Merge tag 'rproc-v4.15' of git://github.com/andersson/remoteproc

Pull remoteproc updates from Bjorn Andersson:
 "This adds an interface for configuring Qualcomm's "secure SMMU" and
  adds support for booting the modem Hexagon on MSM8996.

  Two new debugfs entries are added in the remoteproc core to introspect
  the list of memory carveouts and the loaded resource table"

* tag 'rproc-v4.15' of git://github.com/andersson/remoteproc:
  remoteproc: qcom: Fix error handling paths in order to avoid memory leaks
  remoteproc: qcom: Drop pr_err in q6v5_xfer_mem_ownership()
  remoteproc: debug: add carveouts list dump feature
  remoteproc: debug: add resource table dump feature
  remoteproc: qcom: Add support for mss remoteproc on msm8996
  remoteproc: qcom: Make secure world call for mem ownership switch
  remoteproc: qcom: refactor mss fw image loading sequence
  firmware: scm: Add new SCM call API for switching memory ownership

6 files changed, 516 insertions, 39 deletions

diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index 68b2033bc30e..dfbd894d5bb7 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -585,6 +585,13 @@ int __qcom_scm_set_remote_state(struct device *dev, u32 state, u32 id)
 	return ret ? : le32_to_cpu(scm_ret);
 }
 
+int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region,
+			  size_t mem_sz, phys_addr_t src, size_t src_sz,
+			  phys_addr_t dest, size_t dest_sz)
+{
+	return -ENODEV;
+}
+
 int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id,
 			       u32 spare)
 {
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
index 3fea6f563ca9..688525dd4aee 100644
--- a/drivers/firmware/qcom_scm-64.c
+++ b/drivers/firmware/qcom_scm-64.c
@@ -382,6 +382,33 @@ int __qcom_scm_set_remote_state(struct device *dev, u32 state, u32 id)
 	return ret ? : res.a1;
 }
 
+int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region,
+			  size_t mem_sz, phys_addr_t src, size_t src_sz,
+			  phys_addr_t dest, size_t dest_sz)
+{
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.args[0] = mem_region;
+	desc.args[1] = mem_sz;
+	desc.args[2] = src;
+	desc.args[3] = src_sz;
+	desc.args[4] = dest;
+	desc.args[5] = dest_sz;
+	desc.args[6] = 0;
+
+	desc.arginfo = QCOM_SCM_ARGS(7, QCOM_SCM_RO, QCOM_SCM_VAL,
+				     QCOM_SCM_RO, QCOM_SCM_VAL, QCOM_SCM_RO,
+				     QCOM_SCM_VAL, QCOM_SCM_VAL);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_MP,
+			    QCOM_MEM_PROT_ASSIGN_ID,
+			    &desc, &res);
+
+	return ret ? : res.a1;
+}
+
 int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id, u32 spare)
 {
 	struct qcom_scm_desc desc = {0};
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index 9064e559a01f..af4c75217ea6 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -47,6 +47,19 @@ struct qcom_scm {
 	u64 dload_mode_addr;
 };
 
+struct qcom_scm_current_perm_info {
+	__le32 vmid;
+	__le32 perm;
+	__le64 ctx;
+	__le32 ctx_size;
+	__le32 unused;
+};
+
+struct qcom_scm_mem_map_info {
+	__le64 mem_addr;
+	__le64 mem_size;
+};
+
 static struct qcom_scm *__scm;
 
 static int qcom_scm_clk_enable(void)
@@ -415,6 +428,88 @@ int qcom_scm_set_remote_state(u32 state, u32 id)
 }
 EXPORT_SYMBOL(qcom_scm_set_remote_state);
 
