg_region_info *payload)
+{
+	struct cudbg_mem_desc mem_desc = { 0 };
+	struct cudbg_meminfo meminfo;
+	int rc;
+
+	rc = cudbg_fill_meminfo(padap, &meminfo);
+	if (rc)
+		return rc;
+
+	rc = cudbg_get_mem_region(padap, &meminfo, mem_type, region_name,
+				  &mem_desc);
+	if (rc) {
+		payload->exist = false;
+		return 0;
+	}
+
+	payload->exist = true;
+	payload->start = mem_desc.base;
+	payload->end = mem_desc.limit;
+
+	return cudbg_get_mem_relative(padap, &meminfo, mem_type,
+				      &payload->start, &payload->end);
+}
+
+#define CUDBG_YIELD_ITERATION 256
+
 static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init,
 			     struct cudbg_buffer *dbg_buff, u8 mem_type,
 			     unsigned long tot_len,
 			     struct cudbg_error *cudbg_err)
 {
+	static const char * const region_name[] = { "Tx payload:",
+						    "Rx payload:" };
 	unsigned long bytes, bytes_left, bytes_read = 0;
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_region_info payload[2];
+	u32 yield_count = 0;
 	int rc = 0;
+	u8 i;
+
+	/* Get TX/RX Payload region range if they exist */
+	memset(payload, 0, sizeof(payload));
+	for (i = 0; i < ARRAY_SIZE(region_name); i++) {
+		rc = cudbg_get_payload_range(padap, mem_type, region_name[i],
+					     &payload[i]);
+		if (rc)
+			return rc;
+
+		if (payload[i].exist) {
+			/* Align start and end to avoid wrap around */
+			payload[i].start = roundup(payload[i].start,
+						   CUDBG_CHUNK_SIZE);
+			payload[i].end = rounddown(payload[i].end,
+						   CUDBG_CHUNK_SIZE);
+		}
+	}
 
 	bytes_left = tot_len;
 	while (bytes_left > 0) {
+		/* As MC size is huge and read through PIO access, this
+		 * loop will hold cpu for a longer time. OS may think that
+		 * the process is hanged and will generate CPU stall traces.
+		 * So yield the cpu regularly.
+		 */
+		yield_count++;
+		if (!(yield_count % CUDBG_YIELD_ITERATION))
+			schedule();
+
 		bytes = min_t(unsigned long, bytes_left,
 			      (unsigned long)CUDBG_CHUNK_SIZE);
-		rc = cudbg_get_buff(dbg_buff, bytes, &temp_buff);
+		rc = cudbg_get_buff(pdbg_init, dbg_buff, bytes, &temp_buff);
 		if (rc)
 			return rc;
+
+		for (i = 0; i < ARRAY_SIZE(payload); i++)
+			if (payload[i].exist &&
+			    bytes_read >= payload[i].start &&
+			    bytes_read + bytes <= payload[i].end)
+				/* TX and RX Payload regions can't overlap */
+				goto skip_read;
+
 		spin_lock(&padap->win0_lock);
 		rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type,
 				  bytes_read, bytes,
@@ -445,37 +944,23 @@ static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init,
 		spin_unlock(&padap->win0_lock);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
+
+skip_read:
 		bytes_left -= bytes;
 		bytes_read += bytes;
-		cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+		rc = cudbg_write_and_release_buff(pdbg_init, &temp_buff,
+						  dbg_buff);
+		if (rc) {
+			cudbg_put_buff(pdbg_init, &temp_buff);
+			return rc;
+		}
 	}
 	return rc;
 }
 
-static void cudbg_collect_mem_info(struct cudbg_init *pdbg_init,
-				   struct card_mem *mem_info)
-{
-	struct adapter *padap = pdbg_init->adap;
-	u32 value;
-
-	value = t4_read_reg(padap, MA_EDRAM0_BAR_A);
-	value = EDRAM0_SIZE_G(value);
-	mem_info->size_edc0 = (u16)value;
-
-	value = t4_read_reg(padap, MA_EDRAM1_BAR_A);
-	value = EDRAM1_SIZE_G(value);
-	mem_info->size_edc1 = (u16)value;
-
-	value = t4_read_reg(padap, MA_TARGET_MEM_ENABLE_A);
-	if (value & EDRAM0_ENABLE_F)
-		mem_info->mem_flag |= (1 << EDC0_FLAG);
-	if (value & EDRAM1_ENABLE_F)
-		mem_info->mem_flag |= (1 << EDC1_FLAG);
-}
-
 static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init,
 			     struct cudbg_error *cudbg_err)
 {
@@ -495,37 +980,25 @@ static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
 				    struct cudbg_error *cudbg_err,
 				    u8 mem_type)
 {
-	struct card_mem mem_info = {0};
-	unsigned long flag, size;
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_meminfo mem_info;
+	unsigned long size;
+	u8 mc_idx;
 	int rc;
 
