Merge branch 'add-support-for-marvell-octeontx2-cryptographic'

Srujana Challa says:

====================
Add Support for Marvell OcteonTX2 Cryptographic

This patchset adds support for CPT in OcteonTX2 admin function(AF).
CPT is a cryptographic accelerator unit and it includes microcoded
Giga Cipher engines.

OcteonTX2 SOC's resource virtualization unit (RVU) supports multiple
physical and virtual functions. Each of the PF/VF's functionality is
determined by what kind of resources are attached to it. When the CPT
block is attached to a VF, it can function as a security device.
The following document provides an overview of the hardware and
different drivers for the OcteonTX2 SOC:
https://www.kernel.org/doc/Documentation/networking/device_drivers/marvell/octeontx2.rst

This patch series includes:
- Patch to update existing Marvell sources to support CPT.
- Patch that adds mailbox messages to the admin function (AF) driver,
to configure CPT HW registers.
- Patch to provide debug information about CPT.
====================

Link: https://lore.kernel.org/r/20201118114416.28307-1-schalla@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 630 insertions, 19 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index a7e0f11def8e..d36bee3f1f04 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10453,6 +10453,7 @@ M:	Srujana Challa <schalla@marvell.com>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
 F:	drivers/crypto/marvell/
+F:	include/linux/soc/marvell/octeontx2/
 
 MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
 M:	Mirko Lindner <mlindner@marvell.com>
@@ -10525,6 +10526,7 @@ M:	hariprasad <hkelam@marvell.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/marvell/octeontx2/nic/
+F:	include/linux/soc/marvell/octeontx2/
 
 MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER
 M:	Sunil Goutham <sgoutham@marvell.com>
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
index ffc681b67f1c..7100d1dd856e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@@ -9,4 +9,5 @@ obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o
 
 octeontx2_mbox-y := mbox.o rvu_trace.o
 octeontx2_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
-		  rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o
+		  rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
+		  rvu_cpt.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index cb4e3d86b58b..221fe5b7c093 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -158,6 +158,11 @@ M(NPA_HWCTX_DISABLE,	0x403, npa_hwctx_disable, hwctx_disable_req, msg_rsp)\
 /* SSO/SSOW mbox IDs (range 0x600 - 0x7FF) */				\
 /* TIM mbox IDs (range 0x800 - 0x9FF) */				\
 /* CPT mbox IDs (range 0xA00 - 0xBFF) */				\
+M(CPT_LF_ALLOC,		0xA00, cpt_lf_alloc, cpt_lf_alloc_req_msg,	\
+			       msg_rsp)					\
+M(CPT_LF_FREE,		0xA01, cpt_lf_free, msg_req, msg_rsp)		\
+M(CPT_RD_WR_REGISTER,	0xA02, cpt_rd_wr_register,  cpt_rd_wr_reg_msg,	\
+			       cpt_rd_wr_reg_msg)			\
 /* NPC mbox IDs (range 0x6000 - 0x7FFF) */				\
 M(NPC_MCAM_ALLOC_ENTRY,	0x6000, npc_mcam_alloc_entry, npc_mcam_alloc_entry_req,\
 				npc_mcam_alloc_entry_rsp)		\
@@ -1046,4 +1051,32 @@ struct ptp_rsp {
 	u64 clk;
 };
 