+/**
+ * qcom_scm_assign_mem() - Make a secure call to reassign memory ownership
+ * @mem_addr: mem region whose ownership need to be reassigned
+ * @mem_sz:   size of the region.
+ * @srcvm:    vmid for current set of owners, each set bit in
+ *            flag indicate a unique owner
+ * @newvm:    array having new owners and corrsponding permission
+ *            flags
+ * @dest_cnt: number of owners in next set.
+ *
+ * Return negative errno on failure, 0 on success, with @srcvm updated.
+ */
+int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
+			unsigned int *srcvm,
+			struct qcom_scm_vmperm *newvm, int dest_cnt)
+{
+	struct qcom_scm_current_perm_info *destvm;
+	struct qcom_scm_mem_map_info *mem_to_map;
+	phys_addr_t mem_to_map_phys;
+	phys_addr_t dest_phys;
+	phys_addr_t ptr_phys;
+	size_t mem_to_map_sz;
+	size_t dest_sz;
+	size_t src_sz;
+	size_t ptr_sz;
+	int next_vm;
+	__le32 *src;
+	void *ptr;
+	int ret;
+	int len;
+	int i;
+
+	src_sz = hweight_long(*srcvm) * sizeof(*src);
+	mem_to_map_sz = sizeof(*mem_to_map);
+	dest_sz = dest_cnt * sizeof(*destvm);
+	ptr_sz = ALIGN(src_sz, SZ_64) + ALIGN(mem_to_map_sz, SZ_64) +
+			ALIGN(dest_sz, SZ_64);
+
+	ptr = dma_alloc_coherent(__scm->dev, ptr_sz, &ptr_phys, GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	/* Fill source vmid detail */
+	src = ptr;
+	len = hweight_long(*srcvm);
+	for (i = 0; i < len; i++) {
+		src[i] = cpu_to_le32(ffs(*srcvm) - 1);
+		*srcvm ^= 1 << (ffs(*srcvm) - 1);
+	}
+
+	/* Fill details of mem buff to map */
+	mem_to_map = ptr + ALIGN(src_sz, SZ_64);
+	mem_to_map_phys = ptr_phys + ALIGN(src_sz, SZ_64);
+	mem_to_map[0].mem_addr = cpu_to_le64(mem_addr);
+	mem_to_map[0].mem_size = cpu_to_le64(mem_sz);
+
+	next_vm = 0;
+	/* Fill details of next vmid detail */
+	destvm = ptr + ALIGN(mem_to_map_sz, SZ_64) + ALIGN(src_sz, SZ_64);
+	dest_phys = ptr_phys + ALIGN(mem_to_map_sz, SZ_64) + ALIGN(src_sz, SZ_64);
+	for (i = 0; i < dest_cnt; i++) {
+		destvm[i].vmid = cpu_to_le32(newvm[i].vmid);
+		destvm[i].perm = cpu_to_le32(newvm[i].perm);
+		destvm[i].ctx = 0;
+		destvm[i].ctx_size = 0;
+		next_vm |= BIT(newvm[i].vmid);
+	}
+
+	ret = __qcom_scm_assign_mem(__scm->dev, mem_to_map_phys, mem_to_map_sz,
+				    ptr_phys, src_sz, dest_phys, dest_sz);
+	dma_free_coherent(__scm->dev, ALIGN(ptr_sz, SZ_64), ptr, ptr_phys);
+	if (ret) {
+		dev_err(__scm->dev,
+			"Assign memory protection call failed %d.\n", ret);
+		return -EINVAL;
+	}
+
+	*srcvm = next_vm;
+	return 0;
+}
+EXPORT_SYMBOL(qcom_scm_assign_mem);
+
 static int qcom_scm_probe(struct platform_device *pdev)
 {
 	struct qcom_scm *scm;
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index 83f171c23943..dcd7f7917fc7 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -103,5 +103,10 @@ extern int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare,
 					     size_t *size);
 extern int __qcom_scm_iommu_secure_ptbl_init(struct device *dev, u64 addr,
 					     u32 size, u32 spare);
+#define QCOM_MEM_PROT_ASSIGN_ID	0x16
+extern int  __qcom_scm_assign_mem(struct device *dev,
+				  phys_addr_t mem_region, size_t mem_sz,
+				  phys_addr_t src, size_t src_sz,
+				  phys_addr_t dest, size_t dest_sz);
 
 #endif
diff --git a/drivers/remoteproc/qcom_q6v5_pil.c b/drivers/remoteproc/qcom_q6v5_pil.c
index 2d3d5ac92c06..8a3fa2bcc9f6 100644
--- a/drivers/remoteproc/qcom_q6v5_pil.c
+++ b/drivers/remoteproc/qcom_q6v5_pil.c
@@ -32,6 +32,7 @@
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/soc/qcom/smem.h>
 #include <linux/soc/qcom/smem_state.h>
+#include <linux/iopoll.h>
 