+	memset(&mem_info, 0, sizeof(struct cudbg_meminfo));
+	rc = cudbg_fill_meminfo(padap, &mem_info);
+	if (rc)
+		return rc;
+
 	cudbg_t4_fwcache(pdbg_init, cudbg_err);
-	cudbg_collect_mem_info(pdbg_init, &mem_info);
-	switch (mem_type) {
-	case MEM_EDC0:
-		flag = (1 << EDC0_FLAG);
-		size = cudbg_mbytes_to_bytes(mem_info.size_edc0);
-		break;
-	case MEM_EDC1:
-		flag = (1 << EDC1_FLAG);
-		size = cudbg_mbytes_to_bytes(mem_info.size_edc1);
-		break;
-	default:
-		rc = CUDBG_STATUS_ENTITY_NOT_FOUND;
-		goto err;
-	}
+	rc = cudbg_meminfo_get_mem_index(padap, &mem_info, mem_type, &mc_idx);
+	if (rc)
+		return rc;
 
-	if (mem_info.mem_flag & flag) {
-		rc = cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type,
-				       size, cudbg_err);
-		if (rc)
-			goto err;
-	} else {
-		rc = CUDBG_STATUS_ENTITY_NOT_FOUND;
-		goto err;
-	}
-err:
-	return rc;
+	size = mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base;
+	return cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, size,
+				 cudbg_err);
 }
 
 int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init,
@@ -544,26 +1017,51 @@ int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init,
 					MEM_EDC1);
 }
 
+int cudbg_collect_mc0_meminfo(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err,
+					MEM_MC0);
+}
+
+int cudbg_collect_mc1_meminfo(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err,
+					MEM_MC1);
+}
+
+int cudbg_collect_hma_meminfo(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err,
+					MEM_HMA);
+}
+
 int cudbg_collect_rss(struct cudbg_init *pdbg_init,
 		      struct cudbg_buffer *dbg_buff,
 		      struct cudbg_error *cudbg_err)
 {
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_buffer temp_buff = { 0 };
-	int rc;
+	int rc, nentries;
 
-	rc = cudbg_get_buff(dbg_buff, RSS_NENTRIES * sizeof(u16), &temp_buff);
+	nentries = t4_chip_rss_size(padap);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, nentries * sizeof(u16),
+			    &temp_buff);
 	if (rc)
 		return rc;
 
 	rc = t4_read_rss(padap, (u16 *)temp_buff.data);
 	if (rc) {
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_rss_vf_config(struct cudbg_init *pdbg_init,
@@ -576,7 +1074,7 @@ int cudbg_collect_rss_vf_config(struct cudbg_init *pdbg_init,
 	int vf, rc, vf_count;
 
 	vf_count = padap->params.arch.vfcount;
-	rc = cudbg_get_buff(dbg_buff,
+	rc = cudbg_get_buff(pdbg_init, dbg_buff,
 			    vf_count * sizeof(struct cudbg_rss_vf_conf),
 			    &temp_buff);
 	if (rc)
@@ -586,8 +1084,7 @@ int cudbg_collect_rss_vf_config(struct cudbg_init *pdbg_init,
 	for (vf = 0; vf < vf_count; vf++)
 		t4_read_rss_vf_config(padap, vf, &vfconf[vf].rss_vf_vfl,
 				      &vfconf[vf].rss_vf_vfh, true);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_path_mtu(struct cudbg_init *pdbg_init,
@@ -598,13 +1095,13 @@ int cudbg_collect_path_mtu(struct cudbg_init *pdbg_init,
 	struct cudbg_buffer temp_buff = { 0 };
 	int rc;
 
-	rc = cudbg_get_buff(dbg_buff, NMTUS * sizeof(u16), &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, NMTUS * sizeof(u16),
+			    &temp_buff);
 	if (rc)
 		return rc;
 