+/* CPT mailbox error codes
+ * Range 901 - 1000.
+ */
+enum cpt_af_status {
+	CPT_AF_ERR_PARAM		= -901,
+	CPT_AF_ERR_GRP_INVALID		= -902,
+	CPT_AF_ERR_LF_INVALID		= -903,
+	CPT_AF_ERR_ACCESS_DENIED	= -904,
+	CPT_AF_ERR_SSO_PF_FUNC_INVALID	= -905,
+	CPT_AF_ERR_NIX_PF_FUNC_INVALID	= -906
+};
+
+/* CPT mbox message formats */
+struct cpt_rd_wr_reg_msg {
+	struct mbox_msghdr hdr;
+	u64 reg_offset;
+	u64 *ret_val;
+	u64 val;
+	u8 is_write;
+};
+
+struct cpt_lf_alloc_req_msg {
+	struct mbox_msghdr hdr;
+	u16 nix_pf_func;
+	u16 sso_pf_func;
+	u16 eng_grpmsk;
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 37774bac32b0..b6c0977499ab 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -52,6 +52,7 @@ struct rvu_debugfs {
 	struct dentry *npa;
 	struct dentry *nix;
 	struct dentry *npc;
+	struct dentry *cpt;
 	struct dump_ctx npa_aura_ctx;
 	struct dump_ctx npa_pool_ctx;
 	struct dump_ctx nix_cq_ctx;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
new file mode 100644
index 000000000000..35261d52c997
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include <linux/pci.h>
+#include "rvu_struct.h"
+#include "rvu_reg.h"
+#include "mbox.h"
+#include "rvu.h"
+
+/* CPT PF device id */
+#define	PCI_DEVID_OTX2_CPT_PF	0xA0FD
+
+static int get_cpt_pf_num(struct rvu *rvu)
+{
+	int i, domain_nr, cpt_pf_num = -1;
+	struct pci_dev *pdev;
+
+	domain_nr = pci_domain_nr(rvu->pdev->bus);
+	for (i = 0; i < rvu->hw->total_pfs; i++) {
+		pdev = pci_get_domain_bus_and_slot(domain_nr, i + 1, 0);
+		if (!pdev)
+			continue;
+
+		if (pdev->device == PCI_DEVID_OTX2_CPT_PF) {
+			cpt_pf_num = i;
+			put_device(&pdev->dev);
+			break;
+		}
+		put_device(&pdev->dev);
+	}
+	return cpt_pf_num;
+}
+
+static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
+{
+	int cpt_pf_num = get_cpt_pf_num(rvu);
+
+	if (rvu_get_pf(pcifunc) != cpt_pf_num)
+		return false;
+	if (pcifunc & RVU_PFVF_FUNC_MASK)
+		return false;
+
+	return true;
+}
+
+static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc)
+{
+	int cpt_pf_num = get_cpt_pf_num(rvu);
+
+	if (rvu_get_pf(pcifunc) != cpt_pf_num)
+		return false;
+	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+		return false;
+
+	return true;
+}
+
+int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu,
+				  struct cpt_lf_alloc_req_msg *req,
+				  struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	struct rvu_block *block;
+	int cptlf, blkaddr;
+	int num_lfs, slot;
+	u64 val;
+
+	if (req->eng_grpmsk == 0x0)
+		return CPT_AF_ERR_GRP_INVALID;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return blkaddr;
+
+	block = &rvu->hw->block[blkaddr];
+	num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc),
+					block->addr);
+	if (!num_lfs)
+		return CPT_AF_ERR_LF_INVALID;
+
+	/* Check if requested 'CPTLF <=> NIXLF' mapping is valid */
+	if (req->nix_pf_func) {
+		/* If default, use 'this' CPTLF's PFFUNC */
+		if (req->nix_pf_func == RVU_DEFAULT_PF_FUNC)
+			req->nix_pf_func = pcifunc;
+		if (!is_pffunc_map_valid(rvu, req->nix_pf_func, BLKTYPE_NIX))
+			return CPT_AF_ERR_NIX_PF_FUNC_INVALID;
+	}
+
+	/* Check if requested 'CPTLF <=> SSOLF' mapping is valid */
+	if (req->sso_pf_func) {
+		/* If default, use 'this' CPTLF's PFFUNC */
+		if (req->sso_pf_func == RVU_DEFAULT_PF_FUNC)
+			req->sso_pf_func = pcifunc;
+		if (!is_pffunc_map_valid(rvu, req->sso_pf_func, BLKTYPE_SSO))
+			return CPT_AF_ERR_SSO_PF_FUNC_INVALID;
+	}
+
+	for (slot = 0; slot < num_lfs; slot++) {
+		cptlf = rvu_get_lf(rvu, block, pcifunc, slot);
+		if (cptlf < 0)
+			return CPT_AF_ERR_LF_INVALID;
+