 #include "remoteproc_internal.h"
 #include "qcom_common.h"
@@ -64,6 +65,8 @@
 #define QDSP6SS_RESET_REG		0x014
 #define QDSP6SS_GFMUX_CTL_REG		0x020
 #define QDSP6SS_PWR_CTL_REG		0x030
+#define QDSP6SS_MEM_PWR_CTL		0x0B0
+#define QDSP6SS_STRAP_ACC		0x110
 
 /* AXI Halt Register Offsets */
 #define AXI_HALTREQ_REG			0x0
@@ -92,6 +95,15 @@
 #define QDSS_BHS_ON			BIT(21)
 #define QDSS_LDO_BYP			BIT(22)
 
+/* QDSP6v56 parameters */
+#define QDSP6v56_LDO_BYP		BIT(25)
+#define QDSP6v56_BHS_ON		BIT(24)
+#define QDSP6v56_CLAMP_WL		BIT(21)
+#define QDSP6v56_CLAMP_QMC_MEM		BIT(22)
+#define HALT_CHECK_MAX_LOOPS		200
+#define QDSP6SS_XO_CBCR		0x0038
+#define QDSP6SS_ACC_OVERRIDE_VAL		0x20
+
 struct reg_info {
 	struct regulator *reg;
 	int uV;
@@ -110,6 +122,8 @@ struct rproc_hexagon_res {
 	struct qcom_mss_reg_res *active_supply;
 	char **proxy_clk_names;
 	char **active_clk_names;
+	int version;
+	bool need_mem_protection;
 };
 
 struct q6v5 {
@@ -154,6 +168,16 @@ struct q6v5 {
 
 	struct qcom_rproc_subdev smd_subdev;
 	struct qcom_rproc_ssr ssr_subdev;
+	bool need_mem_protection;
+	int mpss_perm;
+	int mba_perm;
+	int version;
+};
+
+enum {
+	MSS_MSM8916,
+	MSS_MSM8974,
+	MSS_MSM8996,
 };
 
 static int q6v5_regulator_init(struct device *dev, struct reg_info *regs,
@@ -289,6 +313,26 @@ static struct resource_table *q6v5_find_rsc_table(struct rproc *rproc,
 	return &table;
 }
 
+static int q6v5_xfer_mem_ownership(struct q6v5 *qproc, int *current_perm,
+				   bool remote_owner, phys_addr_t addr,
+				   size_t size)
+{
+	struct qcom_scm_vmperm next;
+
+	if (!qproc->need_mem_protection)
+		return 0;
+	if (remote_owner && *current_perm == BIT(QCOM_SCM_VMID_MSS_MSA))
+		return 0;
+	if (!remote_owner && *current_perm == BIT(QCOM_SCM_VMID_HLOS))
+		return 0;
+
+	next.vmid = remote_owner ? QCOM_SCM_VMID_MSS_MSA : QCOM_SCM_VMID_HLOS;
+	next.perm = remote_owner ? QCOM_SCM_PERM_RW : QCOM_SCM_PERM_RWX;
+
+	return qcom_scm_assign_mem(addr, ALIGN(size, SZ_4K),
+				   current_perm, &next, 1);
+}
+
 static int q6v5_load(struct rproc *rproc, const struct firmware *fw)
 {
 	struct q6v5 *qproc = rproc->priv;
@@ -353,33 +397,98 @@ static int q6v5proc_reset(struct q6v5 *qproc)
 {
 	u32 val;
 	int ret;
+	int i;
 
-	/* Assert resets, stop core */
-	val = readl(qproc->reg_base + QDSP6SS_RESET_REG);
-	val |= (Q6SS_CORE_ARES | Q6SS_BUS_ARES_ENABLE | Q6SS_STOP_CORE);
-	writel(val, qproc->reg_base + QDSP6SS_RESET_REG);
 