 	t4_read_mtu_tbl(padap, (u16 *)temp_buff.data, NULL);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_pm_stats(struct cudbg_init *pdbg_init,
@@ -616,7 +1113,7 @@ int cudbg_collect_pm_stats(struct cudbg_init *pdbg_init,
 	struct cudbg_pm_stats *pm_stats_buff;
 	int rc;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_pm_stats),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_pm_stats),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -624,8 +1121,7 @@ int cudbg_collect_pm_stats(struct cudbg_init *pdbg_init,
 	pm_stats_buff = (struct cudbg_pm_stats *)temp_buff.data;
 	t4_pmtx_get_stats(padap, pm_stats_buff->tx_cnt, pm_stats_buff->tx_cyc);
 	t4_pmrx_get_stats(padap, pm_stats_buff->rx_cnt, pm_stats_buff->rx_cyc);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init,
@@ -640,7 +1136,7 @@ int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init,
 	if (!padap->params.vpd.cclk)
 		return CUDBG_STATUS_CCLK_NOT_DEFINED;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_hw_sched),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_hw_sched),
 			    &temp_buff);
 	hw_sched_buff = (struct cudbg_hw_sched *)temp_buff.data;
 	hw_sched_buff->map = t4_read_reg(padap, TP_TX_MOD_QUEUE_REQ_MAP_A);
@@ -649,8 +1145,7 @@ int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init,
 	for (i = 0; i < NTX_SCHED; ++i)
 		t4_get_tx_sched(padap, i, &hw_sched_buff->kbps[i],
 				&hw_sched_buff->ipg[i], true);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init,
@@ -674,7 +1169,7 @@ int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init,
 
 	n = n / (IREG_NUM_ELEM * sizeof(u32));
 	size = sizeof(struct ireg_buf) * n;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -763,8 +1258,7 @@ int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init,
 			       tp_pio->ireg_local_offset, true);
 		ch_tp_pio++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
@@ -776,7 +1270,8 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
 	struct ireg_buf *ch_sge_dbg;
 	int i, rc;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(*ch_sge_dbg) * 2, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(*ch_sge_dbg) * 2,
+			    &temp_buff);
 	if (rc)
 		return rc;
 
@@ -797,8 +1292,7 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
 				 sge_pio->ireg_local_offset);
 		ch_sge_dbg++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_ulprx_la(struct cudbg_init *pdbg_init,
@@ -810,7 +1304,7 @@ int cudbg_collect_ulprx_la(struct cudbg_init *pdbg_init,
 	struct cudbg_ulprx_la *ulprx_la_buff;
 	int rc;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_ulprx_la),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_ulprx_la),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -818,8 +1312,7 @@ int cudbg_collect_ulprx_la(struct cudbg_init *pdbg_init,
 	ulprx_la_buff = (struct cudbg_ulprx_la *)temp_buff.data;
 	t4_ulprx_read_la(padap, (u32 *)ulprx_la_buff->data);
 	ulprx_la_buff->size = ULPRX_LA_SIZE;
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_tp_la(struct cudbg_init *pdbg_init,
@@ -832,15 +1325,39 @@ int cudbg_collect_tp_la(struct cudbg_init *pdbg_init,
 	int size, rc;
 
 	size = sizeof(struct cudbg_tp_la) + TPLA_SIZE *  sizeof(u64);
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
 	tp_la_buff = (struct cudbg_tp_la *)temp_buff.data;
 	tp_la_buff->mode = DBGLAMODE_G(t4_read_reg(padap, TP_DBG_LA_CONFIG_A));
 	t4_tp_read_la(padap, (u64 *)tp_la_buff->data, NULL);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
+}
+
+int cudbg_collect_meminfo(struct cudbg_init *pdbg_init,
+			  struct cudbg_buffer *dbg_buff,
+			  struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_meminfo *meminfo_buff;
+	int rc;
+
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_meminfo),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	meminfo_buff = (struct cudbg_meminfo *)temp_buff.data;
+	rc = cudbg_fill_meminfo(padap, meminfo_buff);
+	if (rc) {
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(pdbg_init, &temp_buff);
+		return rc;
+	}
+
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_cim_pif_la(struct cudbg_init *pdbg_init,
@@ -854,7 +1371,7 @@ int cudbg_collect_cim_pif_la(struct cudbg_init *pdbg_init,
 
 	size = sizeof(struct cudbg_cim_pif_la) +
 	       2 * CIM_PIFLA_SIZE * 6 * sizeof(u32);
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -863,8 +1380,7 @@ int cudbg_collect_cim_pif_la(struct cudbg_init *pdbg_init,
 	t4_cim_read_pif_la(padap, (u32 *)cim_pif_la_buff->data,
 			   (u32 *)cim_pif_la_buff->data + 6 * CIM_PIFLA_SIZE,
 			   NULL, NULL);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_clk_info(struct cudbg_init *pdbg_init,
@@ -880,7 +1396,7 @@ int cudbg_collect_clk_info(struct cudbg_init *pdbg_init,
 	if (!padap->params.vpd.cclk)
 		return CUDBG_STATUS_CCLK_NOT_DEFINED;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_clk_info),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_clk_info),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -912,8 +1428,7 @@ int cudbg_collect_clk_info(struct cudbg_init *pdbg_init,
 	clk_info_buff->finwait2_timer =
 		tp_tick_us * t4_read_reg(padap, TP_FINWAIT2_TIMER_A);
 