+		/* Set CPT LF group and priority */
+		val = (u64)req->eng_grpmsk << 48 | 1;
+		rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val);
+
+		/* Set CPT LF NIX_PF_FUNC and SSO_PF_FUNC */
+		val = (u64)req->nix_pf_func << 48 |
+		      (u64)req->sso_pf_func << 32;
+		rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), val);
+	}
+
+	return 0;
+}
+
+int rvu_mbox_handler_cpt_lf_free(struct rvu *rvu, struct msg_req *req,
+				 struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	struct rvu_block *block;
+	int cptlf, blkaddr;
+	int num_lfs, slot;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return blkaddr;
+
+	block = &rvu->hw->block[blkaddr];
+	num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc),
+					block->addr);
+	if (!num_lfs)
+		return CPT_AF_ERR_LF_INVALID;
+
+	for (slot = 0; slot < num_lfs; slot++) {
+		cptlf = rvu_get_lf(rvu, block, pcifunc, slot);
+		if (cptlf < 0)
+			return CPT_AF_ERR_LF_INVALID;
+
+		/* Reset CPT LF group and priority */
+		rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), 0x0);
+		/* Reset CPT LF NIX_PF_FUNC and SSO_PF_FUNC */
+		rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), 0x0);
+	}
+
+	return 0;
+}
+
+static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
+{
+	u64 offset = req->reg_offset;
+	int blkaddr, num_lfs, lf;
+	struct rvu_block *block;
+	struct rvu_pfvf *pfvf;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+
+	/* Registers that can be accessed from PF/VF */
+	if ((offset & 0xFF000) ==  CPT_AF_LFX_CTL(0) ||
+	    (offset & 0xFF000) ==  CPT_AF_LFX_CTL2(0)) {
+		if (offset & 7)
+			return false;
+
+		lf = (offset & 0xFFF) >> 3;
+		block = &rvu->hw->block[blkaddr];
+		pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
+		num_lfs = rvu_get_rsrc_mapcount(pfvf, block->addr);
+		if (lf >= num_lfs)
+			/* Slot is not valid for that PF/VF */
+			return false;
+
+		/* Translate local LF used by VFs to global CPT LF */
+		lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr],
+				req->hdr.pcifunc, lf);
+		if (lf < 0)
+			return false;
+
+		return true;
+	} else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) {
+		/* Registers that can be accessed from PF */
+		switch (offset) {
+		case CPT_AF_CTL:
+		case CPT_AF_PF_FUNC:
+		case CPT_AF_BLK_RST:
+		case CPT_AF_CONSTANTS1:
+			return true;
+		}
+
+		switch (offset & 0xFF000) {
+		case CPT_AF_EXEX_STS(0):
+		case CPT_AF_EXEX_CTL(0):
+		case CPT_AF_EXEX_CTL2(0):
+		case CPT_AF_EXEX_UCODE_BASE(0):
+			if (offset & 7)
+				return false;
+			break;
+		default:
+			return false;
+		}
+		return true;
+	}
+	return false;
+}
+
+int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
+					struct cpt_rd_wr_reg_msg *req,
+					struct cpt_rd_wr_reg_msg *rsp)
+{
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return blkaddr;
+
+	/* This message is accepted only if sent from CPT PF/VF */
+	if (!is_cpt_pf(rvu, req->hdr.pcifunc) &&
+	    !is_cpt_vf(rvu, req->hdr.pcifunc))
+		return CPT_AF_ERR_ACCESS_DENIED;
+
+	rsp->reg_offset = req->reg_offset;
+	rsp->ret_val = req->ret_val;
+	rsp->is_write = req->is_write;
+
+	if (!is_valid_offset(rvu, req))
+		return CPT_AF_ERR_ACCESS_DENIED;
+
+	if (req->is_write)
+		rvu_write64(rvu, blkaddr, req->reg_offset, req->val);
+	else
+		rsp->val = rvu_read64(rvu, blkaddr, req->reg_offset);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 39e1a614aaf8..c383efc6b90c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -109,6 +109,12 @@ static char *cgx_tx_stats_fields[] = {
 	[CGX_STAT17]	= "Control/PAUSE packets sent",
 };
 