-	/* Enable power block headswitch, and wait for it to stabilize */
-	val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
-	val |= QDSS_BHS_ON | QDSS_LDO_BYP;
-	writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
-	udelay(1);
-
-	/*
-	 * Turn on memories. L2 banks should be done individually
-	 * to minimize inrush current.
-	 */
-	val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
-	val |= Q6SS_SLP_RET_N | Q6SS_L2TAG_SLP_NRET_N |
-		Q6SS_ETB_SLP_NRET_N | Q6SS_L2DATA_STBY_N;
-	writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
-	val |= Q6SS_L2DATA_SLP_NRET_N_2;
-	writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
-	val |= Q6SS_L2DATA_SLP_NRET_N_1;
-	writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
-	val |= Q6SS_L2DATA_SLP_NRET_N_0;
-	writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+	if (qproc->version == MSS_MSM8996) {
+		/* Override the ACC value if required */
+		writel(QDSP6SS_ACC_OVERRIDE_VAL,
+		       qproc->reg_base + QDSP6SS_STRAP_ACC);
 
+		/* Assert resets, stop core */
+		val = readl(qproc->reg_base + QDSP6SS_RESET_REG);
+		val |= Q6SS_CORE_ARES | Q6SS_BUS_ARES_ENABLE | Q6SS_STOP_CORE;
+		writel(val, qproc->reg_base + QDSP6SS_RESET_REG);
+
+		/* BHS require xo cbcr to be enabled */
+		val = readl(qproc->reg_base + QDSP6SS_XO_CBCR);
+		val |= 0x1;
+		writel(val, qproc->reg_base + QDSP6SS_XO_CBCR);
+
+		/* Read CLKOFF bit to go low indicating CLK is enabled */
+		ret = readl_poll_timeout(qproc->reg_base + QDSP6SS_XO_CBCR,
+					 val, !(val & BIT(31)), 1,
+					 HALT_CHECK_MAX_LOOPS);
+		if (ret) {
+			dev_err(qproc->dev,
+				"xo cbcr enabling timed out (rc:%d)\n", ret);
+			return ret;
+		}
+		/* Enable power block headswitch and wait for it to stabilize */
+		val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= QDSP6v56_BHS_ON;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		udelay(1);
+
+		/* Put LDO in bypass mode */
+		val |= QDSP6v56_LDO_BYP;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+
+		/* Deassert QDSP6 compiler memory clamp */
+		val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val &= ~QDSP6v56_CLAMP_QMC_MEM;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+
+		/* Deassert memory peripheral sleep and L2 memory standby */
+		val |= Q6SS_L2DATA_STBY_N | Q6SS_SLP_RET_N;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+
+		/* Turn on L1, L2, ETB and JU memories 1 at a time */
+		val = readl(qproc->reg_base + QDSP6SS_MEM_PWR_CTL);
+		for (i = 19; i >= 0; i--) {
+			val |= BIT(i);
+			writel(val, qproc->reg_base +
+						QDSP6SS_MEM_PWR_CTL);
+			/*
+			 * Read back value to ensure the write is done then
+			 * wait for 1us for both memory peripheral and data
+			 * array to turn on.
+			 */
+			val |= readl(qproc->reg_base + QDSP6SS_MEM_PWR_CTL);
+			udelay(1);
+		}
+		/* Remove word line clamp */
+		val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val &= ~QDSP6v56_CLAMP_WL;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+	} else {
+		/* Assert resets, stop core */
+		val = readl(qproc->reg_base + QDSP6SS_RESET_REG);
+		val |= Q6SS_CORE_ARES | Q6SS_BUS_ARES_ENABLE | Q6SS_STOP_CORE;
+		writel(val, qproc->reg_base + QDSP6SS_RESET_REG);
+
+		/* Enable power block headswitch and wait for it to stabilize */
+		val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= QDSS_BHS_ON | QDSS_LDO_BYP;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		udelay(1);
+		/*
+		 * Turn on memories. L2 banks should be done individually
+		 * to minimize inrush current.
+		 */
+		val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= Q6SS_SLP_RET_N | Q6SS_L2TAG_SLP_NRET_N |
+			Q6SS_ETB_SLP_NRET_N | Q6SS_L2DATA_STBY_N;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= Q6SS_L2DATA_SLP_NRET_N_2;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= Q6SS_L2DATA_SLP_NRET_N_1;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= Q6SS_L2DATA_SLP_NRET_N_0;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+	}
 	/* Remove IO clamp */
 	val &= ~Q6SS_CLAMP_IO;
 	writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
@@ -451,6 +560,8 @@ static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw)
 {
 	unsigned long dma_attrs = DMA_ATTR_FORCE_CONTIGUOUS;
 	dma_addr_t phys;
+	int mdata_perm;
+	int xferop_ret;
 	void *ptr;
 	int ret;
 