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init,
@@ -928,7 +1443,7 @@ int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init,
 
 	n = sizeof(t5_pcie_pdbg_array) / (IREG_NUM_ELEM * sizeof(u32));
 	size = sizeof(struct ireg_buf) * n * 2;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -969,8 +1484,7 @@ int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init,
 				 pcie_pio->ireg_local_offset);
 		ch_pcie++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init,
@@ -985,7 +1499,7 @@ int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init,
 
 	n = sizeof(t5_pm_rx_array) / (IREG_NUM_ELEM * sizeof(u32));
 	size = sizeof(struct ireg_buf) * n * 2;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -1026,8 +1540,7 @@ int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init,
 				 pm_pio->ireg_local_offset);
 		ch_pm++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_tid(struct cudbg_init *pdbg_init,
@@ -1041,7 +1554,8 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init,
 	u32 para[2], val[2];
 	int rc;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_tid_info_region_rev1),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff,
+			    sizeof(struct cudbg_tid_info_region_rev1),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -1053,6 +1567,12 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init,
 	tid1->ver_hdr.size = sizeof(struct cudbg_tid_info_region_rev1) -
 			     sizeof(struct cudbg_ver_hdr);
 
+	/* If firmware is not attached/alive, use backdoor register
+	 * access to collect dump.
+	 */
+	if (!is_fw_attached(pdbg_init))
+		goto fill_tid;
+
 #define FW_PARAM_PFVF_A(param) \
 	(FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) | \
 	 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_##param) | \
@@ -1064,7 +1584,7 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init,
 	rc = t4_query_params(padap, padap->mbox, padap->pf, 0, 2, para, val);
 	if (rc <  0) {
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
 	tid->uotid_base = val[0];
@@ -1083,13 +1603,16 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init,
 				     para, val);
 		if (rc < 0) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 		tid->hpftid_base = val[0];
 		tid->nhpftids = val[1] - val[0] + 1;
 	}
 
+#undef FW_PARAM_PFVF_A
+
+fill_tid:
 	tid->ntids = padap->tids.ntids;
 	tid->nstids = padap->tids.nstids;
 	tid->stid_base = padap->tids.stid_base;
@@ -1109,28 +1632,137 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init,
 	tid->ip_users = t4_read_reg(padap, LE_DB_ACT_CNT_IPV4_A);
 	tid->ipv6_users = t4_read_reg(padap, LE_DB_ACT_CNT_IPV6_A);
 
-#undef FW_PARAM_PFVF_A
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
+}
 
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+int cudbg_collect_pcie_config(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	u32 size, *value, j;
+	int i, rc, n;
+
+	size = sizeof(u32) * CUDBG_NUM_PCIE_CONFIG_REGS;
+	n = sizeof(t5_pcie_config_array) / (2 * sizeof(u32));
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	value = (u32 *)temp_buff.data;
+	for (i = 0; i < n; i++) {
+		for (j = t5_pcie_config_array[i][0];
+		     j <= t5_pcie_config_array[i][1]; j += 4) {
+			t4_hw_pci_read_cfg4(padap, j, value);
+			value++;
+		}
+	}
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
-int cudbg_dump_context_size(struct adapter *padap)
+static int cudbg_sge_ctxt_check_valid(u32 *buf, int type)
+{
+	int index, bit, bit_pos = 0;
+
+	switch (type) {
+	case CTXT_EGRESS:
+		bit_pos = 176;
+		break;
+	case CTXT_INGRESS:
+		bit_pos = 141;
+		break;
+	case CTXT_FLM:
+		bit_pos = 89;
+		break;
+	}
+	index = bit_pos / 32;
+	bit =  bit_pos % 32;
+	return buf[index] & (1U << bit);
+}
+
+static int cudbg_get_ctxt_region_info(struct adapter *padap,
+				      struct cudbg_region_info *ctx_info,
+				      u8 *mem_type)
 {
-	u32 value, size;
+	struct cudbg_mem_desc mem_desc;
+	struct cudbg_meminfo meminfo;
+	u32 i, j, value, found;
 	u8 flq;
+	int rc;
+
+	rc = cudbg_fill_meminfo(padap, &meminfo);
+	if (rc)
+		return rc;
+
+	/* Get EGRESS and INGRESS context region size */
+	for (i = CTXT_EGRESS; i <= CTXT_INGRESS; i++) {
+		found = 0;
+		memset(&mem_desc, 0, sizeof(struct cudbg_mem_desc));
+		for (j = 0; j < ARRAY_SIZE(meminfo.avail); j++) {
+			rc = cudbg_get_mem_region(padap, &meminfo, j,
+						  cudbg_region[i],
+						  &mem_desc);
+			if (!rc) {
+				found = 1;
+				rc = cudbg_get_mem_relative(padap, &meminfo, j,
+							    &mem_desc.base,
+							    &mem_desc.limit);
+				if (rc) {
+					ctx_info[i].exist = false;
+					break;
+				}
+				ctx_info[i].exist = true;
+				ctx_info[i].start = mem_desc.base;
+				ctx_info[i].end = mem_desc.limit;
+				mem_type[i] = j;
+				break;
+			}
+		}
+		if (!found)
+			ctx_info[i].exist = false;
+	}
 
