Merge tag 'qcom-drivers-for-5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux into arm/drivers

Qualcomm driver updates for v5.8

This contains a large set of cleanups, bug fixes, general improvements
and documentation fixes for the RPMH driver. It adds a debugfs mechanism
for inspecting Command DB. Socinfo got the "soc_id" attribute defines
and definitions for a various variants of MSM8939.

RPMH, RPMPD and RPMHPD where made possible to build as modules, but RPMH
had to be reverted due to a compilation issue when tracing is enabled.

RPMHPD gained power-domains for the SM8250 voltage corners.

The SCM driver gained fixes for two build warnings and the SMP2P had an
unnecessary error print removed.

* tag 'qcom-drivers-for-5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux: (42 commits)
  Revert "soc: qcom: rpmh: Allow RPMH driver to be loaded as a module"
  soc: qcom: rpmh-rsc: Remove the pm_lock
  soc: qcom: rpmh-rsc: Simplify locking by eliminating the per-TCS lock
  kernel/cpu_pm: Fix uninitted local in cpu_pm
  soc: qcom: rpmh-rsc: We aren't notified of our own failure w/ NOTIFY_BAD
  soc: qcom: rpmh-rsc: Correctly ignore CPU_CLUSTER_PM notifications
  firmware: qcom_scm-legacy: Replace zero-length array with flexible-array
  soc: qcom: rpmh-rsc: Timeout after 1 second in write_tcs_reg_sync()
  soc: qcom: rpmh-rsc: Factor "tcs_reg_addr" and "tcs_cmd_addr" calculation
  soc: qcom: socinfo: add msm8936/39 and apq8036/39 soc ids
  soc: qcom: aoss: Add SM8250 compatible
  soc: qcom: pdr: Remove impossible error condition
  soc: qcom: rpmh: Dirt can only make you dirtier, not cleaner
  soc: qcom: rpmhpd: Add SM8250 power domains
  firmware: qcom_scm: fix bogous abuse of dma-direct internals
  dt-bindings: soc: qcom: apr: Use generic node names for APR services
  firmware: qcom_scm: Remove unneeded conversion to bool
  soc: qcom: cmd-db: Properly endian swap the slv_id for debugfs
  soc: qcom: cmd-db: Use 5 digits for printing address
  soc: qcom: cmd-db: Cast sizeof() to int to silence field width warning
  ...

Link: https://lore.kernel.org/r/20200519052533.1250024-1-bjorn.andersson@linaro.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

11 files changed, 743 insertions, 287 deletions

diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index bf42a17a45de..19332ea40234 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -117,7 +117,7 @@ config QCOM_RPMH
 	  help apply the aggregated state on the resource.
 
 config QCOM_RPMHPD
-	bool "Qualcomm RPMh Power domain driver"
+	tristate "Qualcomm RPMh Power domain driver"
 	depends on QCOM_RPMH && QCOM_COMMAND_DB
 	help
 	  QCOM RPMh Power domain driver to support power-domains with
@@ -126,8 +126,8 @@ config QCOM_RPMHPD
 	  for the voltage rail.
 
 config QCOM_RPMPD
-	bool "Qualcomm RPM Power domain driver"
-	depends on QCOM_SMD_RPM=y
+	tristate "Qualcomm RPM Power domain driver"
+	depends on QCOM_SMD_RPM
 	help
 	  QCOM RPM Power domain driver to support power-domains with
 	  performance states. The driver communicates a performance state
diff --git a/drivers/soc/qcom/cmd-db.c b/drivers/soc/qcom/cmd-db.c
index f6c3d17b05c7..fc5610603b17 100644
--- a/drivers/soc/qcom/cmd-db.c
+++ b/drivers/soc/qcom/cmd-db.c
@@ -1,12 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. */
 
+#include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
+#include <linux/seq_file.h>
 #include <linux/types.h>
 
 #include <soc/qcom/cmd-db.h>
@@ -236,6 +237,77 @@ enum cmd_db_hw_type cmd_db_read_slave_id(const char *id)
 }
 EXPORT_SYMBOL(cmd_db_read_slave_id);
 
+#ifdef CONFIG_DEBUG_FS
+static int cmd_db_debugfs_dump(struct seq_file *seq, void *p)
+{
+	int i, j;
+	const struct rsc_hdr *rsc;
+	const struct entry_header *ent;
+	const char *name;
+	u16 len, version;
+	u8 major, minor;
+
+	seq_puts(seq, "Command DB DUMP\n");
+
+	for (i = 0; i < MAX_SLV_ID; i++) {
+		rsc = &cmd_db_header->header[i];
+		if (!rsc->slv_id)
+			break;
+
+		switch (le16_to_cpu(rsc->slv_id)) {
+		case CMD_DB_HW_ARC:
+			name = "ARC";
+			break;
+		case CMD_DB_HW_VRM:
+			name = "VRM";
+			break;
+		case CMD_DB_HW_BCM:
+			name = "BCM";
+			break;
+		default:
+			name = "Unknown";
+			break;
+		}
+
+		version = le16_to_cpu(rsc->version);
+		major = version >> 8;
+		minor = version;
+
+		seq_printf(seq, "Slave %s (v%u.%u)\n", name, major, minor);
+		seq_puts(seq, "-------------------------\n");
+
+		ent = rsc_to_entry_header(rsc);
+		for (j = 0; j < le16_to_cpu(rsc->cnt); j++, ent++) {
+			seq_printf(seq, "0x%05x: %*pEp", le32_to_cpu(ent->addr),
+				   (int)sizeof(ent->id), ent->id);
+
+			len = le16_to_cpu(ent->len);
+			if (len) {
+				seq_printf(seq, " [%*ph]",
+					   len, rsc_offset(rsc, ent));
+			}
+			seq_putc(seq, '\n');
+		}
+	}
+
+	return 0;
+}
+
+static int open_cmd_db_debugfs(struct inode *inode, struct file *file)
+{
+	return single_open(file, cmd_db_debugfs_dump, inode->i_private);
+}
+#endif
+
+static const struct file_operations cmd_db_debugfs_ops = {
+#ifdef CONFIG_DEBUG_FS
+	.open = open_cmd_db_debugfs,
+#endif
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 static int cmd_db_dev_probe(struct platform_device *pdev)
 {
 	struct reserved_mem *rmem;
@@ -259,12 +331,14 @@ static int cmd_db_dev_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	debugfs_create_file("cmd-db", 0400, NULL, NULL, &cmd_db_debugfs_ops);
+
 	return 0;
 }
 
 static const struct of_device_id cmd_db_match_table[] = {
 	{ .compatible = "qcom,cmd-db" },
-	{ },
+	{ }
 };
 
 static struct platform_driver cmd_db_dev_driver = {
diff --git a/drivers/soc/qcom/pdr_interface.c b/drivers/soc/qcom/pdr_interface.c
index 17ad3b8698e1..bdcf16f88a97 100644
--- a/drivers/soc/qcom/pdr_interface.c
+++ b/drivers/soc/qcom/pdr_interface.c
@@ -155,10 +155,6 @@ static int pdr_register_listener(struct pdr_handle *pdr,
 		return ret;
 	}
 