@@ -462,6 +573,17 @@ static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw)
 
 	memcpy(ptr, fw->data, fw->size);
 
+	/* Hypervisor mapping to access metadata by modem */
+	mdata_perm = BIT(QCOM_SCM_VMID_HLOS);
+	ret = q6v5_xfer_mem_ownership(qproc, &mdata_perm,
+				      true, phys, fw->size);
+	if (ret) {
+		dev_err(qproc->dev,
+			"assigning Q6 access to metadata failed: %d\n", ret);
+		ret = -EAGAIN;
+		goto free_dma_attrs;
+	}
+
 	writel(phys, qproc->rmb_base + RMB_PMI_META_DATA_REG);
 	writel(RMB_CMD_META_DATA_READY, qproc->rmb_base + RMB_MBA_COMMAND_REG);
 
@@ -471,6 +593,14 @@ static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw)
 	else if (ret < 0)
 		dev_err(qproc->dev, "MPSS header authentication failed: %d\n", ret);
 
+	/* Metadata authentication done, remove modem access */
+	xferop_ret = q6v5_xfer_mem_ownership(qproc, &mdata_perm,
+					     false, phys, fw->size);
+	if (xferop_ret)
+		dev_warn(qproc->dev,
+			 "mdt buffer not reclaimed system may become unstable\n");
+
+free_dma_attrs:
 	dma_free_attrs(qproc->dev, fw->size, ptr, phys, dma_attrs);
 
 	return ret < 0 ? ret : 0;
@@ -504,7 +634,7 @@ static int q6v5_mpss_load(struct q6v5 *qproc)
 	bool relocate = false;
 	char seg_name[10];
 	ssize_t offset;
-	size_t size;
+	size_t size = 0;
 	void *ptr;
 	int ret;
 	int i;
@@ -542,7 +672,7 @@ static int q6v5_mpss_load(struct q6v5 *qproc)
 	}
 
 	mpss_reloc = relocate ? min_addr : qproc->mpss_phys;
-
+	/* Load firmware segments */
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		phdr = &phdrs[i];
 
@@ -575,18 +705,24 @@ static int q6v5_mpss_load(struct q6v5 *qproc)
 			memset(ptr + phdr->p_filesz, 0,
 			       phdr->p_memsz - phdr->p_filesz);
 		}
-
-		size = readl(qproc->rmb_base + RMB_PMI_CODE_LENGTH_REG);
-		if (!size) {
-			boot_addr = relocate ? qproc->mpss_phys : min_addr;
-			writel(boot_addr, qproc->rmb_base + RMB_PMI_CODE_START_REG);
-			writel(RMB_CMD_LOAD_READY, qproc->rmb_base + RMB_MBA_COMMAND_REG);
-		}
-
 		size += phdr->p_memsz;
-		writel(size, qproc->rmb_base + RMB_PMI_CODE_LENGTH_REG);
 	}
 
+	/* Transfer ownership of modem ddr region to q6 */
+	ret = q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm, true,
+				      qproc->mpss_phys, qproc->mpss_size);
+	if (ret) {
+		dev_err(qproc->dev,
+			"assigning Q6 access to mpss memory failed: %d\n", ret);
+		ret = -EAGAIN;
+		goto release_firmware;
+	}
+
+	boot_addr = relocate ? qproc->mpss_phys : min_addr;
+	writel(boot_addr, qproc->rmb_base + RMB_PMI_CODE_START_REG);
+	writel(RMB_CMD_LOAD_READY, qproc->rmb_base + RMB_MBA_COMMAND_REG);
+	writel(size, qproc->rmb_base + RMB_PMI_CODE_LENGTH_REG);
+
 	ret = q6v5_rmb_mba_wait(qproc, RMB_MBA_AUTH_COMPLETE, 10000);
 	if (ret == -ETIMEDOUT)
 		dev_err(qproc->dev, "MPSS authentication timed out\n");
@@ -602,6 +738,7 @@ release_firmware:
 static int q6v5_start(struct rproc *rproc)
 {
 	struct q6v5 *qproc = (struct q6v5 *)rproc->priv;
+	int xfermemop_ret;
 	int ret;
 
 	ret = q6v5_regulator_enable(qproc, qproc->proxy_regs,
@@ -637,11 +774,22 @@ static int q6v5_start(struct rproc *rproc)
 		goto assert_reset;
 	}
 
+	/* Assign MBA image access in DDR to q6 */
+	xfermemop_ret = q6v5_xfer_mem_ownership(qproc, &qproc->mba_perm, true,
+						qproc->mba_phys,
+						qproc->mba_size);
+	if (xfermemop_ret) {
+		dev_err(qproc->dev,
+			"assigning Q6 access to mba memory failed: %d\n",
+			xfermemop_ret);
+		goto disable_active_clks;
+	}
+
 	writel(qproc->mba_phys, qproc->rmb_base + RMB_MBA_IMAGE_REG);
 
 	ret = q6v5proc_reset(qproc);
 	if (ret)
-		goto halt_axi_ports;
+		goto reclaim_mba;
 
 	ret = q6v5_rmb_mba_wait(qproc, 0, 5000);
 	if (ret == -ETIMEDOUT) {
@@ -658,16 +806,22 @@ static int q6v5_start(struct rproc *rproc)
 
 	ret = q6v5_mpss_load(qproc);
 	if (ret)
-		goto halt_axi_ports;
+		goto reclaim_mpss;
 
 	ret = wait_for_completion_timeout(&qproc->start_done,
 					  msecs_to_jiffies(5000));
 	if (ret == 0) {
 		dev_err(qproc->dev, "start timed out\n");
 		ret = -ETIMEDOUT;
-		goto halt_axi_ports;
+		goto reclaim_mpss;
 	}
 
+	xfermemop_ret = q6v5_xfer_mem_ownership(qproc, &qproc->mba_perm, false,
+						qproc->mba_phys,
+						qproc->mba_size);
+	if (xfermemop_ret)
+		dev_err(qproc->dev,
+			"Failed to reclaim mba buffer system may become unstable\n");
 	qproc->running = true;
 
 	q6v5_clk_disable(qproc->dev, qproc->proxy_clks,
@@ -677,12 +831,30 @@ static int q6v5_start(struct rproc *rproc)
 
 	return 0;
 
+reclaim_mpss:
+	xfermemop_ret = q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm,
+						false, qproc->mpss_phys,
+						qproc->mpss_size);
+	WARN_ON(xfermemop_ret);
+
 halt_axi_ports:
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_nc);
+
+reclaim_mba:
+	xfermemop_ret = q6v5_xfer_mem_ownership(qproc, &qproc->mba_perm, false,
+						qproc->mba_phys,
+						qproc->mba_size);
+	if (xfermemop_ret) {
+		dev_err(qproc->dev,
+			"Failed to reclaim mba buffer, system may become unstable\n");
+	}
+
+disable_active_clks:
 	q6v5_clk_disable(qproc->dev, qproc->active_clks,
 			 qproc->active_clk_count);
+
 assert_reset:
 	reset_control_assert(qproc->mss_restart);
 disable_vdd:
@@ -702,6 +874,7 @@ static int q6v5_stop(struct rproc *rproc)
 {
 	struct q6v5 *qproc = (struct q6v5 *)rproc->priv;
 	int ret;
+	u32 val;
 
 	qproc->running = false;
 
@@ -718,6 +891,20 @@ static int q6v5_stop(struct rproc *rproc)
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_nc);
+	if (qproc->version == MSS_MSM8996) {
+		/*
+		 * To avoid high MX current during LPASS/MSS restart.
+		 */
+		val = readl(qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+		val |= Q6SS_CLAMP_IO | QDSP6v56_CLAMP_WL |
+			QDSP6v56_CLAMP_QMC_MEM;
+		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
+	}
+
+
+	ret = q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm, false,
+				      qproc->mpss_phys, qproc->mpss_size);
+	WARN_ON(ret);
 
 	reset_control_assert(qproc->mss_restart);
 	q6v5_clk_disable(qproc->dev, qproc->active_clks,
@@ -1017,6 +1204,8 @@ static int q6v5_probe(struct platform_device *pdev)
 	if (ret)
 		goto free_rproc;
 
+	qproc->version = desc->version;
+	qproc->need_mem_protection = desc->need_mem_protection;
 	ret = q6v5_request_irq(qproc, pdev, "wdog", q6v5_wdog_interrupt);
 	if (ret < 0)
 		goto free_rproc;
@@ -1038,7 +1227,8 @@ static int q6v5_probe(struct platform_device *pdev)
 		ret = PTR_ERR(qproc->state);
 		goto free_rproc;
 	}
-
+	qproc->mpss_perm = BIT(QCOM_SCM_VMID_HLOS);
+	qproc->mba_perm = BIT(QCOM_SCM_VMID_HLOS);
 	qcom_add_smd_subdev(rproc, &qproc->smd_subdev);
 	qcom_add_ssr_subdev(rproc, &qproc->ssr_subdev, "mpss");
 
@@ -1067,6 +1257,24 @@ static int q6v5_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct rproc_hexagon_res msm8996_mss = {
+	.hexagon_mba_image = "mba.mbn",
+	.proxy_clk_names = (char*[]){
+			"xo",
+			"pnoc",
+			NULL
+	},
+	.active_clk_names = (char*[]){
+			"iface",
+			"bus",
+			"mem",
+			"gpll0_mss_clk",
+			NULL
+	},
+	.need_mem_protection = true,
+	.version = MSS_MSM8996,
+};
+
 static const struct rproc_hexagon_res msm8916_mss = {
 	.hexagon_mba_image = "mba.mbn",
 	.proxy_supply = (struct qcom_mss_reg_res[]) {
@@ -1094,6 +1302,8 @@ static const struct rproc_hexagon_res msm8916_mss = {
 		"mem",
 		NULL
 	},
+	.need_mem_protection = false,
+	.version = MSS_MSM8916,
 };
 
 static const struct rproc_hexagon_res msm8974_mss = {
@@ -1131,12 +1341,15 @@ static const struct rproc_hexagon_res msm8974_mss = {
 		"mem",
 		NULL
 	},
+	.need_mem_protection = false,
+	.version = MSS_MSM8974,
 };
 
 static const struct of_device_id q6v5_of_match[] = {
 	{ .compatible = "qcom,q6v5-pil", .data = &msm8916_mss},
 	{ .compatible = "qcom,msm8916-mss-pil", .data = &msm8916_mss},
 	{ .compatible = "qcom,msm8974-mss-pil", .data = &msm8974_mss},
+	{ .compatible = "qcom,msm8996-mss-pil", .data = &msm8996_mss},
 	{ },
 };
 MODULE_DEVICE_TABLE(of, q6v5_of_match);
diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c
index 1c122e230cec..a20488336aa0 100644
--- a/drivers/remoteproc/remoteproc_debugfs.c
+++ b/drivers/remoteproc/remoteproc_debugfs.c
@@ -155,6 +155,132 @@ static const struct file_operations rproc_recovery_ops = {
 	.llseek = generic_file_llseek,
 };
 
+/* Expose resource table content via debugfs */
+static int rproc_rsc_table_show(struct seq_file *seq, void *p)
+{
+	static const char * const types[] = {"carveout", "devmem", "trace", "vdev"};
+	struct rproc *rproc = seq->private;
+	struct resource_table *table = rproc->table_ptr;
+	struct fw_rsc_carveout *c;
+	struct fw_rsc_devmem *d;
+	struct fw_rsc_trace *t;
+	struct fw_rsc_vdev *v;
+	int i, j;
+
+	if (!table) {
+		seq_puts(seq, "No resource table found\n");
+		return 0;
+	}
+
+	for (i = 0; i < table->num; i++) {
+		int offset = table->offset[i];
+		struct fw_rsc_hdr *hdr = (void *)table + offset;
+		void *rsc = (void *)hdr + sizeof(*hdr);
+
+		switch (hdr->type) {
+		case RSC_CARVEOUT:
+			c = rsc;
+			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
+			seq_printf(seq, "  Device Address 0x%x\n", c->da);
+			seq_printf(seq, "  Physical Address 0x%x\n", c->pa);
+			seq_printf(seq, "  Length 0x%x Bytes\n", c->len);
+			seq_printf(seq, "  Flags 0x%x\n", c->flags);
+			seq_printf(seq, "  Reserved (should be zero) [%d]\n", c->reserved);
+			seq_printf(seq, "  Name %s\n\n", c->name);
+			break;
+		case RSC_DEVMEM:
+			d = rsc;
+			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
+			seq_printf(seq, "  Device Address 0x%x\n", d->da);
+			seq_printf(seq, "  Physical Address 0x%x\n", d->pa);
+			seq_printf(seq, "  Length 0x%x Bytes\n", d->len);
+			seq_printf(seq, "  Flags 0x%x\n", d->flags);
+			seq_printf(seq, "  Reserved (should be zero) [%d]\n", d->reserved);
+			seq_printf(seq, "  Name %s\n\n", d->name);
+			break;
+		case RSC_TRACE:
+			t = rsc;
+			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
+			seq_printf(seq, "  Device Address 0x%x\n", t->da);
+			seq_printf(seq, "  Length 0x%x Bytes\n", t->len);
+			seq_printf(seq, "  Reserved (should be zero) [%d]\n", t->reserved);
+			seq_printf(seq, "  Name %s\n\n", t->name);
+			break;
+		case RSC_VDEV:
+			v = rsc;
+			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
+
+			seq_printf(seq, "  ID %d\n", v->id);
+			seq_printf(seq, "  Notify ID %d\n", v->notifyid);
+			seq_printf(seq, "  Device features 0x%x\n", v->dfeatures);
+			seq_printf(seq, "  Guest features 0x%x\n", v->gfeatures);
+			seq_printf(seq, "  Config length 0x%x\n", v->config_len);
+			seq_printf(seq, "  Status 0x%x\n", v->status);
+			seq_printf(seq, "  Number of vrings %d\n", v->num_of_vrings);
+			seq_printf(seq, "  Reserved (should be zero) [%d][%d]\n\n",
+				   v->reserved[0], v->reserved[1]);
+
+			for (j = 0; j < v->num_of_vrings; j++) {
+				seq_printf(seq, "  Vring %d\n", j);
+				seq_printf(seq, "    Device Address 0x%x\n", v->vring[j].da);
+				seq_printf(seq, "    Alignment %d\n", v->vring[j].align);
+				seq_printf(seq, "    Number of buffers %d\n", v->vring[j].num);
+				seq_printf(seq, "    Notify ID %d\n", v->vring[j].notifyid);
+				seq_printf(seq, "    Physical Address 0x%x\n\n",
+					   v->vring[j].pa);
+			}
+			break;
+		default:
+			seq_printf(seq, "Unknown resource type found: %d [hdr: %p]\n",
+				   hdr->type, hdr);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int rproc_rsc_table_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, rproc_rsc_table_show, inode->i_private);
+}
+
+static const struct file_operations rproc_rsc_table_ops = {
+	.open		= rproc_rsc_table_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+/* Expose carveout content via debugfs */
+static int rproc_carveouts_show(struct seq_file *seq, void *p)
+{
+	struct rproc *rproc = seq->private;
+	struct rproc_mem_entry *carveout;
+
+	list_for_each_entry(carveout, &rproc->carveouts, node) {
+		seq_puts(seq, "Carveout memory entry:\n");
+		seq_printf(seq, "\tVirtual address: %p\n", carveout->va);
+		seq_printf(seq, "\tDMA address: %pad\n", &carveout->dma);
+		seq_printf(seq, "\tDevice address: 0x%x\n", carveout->da);
+		seq_printf(seq, "\tLength: 0x%x Bytes\n\n", carveout->len);
+	}
+
+	return 0;
+}
+
+static int rproc_carveouts_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, rproc_carveouts_show, inode->i_private);
+}
+
+static const struct file_operations rproc_carveouts_ops = {
+	.open		= rproc_carveouts_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 void rproc_remove_trace_file(struct dentry *tfile)
 {
 	debugfs_remove(tfile);
@@ -198,6 +324,10 @@ void rproc_create_debug_dir(struct rproc *rproc)
 			    rproc, &rproc_name_ops);
 	debugfs_create_file("recovery", 0400, rproc->dbg_dir,
 			    rproc, &rproc_recovery_ops);
+	debugfs_create_file("resource_table", 0400, rproc->dbg_dir,
+			    rproc, &rproc_rsc_table_ops);
+	debugfs_create_file("carveout_memories", 0400, rproc->dbg_dir,
+			    rproc, &rproc_carveouts_ops);
 }
 
 void __init rproc_init_debugfs(void)