+	/* Get FLM and CNM max qid. */
 	value = t4_read_reg(padap, SGE_FLM_CFG_A);
 
 	/* Get number of data freelist queues */
 	flq = HDRSTARTFLQ_G(value);
-	size = CUDBG_MAX_FL_QIDS >> flq;
+	ctx_info[CTXT_FLM].exist = true;
+	ctx_info[CTXT_FLM].end = (CUDBG_MAX_FL_QIDS >> flq) * SGE_CTXT_SIZE;
 
-	/* Add extra space for congestion manager contexts.
-	 * The number of CONM contexts are same as number of freelist
+	/* The number of CONM contexts are same as number of freelist
 	 * queues.
 	 */
-	size += size;
+	ctx_info[CTXT_CNM].exist = true;
+	ctx_info[CTXT_CNM].end = ctx_info[CTXT_FLM].end;
+
+	return 0;
+}
+
+int cudbg_dump_context_size(struct adapter *padap)
+{
+	struct cudbg_region_info region_info[CTXT_CNM + 1] = { {0} };
+	u8 mem_type[CTXT_INGRESS + 1] = { 0 };
+	u32 i, size = 0;
+	int rc;
+
+	/* Get max valid qid for each type of queue */
+	rc = cudbg_get_ctxt_region_info(padap, region_info, mem_type);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < CTXT_CNM; i++) {
+		if (!region_info[i].exist) {
+			if (i == CTXT_EGRESS || i == CTXT_INGRESS)
+				size += CUDBG_LOWMEM_MAX_CTXT_QIDS *
+					SGE_CTXT_SIZE;
+			continue;
+		}
+
+		size += (region_info[i].end - region_info[i].start + 1) /
+			SGE_CTXT_SIZE;
+	}
 	return size * sizeof(struct cudbg_ch_cntxt);
 }
 
@@ -1153,44 +1785,144 @@ static void cudbg_read_sge_ctxt(struct cudbg_init *pdbg_init, u32 cid,
 		t4_sge_ctxt_rd_bd(padap, cid, ctype, data);
 }
 
+static void cudbg_get_sge_ctxt_fw(struct cudbg_init *pdbg_init, u32 max_qid,
+				  u8 ctxt_type,
+				  struct cudbg_ch_cntxt **out_buff)
+{
+	struct cudbg_ch_cntxt *buff = *out_buff;
+	int rc;
+	u32 j;
+
+	for (j = 0; j < max_qid; j++) {
+		cudbg_read_sge_ctxt(pdbg_init, j, ctxt_type, buff->data);
+		rc = cudbg_sge_ctxt_check_valid(buff->data, ctxt_type);
+		if (!rc)
+			continue;
+
+		buff->cntxt_type = ctxt_type;
+		buff->cntxt_id = j;
+		buff++;
+		if (ctxt_type == CTXT_FLM) {
+			cudbg_read_sge_ctxt(pdbg_init, j, CTXT_CNM, buff->data);
+			buff->cntxt_type = CTXT_CNM;
+			buff->cntxt_id = j;
+			buff++;
+		}
+	}
+
+	*out_buff = buff;
+}
+
 int cudbg_collect_dump_context(struct cudbg_init *pdbg_init,
 			       struct cudbg_buffer *dbg_buff,
 			       struct cudbg_error *cudbg_err)
 {
+	struct cudbg_region_info region_info[CTXT_CNM + 1] = { {0} };
 	struct adapter *padap = pdbg_init->adap;
+	u32 j, size, max_ctx_size, max_ctx_qid;
+	u8 mem_type[CTXT_INGRESS + 1] = { 0 };
 	struct cudbg_buffer temp_buff = { 0 };
 	struct cudbg_ch_cntxt *buff;
-	u32 size, i = 0;
+	u64 *dst_off, *src_off;
+	u8 *ctx_buf;
+	u8 i, k;
 	int rc;
 