-	if ((int)resp.curr_state < INT_MIN || (int)resp.curr_state > INT_MAX)
-		pr_err("PDR: %s notification state invalid: 0x%x\n",
-		       pds->service_path, resp.curr_state);
-
 	pds->state = resp.curr_state;
 
 	return 0;
diff --git a/drivers/soc/qcom/qcom_aoss.c b/drivers/soc/qcom/qcom_aoss.c
index f43a2e07ee83..ed2c687c16b3 100644
--- a/drivers/soc/qcom/qcom_aoss.c
+++ b/drivers/soc/qcom/qcom_aoss.c
@@ -599,6 +599,7 @@ static const struct of_device_id qmp_dt_match[] = {
 	{ .compatible = "qcom,sc7180-aoss-qmp", },
 	{ .compatible = "qcom,sdm845-aoss-qmp", },
 	{ .compatible = "qcom,sm8150-aoss-qmp", },
+	{ .compatible = "qcom,sm8250-aoss-qmp", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, qmp_dt_match);
diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
index 6eec32b97f83..ef60e790a750 100644
--- a/drivers/soc/qcom/rpmh-internal.h
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -22,16 +22,23 @@ struct rsc_drv;
  * struct tcs_group: group of Trigger Command Sets (TCS) to send state requests
  * to the controller
  *
- * @drv:       the controller
- * @type:      type of the TCS in this group - active, sleep, wake
- * @mask:      mask of the TCSes relative to all the TCSes in the RSC
- * @offset:    start of the TCS group relative to the TCSes in the RSC
- * @num_tcs:   number of TCSes in this type
- * @ncpt:      number of commands in each TCS
- * @lock:      lock for synchronizing this TCS writes
- * @req:       requests that are sent from the TCS
- * @cmd_cache: flattened cache of cmds in sleep/wake TCS
- * @slots:     indicates which of @cmd_addr are occupied
+ * @drv:       The controller.
+ * @type:      Type of the TCS in this group - active, sleep, wake.
+ * @mask:      Mask of the TCSes relative to all the TCSes in the RSC.
+ * @offset:    Start of the TCS group relative to the TCSes in the RSC.
+ * @num_tcs:   Number of TCSes in this type.
+ * @ncpt:      Number of commands in each TCS.
+ * @req:       Requests that are sent from the TCS; only used for ACTIVE_ONLY
+ *             transfers (could be on a wake/sleep TCS if we are borrowing for
+ *             an ACTIVE_ONLY transfer).
+ *             Start: grab drv->lock, set req, set tcs_in_use, drop drv->lock,
+ *                    trigger
+ *             End: get irq, access req,
+ *                  grab drv->lock, clear tcs_in_use, drop drv->lock
+ * @slots:     Indicates which of @cmd_addr are occupied; only used for
+ *             SLEEP / WAKE TCSs.  Things are tightly packed in the
+ *             case that (ncpt < MAX_CMDS_PER_TCS).  That is if ncpt = 2 and
+ *             MAX_CMDS_PER_TCS = 16 then bit[2] = the first bit in 2nd TCS.
  */
 struct tcs_group {
 	struct rsc_drv *drv;
@@ -40,9 +47,7 @@ struct tcs_group {
 	u32 offset;
 	int num_tcs;
 	int ncpt;
-	spinlock_t lock;
 	const struct tcs_request *req[MAX_TCS_PER_TYPE];
-	u32 *cmd_cache;
 	DECLARE_BITMAP(slots, MAX_TCS_SLOTS);
 };
 
@@ -84,20 +89,32 @@ struct rpmh_ctrlr {
  * struct rsc_drv: the Direct Resource Voter (DRV) of the
  * Resource State Coordinator controller (RSC)
  *
- * @name:       controller identifier
- * @tcs_base:   start address of the TCS registers in this controller
- * @id:         instance id in the controller (Direct Resource Voter)
- * @num_tcs:    number of TCSes in this DRV
- * @tcs:        TCS groups
- * @tcs_in_use: s/w state of the TCS
- * @lock:       synchronize state of the controller
- * @client:     handle to the DRV's client.
+ * @name:               Controller identifier.
+ * @tcs_base:           Start address of the TCS registers in this controller.
+ * @id:                 Instance id in the controller (Direct Resource Voter).
+ * @num_tcs:            Number of TCSes in this DRV.
+ * @rsc_pm:             CPU PM notifier for controller.
+ *                      Used when solver mode is not present.
+ * @cpus_in_pm:         Number of CPUs not in idle power collapse.
+ *                      Used when solver mode is not present.
+ * @tcs:                TCS groups.
+ * @tcs_in_use:         S/W state of the TCS; only set for ACTIVE_ONLY
+ *                      transfers, but might show a sleep/wake TCS in use if
+ *                      it was borrowed for an active_only transfer.  You
+ *                      must hold the lock in this struct (AKA drv->lock) in
+ *                      order to update this.
+ * @lock:               Synchronize state of the controller.  If RPMH's cache
+ *                      lock will also be held, the order is: drv->lock then
+ *                      cache_lock.
+ * @client:             Handle to the DRV's client.
  */
 struct rsc_drv {
 	const char *name;
 	void __iomem *tcs_base;
 	int id;
 	int num_tcs;
+	struct notifier_block rsc_pm;
+	atomic_t cpus_in_pm;
 	struct tcs_group tcs[TCS_TYPE_NR];
 	DECLARE_BITMAP(tcs_in_use, MAX_TCS_NR);
 	spinlock_t lock;
@@ -107,7 +124,7 @@ struct rsc_drv {
 int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg);
 int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv,
 			     const struct tcs_request *msg);
-int rpmh_rsc_invalidate(struct rsc_drv *drv);
+void rpmh_rsc_invalidate(struct rsc_drv *drv);
 
 void rpmh_tx_done(const struct tcs_request *msg, int r);
 int rpmh_flush(struct rpmh_ctrlr *ctrlr);
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index b71822131f59..076fd27f3081 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -6,9 +6,11 @@
 #define pr_fmt(fmt) "%s " fmt, KBUILD_MODNAME
 
 #include <linux/atomic.h>
+#include <linux/cpu_pm.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/of.h>
@@ -30,21 +32,41 @@
 #define RSC_DRV_TCS_OFFSET		672
 #define RSC_DRV_CMD_OFFSET		20
 
-/* DRV Configuration Information Register */
+/* DRV HW Solver Configuration Information Register */
+#define DRV_SOLVER_CONFIG		0x04
+#define DRV_HW_SOLVER_MASK		1
+#define DRV_HW_SOLVER_SHIFT		24
+
+/* DRV TCS Configuration Information Register */
 #define DRV_PRNT_CHLD_CONFIG		0x0C
 #define DRV_NUM_TCS_MASK		0x3F
 #define DRV_NUM_TCS_SHIFT		6
 #define DRV_NCPT_MASK			0x1F
 #define DRV_NCPT_SHIFT			27
 
-/* Register offsets */
+/* Offsets for common TCS Registers, one bit per TCS */
 #define RSC_DRV_IRQ_ENABLE		0x00
 #define RSC_DRV_IRQ_STATUS		0x04
-#define RSC_DRV_IRQ_CLEAR		0x08
-#define RSC_DRV_CMD_WAIT_FOR_CMPL	0x10
+#define RSC_DRV_IRQ_CLEAR		0x08	/* w/o; write 1 to clear */
+
+/*
+ * Offsets for per TCS Registers.
+ *
+ * TCSes start at 0x10 from tcs_base and are stored one after another.
+ * Multiply tcs_id by RSC_DRV_TCS_OFFSET to find a given TCS and add one
+ * of the below to find a register.
+ */
+#define RSC_DRV_CMD_WAIT_FOR_CMPL	0x10	/* 1 bit per command */
 #define RSC_DRV_CONTROL			0x14
-#define RSC_DRV_STATUS			0x18
-#define RSC_DRV_CMD_ENABLE		0x1C
+#define RSC_DRV_STATUS			0x18	/* zero if tcs is busy */
+#define RSC_DRV_CMD_ENABLE		0x1C	/* 1 bit per command */
+
+/*
+ * Offsets for per command in a TCS.
+ *
+ * Commands (up to 16) start at 0x30 in a TCS; multiply command index
+ * by RSC_DRV_CMD_OFFSET and add one of the below to find a register.
+ */
 #define RSC_DRV_CMD_MSGID		0x30
 #define RSC_DRV_CMD_ADDR		0x34
 #define RSC_DRV_CMD_DATA		0x38
@@ -61,94 +83,179 @@
 #define CMD_STATUS_ISSUED		BIT(8)
 #define CMD_STATUS_COMPL		BIT(16)
 