+enum cpt_eng_type {
+	CPT_AE_TYPE = 1,
+	CPT_SE_TYPE = 2,
+	CPT_IE_TYPE = 3,
+};
+
 #define NDC_MAX_BANK(rvu, blk_addr) (rvu_read64(rvu, \
 						blk_addr, NDC_AF_CONST) & 0xFF)
 
@@ -1993,6 +1999,271 @@ create_failed:
 	debugfs_remove_recursive(rvu->rvu_dbg.npc);
 }
 
+/* CPT debugfs APIs */
+static int cpt_eng_sts_display(struct seq_file *filp, u8 eng_type)
+{
+	struct rvu *rvu = filp->private;
+	u64 busy_sts = 0, free_sts = 0;
+	u32 e_min = 0, e_max = 0, e, i;
+	u16 max_ses, max_ies, max_aes;
+	int blkaddr;
+	u64 reg;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return -ENODEV;
+
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS1);
+	max_ses = reg & 0xffff;
+	max_ies = (reg >> 16) & 0xffff;
+	max_aes = (reg >> 32) & 0xffff;
+
+	switch (eng_type) {
+	case CPT_AE_TYPE:
+		e_min = max_ses + max_ies;
+		e_max = max_ses + max_ies + max_aes;
+		break;
+	case CPT_SE_TYPE:
+		e_min = 0;
+		e_max = max_ses;
+		break;
+	case CPT_IE_TYPE:
+		e_min = max_ses;
+		e_max = max_ses + max_ies;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (e = e_min, i = 0; e < e_max; e++, i++) {
+		reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_STS(e));
+		if (reg & 0x1)
+			busy_sts |= 1ULL << i;
+
+		if (reg & 0x2)
+			free_sts |= 1ULL << i;
+	}
+	seq_printf(filp, "FREE STS : 0x%016llx\n", free_sts);
+	seq_printf(filp, "BUSY STS : 0x%016llx\n", busy_sts);
+
+	return 0;
+}
+
+static int rvu_dbg_cpt_ae_sts_display(struct seq_file *filp, void *unused)
+{
+	return cpt_eng_sts_display(filp, CPT_AE_TYPE);
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_ae_sts, cpt_ae_sts_display, NULL);
+
+static int rvu_dbg_cpt_se_sts_display(struct seq_file *filp, void *unused)
+{
+	return cpt_eng_sts_display(filp, CPT_SE_TYPE);
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_se_sts, cpt_se_sts_display, NULL);
+
+static int rvu_dbg_cpt_ie_sts_display(struct seq_file *filp, void *unused)
+{
+	return cpt_eng_sts_display(filp, CPT_IE_TYPE);
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_ie_sts, cpt_ie_sts_display, NULL);
+
+static int rvu_dbg_cpt_engines_info_display(struct seq_file *filp, void *unused)
+{
+	struct rvu *rvu = filp->private;
+	u16 max_ses, max_ies, max_aes;
+	u32 e_max, e;
+	int blkaddr;
+	u64 reg;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return -ENODEV;
+
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS1);
+	max_ses = reg & 0xffff;
+	max_ies = (reg >> 16) & 0xffff;
+	max_aes = (reg >> 32) & 0xffff;
+
+	e_max = max_ses + max_ies + max_aes;
+
+	seq_puts(filp, "===========================================\n");
+	for (e = 0; e < e_max; e++) {
+		reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL2(e));
+		seq_printf(filp, "CPT Engine[%u] Group Enable   0x%02llx\n", e,
+			   reg & 0xff);
+		reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_ACTIVE(e));
+		seq_printf(filp, "CPT Engine[%u] Active Info    0x%llx\n", e,
+			   reg);
+		reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL(e));
+		seq_printf(filp, "CPT Engine[%u] Control        0x%llx\n", e,
+			   reg);
+		seq_puts(filp, "===========================================\n");
+	}
+	return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_engines_info, cpt_engines_info_display, NULL);
+
+static int rvu_dbg_cpt_lfs_info_display(struct seq_file *filp, void *unused)
+{
+	struct rvu *rvu = filp->private;
+	struct rvu_hwinfo *hw = rvu->hw;
+	struct rvu_block *block;
+	int blkaddr;
+	u64 reg;
+	u32 lf;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return -ENODEV;
+
+	block = &hw->block[blkaddr];
+	if (!block->lf.bmap)
+		return -ENODEV;
+
+	seq_puts(filp, "===========================================\n");
+	for (lf = 0; lf < block->lf.max; lf++) {
+		reg = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(lf));
+		seq_printf(filp, "CPT Lf[%u] CTL          0x%llx\n", lf, reg);
+		reg = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(lf));
+		seq_printf(filp, "CPT Lf[%u] CTL2         0x%llx\n", lf, reg);
+		reg = rvu_read64(rvu, blkaddr, CPT_AF_LFX_PTR_CTL(lf));
+		seq_printf(filp, "CPT Lf[%u] PTR_CTL      0x%llx\n", lf, reg);
+		reg = rvu_read64(rvu, blkaddr, block->lfcfg_reg |
+				(lf << block->lfshift));
+		seq_printf(filp, "CPT Lf[%u] CFG          0x%llx\n", lf, reg);
+		seq_puts(filp, "===========================================\n");
+	}
+	return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_lfs_info, cpt_lfs_info_display, NULL);
+
+static int rvu_dbg_cpt_err_info_display(struct seq_file *filp, void *unused)
+{
+	struct rvu *rvu = filp->private;
+	u64 reg0, reg1;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return -ENODEV;
+
+	reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0));
+	reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1));
+	seq_printf(filp, "CPT_AF_FLTX_INT:       0x%llx 0x%llx\n", reg0, reg1);
+	reg0 = rvu_read64(rvu, blkaddr, CPT_AF_PSNX_EXE(0));
+	reg1 = rvu_read64(rvu, blkaddr, CPT_AF_PSNX_EXE(1));
+	seq_printf(filp, "CPT_AF_PSNX_EXE:       0x%llx 0x%llx\n", reg0, reg1);
+	reg0 = rvu_read64(rvu, blkaddr, CPT_AF_PSNX_LF(0));
+	seq_printf(filp, "CPT_AF_PSNX_LF:        0x%llx\n", reg0);
+	reg0 = rvu_read64(rvu, blkaddr, CPT_AF_RVU_INT);
+	seq_printf(filp, "CPT_AF_RVU_INT:        0x%llx\n", reg0);
+	reg0 = rvu_read64(rvu, blkaddr, CPT_AF_RAS_INT);
+	seq_printf(filp, "CPT_AF_RAS_INT:        0x%llx\n", reg0);
+	reg0 = rvu_read64(rvu, blkaddr, CPT_AF_EXE_ERR_INFO);
+	seq_printf(filp, "CPT_AF_EXE_ERR_INFO:   0x%llx\n", reg0);
+
+	return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_err_info, cpt_err_info_display, NULL);
+
+static int rvu_dbg_cpt_pc_display(struct seq_file *filp, void *unused)
+{
+	struct rvu *rvu;
+	int blkaddr;
+	u64 reg;
+
+	rvu = filp->private;
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+	if (blkaddr < 0)
+		return -ENODEV;
+
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_INST_REQ_PC);
+	seq_printf(filp, "CPT instruction requests   %llu\n", reg);
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_INST_LATENCY_PC);
+	seq_printf(filp, "CPT instruction latency    %llu\n", reg);
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_RD_REQ_PC);
+	seq_printf(filp, "CPT NCB read requests      %llu\n", reg);
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_RD_LATENCY_PC);
+	seq_printf(filp, "CPT NCB read latency       %llu\n", reg);
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_RD_UC_PC);
+	seq_printf(filp, "CPT read requests caused by UC fills   %llu\n", reg);
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_ACTIVE_CYCLES_PC);
+	seq_printf(filp, "CPT active cycles pc       %llu\n", reg);
+	reg = rvu_read64(rvu, blkaddr, CPT_AF_CPTCLK_CNT);
+	seq_printf(filp, "CPT clock count pc         %llu\n", reg);
+
+	return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_pc, cpt_pc_display, NULL);
+
+static void rvu_dbg_cpt_init(struct rvu *rvu)
+{
+	const struct device *dev = &rvu->pdev->dev;
+	struct dentry *pfile;
+
+	if (!is_block_implemented(rvu->hw, BLKADDR_CPT0))
+		return;
+
+	rvu->rvu_dbg.cpt = debugfs_create_dir("cpt", rvu->rvu_dbg.root);
+	if (!rvu->rvu_dbg.cpt)
+		return;
+
+	pfile = debugfs_create_file("cpt_pc", 0600,
+				    rvu->rvu_dbg.cpt, rvu,
+				    &rvu_dbg_cpt_pc_fops);
+	if (!pfile)
+		goto create_failed;
+
+	pfile = debugfs_create_file("cpt_ae_sts", 0600,
+				    rvu->rvu_dbg.cpt, rvu,
+				    &rvu_dbg_cpt_ae_sts_fops);
+	if (!pfile)
+		goto create_failed;
+
+	pfile = debugfs_create_file("cpt_se_sts", 0600,
+				    rvu->rvu_dbg.cpt, rvu,
+				    &rvu_dbg_cpt_se_sts_fops);
+	if (!pfile)
+		goto create_failed;
+
+	pfile = debugfs_create_file("cpt_ie_sts", 0600,
+				    rvu->rvu_dbg.cpt, rvu,
+				    &rvu_dbg_cpt_ie_sts_fops);
+	if (!pfile)
+		goto create_failed;
+
+	pfile = debugfs_create_file("cpt_engines_info", 0600,
+				    rvu->rvu_dbg.cpt, rvu,
+				    &rvu_dbg_cpt_engines_info_fops);
+	if (!pfile)
+		goto create_failed;
+
+	pfile = debugfs_create_file("cpt_lfs_info", 0600,
+				    rvu->rvu_dbg.cpt, rvu,
+				    &rvu_dbg_cpt_lfs_info_fops);
+	if (!pfile)
+		goto create_failed;
+
+	pfile = debugfs_create_file("cpt_err_info", 0600,
+				    rvu->rvu_dbg.cpt, rvu,
+				    &rvu_dbg_cpt_err_info_fops);
+	if (!pfile)
+		goto create_failed;
+
+	return;
+
+create_failed:
+	dev_err(dev, "Failed to create debugfs dir/file for CPT\n");
+	debugfs_remove_recursive(rvu->rvu_dbg.cpt);
+}
+
 void rvu_dbg_init(struct rvu *rvu)
 {
 	struct device *dev = &rvu->pdev->dev;
@@ -2019,6 +2290,7 @@ void rvu_dbg_init(struct rvu *rvu)
 	rvu_dbg_nix_init(rvu, BLKADDR_NIX1);
 	rvu_dbg_cgx_init(rvu);
 	rvu_dbg_npc_init(rvu);
+	rvu_dbg_cpt_init(rvu);
 
 	return;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 1f3379f12b81..0fb2aa909a23 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -429,12 +429,63 @@
 #define TIM_AF_LF_RST			(0x20)
 
 /* CPT */
-#define CPT_AF_CONSTANTS0		(0x0000)
-#define CPT_PRIV_LFX_CFG		(0x41000)
-#define CPT_PRIV_LFX_INT_CFG		(0x43000)
-#define CPT_AF_RVU_LF_CFG_DEBUG		(0x45000)
-#define CPT_AF_LF_RST			(0x44000)
-#define CPT_AF_BLK_RST			(0x46000)
+#define CPT_AF_CONSTANTS0               (0x0000)
+#define CPT_AF_CONSTANTS1               (0x1000)
+#define CPT_AF_DIAG                     (0x3000)
+#define CPT_AF_ECO                      (0x4000)
+#define CPT_AF_FLTX_INT(a)              (0xa000ull | (u64)(a) << 3)
+#define CPT_AF_FLTX_INT_W1S(a)          (0xb000ull | (u64)(a) << 3)
+#define CPT_AF_FLTX_INT_ENA_W1C(a)      (0xc000ull | (u64)(a) << 3)
+#define CPT_AF_FLTX_INT_ENA_W1S(a)      (0xd000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_EXE(a)              (0xe000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_EXE_W1S(a)          (0xf000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_LF(a)               (0x10000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_LF_W1S(a)           (0x11000ull | (u64)(a) << 3)
+#define CPT_AF_EXEX_CTL2(a)             (0x12000ull | (u64)(a) << 3)
+#define CPT_AF_EXEX_STS(a)              (0x13000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_ERR_INFO             (0x14000)
+#define CPT_AF_EXEX_ACTIVE(a)           (0x16000ull | (u64)(a) << 3)
+#define CPT_AF_INST_REQ_PC              (0x17000)
+#define CPT_AF_INST_LATENCY_PC          (0x18000)
+#define CPT_AF_RD_REQ_PC                (0x19000)
+#define CPT_AF_RD_LATENCY_PC            (0x1a000)
+#define CPT_AF_RD_UC_PC                 (0x1b000)
+#define CPT_AF_ACTIVE_CYCLES_PC         (0x1c000)
+#define CPT_AF_EXE_DBG_CTL              (0x1d000)
+#define CPT_AF_EXE_DBG_DATA             (0x1e000)
+#define CPT_AF_EXE_REQ_TIMER            (0x1f000)
+#define CPT_AF_EXEX_CTL(a)              (0x20000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_PERF_CTL             (0x21000)
+#define CPT_AF_EXE_DBG_CNTX(a)          (0x22000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_PERF_EVENT_CNT       (0x23000)
+#define CPT_AF_EXE_EPCI_INBX_CNT(a)     (0x24000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_EPCI_OUTBX_CNT(a)    (0x25000ull | (u64)(a) << 3)
+#define CPT_AF_EXEX_UCODE_BASE(a)       (0x26000ull | (u64)(a) << 3)
+#define CPT_AF_LFX_CTL(a)               (0x27000ull | (u64)(a) << 3)
+#define CPT_AF_LFX_CTL2(a)              (0x29000ull | (u64)(a) << 3)
+#define CPT_AF_CPTCLK_CNT               (0x2a000)
+#define CPT_AF_PF_FUNC                  (0x2b000)
+#define CPT_AF_LFX_PTR_CTL(a)           (0x2c000ull | (u64)(a) << 3)
+#define CPT_AF_GRPX_THR(a)              (0x2d000ull | (u64)(a) << 3)
+#define CPT_AF_CTL                      (0x2e000ull)
+#define CPT_AF_XEX_THR(a)               (0x2f000ull | (u64)(a) << 3)
+#define CPT_PRIV_LFX_CFG                (0x41000)
+#define CPT_PRIV_AF_INT_CFG             (0x42000)
+#define CPT_PRIV_LFX_INT_CFG            (0x43000)
+#define CPT_AF_LF_RST                   (0x44000)
+#define CPT_AF_RVU_LF_CFG_DEBUG         (0x45000)
+#define CPT_AF_BLK_RST                  (0x46000)
+#define CPT_AF_RVU_INT                  (0x47000)
+#define CPT_AF_RVU_INT_W1S              (0x47008)
+#define CPT_AF_RVU_INT_ENA_W1S          (0x47010)
+#define CPT_AF_RVU_INT_ENA_W1C          (0x47018)
+#define CPT_AF_RAS_INT                  (0x47020)
+#define CPT_AF_RAS_INT_W1S              (0x47028)
+#define CPT_AF_RAS_INT_ENA_W1S          (0x47030)
+#define CPT_AF_RAS_INT_ENA_W1C          (0x47038)
+
+#define CPT_AF_LF_CTL2_SHIFT 3
+#define CPT_AF_LF_SSO_PF_FUNC_SHIFT 32
 
 #define NPC_AF_BLK_RST                  (0x00040)
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index b18b45d02165..ceec649bdd13 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -16,6 +16,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
+#include <linux/soc/marvell/octeontx2/asm.h>
 
 #include <mbox.h>
 #include <npc.h>
@@ -462,21 +463,9 @@ static inline u64 otx2_atomic64_add(u64 incr, u64 *ptr)
 	return result;
 }
 
-static inline u64 otx2_lmt_flush(uint64_t addr)
-{
-	u64 result = 0;
-
-	__asm__ volatile(".cpu  generic+lse\n"
-			 "ldeor xzr,%x[rf],[%[rs]]"
-			 : [rf]"=r"(result)
-			 : [rs]"r"(addr));
-	return result;
-}
-
 #else
 #define otx2_write128(lo, hi, addr)
 #define otx2_atomic64_add(incr, ptr)		({ *ptr += incr; })
-#define otx2_lmt_flush(addr)			({ 0; })
 #endif
 
 /* Alloc pointer from pool/aura */
diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h
new file mode 100644
index 000000000000..ae2279fe830a
--- /dev/null
+++ b/include/linux/soc/marvell/octeontx2/asm.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __SOC_OTX2_ASM_H
+#define __SOC_OTX2_ASM_H
+
+#if defined(CONFIG_ARM64)
+/*
+ * otx2_lmt_flush is used for LMT store operation.
+ * On octeontx2 platform CPT instruction enqueue and
+ * NIX packet send are only possible via LMTST
+ * operations and it uses LDEOR instruction targeting
+ * the coprocessor address.
+ */
+#define otx2_lmt_flush(ioaddr)                          \
+({                                                      \
+	u64 result = 0;                                 \
+	__asm__ volatile(".cpu  generic+lse\n"          \
+			 "ldeor xzr, %x[rf], [%[rs]]"   \
+			 : [rf]"=r" (result)            \
+			 : [rs]"r" (ioaddr));           \
+	(result);                                       \
+})
+#else
+#define otx2_lmt_flush(ioaddr)          ({ 0; })
+#endif
+
+#endif /* __SOC_OTX2_ASM_H */