+	/* Get max valid qid for each type of queue */
+	rc = cudbg_get_ctxt_region_info(padap, region_info, mem_type);
+	if (rc)
+		return rc;
+
 	rc = cudbg_dump_context_size(padap);
 	if (rc <= 0)
 		return CUDBG_STATUS_ENTITY_NOT_FOUND;
 
 	size = rc;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
+	/* Get buffer with enough space to read the biggest context
+	 * region in memory.
+	 */
+	max_ctx_size = max(region_info[CTXT_EGRESS].end -
+			   region_info[CTXT_EGRESS].start + 1,
+			   region_info[CTXT_INGRESS].end -
+			   region_info[CTXT_INGRESS].start + 1);
+
+	ctx_buf = kvzalloc(max_ctx_size, GFP_KERNEL);
+	if (!ctx_buf) {
+		cudbg_put_buff(pdbg_init, &temp_buff);
+		return -ENOMEM;
+	}
+
 	buff = (struct cudbg_ch_cntxt *)temp_buff.data;
-	while (size > 0) {
-		buff->cntxt_type = CTXT_FLM;
-		buff->cntxt_id = i;
-		cudbg_read_sge_ctxt(pdbg_init, i, CTXT_FLM, buff->data);
-		buff++;
-		size -= sizeof(struct cudbg_ch_cntxt);
 
-		buff->cntxt_type = CTXT_CNM;
-		buff->cntxt_id = i;
-		cudbg_read_sge_ctxt(pdbg_init, i, CTXT_CNM, buff->data);
-		buff++;
-		size -= sizeof(struct cudbg_ch_cntxt);
+	/* Collect EGRESS and INGRESS context data.
+	 * In case of failures, fallback to collecting via FW or
+	 * backdoor access.
+	 */
+	for (i = CTXT_EGRESS; i <= CTXT_INGRESS; i++) {
+		if (!region_info[i].exist) {
+			max_ctx_qid = CUDBG_LOWMEM_MAX_CTXT_QIDS;
+			cudbg_get_sge_ctxt_fw(pdbg_init, max_ctx_qid, i,
+					      &buff);
+			continue;
+		}
 
-		i++;
+		max_ctx_size = region_info[i].end - region_info[i].start + 1;
+		max_ctx_qid = max_ctx_size / SGE_CTXT_SIZE;
+
+		/* If firmware is not attached/alive, use backdoor register
+		 * access to collect dump.
+		 */
+		if (is_fw_attached(pdbg_init)) {
+			t4_sge_ctxt_flush(padap, padap->mbox, i);
+
+			rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type[i],
+					  region_info[i].start, max_ctx_size,
+					  (__be32 *)ctx_buf, 1);
+		}
+
+		if (rc || !is_fw_attached(pdbg_init)) {
+			max_ctx_qid = CUDBG_LOWMEM_MAX_CTXT_QIDS;
+			cudbg_get_sge_ctxt_fw(pdbg_init, max_ctx_qid, i,
+					      &buff);
+			continue;
+		}
+
+		for (j = 0; j < max_ctx_qid; j++) {
+			src_off = (u64 *)(ctx_buf + j * SGE_CTXT_SIZE);
+			dst_off = (u64 *)buff->data;
+
+			/* The data is stored in 64-bit cpu order.  Convert it
+			 * to big endian before parsing.
+			 */
+			for (k = 0; k < SGE_CTXT_SIZE / sizeof(u64); k++)
+				dst_off[k] = cpu_to_be64(src_off[k]);
+
+			rc = cudbg_sge_ctxt_check_valid(buff->data, i);
+			if (!rc)
+				continue;
+
+			buff->cntxt_type = i;
+			buff->cntxt_id = j;
+			buff++;
+		}
 	}
 
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	kvfree(ctx_buf);
+
+	/* Collect FREELIST and CONGESTION MANAGER contexts */
+	max_ctx_size = region_info[CTXT_FLM].end -
+		       region_info[CTXT_FLM].start + 1;
+	max_ctx_qid = max_ctx_size / SGE_CTXT_SIZE;
+	/* Since FLM and CONM are 1-to-1 mapped, the below function
+	 * will fetch both FLM and CONM contexts.
+	 */
+	cudbg_get_sge_ctxt_fw(pdbg_init, max_ctx_qid, CTXT_FLM, &buff);
+
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 static inline void cudbg_tcamxy2valmask(u64 x, u64 y, u8 *addr, u64 *mask)
@@ -1228,9 +1960,10 @@ static void cudbg_mps_rpl_backdoor(struct adapter *padap,
 	mps_rplc->rplc31_0 = htonl(t4_read_reg(padap, MPS_VF_RPLCT_MAP0_A));
 }
 