-static u32 read_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id)
+/*
+ * Here's a high level overview of how all the registers in RPMH work
+ * together:
+ *
+ * - The main rpmh-rsc address is the base of a register space that can
+ *   be used to find overall configuration of the hardware
+ *   (DRV_PRNT_CHLD_CONFIG). Also found within the rpmh-rsc register
+ *   space are all the TCS blocks. The offset of the TCS blocks is
+ *   specified in the device tree by "qcom,tcs-offset" and used to
+ *   compute tcs_base.
+ * - TCS blocks come one after another. Type, count, and order are
+ *   specified by the device tree as "qcom,tcs-config".
+ * - Each TCS block has some registers, then space for up to 16 commands.
+ *   Note that though address space is reserved for 16 commands, fewer
+ *   might be present. See ncpt (num cmds per TCS).
+ *
+ * Here's a picture:
+ *
+ *  +---------------------------------------------------+
+ *  |RSC                                                |
+ *  | ctrl                                              |
+ *  |                                                   |
+ *  | Drvs:                                             |
+ *  | +-----------------------------------------------+ |
+ *  | |DRV0                                           | |
+ *  | | ctrl/config                                   | |
+ *  | | IRQ                                           | |
+ *  | |                                               | |
+ *  | | TCSes:                                        | |
+ *  | | +------------------------------------------+  | |
+ *  | | |TCS0  |  |  |  |  |  |  |  |  |  |  |  |  |  | |
+ *  | | | ctrl | 0| 1| 2| 3| 4| 5| .| .| .| .|14|15|  | |
+ *  | | |      |  |  |  |  |  |  |  |  |  |  |  |  |  | |
+ *  | | +------------------------------------------+  | |
+ *  | | +------------------------------------------+  | |
+ *  | | |TCS1  |  |  |  |  |  |  |  |  |  |  |  |  |  | |
+ *  | | | ctrl | 0| 1| 2| 3| 4| 5| .| .| .| .|14|15|  | |
+ *  | | |      |  |  |  |  |  |  |  |  |  |  |  |  |  | |
+ *  | | +------------------------------------------+  | |
+ *  | | +------------------------------------------+  | |
+ *  | | |TCS2  |  |  |  |  |  |  |  |  |  |  |  |  |  | |
+ *  | | | ctrl | 0| 1| 2| 3| 4| 5| .| .| .| .|14|15|  | |
+ *  | | |      |  |  |  |  |  |  |  |  |  |  |  |  |  | |
+ *  | | +------------------------------------------+  | |
+ *  | |                    ......                     | |
+ *  | +-----------------------------------------------+ |
+ *  | +-----------------------------------------------+ |
+ *  | |DRV1                                           | |
+ *  | | (same as DRV0)                                | |
+ *  | +-----------------------------------------------+ |
+ *  |                      ......                       |
+ *  +---------------------------------------------------+
+ */
+
+static inline void __iomem *
+tcs_reg_addr(const struct rsc_drv *drv, int reg, int tcs_id)
 {
-	return readl_relaxed(drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
-			     RSC_DRV_CMD_OFFSET * cmd_id);
+	return drv->tcs_base + RSC_DRV_TCS_OFFSET * tcs_id + reg;
 }
 
-static void write_tcs_cmd(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id,
-			  u32 data)
+static inline void __iomem *
+tcs_cmd_addr(const struct rsc_drv *drv, int reg, int tcs_id, int cmd_id)
 {
-	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
-		       RSC_DRV_CMD_OFFSET * cmd_id);
+	return tcs_reg_addr(drv, reg, tcs_id) + RSC_DRV_CMD_OFFSET * cmd_id;
 }
 
-static void write_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, u32 data)
+static u32 read_tcs_cmd(const struct rsc_drv *drv, int reg, int tcs_id,
+			int cmd_id)
 {
-	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
+	return readl_relaxed(tcs_cmd_addr(drv, reg, tcs_id, cmd_id));
 }
 
-static void write_tcs_reg_sync(struct rsc_drv *drv, int reg, int tcs_id,
-			       u32 data)
+static u32 read_tcs_reg(const struct rsc_drv *drv, int reg, int tcs_id)
 {
-	writel(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
-	for (;;) {
-		if (data == readl(drv->tcs_base + reg +
-				  RSC_DRV_TCS_OFFSET * tcs_id))
-			break;
-		udelay(1);
-	}
+	return readl_relaxed(tcs_reg_addr(drv, reg, tcs_id));
 }
 
-static bool tcs_is_free(struct rsc_drv *drv, int tcs_id)
+static void write_tcs_cmd(const struct rsc_drv *drv, int reg, int tcs_id,
+			  int cmd_id, u32 data)
 {
-	return !test_bit(tcs_id, drv->tcs_in_use) &&
-	       read_tcs_reg(drv, RSC_DRV_STATUS, tcs_id, 0);
+	writel_relaxed(data, tcs_cmd_addr(drv, reg, tcs_id, cmd_id));
 }
 
-static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type)
+static void write_tcs_reg(const struct rsc_drv *drv, int reg, int tcs_id,
+			  u32 data)
 {
-	return &drv->tcs[type];
+	writel_relaxed(data, tcs_reg_addr(drv, reg, tcs_id));
 }
 
-static int tcs_invalidate(struct rsc_drv *drv, int type)
+static void write_tcs_reg_sync(const struct rsc_drv *drv, int reg, int tcs_id,
+			       u32 data)
 {
-	int m;
-	struct tcs_group *tcs;
+	u32 new_data;
 
-	tcs = get_tcs_of_type(drv, type);
+	writel(data, tcs_reg_addr(drv, reg, tcs_id));
+	if (readl_poll_timeout_atomic(tcs_reg_addr(drv, reg, tcs_id), new_data,
+				      new_data == data, 1, USEC_PER_SEC))
+		pr_err("%s: error writing %#x to %d:%#x\n", drv->name,
+		       data, tcs_id, reg);
+}
 
-	spin_lock(&tcs->lock);
-	if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) {
-		spin_unlock(&tcs->lock);
-		return 0;
-	}
+/**
+ * tcs_is_free() - Return if a TCS is totally free.
+ * @drv:    The RSC controller.
+ * @tcs_id: The global ID of this TCS.
+ *
+ * Returns true if nobody has claimed this TCS (by setting tcs_in_use).
+ *
+ * Context: Must be called with the drv->lock held.
+ *
+ * Return: true if the given TCS is free.
+ */
+static bool tcs_is_free(struct rsc_drv *drv, int tcs_id)
+{
+	return !test_bit(tcs_id, drv->tcs_in_use);
+}
+
+/**
+ * tcs_invalidate() - Invalidate all TCSes of the given type (sleep or wake).
+ * @drv:  The RSC controller.
+ * @type: SLEEP_TCS or WAKE_TCS
+ *
+ * This will clear the "slots" variable of the given tcs_group and also
+ * tell the hardware to forget about all entries.
+ *
+ * The caller must ensure that no other RPMH actions are happening when this
+ * function is called, since otherwise the device may immediately become
+ * used again even before this function exits.
+ */
+static void tcs_invalidate(struct rsc_drv *drv, int type)
+{
+	int m;
+	struct tcs_group *tcs = &drv->tcs[type];
+
+	/* Caller ensures nobody else is running so no lock */
+	if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS))
+		return;
 
 	for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) {
-		if (!tcs_is_free(drv, m)) {
-			spin_unlock(&tcs->lock);
-			return -EAGAIN;
-		}
 		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, m, 0);
 		write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, m, 0);
 	}
 	bitmap_zero(tcs->slots, MAX_TCS_SLOTS);
-	spin_unlock(&tcs->lock);
-
-	return 0;
 }
 
 /**
- * rpmh_rsc_invalidate - Invalidate sleep and wake TCSes
+ * rpmh_rsc_invalidate() - Invalidate sleep and wake TCSes.
+ * @drv: The RSC controller.
  *
- * @drv: the RSC controller
+ * The caller must ensure that no other RPMH actions are happening when this
+ * function is called, since otherwise the device may immediately become
+ * used again even before this function exits.
  */
-int rpmh_rsc_invalidate(struct rsc_drv *drv)
+void rpmh_rsc_invalidate(struct rsc_drv *drv)
 {
-	int ret;
-
-	ret = tcs_invalidate(drv, SLEEP_TCS);
-	if (!ret)
-		ret = tcs_invalidate(drv, WAKE_TCS);
-
-	return ret;
+	tcs_invalidate(drv, SLEEP_TCS);
+	tcs_invalidate(drv, WAKE_TCS);
 }
 
+/**
+ * get_tcs_for_msg() - Get the tcs_group used to send the given message.
+ * @drv: The RSC controller.
+ * @msg: The message we want to send.
+ *
+ * This is normally pretty straightforward except if we are trying to send
+ * an ACTIVE_ONLY message but don't have any active_only TCSes.
+ *
+ * Return: A pointer to a tcs_group or an ERR_PTR.
+ */
 static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 					 const struct tcs_request *msg)
 {
-	int type, ret;
+	int type;
 	struct tcs_group *tcs;
 
 	switch (msg->state) {
@@ -168,24 +275,33 @@ static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 	/*
 	 * If we are making an active request on a RSC that does not have a
 	 * dedicated TCS for active state use, then re-purpose a wake TCS to
-	 * send active votes.
-	 * NOTE: The driver must be aware that this RSC does not have a
-	 * dedicated AMC, and therefore would invalidate the sleep and wake
-	 * TCSes before making an active state request.
+	 * send active votes. This is safe because we ensure any active-only
+	 * transfers have finished before we use it (maybe by running from
+	 * the last CPU in PM code).
 	 */
-	tcs = get_tcs_of_type(drv, type);
-	if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs) {
-		tcs = get_tcs_of_type(drv, WAKE_TCS);
-		if (tcs->num_tcs) {
-			ret = rpmh_rsc_invalidate(drv);
-			if (ret)
-				return ERR_PTR(ret);
-		}
-	}
+	tcs = &drv->tcs[type];
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs)
+		tcs = &drv->tcs[WAKE_TCS];
 
 	return tcs;
 }
 
+/**
+ * get_req_from_tcs() - Get a stashed request that was xfering on the given TCS.
+ * @drv:    The RSC controller.
+ * @tcs_id: The global ID of this TCS.
+ *
+ * For ACTIVE_ONLY transfers we want to call back into the client when the
+ * transfer finishes. To do this we need the "request" that the client
+ * originally provided us. This function grabs the request that we stashed
+ * when we started the transfer.
+ *
+ * This only makes sense for ACTIVE_ONLY transfers since those are the only
+ * ones we track sending (the only ones we enable interrupts for and the only
+ * ones we call back to the client for).
+ *
+ * Return: The stashed request.
+ */
 static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
 						  int tcs_id)
 {
@@ -202,7 +318,76 @@ static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
 }
 
 /**
- * tcs_tx_done: TX Done interrupt handler
+ * __tcs_set_trigger() - Start xfer on a TCS or unset trigger on a borrowed TCS
+ * @drv:     The controller.
+ * @tcs_id:  The global ID of this TCS.
+ * @trigger: If true then untrigger/retrigger. If false then just untrigger.
+ *
+ * In the normal case we only ever call with "trigger=true" to start a
+ * transfer. That will un-trigger/disable the TCS from the last transfer
+ * then trigger/enable for this transfer.
+ *
+ * If we borrowed a wake TCS for an active-only transfer we'll also call
+ * this function with "trigger=false" to just do the un-trigger/disable
+ * before using the TCS for wake purposes again.
+ *
+ * Note that the AP is only in charge of triggering active-only transfers.
+ * The AP never triggers sleep/wake values using this function.
+ */
+static void __tcs_set_trigger(struct rsc_drv *drv, int tcs_id, bool trigger)
+{
+	u32 enable;
+
+	/*
+	 * HW req: Clear the DRV_CONTROL and enable TCS again
+	 * While clearing ensure that the AMC mode trigger is cleared
+	 * and then the mode enable is cleared.
+	 */
+	enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id);
+	enable &= ~TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable &= ~TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+
+	if (trigger) {
+		/* Enable the AMC mode on the TCS and then trigger the TCS */
+		enable = TCS_AMC_MODE_ENABLE;
+		write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+		enable |= TCS_AMC_MODE_TRIGGER;
+		write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	}
+}
+
+/**
+ * enable_tcs_irq() - Enable or disable interrupts on the given TCS.
+ * @drv:     The controller.
+ * @tcs_id:  The global ID of this TCS.
+ * @enable:  If true then enable; if false then disable
+ *
+ * We only ever call this when we borrow a wake TCS for an active-only
+ * transfer. For active-only TCSes interrupts are always left enabled.
+ */
+static void enable_tcs_irq(struct rsc_drv *drv, int tcs_id, bool enable)
+{
+	u32 data;
+
+	data = readl_relaxed(drv->tcs_base + RSC_DRV_IRQ_ENABLE);
+	if (enable)
+		data |= BIT(tcs_id);
+	else
+		data &= ~BIT(tcs_id);
+	writel_relaxed(data, drv->tcs_base + RSC_DRV_IRQ_ENABLE);
+}
+
+/**
+ * tcs_tx_done() - TX Done interrupt handler.
+ * @irq: The IRQ number (ignored).
+ * @p:   Pointer to "struct rsc_drv".
+ *
+ * Called for ACTIVE_ONLY transfers (those are the only ones we enable the
+ * IRQ for) when a transfer is done.
+ *
+ * Return: IRQ_HANDLED
  */
 static irqreturn_t tcs_tx_done(int irq, void *p)
 {
@@ -212,7 +397,7 @@ static irqreturn_t tcs_tx_done(int irq, void *p)
 	const struct tcs_request *req;
 	struct tcs_cmd *cmd;
 
-	irq_status = read_tcs_reg(drv, RSC_DRV_IRQ_STATUS, 0, 0);
+	irq_status = readl_relaxed(drv->tcs_base + RSC_DRV_IRQ_STATUS);
 
 	for_each_set_bit(i, &irq_status, BITS_PER_LONG) {
 		req = get_req_from_tcs(drv, i);
@@ -226,7 +411,7 @@ static irqreturn_t tcs_tx_done(int irq, void *p)
 			u32 sts;
 
 			cmd = &req->cmds[j];
-			sts = read_tcs_reg(drv, RSC_DRV_CMD_STATUS, i, j);
+			sts = read_tcs_cmd(drv, RSC_DRV_CMD_STATUS, i, j);
 			if (!(sts & CMD_STATUS_ISSUED) ||
 			   ((req->wait_for_compl || cmd->wait) &&
 			   !(sts & CMD_STATUS_COMPL))) {
@@ -237,13 +422,28 @@ static irqreturn_t tcs_tx_done(int irq, void *p)
 		}
 
 		trace_rpmh_tx_done(drv, i, req, err);
+
+		/*
+		 * If wake tcs was re-purposed for sending active
+		 * votes, clear AMC trigger & enable modes and
+		 * disable interrupt for this TCS
+		 */
+		if (!drv->tcs[ACTIVE_TCS].num_tcs)
+			__tcs_set_trigger(drv, i, false);
 skip:
 		/* Reclaim the TCS */
 		write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0);
 		write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, i, 0);
-		write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i));
+		writel_relaxed(BIT(i), drv->tcs_base + RSC_DRV_IRQ_CLEAR);
 		spin_lock(&drv->lock);
 		clear_bit(i, drv->tcs_in_use);
+		/*
+		 * Disable interrupt for WAKE TCS to avoid being
+		 * spammed with interrupts coming when the solver
+		 * sends its wake votes.
+		 */
+		if (!drv->tcs[ACTIVE_TCS].num_tcs)
+			enable_tcs_irq(drv, i, false);
 		spin_unlock(&drv->lock);
 		if (req)
 			rpmh_tx_done(req, err);
@@ -252,6 +452,16 @@ skip:
 	return IRQ_HANDLED;
 }
 
+/**
+ * __tcs_buffer_write() - Write to TCS hardware from a request; don't trigger.
+ * @drv:    The controller.
+ * @tcs_id: The global ID of this TCS.
+ * @cmd_id: The index within the TCS to start writing.
+ * @msg:    The message we want to send, which will contain several addr/data
+ *          pairs to program (but few enough that they all fit in one TCS).
+ *
+ * This is used for all types of transfers (active, sleep, and wake).
+ */
 static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
 			       const struct tcs_request *msg)
 {
@@ -265,7 +475,7 @@ static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
 	cmd_msgid |= msg->wait_for_compl ? CMD_MSGID_RESP_REQ : 0;
 	cmd_msgid |= CMD_MSGID_WRITE;
 
-	cmd_complete = read_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0);
+	cmd_complete = read_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id);
 
 	for (i = 0, j = cmd_id; i < msg->num_cmds; i++, j++) {
 		cmd = &msg->cmds[i];
@@ -281,32 +491,30 @@ static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
 	}
 
 	write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, cmd_complete);
-	cmd_enable |= read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+	cmd_enable |= read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id);
 	write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable);
 }
 
-static void __tcs_trigger(struct rsc_drv *drv, int tcs_id)
-{
-	u32 enable;
-
-	/*
-	 * HW req: Clear the DRV_CONTROL and enable TCS again
-	 * While clearing ensure that the AMC mode trigger is cleared
-	 * and then the mode enable is cleared.
-	 */
-	enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0);
-	enable &= ~TCS_AMC_MODE_TRIGGER;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-	enable &= ~TCS_AMC_MODE_ENABLE;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-
-	/* Enable the AMC mode on the TCS and then trigger the TCS */
-	enable = TCS_AMC_MODE_ENABLE;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-	enable |= TCS_AMC_MODE_TRIGGER;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-}
-
+/**
+ * check_for_req_inflight() - Look to see if conflicting cmds are in flight.
+ * @drv: The controller.
+ * @tcs: A pointer to the tcs_group used for ACTIVE_ONLY transfers.
+ * @msg: The message we want to send, which will contain several addr/data
+ *       pairs to program (but few enough that they all fit in one TCS).
+ *
+ * This will walk through the TCSes in the group and check if any of them
+ * appear to be sending to addresses referenced in the message. If it finds
+ * one it'll return -EBUSY.
+ *
+ * Only for use for active-only transfers.
+ *
+ * Must be called with the drv->lock held since that protects tcs_in_use.
+ *
+ * Return: 0 if nothing in flight or -EBUSY if we should try again later.
+ *         The caller must re-enable interrupts between tries since that's
+ *         the only way tcs_is_free() will ever return true and the only way
+ *         RSC_DRV_CMD_ENABLE will ever be cleared.
+ */
 static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs,
 				  const struct tcs_request *msg)
 {
@@ -319,10 +527,10 @@ static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs,
 		if (tcs_is_free(drv, tcs_id))
 			continue;
 
-		curr_enabled = read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+		curr_enabled = read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id);
 
 		for_each_set_bit(j, &curr_enabled, MAX_CMDS_PER_TCS) {
-			addr = read_tcs_reg(drv, RSC_DRV_CMD_ADDR, tcs_id, j);
+			addr = read_tcs_cmd(drv, RSC_DRV_CMD_ADDR, tcs_id, j);
 			for (k = 0; k < msg->num_cmds; k++) {
 				if (addr == msg->cmds[k].addr)
 					return -EBUSY;
@@ -333,6 +541,15 @@ static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs,
 	return 0;
 }
 
+/**
+ * find_free_tcs() - Find free tcs in the given tcs_group; only for active.
+ * @tcs: A pointer to the active-only tcs_group (or the wake tcs_group if
+ *       we borrowed it because there are zero active-only ones).
+ *
+ * Must be called with the drv->lock held since that protects tcs_in_use.
+ *
+ * Return: The first tcs that's free.
+ */
 static int find_free_tcs(struct tcs_group *tcs)
 {
 	int i;
@@ -345,6 +562,20 @@ static int find_free_tcs(struct tcs_group *tcs)
 	return -EBUSY;
 }
 
+/**
+ * tcs_write() - Store messages into a TCS right now, or return -EBUSY.
+ * @drv: The controller.
+ * @msg: The data to be sent.
+ *
+ * Grabs a TCS for ACTIVE_ONLY transfers and writes the messages to it.
+ *
+ * If there are no free TCSes for ACTIVE_ONLY transfers or if a command for
+ * the same address is already transferring returns -EBUSY which means the
+ * client should retry shortly.
+ *
+ * Return: 0 on success, -EBUSY if client should retry, or an error.
+ *         Client should have interrupts enabled for a bit before retrying.
+ */
 static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg)
 {
 	struct tcs_group *tcs;
@@ -356,57 +587,77 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg)
 	if (IS_ERR(tcs))
 		return PTR_ERR(tcs);
 
-	spin_lock_irqsave(&tcs->lock, flags);
-	spin_lock(&drv->lock);
+	spin_lock_irqsave(&drv->lock, flags);
 	/*
 	 * The h/w does not like if we send a request to the same address,
 	 * when one is already in-flight or being processed.
 	 */
 	ret = check_for_req_inflight(drv, tcs, msg);
-	if (ret) {
-		spin_unlock(&drv->lock);
-		goto done_write;
-	}
+	if (ret)
+		goto unlock;
 
-	tcs_id = find_free_tcs(tcs);
-	if (tcs_id < 0) {
-		ret = tcs_id;
-		spin_unlock(&drv->lock);
-		goto done_write;
-	}
+	ret = find_free_tcs(tcs);
+	if (ret < 0)
+		goto unlock;
+	tcs_id = ret;
 
 	tcs->req[tcs_id - tcs->offset] = msg;
 	set_bit(tcs_id, drv->tcs_in_use);
-	spin_unlock(&drv->lock);
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && tcs->type != ACTIVE_TCS) {
+		/*
+		 * Clear previously programmed WAKE commands in selected
+		 * repurposed TCS to avoid triggering them. tcs->slots will be
+		 * cleaned from rpmh_flush() by invoking rpmh_rsc_invalidate()
+		 */
+		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+		write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0);
+		enable_tcs_irq(drv, tcs_id, true);
+	}
+	spin_unlock_irqrestore(&drv->lock, flags);
 
+	/*
+	 * These two can be done after the lock is released because:
+	 * - We marked "tcs_in_use" under lock.
+	 * - Once "tcs_in_use" has been marked nobody else could be writing
+	 *   to these registers until the interrupt goes off.
+	 * - The interrupt can't go off until we trigger w/ the last line
+	 *   of __tcs_set_trigger() below.
+	 */
 	__tcs_buffer_write(drv, tcs_id, 0, msg);
-	__tcs_trigger(drv, tcs_id);
+	__tcs_set_trigger(drv, tcs_id, true);
 
-done_write:
-	spin_unlock_irqrestore(&tcs->lock, flags);
+	return 0;
+unlock:
+	spin_unlock_irqrestore(&drv->lock, flags);
 	return ret;
 }
 
 /**
- * rpmh_rsc_send_data: Validate the incoming message and write to the
- * appropriate TCS block.
+ * rpmh_rsc_send_data() - Write / trigger active-only message.
+ * @drv: The controller.
+ * @msg: The data to be sent.
  *
- * @drv: the controller
- * @msg: the data to be sent
+ * NOTES:
+ * - This is only used for "ACTIVE_ONLY" since the limitations of this
+ *   function don't make sense for sleep/wake cases.
+ * - To do the transfer, we will grab a whole TCS for ourselves--we don't
+ *   try to share. If there are none available we'll wait indefinitely
+ *   for a free one.
+ * - This function will not wait for the commands to be finished, only for
+ *   data to be programmed into the RPMh. See rpmh_tx_done() which will
+ *   be called when the transfer is fully complete.
+ * - This function must be called with interrupts enabled. If the hardware
+ *   is busy doing someone else's transfer we need that transfer to fully
+ *   finish so that we can have the hardware, and to fully finish it needs
+ *   the interrupt handler to run. If the interrupts is set to run on the
+ *   active CPU this can never happen if interrupts are disabled.
  *
  * Return: 0 on success, -EINVAL on error.
- * Note: This call blocks until a valid data is written to the TCS.
  */
 int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
 {
 	int ret;
 
-	if (!msg || !msg->cmds || !msg->num_cmds ||
-	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
-		WARN_ON(1);
-		return -EINVAL;
-	}
-
 	do {
 		ret = tcs_write(drv, msg);
 		if (ret == -EBUSY) {
@@ -419,43 +670,28 @@ int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
 	return ret;
 }
 
-static int find_match(const struct tcs_group *tcs, const struct tcs_cmd *cmd,
-		      int len)
-{
-	int i, j;
-
-	/* Check for already cached commands */
-	for_each_set_bit(i, tcs->slots, MAX_TCS_SLOTS) {
-		if (tcs->cmd_cache[i] != cmd[0].addr)
-			continue;
-		if (i + len >= tcs->num_tcs * tcs->ncpt)
-			goto seq_err;
-		for (j = 0; j < len; j++) {
-			if (tcs->cmd_cache[i + j] != cmd[j].addr)
-				goto seq_err;
-		}
-		return i;
-	}
-
-	return -ENODATA;
-
-seq_err:
-	WARN(1, "Message does not match previous sequence.\n");
-	return -EINVAL;
-}
-
+/**
+ * find_slots() - Find a place to write the given message.
+ * @tcs:    The tcs group to search.
+ * @msg:    The message we want to find room for.
+ * @tcs_id: If we return 0 from the function, we return the global ID of the
+ *          TCS to write to here.
+ * @cmd_id: If we return 0 from the function, we return the index of
+ *          the command array of the returned TCS where the client should
+ *          start writing the message.
+ *
+ * Only for use on sleep/wake TCSes since those are the only ones we maintain
+ * tcs->slots for.
+ *
+ * Return: -ENOMEM if there was no room, else 0.
+ */
 static int find_slots(struct tcs_group *tcs, const struct tcs_request *msg,
 		      int *tcs_id, int *cmd_id)
 {
 	int slot, offset;
 	int i = 0;
 
-	/* Find if we already have the msg in our TCS */
-	slot = find_match(tcs, msg->cmds, msg->num_cmds);
-	if (slot >= 0)
-		goto copy_data;
-
-	/* Do over, until we can fit the full payload in a TCS */
+	/* Do over, until we can fit the full payload in a single TCS */
 	do {
 		slot = bitmap_find_next_zero_area(tcs->slots, MAX_TCS_SLOTS,
 						  i, msg->num_cmds, 0);
@@ -464,11 +700,7 @@ static int find_slots(struct tcs_group *tcs, const struct tcs_request *msg,
 		i += tcs->ncpt;
 	} while (slot + msg->num_cmds - 1 >= i);
 
-copy_data:
 	bitmap_set(tcs->slots, slot, msg->num_cmds);
-	/* Copy the addresses of the resources over to the slots */
-	for (i = 0; i < msg->num_cmds; i++)
-		tcs->cmd_cache[slot + i] = msg->cmds[i].addr;
 
 	offset = slot / tcs->ncpt;
 	*tcs_id = offset + tcs->offset;
@@ -477,52 +709,157 @@ copy_data:
 	return 0;
 }
 
-static int tcs_ctrl_write(struct rsc_drv *drv, const struct tcs_request *msg)
+/**
+ * rpmh_rsc_write_ctrl_data() - Write request to controller but don't trigger.
+ * @drv: The controller.
+ * @msg: The data to be written to the controller.
+ *
+ * This should only be called for for sleep/wake state, never active-only
+ * state.
+ *
+ * The caller must ensure that no other RPMH actions are happening and the
+ * controller is idle when this function is called since it runs lockless.
+ *
+ * Return: 0 if no error; else -error.
+ */
+int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv, const struct tcs_request *msg)
 {
 	struct tcs_group *tcs;
 	int tcs_id = 0, cmd_id = 0;
-	unsigned long flags;
 	int ret;
 
 	tcs = get_tcs_for_msg(drv, msg);
 	if (IS_ERR(tcs))
 		return PTR_ERR(tcs);
 
-	spin_lock_irqsave(&tcs->lock, flags);
 	/* find the TCS id and the command in the TCS to write to */
 	ret = find_slots(tcs, msg, &tcs_id, &cmd_id);
 	if (!ret)
 		__tcs_buffer_write(drv, tcs_id, cmd_id, msg);
-	spin_unlock_irqrestore(&tcs->lock, flags);
 
 	return ret;
 }
 
 /**
- * rpmh_rsc_write_ctrl_data: Write request to the controller
+ * rpmh_rsc_ctrlr_is_busy() - Check if any of the AMCs are busy.
+ * @drv: The controller
+ *
+ * Checks if any of the AMCs are busy in handling ACTIVE sets.
+ * This is called from the last cpu powering down before flushing
+ * SLEEP and WAKE sets. If AMCs are busy, controller can not enter
+ * power collapse, so deny from the last cpu's pm notification.
  *
- * @drv: the controller
- * @msg: the data to be written to the controller
+ * Context: Must be called with the drv->lock held.
  *
- * There is no response returned for writing the request to the controller.
+ * Return:
+ * * False		- AMCs are idle
+ * * True		- AMCs are busy
  */
-int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv, const struct tcs_request *msg)
+static bool rpmh_rsc_ctrlr_is_busy(struct rsc_drv *drv)
 {
-	if (!msg || !msg->cmds || !msg->num_cmds ||
-	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
-		pr_err("Payload error\n");
-		return -EINVAL;
+	int m;
+	struct tcs_group *tcs = &drv->tcs[ACTIVE_TCS];
+
+	/*
+	 * If we made an active request on a RSC that does not have a
+	 * dedicated TCS for active state use, then re-purposed wake TCSes
+	 * should be checked for not busy, because we used wake TCSes for
+	 * active requests in this case.
+	 */
+	if (!tcs->num_tcs)
+		tcs = &drv->tcs[WAKE_TCS];
+
+	for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) {
+		if (!tcs_is_free(drv, m))
+			return true;
 	}
 
-	/* Data sent to this API will not be sent immediately */
-	if (msg->state == RPMH_ACTIVE_ONLY_STATE)
-		return -EINVAL;
+	return false;
+}
+
+/**
+ * rpmh_rsc_cpu_pm_callback() - Check if any of the AMCs are busy.
+ * @nfb:    Pointer to the notifier block in struct rsc_drv.
+ * @action: CPU_PM_ENTER, CPU_PM_ENTER_FAILED, or CPU_PM_EXIT.
+ * @v:      Unused
+ *
+ * This function is given to cpu_pm_register_notifier so we can be informed
+ * about when CPUs go down. When all CPUs go down we know no more active
+ * transfers will be started so we write sleep/wake sets. This function gets
+ * called from cpuidle code paths and also at system suspend time.
+ *
+ * If its last CPU going down and AMCs are not busy then writes cached sleep
+ * and wake messages to TCSes. The firmware then takes care of triggering
+ * them when entering deepest low power modes.
+ *
+ * Return: See cpu_pm_register_notifier()
+ */
+static int rpmh_rsc_cpu_pm_callback(struct notifier_block *nfb,
+				    unsigned long action, void *v)
+{
+	struct rsc_drv *drv = container_of(nfb, struct rsc_drv, rsc_pm);
+	int ret = NOTIFY_OK;
+	int cpus_in_pm;
 
-	return tcs_ctrl_write(drv, msg);
+	switch (action) {
+	case CPU_PM_ENTER:
+		cpus_in_pm = atomic_inc_return(&drv->cpus_in_pm);
+		/*
+		 * NOTE: comments for num_online_cpus() point out that it's
+		 * only a snapshot so we need to be careful. It should be OK
+		 * for us to use, though.  It's important for us not to miss
+		 * if we're the last CPU going down so it would only be a
+		 * problem if a CPU went offline right after we did the check
+		 * AND that CPU was not idle AND that CPU was the last non-idle
+		 * CPU. That can't happen. CPUs would have to come out of idle
+		 * before the CPU could go offline.
+		 */
+		if (cpus_in_pm < num_online_cpus())
+			return NOTIFY_OK;
+		break;
+	case CPU_PM_ENTER_FAILED:
+	case CPU_PM_EXIT:
+		atomic_dec(&drv->cpus_in_pm);
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	/*
+	 * It's likely we're on the last CPU. Grab the drv->lock and write
+	 * out the sleep/wake commands to RPMH hardware. Grabbing the lock
+	 * means that if we race with another CPU coming up we are still
+	 * guaranteed to be safe. If another CPU came up just after we checked
+	 * and has grabbed the lock or started an active transfer then we'll
+	 * notice we're busy and abort. If another CPU comes up after we start
+	 * flushing it will be blocked from starting an active transfer until
+	 * we're done flushing. If another CPU starts an active transfer after
+	 * we release the lock we're still OK because we're no longer the last
+	 * CPU.
+	 */
+	if (spin_trylock(&drv->lock)) {
+		if (rpmh_rsc_ctrlr_is_busy(drv) || rpmh_flush(&drv->client))
+			ret = NOTIFY_BAD;
+		spin_unlock(&drv->lock);
+	} else {
+		/* Another CPU must be up */
+		return NOTIFY_OK;
+	}
+
+	if (ret == NOTIFY_BAD) {
+		/* Double-check if we're here because someone else is up */
+		if (cpus_in_pm < num_online_cpus())
+			ret = NOTIFY_OK;
+		else
+			/* We won't be called w/ CPU_PM_ENTER_FAILED */
+			atomic_dec(&drv->cpus_in_pm);
+	}
+
+	return ret;
 }
 