-static int cudbg_collect_tcam_index(struct adapter *padap,
+static int cudbg_collect_tcam_index(struct cudbg_init *pdbg_init,
 				    struct cudbg_mps_tcam *tcam, u32 idx)
 {
+	struct adapter *padap = pdbg_init->adap;
 	u64 tcamy, tcamx, val;
 	u32 ctl, data2;
 	int rc = 0;
@@ -1315,12 +2048,22 @@ static int cudbg_collect_tcam_index(struct adapter *padap,
 			htons(FW_LDST_CMD_FID_V(FW_LDST_MPS_RPLC) |
 			      FW_LDST_CMD_IDX_V(idx));
 
-		rc = t4_wr_mbox(padap, padap->mbox, &ldst_cmd, sizeof(ldst_cmd),
-				&ldst_cmd);
-		if (rc)
+		/* If firmware is not attached/alive, use backdoor register
+		 * access to collect dump.
+		 */
+		if (is_fw_attached(pdbg_init))
+			rc = t4_wr_mbox(padap, padap->mbox, &ldst_cmd,
+					sizeof(ldst_cmd), &ldst_cmd);
+
+		if (rc || !is_fw_attached(pdbg_init)) {
 			cudbg_mps_rpl_backdoor(padap, &mps_rplc);
-		else
+			/* Ignore error since we collected directly from
+			 * reading registers.
+			 */
+			rc = 0;
+		} else {
 			mps_rplc = ldst_cmd.u.mps.rplc;
+		}
 
 		tcam->rplc[0] = ntohl(mps_rplc.rplc31_0);
 		tcam->rplc[1] = ntohl(mps_rplc.rplc63_32);
@@ -1351,16 +2094,16 @@ int cudbg_collect_mps_tcam(struct cudbg_init *pdbg_init,
 
 	n = padap->params.arch.mps_tcam_size;
 	size = sizeof(struct cudbg_mps_tcam) * n;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
 	tcam = (struct cudbg_mps_tcam *)temp_buff.data;
 	for (i = 0; i < n; i++) {
-		rc = cudbg_collect_tcam_index(padap, tcam, i);
+		rc = cudbg_collect_tcam_index(pdbg_init, tcam, i);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 		total_size += sizeof(struct cudbg_mps_tcam);
@@ -1370,11 +2113,10 @@ int cudbg_collect_mps_tcam(struct cudbg_init *pdbg_init,
 	if (!total_size) {
 		rc = CUDBG_SYSTEM_ERROR;
 		cudbg_err->sys_err = rc;
-		cudbg_put_buff(&temp_buff, dbg_buff);
+		cudbg_put_buff(pdbg_init, &temp_buff);
 		return rc;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_vpd_data(struct cudbg_init *pdbg_init,
@@ -1425,7 +2167,7 @@ int cudbg_collect_vpd_data(struct cudbg_init *pdbg_init,
 	if (rc)
 		return rc;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_vpd_data),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_vpd_data),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -1441,8 +2183,7 @@ int cudbg_collect_vpd_data(struct cudbg_init *pdbg_init,
 	vpd_data->fw_minor = FW_HDR_FW_VER_MINOR_G(fw_vers);
 	vpd_data->fw_micro = FW_HDR_FW_VER_MICRO_G(fw_vers);
 	vpd_data->fw_build = FW_HDR_FW_VER_BUILD_G(fw_vers);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 static int cudbg_read_tid(struct cudbg_init *pdbg_init, u32 tid,
@@ -1593,7 +2334,7 @@ int cudbg_collect_le_tcam(struct cudbg_init *pdbg_init,
 
 	size = sizeof(struct cudbg_tid_data) * tcam_region.max_tid;
 	size += sizeof(struct cudbg_tcam);
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -1605,7 +2346,7 @@ int cudbg_collect_le_tcam(struct cudbg_init *pdbg_init,
 		rc = cudbg_read_tid(pdbg_init, i, tid_data);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 
@@ -1616,8 +2357,7 @@ int cudbg_collect_le_tcam(struct cudbg_init *pdbg_init,
 		bytes += sizeof(struct cudbg_tid_data);
 	}
 
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_cctrl(struct cudbg_init *pdbg_init,
@@ -1630,13 +2370,12 @@ int cudbg_collect_cctrl(struct cudbg_init *pdbg_init,
 	int rc;
 
 	size = sizeof(u16) * NMTUS * NCCTRL_WIN;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
 	t4_read_cong_tbl(padap, (void *)temp_buff.data);
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init,
@@ -1654,7 +2393,7 @@ int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init,
 
 	n = sizeof(t6_ma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32));
 	size = sizeof(struct ireg_buf) * n * 2;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -1690,8 +2429,7 @@ int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init,
 		}
 		ma_indr++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
@@ -1704,7 +2442,7 @@ int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
 	u32 i, j;
 	int rc;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_ulptx_la),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_ulptx_la),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -1725,8 +2463,7 @@ int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
 				t4_read_reg(padap,
 					    ULP_TX_LA_RDDATA_0_A + 0x10 * i);
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init,
@@ -1735,13 +2472,23 @@ int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init,
 {
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_buffer temp_buff = { 0 };
+	u32 local_offset, local_range;
 	struct ireg_buf *up_cim;
+	u32 size, j, iter;
+	u32 instance = 0;
 	int i, rc, n;
-	u32 size;
 