 static int rpmh_probe_tcs_config(struct platform_device *pdev,
-				 struct rsc_drv *drv)
+				 struct rsc_drv *drv, void __iomem *base)
 {
 	struct tcs_type_config {
 		u32 type;
@@ -532,15 +869,6 @@ static int rpmh_probe_tcs_config(struct platform_device *pdev,
 	u32 config, max_tcs, ncpt, offset;
 	int i, ret, n, st = 0;
 	struct tcs_group *tcs;
-	struct resource *res;
-	void __iomem *base;
-	char drv_id[10] = {0};
-
-	snprintf(drv_id, ARRAY_SIZE(drv_id), "drv-%d", drv->id);
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, drv_id);
-	base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(base))
-		return PTR_ERR(base);
 
 	ret = of_property_read_u32(dn, "qcom,tcs-offset", &offset);
 	if (ret)
@@ -584,7 +912,6 @@ static int rpmh_probe_tcs_config(struct platform_device *pdev,
 		tcs->type = tcs_cfg[i].type;
 		tcs->num_tcs = tcs_cfg[i].n;
 		tcs->ncpt = ncpt;
-		spin_lock_init(&tcs->lock);
 
 		if (!tcs->num_tcs || tcs->type == CONTROL_TCS)
 			continue;
@@ -596,19 +923,6 @@ static int rpmh_probe_tcs_config(struct platform_device *pdev,
 		tcs->mask = ((1 << tcs->num_tcs) - 1) << st;
 		tcs->offset = st;
 		st += tcs->num_tcs;
-
-		/*
-		 * Allocate memory to cache sleep and wake requests to
-		 * avoid reading TCS register memory.
-		 */
-		if (tcs->type == ACTIVE_TCS)
-			continue;
-
-		tcs->cmd_cache = devm_kcalloc(&pdev->dev,
-					      tcs->num_tcs * ncpt, sizeof(u32),
-					      GFP_KERNEL);
-		if (!tcs->cmd_cache)
-			return -ENOMEM;
 	}
 
 	drv->num_tcs = st;
@@ -620,7 +934,11 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 {
 	struct device_node *dn = pdev->dev.of_node;
 	struct rsc_drv *drv;
+	struct resource *res;
+	char drv_id[10] = {0};
 	int ret, irq;
+	u32 solver_config;
+	void __iomem *base;
 
 	/*
 	 * Even though RPMh doesn't directly use cmd-db, all of its children
@@ -646,7 +964,13 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 	if (!drv->name)
 		drv->name = dev_name(&pdev->dev);
 
-	ret = rpmh_probe_tcs_config(pdev, drv);
+	snprintf(drv_id, ARRAY_SIZE(drv_id), "drv-%d", drv->id);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, drv_id);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	ret = rpmh_probe_tcs_config(pdev, drv, base);
 	if (ret)
 		return ret;
 
@@ -663,8 +987,22 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	/*
+	 * CPU PM notification are not required for controllers that support
+	 * 'HW solver' mode where they can be in autonomous mode executing low
+	 * power mode to power down.
+	 */
+	solver_config = readl_relaxed(base + DRV_SOLVER_CONFIG);
+	solver_config &= DRV_HW_SOLVER_MASK << DRV_HW_SOLVER_SHIFT;
+	solver_config = solver_config >> DRV_HW_SOLVER_SHIFT;
+	if (!solver_config) {
+		drv->rsc_pm.notifier_call = rpmh_rsc_cpu_pm_callback;
+		cpu_pm_register_notifier(&drv->rsc_pm);
+	}
+
 	/* Enable the active TCS to send requests immediately */
-	write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask);
+	writel_relaxed(drv->tcs[ACTIVE_TCS].mask,
+		       drv->tcs_base + RSC_DRV_IRQ_ENABLE);
 
 	spin_lock_init(&drv->client.cache_lock);
 	INIT_LIST_HEAD(&drv->client.cache);
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
index eb0ded059d2e..f2b5b46ccd1f 100644
--- a/drivers/soc/qcom/rpmh.c
+++ b/drivers/soc/qcom/rpmh.c
@@ -9,6 +9,7 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/lockdep.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -119,6 +120,7 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr,
 {
 	struct cache_req *req;
 	unsigned long flags;
+	u32 old_sleep_val, old_wake_val;
 
 	spin_lock_irqsave(&ctrlr->cache_lock, flags);
 	req = __find_req(ctrlr, cmd->addr);
@@ -133,26 +135,27 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr,
 
 	req->addr = cmd->addr;
 	req->sleep_val = req->wake_val = UINT_MAX;
-	INIT_LIST_HEAD(&req->list);
 	list_add_tail(&req->list, &ctrlr->cache);
 
 existing:
+	old_sleep_val = req->sleep_val;
+	old_wake_val = req->wake_val;
+
 	switch (state) {
 	case RPMH_ACTIVE_ONLY_STATE:
-		if (req->sleep_val != UINT_MAX)
-			req->wake_val = cmd->data;
-		break;
 	case RPMH_WAKE_ONLY_STATE:
 		req->wake_val = cmd->data;
 		break;
 	case RPMH_SLEEP_STATE:
 		req->sleep_val = cmd->data;
 		break;
-	default:
-		break;
 	}
 
-	ctrlr->dirty = true;
+	ctrlr->dirty |= (req->sleep_val != old_sleep_val ||
+			 req->wake_val != old_wake_val) &&
+			 req->sleep_val != UINT_MAX &&
+			 req->wake_val != UINT_MAX;
+
 unlock:
 	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
 
@@ -287,6 +290,7 @@ static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req)
 
 	spin_lock_irqsave(&ctrlr->cache_lock, flags);
 	list_add_tail(&req->list, &ctrlr->batch_cache);
+	ctrlr->dirty = true;
 	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
 }
 
@@ -294,12 +298,10 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr)
 {
 	struct batch_cache_req *req;
 	const struct rpmh_request *rpm_msg;
-	unsigned long flags;
 	int ret = 0;
 	int i;
 
 	/* Send Sleep/Wake requests to the controller, expect no response */
-	spin_lock_irqsave(&ctrlr->cache_lock, flags);
 	list_for_each_entry(req, &ctrlr->batch_cache, list) {
 		for (i = 0; i < req->count; i++) {
 			rpm_msg = req->rpm_msgs + i;
@@ -309,23 +311,10 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr)
 				break;
 		}
 	}
-	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
 
 	return ret;
 }
 
-static void invalidate_batch(struct rpmh_ctrlr *ctrlr)
-{
-	struct batch_cache_req *req, *tmp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctrlr->cache_lock, flags);
-	list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list)
-		kfree(req);
-	INIT_LIST_HEAD(&ctrlr->batch_cache);
-	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
-}
-
 /**
  * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the
  * batch to finish.
@@ -442,36 +431,42 @@ static int send_single(struct rpmh_ctrlr *ctrlr, enum rpmh_state state,
 }
 
 /**
- * rpmh_flush: Flushes the buffered active and sleep sets to TCS
- *
- * @ctrlr: controller making request to flush cached data
+ * rpmh_flush() - Flushes the buffered sleep and wake sets to TCSes
  *
- * Return: -EBUSY if the controller is busy, probably waiting on a response
- * to a RPMH request sent earlier.
+ * @ctrlr: Controller making request to flush cached data
  *
- * This function is always called from the sleep code from the last CPU
- * that is powering down the entire system. Since no other RPMH API would be
- * executing at this time, it is safe to run lockless.
+ * Return:
+ * * 0          - Success
+ * * Error code - Otherwise
  */
 int rpmh_flush(struct rpmh_ctrlr *ctrlr)
 {
 	struct cache_req *p;
-	int ret;
+	int ret = 0;
+
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Currently rpmh_flush() is only called when we think we're running
+	 * on the last processor.  If the lock is busy it means another
+	 * processor is up and it's better to abort than spin.
+	 */
+	if (!spin_trylock(&ctrlr->cache_lock))
+		return -EBUSY;
 
 	if (!ctrlr->dirty) {
 		pr_debug("Skipping flush, TCS has latest data.\n");
-		return 0;
+		goto exit;
 	}
 
+	/* Invalidate the TCSes first to avoid stale data */
+	rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr));
+
 	/* First flush the cached batch requests */
 	ret = flush_batch(ctrlr);
 	if (ret)
-		return ret;
+		goto exit;
 
-	/*
-	 * Nobody else should be calling this function other than system PM,
-	 * hence we can run without locks.
-	 */
 	list_for_each_entry(p, &ctrlr->cache, list) {
 		if (!is_req_valid(p)) {
 			pr_debug("%s: skipping RPMH req: a:%#x s:%#x w:%#x",
@@ -481,38 +476,40 @@ int rpmh_flush(struct rpmh_ctrlr *ctrlr)
 		ret = send_single(ctrlr, RPMH_SLEEP_STATE, p->addr,
 				  p->sleep_val);
 		if (ret)
-			return ret;
+			goto exit;
 		ret = send_single(ctrlr, RPMH_WAKE_ONLY_STATE, p->addr,
 				  p->wake_val);
 		if (ret)
-			return ret;
+			goto exit;
 	}
 
 	ctrlr->dirty = false;
 
-	return 0;
+exit:
+	spin_unlock(&ctrlr->cache_lock);
+	return ret;
 }
 
 /**
- * rpmh_invalidate: Invalidate all sleep and active sets
- * sets.
+ * rpmh_invalidate: Invalidate sleep and wake sets in batch_cache
  *
  * @dev: The device making the request
  *
- * Invalidate the sleep and active values in the TCS blocks.
+ * Invalidate the sleep and wake values in batch_cache.
  */
 int rpmh_invalidate(const struct device *dev)
 {
 	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
-	int ret;
+	struct batch_cache_req *req, *tmp;
+	unsigned long flags;
 
-	invalidate_batch(ctrlr);
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list)
+		kfree(req);
+	INIT_LIST_HEAD(&ctrlr->batch_cache);
 	ctrlr->dirty = true;
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
 
-	do {
-		ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr));
-	} while (ret == -EAGAIN);
-
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(rpmh_invalidate);
diff --git a/drivers/soc/qcom/rpmhpd.c b/drivers/soc/qcom/rpmhpd.c
index 4d264d0672c4..e72426221a69 100644
--- a/drivers/soc/qcom/rpmhpd.c
+++ b/drivers/soc/qcom/rpmhpd.c
@@ -4,6 +4,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/pm_domain.h>
 #include <linux/slab.h>
@@ -166,6 +167,24 @@ static const struct rpmhpd_desc sm8150_desc = {
 	.num_pds = ARRAY_SIZE(sm8150_rpmhpds),
 };
 
+static struct rpmhpd *sm8250_rpmhpds[] = {
+	[SM8250_CX] = &sdm845_cx,
+	[SM8250_CX_AO] = &sdm845_cx_ao,
+	[SM8250_EBI] = &sdm845_ebi,
+	[SM8250_GFX] = &sdm845_gfx,
+	[SM8250_LCX] = &sdm845_lcx,
+	[SM8250_LMX] = &sdm845_lmx,
+	[SM8250_MMCX] = &sm8150_mmcx,
+	[SM8250_MMCX_AO] = &sm8150_mmcx_ao,
+	[SM8250_MX] = &sdm845_mx,
+	[SM8250_MX_AO] = &sdm845_mx_ao,
+};
+
+static const struct rpmhpd_desc sm8250_desc = {
+	.rpmhpds = sm8250_rpmhpds,
+	.num_pds = ARRAY_SIZE(sm8250_rpmhpds),
+};
+
 /* SC7180 RPMH powerdomains */
 static struct rpmhpd *sc7180_rpmhpds[] = {
 	[SC7180_CX] = &sdm845_cx,
@@ -187,8 +206,10 @@ static const struct of_device_id rpmhpd_match_table[] = {
 	{ .compatible = "qcom,sc7180-rpmhpd", .data = &sc7180_desc },
 	{ .compatible = "qcom,sdm845-rpmhpd", .data = &sdm845_desc },
 	{ .compatible = "qcom,sm8150-rpmhpd", .data = &sm8150_desc },
+	{ .compatible = "qcom,sm8250-rpmhpd", .data = &sm8250_desc },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, rpmhpd_match_table);
 
 static int rpmhpd_send_corner(struct rpmhpd *pd, int state,
 			      unsigned int corner, bool sync)
@@ -460,3 +481,6 @@ static int __init rpmhpd_init(void)
 	return platform_driver_register(&rpmhpd_driver);
 }
 core_initcall(rpmhpd_init);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. RPMh Power Domain Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/rpmpd.c b/drivers/soc/qcom/rpmpd.c
index 2b1834c5609a..f2168e4259b2 100644
--- a/drivers/soc/qcom/rpmpd.c
+++ b/drivers/soc/qcom/rpmpd.c
@@ -4,6 +4,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/pm_domain.h>
 #include <linux/of.h>
@@ -226,6 +227,7 @@ static const struct of_device_id rpmpd_match_table[] = {
 	{ .compatible = "qcom,qcs404-rpmpd", .data = &qcs404_desc },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, rpmpd_match_table);
 
 static int rpmpd_send_enable(struct rpmpd *pd, bool enable)
 {
@@ -422,3 +424,6 @@ static int __init rpmpd_init(void)
 	return platform_driver_register(&rpmpd_driver);
 }
 core_initcall(rpmpd_init);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. RPM Power Domain Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/smp2p.c b/drivers/soc/qcom/smp2p.c
index c7300d54e444..07183d731d74 100644
--- a/drivers/soc/qcom/smp2p.c
+++ b/drivers/soc/qcom/smp2p.c
@@ -474,10 +474,8 @@ static int qcom_smp2p_probe(struct platform_device *pdev)
 		goto report_read_failure;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "unable to acquire smp2p interrupt\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	smp2p->mbox_client.dev = &pdev->dev;
 	smp2p->mbox_client.knows_txdone = true;
diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c
index ebb49aee179b..5983c6ffb078 100644
--- a/drivers/soc/qcom/socinfo.c
+++ b/drivers/soc/qcom/socinfo.c
@@ -188,6 +188,10 @@ static const struct soc_id soc_id[] = {
 	{ 216, "MSM8674PRO" },
 	{ 217, "MSM8974-AA" },
 	{ 218, "MSM8974-AB" },
+	{ 233, "MSM8936" },
+	{ 239, "MSM8939" },
+	{ 240, "APQ8036" },
+	{ 241, "APQ8039" },
 	{ 246, "MSM8996" },
 	{ 247, "APQ8016" },
 	{ 248, "MSM8216" },
@@ -430,6 +434,8 @@ static int qcom_socinfo_probe(struct platform_device *pdev)
 	qs->attr.family = "Snapdragon";
 	qs->attr.machine = socinfo_machine(&pdev->dev,
 					   le32_to_cpu(info->id));
+	qs->attr.soc_id = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%u",
+					 le32_to_cpu(info->id));
 	qs->attr.revision = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%u.%u",
 					   SOCINFO_MAJOR(le32_to_cpu(info->ver)),
 					   SOCINFO_MINOR(le32_to_cpu(info->ver)));