-	n = sizeof(t5_up_cim_reg_array) / (IREG_NUM_ELEM * sizeof(u32));
+	if (is_t5(padap->params.chip))
+		n = sizeof(t5_up_cim_reg_array) /
+		    ((IREG_NUM_ELEM + 1) * sizeof(u32));
+	else if (is_t6(padap->params.chip))
+		n = sizeof(t6_up_cim_reg_array) /
+		    ((IREG_NUM_ELEM + 1) * sizeof(u32));
+	else
+		return CUDBG_STATUS_NOT_IMPLEMENTED;
+
 	size = sizeof(struct ireg_buf) * n;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -1757,6 +2504,7 @@ int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init,
 						t5_up_cim_reg_array[i][2];
 			up_cim_reg->ireg_offset_range =
 						t5_up_cim_reg_array[i][3];
+			instance = t5_up_cim_reg_array[i][4];
 		} else if (is_t6(padap->params.chip)) {
 			up_cim_reg->ireg_addr = t6_up_cim_reg_array[i][0];
 			up_cim_reg->ireg_data = t6_up_cim_reg_array[i][1];
@@ -1764,18 +2512,39 @@ int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init,
 						t6_up_cim_reg_array[i][2];
 			up_cim_reg->ireg_offset_range =
 						t6_up_cim_reg_array[i][3];
+			instance = t6_up_cim_reg_array[i][4];
 		}
 
-		rc = t4_cim_read(padap, up_cim_reg->ireg_local_offset,
-				 up_cim_reg->ireg_offset_range, buff);
-		if (rc) {
-			cudbg_put_buff(&temp_buff, dbg_buff);
-			return rc;
+		switch (instance) {
+		case NUM_CIM_CTL_TSCH_CHANNEL_INSTANCES:
+			iter = up_cim_reg->ireg_offset_range;
+			local_offset = 0x120;
+			local_range = 1;
+			break;
+		case NUM_CIM_CTL_TSCH_CHANNEL_TSCH_CLASS_INSTANCES:
+			iter = up_cim_reg->ireg_offset_range;
+			local_offset = 0x10;
+			local_range = 1;
+			break;
+		default:
+			iter = 1;
+			local_offset = 0;
+			local_range = up_cim_reg->ireg_offset_range;
+			break;
+		}
+
+		for (j = 0; j < iter; j++, buff++) {
+			rc = t4_cim_read(padap,
+					 up_cim_reg->ireg_local_offset +
+					 (j * local_offset), local_range, buff);
+			if (rc) {
+				cudbg_put_buff(pdbg_init, &temp_buff);
+				return rc;
+			}
 		}
 		up_cim++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
@@ -1788,7 +2557,8 @@ int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
 	int i, rc;
 	u32 addr;
 
-	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_pbt_tables),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff,
+			    sizeof(struct cudbg_pbt_tables),
 			    &temp_buff);
 	if (rc)
 		return rc;
@@ -1801,7 +2571,7 @@ int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
 				 &pbt->pbt_dynamic[i]);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 	}
@@ -1814,7 +2584,7 @@ int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
 				 &pbt->pbt_static[i]);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 	}
@@ -1826,7 +2596,7 @@ int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
 				 &pbt->lrf_table[i]);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 	}
@@ -1838,12 +2608,11 @@ int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
 				 &pbt->pbt_data[i]);
 		if (rc) {
 			cudbg_err->sys_err = rc;
-			cudbg_put_buff(&temp_buff, dbg_buff);
+			cudbg_put_buff(pdbg_init, &temp_buff);
 			return rc;
 		}
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init,
@@ -1864,7 +2633,7 @@ int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init,
 	log = padap->mbox_log;
 	mbox_cmds = padap->mbox_log->size;
 	size = sizeof(struct cudbg_mbox_log) * mbox_cmds;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -1887,8 +2656,7 @@ int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init,
 		}
 		mboxlog++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
 int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init,
@@ -1906,7 +2674,7 @@ int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init,
 
 	n = sizeof(t6_hma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32));
 	size = sizeof(struct ireg_buf) * n;
-	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -1924,6 +2692,5 @@ int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init,
 				 hma_fli->ireg_local_offset);
 		hma_indr++;
 	}
-	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
-	return rc;
+	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }