Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig
index f9ad8ad..4df32bc 100644
--- a/drivers/soc/fsl/Kconfig
+++ b/drivers/soc/fsl/Kconfig
@@ -40,4 +40,14 @@
 	  /dev/dpaa2_mc_console and /dev/dpaa2_aiop_console,
 	  which can be used to dump the Management Complex and AIOP
 	  firmware logs.
+
+config FSL_RCPM
+	bool "Freescale RCPM support"
+	depends on PM_SLEEP && (ARM || ARM64)
+	help
+	  The NXP QorIQ Processors based on ARM Core have RCPM module
+	  (Run Control and Power Management), which performs all device-level
+	  tasks associated with power management, such as wakeup source control.
+	  Note that currently this driver will not support PowerPC based
+	  QorIQ processor.
 endmenu
diff --git a/drivers/soc/fsl/Makefile b/drivers/soc/fsl/Makefile
index 71dee8d..906f1cd 100644
--- a/drivers/soc/fsl/Makefile
+++ b/drivers/soc/fsl/Makefile
@@ -6,6 +6,7 @@
 obj-$(CONFIG_FSL_DPAA)                 += qbman/
 obj-$(CONFIG_QUICC_ENGINE)		+= qe/
 obj-$(CONFIG_CPM)			+= qe/
+obj-$(CONFIG_FSL_RCPM)			+= rcpm.o
 obj-$(CONFIG_FSL_GUTS)			+= guts.o
 obj-$(CONFIG_FSL_MC_DPIO) 		+= dpio/
 obj-$(CONFIG_DPAA2_CONSOLE)		+= dpaa2-console.o
diff --git a/drivers/soc/fsl/dpaa2-console.c b/drivers/soc/fsl/dpaa2-console.c
index 27243f7..5391741 100644
--- a/drivers/soc/fsl/dpaa2-console.c
+++ b/drivers/soc/fsl/dpaa2-console.c
@@ -231,6 +231,7 @@
 	cd->cur_ptr += bytes;
 	written += bytes;
 
+	kfree(kbuf);
 	return written;
 
 err_free_buf:
diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c
index 518a8e0..779c319 100644
--- a/drivers/soc/fsl/dpio/dpio-service.c
+++ b/drivers/soc/fsl/dpio/dpio-service.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
 /*
  * Copyright 2014-2016 Freescale Semiconductor Inc.
- * Copyright 2016 NXP
+ * Copyright 2016-2019 NXP
  *
  */
 #include <linux/types.h>
@@ -58,8 +58,8 @@
 	 * If cpu == -1, choose the current cpu, with no guarantees about
 	 * potentially being migrated away.
 	 */
-	if (unlikely(cpu < 0))
-		cpu = smp_processor_id();
+	if (cpu < 0)
+		cpu = raw_smp_processor_id();
 
 	/* If a specific cpu was requested, pick it up immediately */
 	return dpio_by_cpu[cpu];
@@ -70,6 +70,10 @@
 	if (d)
 		return d;
 
+	d = service_select_by_cpu(d, -1);
+	if (d)
+		return d;
+
 	spin_lock(&dpio_list_lock);
 	d = list_entry(dpio_list.next, struct dpaa2_io, node);
 	list_del(&d->node);
@@ -433,6 +437,78 @@
 EXPORT_SYMBOL(dpaa2_io_service_enqueue_fq);
 
 /**
+ * dpaa2_io_service_enqueue_multiple_fq() - Enqueue multiple frames
+ * to a frame queue using one fqid.
+ * @d: the given DPIO service.
+ * @fqid: the given frame queue id.
+ * @fd: the frame descriptor which is enqueued.
+ * @nb: number of frames to be enqueud
+ *
+ * Return 0 for successful enqueue, -EBUSY if the enqueue ring is not ready,
+ * or -ENODEV if there is no dpio service.
+ */
+int dpaa2_io_service_enqueue_multiple_fq(struct dpaa2_io *d,
+				u32 fqid,
+				const struct dpaa2_fd *fd,
+				int nb)
+{
+	struct qbman_eq_desc ed;
+
+	d = service_select(d);
+	if (!d)
+		return -ENODEV;
+
+	qbman_eq_desc_clear(&ed);
+	qbman_eq_desc_set_no_orp(&ed, 0);
+	qbman_eq_desc_set_fq(&ed, fqid);
+
+	return qbman_swp_enqueue_multiple(d->swp, &ed, fd, 0, nb);
+}
+EXPORT_SYMBOL(dpaa2_io_service_enqueue_multiple_fq);
+
+/**
+ * dpaa2_io_service_enqueue_multiple_desc_fq() - Enqueue multiple frames
+ * to different frame queue using a list of fqids.
+ * @d: the given DPIO service.
+ * @fqid: the given list of frame queue ids.
+ * @fd: the frame descriptor which is enqueued.
+ * @nb: number of frames to be enqueud
+ *
+ * Return 0 for successful enqueue, -EBUSY if the enqueue ring is not ready,
+ * or -ENODEV if there is no dpio service.
+ */
+int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d,
+				u32 *fqid,
+				const struct dpaa2_fd *fd,
+				int nb)
+{
+	struct qbman_eq_desc *ed;
+	int i, ret;
+
+	ed = kcalloc(sizeof(struct qbman_eq_desc), 32, GFP_KERNEL);
+	if (!ed)
+		return -ENOMEM;
+
+	d = service_select(d);
+	if (!d) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	for (i = 0; i < nb; i++) {
+		qbman_eq_desc_clear(&ed[i]);
+		qbman_eq_desc_set_no_orp(&ed[i], 0);
+		qbman_eq_desc_set_fq(&ed[i], fqid[i]);
+	}
+
+	ret = qbman_swp_enqueue_multiple_desc(d->swp, &ed[0], fd, nb);
+out:
+	kfree(ed);
+	return ret;
+}
+EXPORT_SYMBOL(dpaa2_io_service_enqueue_multiple_desc_fq);
+
+/**
  * dpaa2_io_service_enqueue_qd() - Enqueue a frame to a QD.
  * @d: the given DPIO service.
  * @qdid: the given queuing destination id.
@@ -526,7 +602,7 @@
 
 /**
  * dpaa2_io_store_create() - Create the dma memory storage for dequeue result.
- * @max_frames: the maximum number of dequeued result for frames, must be <= 16.
+ * @max_frames: the maximum number of dequeued result for frames, must be <= 32.
  * @dev:        the device to allow mapping/unmapping the DMAable region.
  *
  * The size of the storage is "max_frames*sizeof(struct dpaa2_dq)".
@@ -541,7 +617,7 @@
 	struct dpaa2_io_store *ret;
 	size_t size;
 
-	if (!max_frames || (max_frames > 16))
+	if (!max_frames || (max_frames > 32))
 		return NULL;
 
 	ret = kmalloc(sizeof(*ret), GFP_KERNEL);
diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c
index c66f5b7..3d69f56 100644
--- a/drivers/soc/fsl/dpio/qbman-portal.c
+++ b/drivers/soc/fsl/dpio/qbman-portal.c
@@ -1,24 +1,18 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
 /*
  * Copyright (C) 2014-2016 Freescale Semiconductor, Inc.
- * Copyright 2016 NXP
+ * Copyright 2016-2019 NXP
  *
  */
 
 #include <asm/cacheflush.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <soc/fsl/dpaa2-global.h>
 
 #include "qbman-portal.h"
 
-#define QMAN_REV_4000   0x04000000
-#define QMAN_REV_4100   0x04010000
-#define QMAN_REV_4101   0x04010001
-#define QMAN_REV_5000   0x05000000
-
-#define QMAN_REV_MASK   0xffff0000
-
 /* All QBMan command and result structures use this "valid bit" encoding */
 #define QB_VALID_BIT ((u32)0x80)
 
@@ -28,6 +22,7 @@
 
 /* CINH register offsets */
 #define QBMAN_CINH_SWP_EQCR_PI      0x800
+#define QBMAN_CINH_SWP_EQCR_CI	    0x840
 #define QBMAN_CINH_SWP_EQAR    0x8c0
 #define QBMAN_CINH_SWP_CR_RT        0x900
 #define QBMAN_CINH_SWP_VDQCR_RT     0x940
@@ -51,6 +46,8 @@
 #define QBMAN_CENA_SWP_CR      0x600
 #define QBMAN_CENA_SWP_RR(vb)  (0x700 + ((u32)(vb) >> 1))
 #define QBMAN_CENA_SWP_VDQCR   0x780
+#define QBMAN_CENA_SWP_EQCR_CI 0x840
+#define QBMAN_CENA_SWP_EQCR_CI_MEMBACK 0x1840
 
 /* CENA register offsets in memory-backed mode */
 #define QBMAN_CENA_SWP_DQRR_MEM(n)  (0x800 + ((u32)(n) << 6))
@@ -78,6 +75,12 @@
 /* opaque token for static dequeues */
 #define QMAN_SDQCR_TOKEN    0xbb
 
+#define QBMAN_EQCR_DCA_IDXMASK          0x0f
+#define QBMAN_ENQUEUE_FLAG_DCA          (1ULL << 31)
+
+#define EQ_DESC_SIZE_WITHOUT_FD 29
+#define EQ_DESC_SIZE_FD_START 32
+
 enum qbman_sdqcr_dct {
 	qbman_sdqcr_dct_null = 0,
 	qbman_sdqcr_dct_prio_ics,
@@ -90,6 +93,82 @@
 	qbman_sdqcr_fc_up_to_3 = 1
 };
 
+/* Internal Function declaration */
+static int qbman_swp_enqueue_direct(struct qbman_swp *s,
+				    const struct qbman_eq_desc *d,
+				    const struct dpaa2_fd *fd);
+static int qbman_swp_enqueue_mem_back(struct qbman_swp *s,
+				      const struct qbman_eq_desc *d,
+				      const struct dpaa2_fd *fd);
+static int qbman_swp_enqueue_multiple_direct(struct qbman_swp *s,
+					     const struct qbman_eq_desc *d,
+					     const struct dpaa2_fd *fd,
+					     uint32_t *flags,
+					     int num_frames);
+static int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s,
+					       const struct qbman_eq_desc *d,
+					       const struct dpaa2_fd *fd,
+					       uint32_t *flags,
+					       int num_frames);
+static int
+qbman_swp_enqueue_multiple_desc_direct(struct qbman_swp *s,
+				       const struct qbman_eq_desc *d,
+				       const struct dpaa2_fd *fd,
+				       int num_frames);
+static
+int qbman_swp_enqueue_multiple_desc_mem_back(struct qbman_swp *s,
+					     const struct qbman_eq_desc *d,
+					     const struct dpaa2_fd *fd,
+					     int num_frames);
+static int qbman_swp_pull_direct(struct qbman_swp *s,
+				 struct qbman_pull_desc *d);
+static int qbman_swp_pull_mem_back(struct qbman_swp *s,
+				   struct qbman_pull_desc *d);
+
+const struct dpaa2_dq *qbman_swp_dqrr_next_direct(struct qbman_swp *s);
+const struct dpaa2_dq *qbman_swp_dqrr_next_mem_back(struct qbman_swp *s);
+
+static int qbman_swp_release_direct(struct qbman_swp *s,
+				    const struct qbman_release_desc *d,
+				    const u64 *buffers,
+				    unsigned int num_buffers);
+static int qbman_swp_release_mem_back(struct qbman_swp *s,
+				      const struct qbman_release_desc *d,
+				      const u64 *buffers,
+				      unsigned int num_buffers);
+
+/* Function pointers */
+int (*qbman_swp_enqueue_ptr)(struct qbman_swp *s,
+			     const struct qbman_eq_desc *d,
+			     const struct dpaa2_fd *fd)
+	= qbman_swp_enqueue_direct;
+
+int (*qbman_swp_enqueue_multiple_ptr)(struct qbman_swp *s,
+				      const struct qbman_eq_desc *d,
+				      const struct dpaa2_fd *fd,
+				      uint32_t *flags,
+					     int num_frames)
+	= qbman_swp_enqueue_multiple_direct;
+
+int
+(*qbman_swp_enqueue_multiple_desc_ptr)(struct qbman_swp *s,
+				       const struct qbman_eq_desc *d,
+				       const struct dpaa2_fd *fd,
+				       int num_frames)
+	= qbman_swp_enqueue_multiple_desc_direct;
+
+int (*qbman_swp_pull_ptr)(struct qbman_swp *s, struct qbman_pull_desc *d)
+			= qbman_swp_pull_direct;
+
+const struct dpaa2_dq *(*qbman_swp_dqrr_next_ptr)(struct qbman_swp *s)
+			= qbman_swp_dqrr_next_direct;
+
+int (*qbman_swp_release_ptr)(struct qbman_swp *s,
+			     const struct qbman_release_desc *d,
+			     const u64 *buffers,
+			     unsigned int num_buffers)
+			= qbman_swp_release_direct;
+
 /* Portal Access */
 
 static inline u32 qbman_read_register(struct qbman_swp *p, u32 offset)
@@ -146,6 +225,15 @@
 
 #define QMAN_RT_MODE	   0x00000100
 
+static inline u8 qm_cyc_diff(u8 ringsize, u8 first, u8 last)
+{
+	/* 'first' is included, 'last' is excluded */
+	if (first <= last)
+		return last - first;
+	else
+		return (2 * ringsize) - (first - last);
+}
+
 /**
  * qbman_swp_init() - Create a functional object representing the given
  *                    QBMan portal descriptor.
@@ -156,11 +244,16 @@
  */
 struct qbman_swp *qbman_swp_init(const struct qbman_swp_desc *d)
 {
-	struct qbman_swp *p = kmalloc(sizeof(*p), GFP_KERNEL);
+	struct qbman_swp *p = kzalloc(sizeof(*p), GFP_KERNEL);
 	u32 reg;
+	u32 mask_size;
+	u32 eqcr_pi;
 
 	if (!p)
 		return NULL;
+
+	spin_lock_init(&p->access_spinlock);
+
 	p->desc = d;
 	p->mc.valid_bit = QB_VALID_BIT;
 	p->sdq = 0;
@@ -186,25 +279,38 @@
 	p->addr_cena = d->cena_bar;
 	p->addr_cinh = d->cinh_bar;
 
-	if ((p->desc->qman_version & QMAN_REV_MASK) >= QMAN_REV_5000)
-		memset(p->addr_cena, 0, 64 * 1024);
+	if ((p->desc->qman_version & QMAN_REV_MASK) < QMAN_REV_5000) {
 
-	reg = qbman_set_swp_cfg(p->dqrr.dqrr_size,
-				1, /* Writes Non-cacheable */
-				0, /* EQCR_CI stashing threshold */
-				3, /* RPM: Valid bit mode, RCR in array mode */
-				2, /* DCM: Discrete consumption ack mode */
-				3, /* EPM: Valid bit mode, EQCR in array mode */
-				1, /* mem stashing drop enable == TRUE */
-				1, /* mem stashing priority == TRUE */
-				1, /* mem stashing enable == TRUE */
-				1, /* dequeue stashing priority == TRUE */
-				0, /* dequeue stashing enable == FALSE */
-				0); /* EQCR_CI stashing priority == FALSE */
-	if ((p->desc->qman_version & QMAN_REV_MASK) >= QMAN_REV_5000)
+		reg = qbman_set_swp_cfg(p->dqrr.dqrr_size,
+			1, /* Writes Non-cacheable */
+			0, /* EQCR_CI stashing threshold */
+			3, /* RPM: RCR in array mode */
+			2, /* DCM: Discrete consumption ack */
+			2, /* EPM: EQCR in ring mode */
+			1, /* mem stashing drop enable enable */
+			1, /* mem stashing priority enable */
+			1, /* mem stashing enable */
+			1, /* dequeue stashing priority enable */
+			0, /* dequeue stashing enable enable */
+			0); /* EQCR_CI stashing priority enable */
+	} else {
+		memset(p->addr_cena, 0, 64 * 1024);
+		reg = qbman_set_swp_cfg(p->dqrr.dqrr_size,
+			1, /* Writes Non-cacheable */
+			1, /* EQCR_CI stashing threshold */
+			3, /* RPM: RCR in array mode */
+			2, /* DCM: Discrete consumption ack */
+			0, /* EPM: EQCR in ring mode */
+			1, /* mem stashing drop enable */
+			1, /* mem stashing priority enable */
+			1, /* mem stashing enable */
+			1, /* dequeue stashing priority enable */
+			0, /* dequeue stashing enable */
+			0); /* EQCR_CI stashing priority enable */
 		reg |= 1 << SWP_CFG_CPBS_SHIFT | /* memory-backed mode */
 		       1 << SWP_CFG_VPM_SHIFT |  /* VDQCR read triggered mode */
 		       1 << SWP_CFG_CPM_SHIFT;   /* CR read triggered mode */
+	}
 
 	qbman_write_register(p, QBMAN_CINH_SWP_CFG, reg);
 	reg = qbman_read_register(p, QBMAN_CINH_SWP_CFG);
@@ -225,6 +331,30 @@
 	 * applied when dequeues from a specific channel are enabled.
 	 */
 	qbman_write_register(p, QBMAN_CINH_SWP_SDQCR, 0);
+
+	p->eqcr.pi_ring_size = 8;
+	if ((p->desc->qman_version & QMAN_REV_MASK) >= QMAN_REV_5000) {
+		p->eqcr.pi_ring_size = 32;
+		qbman_swp_enqueue_ptr =
+			qbman_swp_enqueue_mem_back;
+		qbman_swp_enqueue_multiple_ptr =
+			qbman_swp_enqueue_multiple_mem_back;
+		qbman_swp_enqueue_multiple_desc_ptr =
+			qbman_swp_enqueue_multiple_desc_mem_back;
+		qbman_swp_pull_ptr = qbman_swp_pull_mem_back;
+		qbman_swp_dqrr_next_ptr = qbman_swp_dqrr_next_mem_back;
+		qbman_swp_release_ptr = qbman_swp_release_mem_back;
+	}
+
+	for (mask_size = p->eqcr.pi_ring_size; mask_size > 0; mask_size >>= 1)
+		p->eqcr.pi_ci_mask = (p->eqcr.pi_ci_mask << 1) + 1;
+	eqcr_pi = qbman_read_register(p, QBMAN_CINH_SWP_EQCR_PI);
+	p->eqcr.pi = eqcr_pi & p->eqcr.pi_ci_mask;
+	p->eqcr.pi_vb = eqcr_pi & QB_VALID_BIT;
+	p->eqcr.ci = qbman_read_register(p, QBMAN_CINH_SWP_EQCR_CI)
+			& p->eqcr.pi_ci_mask;
+	p->eqcr.available = p->eqcr.pi_ring_size;
+
 	return p;
 }
 
@@ -378,6 +508,7 @@
 #define QB_ENQUEUE_CMD_ORP_ENABLE_SHIFT      2
 #define QB_ENQUEUE_CMD_IRQ_ON_DISPATCH_SHIFT 3
 #define QB_ENQUEUE_CMD_TARGET_TYPE_SHIFT     4
+#define QB_ENQUEUE_CMD_DCA_EN_SHIFT          7
 
 /**
  * qbman_eq_desc_clear() - Clear the contents of a descriptor to
@@ -441,20 +572,9 @@
 #define EQAR_VB(eqar)      ((eqar) & 0x80)
 #define EQAR_SUCCESS(eqar) ((eqar) & 0x100)
 
-static inline void qbman_write_eqcr_am_rt_register(struct qbman_swp *p,
-						   u8 idx)
-{
-	if (idx < 16)
-		qbman_write_register(p, QBMAN_CINH_SWP_EQCR_AM_RT + idx * 4,
-				     QMAN_RT_MODE);
-	else
-		qbman_write_register(p, QBMAN_CINH_SWP_EQCR_AM_RT2 +
-				     (idx - 16) * 4,
-				     QMAN_RT_MODE);
-}
-
+#define QB_RT_BIT ((u32)0x100)
 /**
- * qbman_swp_enqueue() - Issue an enqueue command
+ * qbman_swp_enqueue_direct() - Issue an enqueue command
  * @s:  the software portal used for enqueue
  * @d:  the enqueue descriptor
  * @fd: the frame descriptor to be enqueued
@@ -464,30 +584,345 @@
  *
  * Return 0 for successful enqueue, -EBUSY if the EQCR is not ready.
  */
-int qbman_swp_enqueue(struct qbman_swp *s, const struct qbman_eq_desc *d,
-		      const struct dpaa2_fd *fd)
+static
+int qbman_swp_enqueue_direct(struct qbman_swp *s,
+			     const struct qbman_eq_desc *d,
+			     const struct dpaa2_fd *fd)
 {
-	struct qbman_eq_desc *p;
-	u32 eqar = qbman_read_register(s, QBMAN_CINH_SWP_EQAR);
+	int flags = 0;
+	int ret = qbman_swp_enqueue_multiple_direct(s, d, fd, &flags, 1);
 
-	if (!EQAR_SUCCESS(eqar))
-		return -EBUSY;
+	if (ret >= 0)
+		ret = 0;
+	else
+		ret = -EBUSY;
+	return  ret;
+}
 
-	p = qbman_get_cmd(s, QBMAN_CENA_SWP_EQCR(EQAR_IDX(eqar)));
-	memcpy(&p->dca, &d->dca, 31);
-	memcpy(&p->fd, fd, sizeof(*fd));
+/**
+ * qbman_swp_enqueue_mem_back() - Issue an enqueue command
+ * @s:  the software portal used for enqueue
+ * @d:  the enqueue descriptor
+ * @fd: the frame descriptor to be enqueued
+ *
+ * Please note that 'fd' should only be NULL if the "action" of the
+ * descriptor is "orp_hole" or "orp_nesn".
+ *
+ * Return 0 for successful enqueue, -EBUSY if the EQCR is not ready.
+ */
+static
+int qbman_swp_enqueue_mem_back(struct qbman_swp *s,
+			       const struct qbman_eq_desc *d,
+			       const struct dpaa2_fd *fd)
+{
+	int flags = 0;
+	int ret = qbman_swp_enqueue_multiple_mem_back(s, d, fd, &flags, 1);
 
-	if ((s->desc->qman_version & QMAN_REV_MASK) < QMAN_REV_5000) {
-		/* Set the verb byte, have to substitute in the valid-bit */
-		dma_wmb();
-		p->verb = d->verb | EQAR_VB(eqar);
-	} else {
-		p->verb = d->verb | EQAR_VB(eqar);
-		dma_wmb();
-		qbman_write_eqcr_am_rt_register(s, EQAR_IDX(eqar));
+	if (ret >= 0)
+		ret = 0;
+	else
+		ret = -EBUSY;
+	return  ret;
+}
+
+/**
+ * qbman_swp_enqueue_multiple_direct() - Issue a multi enqueue command
+ * using one enqueue descriptor
+ * @s:  the software portal used for enqueue
+ * @d:  the enqueue descriptor
+ * @fd: table pointer of frame descriptor table to be enqueued
+ * @flags: table pointer of QBMAN_ENQUEUE_FLAG_DCA flags, not used if NULL
+ * @num_frames: number of fd to be enqueued
+ *
+ * Return the number of fd enqueued, or a negative error number.
+ */
+static
+int qbman_swp_enqueue_multiple_direct(struct qbman_swp *s,
+				      const struct qbman_eq_desc *d,
+				      const struct dpaa2_fd *fd,
+				      uint32_t *flags,
+				      int num_frames)
+{
+	uint32_t *p = NULL;
+	const uint32_t *cl = (uint32_t *)d;
+	uint32_t eqcr_ci, eqcr_pi, half_mask, full_mask;
+	int i, num_enqueued = 0;
+
+	spin_lock(&s->access_spinlock);
+	half_mask = (s->eqcr.pi_ci_mask>>1);
+	full_mask = s->eqcr.pi_ci_mask;
+
+	if (!s->eqcr.available) {
+		eqcr_ci = s->eqcr.ci;
+		p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI;
+		s->eqcr.ci = qbman_read_register(s, QBMAN_CINH_SWP_EQCR_CI);
+		s->eqcr.ci &= full_mask;
+
+		s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size,
+					eqcr_ci, s->eqcr.ci);
+		if (!s->eqcr.available) {
+			spin_unlock(&s->access_spinlock);
+			return 0;
+		}
 	}
 
-	return 0;
+	eqcr_pi = s->eqcr.pi;
+	num_enqueued = (s->eqcr.available < num_frames) ?
+			s->eqcr.available : num_frames;
+	s->eqcr.available -= num_enqueued;
+	/* Fill in the EQCR ring */
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		/* Skip copying the verb */
+		memcpy(&p[1], &cl[1], EQ_DESC_SIZE_WITHOUT_FD - 1);
+		memcpy(&p[EQ_DESC_SIZE_FD_START/sizeof(uint32_t)],
+		       &fd[i], sizeof(*fd));
+		eqcr_pi++;
+	}
+
+	dma_wmb();
+
+	/* Set the verb byte, have to substitute in the valid-bit */
+	eqcr_pi = s->eqcr.pi;
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		p[0] = cl[0] | s->eqcr.pi_vb;
+		if (flags && (flags[i] & QBMAN_ENQUEUE_FLAG_DCA)) {
+			struct qbman_eq_desc *d = (struct qbman_eq_desc *)p;
+
+			d->dca = (1 << QB_ENQUEUE_CMD_DCA_EN_SHIFT) |
+				((flags[i]) & QBMAN_EQCR_DCA_IDXMASK);
+		}
+		eqcr_pi++;
+		if (!(eqcr_pi & half_mask))
+			s->eqcr.pi_vb ^= QB_VALID_BIT;
+	}
+
+	/* Flush all the cacheline without load/store in between */
+	eqcr_pi = s->eqcr.pi;
+	for (i = 0; i < num_enqueued; i++)
+		eqcr_pi++;
+	s->eqcr.pi = eqcr_pi & full_mask;
+	spin_unlock(&s->access_spinlock);
+
+	return num_enqueued;
+}
+
+/**
+ * qbman_swp_enqueue_multiple_mem_back() - Issue a multi enqueue command
+ * using one enqueue descriptor
+ * @s:  the software portal used for enqueue
+ * @d:  the enqueue descriptor
+ * @fd: table pointer of frame descriptor table to be enqueued
+ * @flags: table pointer of QBMAN_ENQUEUE_FLAG_DCA flags, not used if NULL
+ * @num_frames: number of fd to be enqueued
+ *
+ * Return the number of fd enqueued, or a negative error number.
+ */
+static
+int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s,
+					const struct qbman_eq_desc *d,
+					const struct dpaa2_fd *fd,
+					uint32_t *flags,
+					int num_frames)
+{
+	uint32_t *p = NULL;
+	const uint32_t *cl = (uint32_t *)(d);
+	uint32_t eqcr_ci, eqcr_pi, half_mask, full_mask;
+	int i, num_enqueued = 0;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&s->access_spinlock, irq_flags);
+
+	half_mask = (s->eqcr.pi_ci_mask>>1);
+	full_mask = s->eqcr.pi_ci_mask;
+	if (!s->eqcr.available) {
+		eqcr_ci = s->eqcr.ci;
+		p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK;
+		s->eqcr.ci = *p & full_mask;
+		s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size,
+					eqcr_ci, s->eqcr.ci);
+		if (!s->eqcr.available) {
+			spin_unlock_irqrestore(&s->access_spinlock, irq_flags);
+			return 0;
+		}
+	}
+
+	eqcr_pi = s->eqcr.pi;
+	num_enqueued = (s->eqcr.available < num_frames) ?
+			s->eqcr.available : num_frames;
+	s->eqcr.available -= num_enqueued;
+	/* Fill in the EQCR ring */
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		/* Skip copying the verb */
+		memcpy(&p[1], &cl[1], EQ_DESC_SIZE_WITHOUT_FD - 1);
+		memcpy(&p[EQ_DESC_SIZE_FD_START/sizeof(uint32_t)],
+		       &fd[i], sizeof(*fd));
+		eqcr_pi++;
+	}
+
+	/* Set the verb byte, have to substitute in the valid-bit */
+	eqcr_pi = s->eqcr.pi;
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		p[0] = cl[0] | s->eqcr.pi_vb;
+		if (flags && (flags[i] & QBMAN_ENQUEUE_FLAG_DCA)) {
+			struct qbman_eq_desc *d = (struct qbman_eq_desc *)p;
+
+			d->dca = (1 << QB_ENQUEUE_CMD_DCA_EN_SHIFT) |
+				((flags[i]) & QBMAN_EQCR_DCA_IDXMASK);
+		}
+		eqcr_pi++;
+		if (!(eqcr_pi & half_mask))
+			s->eqcr.pi_vb ^= QB_VALID_BIT;
+	}
+	s->eqcr.pi = eqcr_pi & full_mask;
+
+	dma_wmb();
+	qbman_write_register(s, QBMAN_CINH_SWP_EQCR_PI,
+				(QB_RT_BIT)|(s->eqcr.pi)|s->eqcr.pi_vb);
+	spin_unlock_irqrestore(&s->access_spinlock, irq_flags);
+
+	return num_enqueued;
+}
+
+/**
+ * qbman_swp_enqueue_multiple_desc_direct() - Issue a multi enqueue command
+ * using multiple enqueue descriptor
+ * @s:  the software portal used for enqueue
+ * @d:  table of minimal enqueue descriptor
+ * @fd: table pointer of frame descriptor table to be enqueued
+ * @num_frames: number of fd to be enqueued
+ *
+ * Return the number of fd enqueued, or a negative error number.
+ */
+static
+int qbman_swp_enqueue_multiple_desc_direct(struct qbman_swp *s,
+					   const struct qbman_eq_desc *d,
+					   const struct dpaa2_fd *fd,
+					   int num_frames)
+{
+	uint32_t *p;
+	const uint32_t *cl;
+	uint32_t eqcr_ci, eqcr_pi, half_mask, full_mask;
+	int i, num_enqueued = 0;
+
+	half_mask = (s->eqcr.pi_ci_mask>>1);
+	full_mask = s->eqcr.pi_ci_mask;
+	if (!s->eqcr.available) {
+		eqcr_ci = s->eqcr.ci;
+		p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI;
+		s->eqcr.ci = qbman_read_register(s, QBMAN_CINH_SWP_EQCR_CI);
+		s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size,
+					eqcr_ci, s->eqcr.ci);
+		if (!s->eqcr.available)
+			return 0;
+	}
+
+	eqcr_pi = s->eqcr.pi;
+	num_enqueued = (s->eqcr.available < num_frames) ?
+			s->eqcr.available : num_frames;
+	s->eqcr.available -= num_enqueued;
+	/* Fill in the EQCR ring */
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		cl = (uint32_t *)(&d[i]);
+		/* Skip copying the verb */
+		memcpy(&p[1], &cl[1], EQ_DESC_SIZE_WITHOUT_FD - 1);
+		memcpy(&p[EQ_DESC_SIZE_FD_START/sizeof(uint32_t)],
+		       &fd[i], sizeof(*fd));
+		eqcr_pi++;
+	}
+
+	dma_wmb();
+
+	/* Set the verb byte, have to substitute in the valid-bit */
+	eqcr_pi = s->eqcr.pi;
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		cl = (uint32_t *)(&d[i]);
+		p[0] = cl[0] | s->eqcr.pi_vb;
+		eqcr_pi++;
+		if (!(eqcr_pi & half_mask))
+			s->eqcr.pi_vb ^= QB_VALID_BIT;
+	}
+
+	/* Flush all the cacheline without load/store in between */
+	eqcr_pi = s->eqcr.pi;
+	for (i = 0; i < num_enqueued; i++)
+		eqcr_pi++;
+	s->eqcr.pi = eqcr_pi & full_mask;
+
+	return num_enqueued;
+}
+
+/**
+ * qbman_swp_enqueue_multiple_desc_mem_back() - Issue a multi enqueue command
+ * using multiple enqueue descriptor
+ * @s:  the software portal used for enqueue
+ * @d:  table of minimal enqueue descriptor
+ * @fd: table pointer of frame descriptor table to be enqueued
+ * @num_frames: number of fd to be enqueued
+ *
+ * Return the number of fd enqueued, or a negative error number.
+ */
+static
+int qbman_swp_enqueue_multiple_desc_mem_back(struct qbman_swp *s,
+					   const struct qbman_eq_desc *d,
+					   const struct dpaa2_fd *fd,
+					   int num_frames)
+{
+	uint32_t *p;
+	const uint32_t *cl;
+	uint32_t eqcr_ci, eqcr_pi, half_mask, full_mask;
+	int i, num_enqueued = 0;
+
+	half_mask = (s->eqcr.pi_ci_mask>>1);
+	full_mask = s->eqcr.pi_ci_mask;
+	if (!s->eqcr.available) {
+		eqcr_ci = s->eqcr.ci;
+		p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK;
+		s->eqcr.ci = *p & full_mask;
+		s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size,
+					eqcr_ci, s->eqcr.ci);
+		if (!s->eqcr.available)
+			return 0;
+	}
+
+	eqcr_pi = s->eqcr.pi;
+	num_enqueued = (s->eqcr.available < num_frames) ?
+			s->eqcr.available : num_frames;
+	s->eqcr.available -= num_enqueued;
+	/* Fill in the EQCR ring */
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		cl = (uint32_t *)(&d[i]);
+		/* Skip copying the verb */
+		memcpy(&p[1], &cl[1], EQ_DESC_SIZE_WITHOUT_FD - 1);
+		memcpy(&p[EQ_DESC_SIZE_FD_START/sizeof(uint32_t)],
+		       &fd[i], sizeof(*fd));
+		eqcr_pi++;
+	}
+
+	/* Set the verb byte, have to substitute in the valid-bit */
+	eqcr_pi = s->eqcr.pi;
+	for (i = 0; i < num_enqueued; i++) {
+		p = (s->addr_cena + QBMAN_CENA_SWP_EQCR(eqcr_pi & half_mask));
+		cl = (uint32_t *)(&d[i]);
+		p[0] = cl[0] | s->eqcr.pi_vb;
+		eqcr_pi++;
+		if (!(eqcr_pi & half_mask))
+			s->eqcr.pi_vb ^= QB_VALID_BIT;
+	}
+
+	s->eqcr.pi = eqcr_pi & full_mask;
+
+	dma_wmb();
+	qbman_write_register(s, QBMAN_CINH_SWP_EQCR_PI,
+				(QB_RT_BIT)|(s->eqcr.pi)|s->eqcr.pi_vb);
+
+	return num_enqueued;
 }
 
 /* Static (push) dequeue */
@@ -645,7 +1080,7 @@
 }
 
 /**
- * qbman_swp_pull() - Issue the pull dequeue command
+ * qbman_swp_pull_direct() - Issue the pull dequeue command
  * @s: the software portal object
  * @d: the software portal descriptor which has been configured with
  *     the set of qbman_pull_desc_set_*() calls
@@ -653,7 +1088,44 @@
  * Return 0 for success, and -EBUSY if the software portal is not ready
  * to do pull dequeue.
  */
-int qbman_swp_pull(struct qbman_swp *s, struct qbman_pull_desc *d)
+static
+int qbman_swp_pull_direct(struct qbman_swp *s, struct qbman_pull_desc *d)
+{
+	struct qbman_pull_desc *p;
+
+	if (!atomic_dec_and_test(&s->vdq.available)) {
+		atomic_inc(&s->vdq.available);
+		return -EBUSY;
+	}
+	s->vdq.storage = (void *)(uintptr_t)d->rsp_addr_virt;
+	if ((s->desc->qman_version & QMAN_REV_MASK) < QMAN_REV_5000)
+		p = qbman_get_cmd(s, QBMAN_CENA_SWP_VDQCR);
+	else
+		p = qbman_get_cmd(s, QBMAN_CENA_SWP_VDQCR_MEM);
+	p->numf = d->numf;
+	p->tok = QMAN_DQ_TOKEN_VALID;
+	p->dq_src = d->dq_src;
+	p->rsp_addr = d->rsp_addr;
+	p->rsp_addr_virt = d->rsp_addr_virt;
+	dma_wmb();
+	/* Set the verb byte, have to substitute in the valid-bit */
+	p->verb = d->verb | s->vdq.valid_bit;
+	s->vdq.valid_bit ^= QB_VALID_BIT;
+
+	return 0;
+}
+
+/**
+ * qbman_swp_pull_mem_back() - Issue the pull dequeue command
+ * @s: the software portal object
+ * @d: the software portal descriptor which has been configured with
+ *     the set of qbman_pull_desc_set_*() calls
+ *
+ * Return 0 for success, and -EBUSY if the software portal is not ready
+ * to do pull dequeue.
+ */
+static
+int qbman_swp_pull_mem_back(struct qbman_swp *s, struct qbman_pull_desc *d)
 {
 	struct qbman_pull_desc *p;
 
@@ -672,17 +1144,11 @@
 	p->rsp_addr = d->rsp_addr;
 	p->rsp_addr_virt = d->rsp_addr_virt;
 
-	if ((s->desc->qman_version & QMAN_REV_MASK) < QMAN_REV_5000) {
-		dma_wmb();
-		/* Set the verb byte, have to substitute in the valid-bit */
-		p->verb = d->verb | s->vdq.valid_bit;
-		s->vdq.valid_bit ^= QB_VALID_BIT;
-	} else {
-		p->verb = d->verb | s->vdq.valid_bit;
-		s->vdq.valid_bit ^= QB_VALID_BIT;
-		dma_wmb();
-		qbman_write_register(s, QBMAN_CINH_SWP_VDQCR_RT, QMAN_RT_MODE);
-	}
+	/* Set the verb byte, have to substitute in the valid-bit */
+	p->verb = d->verb | s->vdq.valid_bit;
+	s->vdq.valid_bit ^= QB_VALID_BIT;
+	dma_wmb();
+	qbman_write_register(s, QBMAN_CINH_SWP_VDQCR_RT, QMAN_RT_MODE);
 
 	return 0;
 }
@@ -690,14 +1156,14 @@
 #define QMAN_DQRR_PI_MASK   0xf
 
 /**
- * qbman_swp_dqrr_next() - Get an valid DQRR entry
+ * qbman_swp_dqrr_next_direct() - Get an valid DQRR entry
  * @s: the software portal object
  *
  * Return NULL if there are no unconsumed DQRR entries. Return a DQRR entry
  * only once, so repeated calls can return a sequence of DQRR entries, without
  * requiring they be consumed immediately or in any particular order.
  */
-const struct dpaa2_dq *qbman_swp_dqrr_next(struct qbman_swp *s)
+const struct dpaa2_dq *qbman_swp_dqrr_next_direct(struct qbman_swp *s)
 {
 	u32 verb;
 	u32 response_verb;
@@ -740,10 +1206,99 @@
 				       QBMAN_CENA_SWP_DQRR(s->dqrr.next_idx)));
 	}
 
-	if ((s->desc->qman_version & QMAN_REV_MASK) < QMAN_REV_5000)
-		p = qbman_get_cmd(s, QBMAN_CENA_SWP_DQRR(s->dqrr.next_idx));
-	else
-		p = qbman_get_cmd(s, QBMAN_CENA_SWP_DQRR_MEM(s->dqrr.next_idx));
+	p = qbman_get_cmd(s, QBMAN_CENA_SWP_DQRR(s->dqrr.next_idx));
+	verb = p->dq.verb;
+
+	/*
+	 * If the valid-bit isn't of the expected polarity, nothing there. Note,
+	 * in the DQRR reset bug workaround, we shouldn't need to skip these
+	 * check, because we've already determined that a new entry is available
+	 * and we've invalidated the cacheline before reading it, so the
+	 * valid-bit behaviour is repaired and should tell us what we already
+	 * knew from reading PI.
+	 */
+	if ((verb & QB_VALID_BIT) != s->dqrr.valid_bit) {
+		prefetch(qbman_get_cmd(s,
+				       QBMAN_CENA_SWP_DQRR(s->dqrr.next_idx)));
+		return NULL;
+	}
+	/*
+	 * There's something there. Move "next_idx" attention to the next ring
+	 * entry (and prefetch it) before returning what we found.
+	 */
+	s->dqrr.next_idx++;
+	s->dqrr.next_idx &= s->dqrr.dqrr_size - 1; /* Wrap around */
+	if (!s->dqrr.next_idx)
+		s->dqrr.valid_bit ^= QB_VALID_BIT;
+
+	/*
+	 * If this is the final response to a volatile dequeue command
+	 * indicate that the vdq is available
+	 */
+	flags = p->dq.stat;
+	response_verb = verb & QBMAN_RESULT_MASK;
+	if ((response_verb == QBMAN_RESULT_DQ) &&
+	    (flags & DPAA2_DQ_STAT_VOLATILE) &&
+	    (flags & DPAA2_DQ_STAT_EXPIRED))
+		atomic_inc(&s->vdq.available);
+
+	prefetch(qbman_get_cmd(s, QBMAN_CENA_SWP_DQRR(s->dqrr.next_idx)));
+
+	return p;
+}
+
+/**
+ * qbman_swp_dqrr_next_mem_back() - Get an valid DQRR entry
+ * @s: the software portal object
+ *
+ * Return NULL if there are no unconsumed DQRR entries. Return a DQRR entry
+ * only once, so repeated calls can return a sequence of DQRR entries, without
+ * requiring they be consumed immediately or in any particular order.
+ */
+const struct dpaa2_dq *qbman_swp_dqrr_next_mem_back(struct qbman_swp *s)
+{
+	u32 verb;
+	u32 response_verb;
+	u32 flags;
+	struct dpaa2_dq *p;
+
+	/* Before using valid-bit to detect if something is there, we have to
+	 * handle the case of the DQRR reset bug...
+	 */
+	if (unlikely(s->dqrr.reset_bug)) {
+		/*
+		 * We pick up new entries by cache-inhibited producer index,
+		 * which means that a non-coherent mapping would require us to
+		 * invalidate and read *only* once that PI has indicated that
+		 * there's an entry here. The first trip around the DQRR ring
+		 * will be much less efficient than all subsequent trips around
+		 * it...
+		 */
+		u8 pi = qbman_read_register(s, QBMAN_CINH_SWP_DQPI) &
+			QMAN_DQRR_PI_MASK;
+
+		/* there are new entries if pi != next_idx */
+		if (pi == s->dqrr.next_idx)
+			return NULL;
+
+		/*
+		 * if next_idx is/was the last ring index, and 'pi' is
+		 * different, we can disable the workaround as all the ring
+		 * entries have now been DMA'd to so valid-bit checking is
+		 * repaired. Note: this logic needs to be based on next_idx
+		 * (which increments one at a time), rather than on pi (which
+		 * can burst and wrap-around between our snapshots of it).
+		 */
+		if (s->dqrr.next_idx == (s->dqrr.dqrr_size - 1)) {
+			pr_debug("next_idx=%d, pi=%d, clear reset bug\n",
+				 s->dqrr.next_idx, pi);
+			s->dqrr.reset_bug = 0;
+		}
+		prefetch(qbman_get_cmd(s,
+				       QBMAN_CENA_SWP_DQRR(s->dqrr.next_idx)));
+	}
+
+	p = qbman_get_cmd(s, QBMAN_CENA_SWP_DQRR_MEM(s->dqrr.next_idx));
 	verb = p->dq.verb;
 
 	/*
@@ -872,7 +1427,7 @@
 #define RAR_SUCCESS(rar) ((rar) & 0x100)
 
 /**
- * qbman_swp_release() - Issue a buffer release command
+ * qbman_swp_release_direct() - Issue a buffer release command
  * @s:           the software portal object
  * @d:           the release descriptor
  * @buffers:     a pointer pointing to the buffer address to be released
@@ -880,8 +1435,9 @@
  *
  * Return 0 for success, -EBUSY if the release command ring is not ready.
  */
-int qbman_swp_release(struct qbman_swp *s, const struct qbman_release_desc *d,
-		      const u64 *buffers, unsigned int num_buffers)
+int qbman_swp_release_direct(struct qbman_swp *s,
+			     const struct qbman_release_desc *d,
+			     const u64 *buffers, unsigned int num_buffers)
 {
 	int i;
 	struct qbman_release_desc *p;
@@ -895,28 +1451,59 @@
 		return -EBUSY;
 
 	/* Start the release command */
-	if ((s->desc->qman_version & QMAN_REV_MASK) < QMAN_REV_5000)
-		p = qbman_get_cmd(s, QBMAN_CENA_SWP_RCR(RAR_IDX(rar)));
-	else
-		p = qbman_get_cmd(s, QBMAN_CENA_SWP_RCR_MEM(RAR_IDX(rar)));
+	p = qbman_get_cmd(s, QBMAN_CENA_SWP_RCR(RAR_IDX(rar)));
+
 	/* Copy the caller's buffer pointers to the command */
 	for (i = 0; i < num_buffers; i++)
 		p->buf[i] = cpu_to_le64(buffers[i]);
 	p->bpid = d->bpid;
 
-	if ((s->desc->qman_version & QMAN_REV_MASK) < QMAN_REV_5000) {
-		/*
-		 * Set the verb byte, have to substitute in the valid-bit
-		 * and the number of buffers.
-		 */
-		dma_wmb();
-		p->verb = d->verb | RAR_VB(rar) | num_buffers;
-	} else {
-		p->verb = d->verb | RAR_VB(rar) | num_buffers;
-		dma_wmb();
-		qbman_write_register(s, QBMAN_CINH_SWP_RCR_AM_RT +
-				     RAR_IDX(rar)  * 4, QMAN_RT_MODE);
-	}
+	/*
+	 * Set the verb byte, have to substitute in the valid-bit
+	 * and the number of buffers.
+	 */
+	dma_wmb();
+	p->verb = d->verb | RAR_VB(rar) | num_buffers;
+
+	return 0;
+}
+
+/**
+ * qbman_swp_release_mem_back() - Issue a buffer release command
+ * @s:           the software portal object
+ * @d:           the release descriptor
+ * @buffers:     a pointer pointing to the buffer address to be released
+ * @num_buffers: number of buffers to be released,  must be less than 8
+ *
+ * Return 0 for success, -EBUSY if the release command ring is not ready.
+ */
+int qbman_swp_release_mem_back(struct qbman_swp *s,
+			       const struct qbman_release_desc *d,
+			       const u64 *buffers, unsigned int num_buffers)
+{
+	int i;
+	struct qbman_release_desc *p;
+	u32 rar;
+
+	if (!num_buffers || (num_buffers > 7))
+		return -EINVAL;
+
+	rar = qbman_read_register(s, QBMAN_CINH_SWP_RAR);
+	if (!RAR_SUCCESS(rar))
+		return -EBUSY;
+
+	/* Start the release command */
+	p = qbman_get_cmd(s, QBMAN_CENA_SWP_RCR_MEM(RAR_IDX(rar)));
+
+	/* Copy the caller's buffer pointers to the command */
+	for (i = 0; i < num_buffers; i++)
+		p->buf[i] = cpu_to_le64(buffers[i]);
+	p->bpid = d->bpid;
+
+	p->verb = d->verb | RAR_VB(rar) | num_buffers;
+	dma_wmb();
+	qbman_write_register(s, QBMAN_CINH_SWP_RCR_AM_RT +
+			     RAR_IDX(rar)  * 4, QMAN_RT_MODE);
 
 	return 0;
 }
diff --git a/drivers/soc/fsl/dpio/qbman-portal.h b/drivers/soc/fsl/dpio/qbman-portal.h
index f3ec5d2..c7c2225 100644
--- a/drivers/soc/fsl/dpio/qbman-portal.h
+++ b/drivers/soc/fsl/dpio/qbman-portal.h
@@ -9,6 +9,13 @@
 
 #include <soc/fsl/dpaa2-fd.h>
 
+#define QMAN_REV_4000   0x04000000
+#define QMAN_REV_4100   0x04010000
+#define QMAN_REV_4101   0x04010001
+#define QMAN_REV_5000   0x05000000
+
+#define QMAN_REV_MASK   0xffff0000
+
 struct dpaa2_dq;
 struct qbman_swp;
 
@@ -81,6 +88,10 @@
 	u8 wae;
 	u8 rspid;
 	__le64 rsp_addr;
+};
+
+struct qbman_eq_desc_with_fd {
+	struct qbman_eq_desc desc;
 	u8 fd[32];
 };
 
@@ -132,8 +143,48 @@
 		u8 dqrr_size;
 		int reset_bug; /* indicates dqrr reset workaround is needed */
 	} dqrr;
+
+	struct {
+		u32 pi;
+		u32 pi_vb;
+		u32 pi_ring_size;
+		u32 pi_ci_mask;
+		u32 ci;
+		int available;
+		u32 pend;
+		u32 no_pfdr;
+	} eqcr;
+
+	spinlock_t access_spinlock;
 };
 
+/* Function pointers */
+extern
+int (*qbman_swp_enqueue_ptr)(struct qbman_swp *s,
+			     const struct qbman_eq_desc *d,
+			     const struct dpaa2_fd *fd);
+extern
+int (*qbman_swp_enqueue_multiple_ptr)(struct qbman_swp *s,
+				      const struct qbman_eq_desc *d,
+				      const struct dpaa2_fd *fd,
+				      uint32_t *flags,
+				      int num_frames);
+extern
+int (*qbman_swp_enqueue_multiple_desc_ptr)(struct qbman_swp *s,
+					   const struct qbman_eq_desc *d,
+					   const struct dpaa2_fd *fd,
+					   int num_frames);
+extern
+int (*qbman_swp_pull_ptr)(struct qbman_swp *s, struct qbman_pull_desc *d);
+extern
+const struct dpaa2_dq *(*qbman_swp_dqrr_next_ptr)(struct qbman_swp *s);
+extern
+int (*qbman_swp_release_ptr)(struct qbman_swp *s,
+			     const struct qbman_release_desc *d,
+			     const u64 *buffers,
+			     unsigned int num_buffers);
+
+/* Functions */
 struct qbman_swp *qbman_swp_init(const struct qbman_swp_desc *d);
 void qbman_swp_finish(struct qbman_swp *p);
 u32 qbman_swp_interrupt_read_status(struct qbman_swp *p);
@@ -158,9 +209,6 @@
 void qbman_pull_desc_set_channel(struct qbman_pull_desc *d, u32 chid,
 				 enum qbman_pull_type_e dct);
 
-int qbman_swp_pull(struct qbman_swp *p, struct qbman_pull_desc *d);
-
-const struct dpaa2_dq *qbman_swp_dqrr_next(struct qbman_swp *s);
 void qbman_swp_dqrr_consume(struct qbman_swp *s, const struct dpaa2_dq *dq);
 
 int qbman_result_has_new_result(struct qbman_swp *p, const struct dpaa2_dq *dq);
@@ -172,15 +220,11 @@
 void qbman_eq_desc_set_qd(struct qbman_eq_desc *d, u32 qdid,
 			  u32 qd_bin, u32 qd_prio);
 
-int qbman_swp_enqueue(struct qbman_swp *p, const struct qbman_eq_desc *d,
-		      const struct dpaa2_fd *fd);
 
 void qbman_release_desc_clear(struct qbman_release_desc *d);
 void qbman_release_desc_set_bpid(struct qbman_release_desc *d, u16 bpid);
 void qbman_release_desc_set_rcdi(struct qbman_release_desc *d, int enable);
 
-int qbman_swp_release(struct qbman_swp *s, const struct qbman_release_desc *d,
-		      const u64 *buffers, unsigned int num_buffers);
 int qbman_swp_acquire(struct qbman_swp *s, u16 bpid, u64 *buffers,
 		      unsigned int num_buffers);
 int qbman_swp_alt_fq_state(struct qbman_swp *s, u32 fqid,
@@ -194,6 +238,61 @@
 void *qbman_swp_mc_result(struct qbman_swp *p);
 
 /**
+ * qbman_swp_enqueue() - Issue an enqueue command
+ * @s:  the software portal used for enqueue
+ * @d:  the enqueue descriptor
+ * @fd: the frame descriptor to be enqueued
+ *
+ * Return 0 for successful enqueue, -EBUSY if the EQCR is not ready.
+ */
+static inline int
+qbman_swp_enqueue(struct qbman_swp *s, const struct qbman_eq_desc *d,
+		  const struct dpaa2_fd *fd)
+{
+	return qbman_swp_enqueue_ptr(s, d, fd);
+}
+
+/**
+ * qbman_swp_enqueue_multiple() - Issue a multi enqueue command
+ * using one enqueue descriptor
+ * @s:  the software portal used for enqueue
+ * @d:  the enqueue descriptor
+ * @fd: table pointer of frame descriptor table to be enqueued
+ * @flags: table pointer of QBMAN_ENQUEUE_FLAG_DCA flags, not used if NULL
+ * @num_frames: number of fd to be enqueued
+ *
+ * Return the number of fd enqueued, or a negative error number.
+ */
+static inline int
+qbman_swp_enqueue_multiple(struct qbman_swp *s,
+			   const struct qbman_eq_desc *d,
+			   const struct dpaa2_fd *fd,
+			   uint32_t *flags,
+			   int num_frames)
+{
+	return qbman_swp_enqueue_multiple_ptr(s, d, fd, flags, num_frames);
+}
+
+/**
+ * qbman_swp_enqueue_multiple_desc() - Issue a multi enqueue command
+ * using multiple enqueue descriptor
+ * @s:  the software portal used for enqueue
+ * @d:  table of minimal enqueue descriptor
+ * @fd: table pointer of frame descriptor table to be enqueued
+ * @num_frames: number of fd to be enqueued
+ *
+ * Return the number of fd enqueued, or a negative error number.
+ */
+static inline int
+qbman_swp_enqueue_multiple_desc(struct qbman_swp *s,
+				const struct qbman_eq_desc *d,
+				const struct dpaa2_fd *fd,
+				int num_frames)
+{
+	return qbman_swp_enqueue_multiple_desc_ptr(s, d, fd, num_frames);
+}
+
+/**
  * qbman_result_is_DQ() - check if the dequeue result is a dequeue response
  * @dq: the dequeue result to be checked
  *
@@ -504,4 +603,49 @@
 
 u32 qbman_bp_info_num_free_bufs(struct qbman_bp_query_rslt *a);
 
+/**
+ * qbman_swp_release() - Issue a buffer release command
+ * @s:           the software portal object
+ * @d:           the release descriptor
+ * @buffers:     a pointer pointing to the buffer address to be released
+ * @num_buffers: number of buffers to be released,  must be less than 8
+ *
+ * Return 0 for success, -EBUSY if the release command ring is not ready.
+ */
+static inline int qbman_swp_release(struct qbman_swp *s,
+				    const struct qbman_release_desc *d,
+				    const u64 *buffers,
+				    unsigned int num_buffers)
+{
+	return qbman_swp_release_ptr(s, d, buffers, num_buffers);
+}
+
+/**
+ * qbman_swp_pull() - Issue the pull dequeue command
+ * @s: the software portal object
+ * @d: the software portal descriptor which has been configured with
+ *     the set of qbman_pull_desc_set_*() calls
+ *
+ * Return 0 for success, and -EBUSY if the software portal is not ready
+ * to do pull dequeue.
+ */
+static inline int qbman_swp_pull(struct qbman_swp *s,
+				 struct qbman_pull_desc *d)
+{
+	return qbman_swp_pull_ptr(s, d);
+}
+
+/**
+ * qbman_swp_dqrr_next() - Get an valid DQRR entry
+ * @s: the software portal object
+ *
+ * Return NULL if there are no unconsumed DQRR entries. Return a DQRR entry
+ * only once, so repeated calls can return a sequence of DQRR entries, without
+ * requiring they be consumed immediately or in any particular order.
+ */
+static inline const struct dpaa2_dq *qbman_swp_dqrr_next(struct qbman_swp *s)
+{
+	return qbman_swp_dqrr_next_ptr(s);
+}
+
 #endif /* __FSL_QBMAN_PORTAL_H */
diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index 34810f9..091e94c 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -28,7 +28,6 @@
 static struct guts *guts;
 static struct soc_device_attribute soc_dev_attr;
 static struct soc_device *soc_dev;
-static struct device_node *root;
 
 
 /* SoC die attribute definition for QorIQ platform */
@@ -138,7 +137,7 @@
 
 static int fsl_guts_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
+	struct device_node *root, *np = pdev->dev.of_node;
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	const struct fsl_soc_die_attr *soc_die;
@@ -161,8 +160,14 @@
 	root = of_find_node_by_path("/");
 	if (of_property_read_string(root, "model", &machine))
 		of_property_read_string_index(root, "compatible", 0, &machine);
-	if (machine)
-		soc_dev_attr.machine = machine;
+	if (machine) {
+		soc_dev_attr.machine = devm_kstrdup(dev, machine, GFP_KERNEL);
+		if (!soc_dev_attr.machine) {
+			of_node_put(root);
+			return -ENOMEM;
+		}
+	}
+	of_node_put(root);
 
 	svr = fsl_guts_get_svr();
 	soc_die = fsl_soc_die_match(svr, fsl_soc_die);
@@ -197,7 +202,6 @@
 static int fsl_guts_remove(struct platform_device *dev)
 {
 	soc_device_unregister(soc_dev);
-	of_node_put(root);
 	return 0;
 }
 
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 95f9e48..feb9747 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -449,11 +449,6 @@
 	return 0;
 }
 
-static inline unsigned int qm_eqcr_get_ci_stashing(struct qm_portal *portal)
-{
-	return (qm_in(portal, QM_REG_CFG) >> 28) & 0x7;
-}
-
 static inline void qm_eqcr_finish(struct qm_portal *portal)
 {
 	struct qm_eqcr *eqcr = &portal->eqcr;
@@ -1749,6 +1744,13 @@
 }
 EXPORT_SYMBOL(qman_get_affine_portal);
 
+int qman_start_using_portal(struct qman_portal *p, struct device *dev)
+{
+	return (!device_link_add(dev, p->config->dev,
+				 DL_FLAG_AUTOREMOVE_CONSUMER)) ? -EINVAL : 0;
+}
+EXPORT_SYMBOL(qman_start_using_portal);
+
 int qman_p_poll_dqrr(struct qman_portal *p, unsigned int limit)
 {
 	return __poll_portal_fast(p, limit);
diff --git a/drivers/soc/fsl/qbman/qman_test_api.c b/drivers/soc/fsl/qbman/qman_test_api.c
index 2895d06..7066b2f 100644
--- a/drivers/soc/fsl/qbman/qman_test_api.c
+++ b/drivers/soc/fsl/qbman/qman_test_api.c
@@ -86,7 +86,7 @@
 	len--;
 	qm_fd_set_param(fd, fmt, off, len);
 
-	fd->cmd = cpu_to_be32(be32_to_cpu(fd->cmd) + 1);
+	be32_add_cpu(&fd->cmd, 1);
 }
 
 /* The only part of the 'fd' we can't memcmp() is the ppid */
diff --git a/drivers/soc/fsl/qe/Kconfig b/drivers/soc/fsl/qe/Kconfig
index cfa4b29..357c580 100644
--- a/drivers/soc/fsl/qe/Kconfig
+++ b/drivers/soc/fsl/qe/Kconfig
@@ -5,7 +5,8 @@
 
 config QUICC_ENGINE
 	bool "QUICC Engine (QE) framework support"
-	depends on FSL_SOC && PPC32
+	depends on OF && HAS_IOMEM
+	depends on PPC || ARM || ARM64 || COMPILE_TEST
 	select GENERIC_ALLOCATOR
 	select CRC32
 	help
diff --git a/drivers/soc/fsl/qe/gpio.c b/drivers/soc/fsl/qe/gpio.c
index f0c29ed..ed75198 100644
--- a/drivers/soc/fsl/qe/gpio.c
+++ b/drivers/soc/fsl/qe/gpio.c
@@ -41,13 +41,13 @@
 		container_of(mm_gc, struct qe_gpio_chip, mm_gc);
 	struct qe_pio_regs __iomem *regs = mm_gc->regs;
 
-	qe_gc->cpdata = in_be32(&regs->cpdata);
+	qe_gc->cpdata = qe_ioread32be(&regs->cpdata);
 	qe_gc->saved_regs.cpdata = qe_gc->cpdata;
-	qe_gc->saved_regs.cpdir1 = in_be32(&regs->cpdir1);
-	qe_gc->saved_regs.cpdir2 = in_be32(&regs->cpdir2);
-	qe_gc->saved_regs.cppar1 = in_be32(&regs->cppar1);
-	qe_gc->saved_regs.cppar2 = in_be32(&regs->cppar2);
-	qe_gc->saved_regs.cpodr = in_be32(&regs->cpodr);
+	qe_gc->saved_regs.cpdir1 = qe_ioread32be(&regs->cpdir1);
+	qe_gc->saved_regs.cpdir2 = qe_ioread32be(&regs->cpdir2);
+	qe_gc->saved_regs.cppar1 = qe_ioread32be(&regs->cppar1);
+	qe_gc->saved_regs.cppar2 = qe_ioread32be(&regs->cppar2);
+	qe_gc->saved_regs.cpodr = qe_ioread32be(&regs->cpodr);
 }
 
 static int qe_gpio_get(struct gpio_chip *gc, unsigned int gpio)
@@ -56,7 +56,7 @@
 	struct qe_pio_regs __iomem *regs = mm_gc->regs;
 	u32 pin_mask = 1 << (QE_PIO_PINS - 1 - gpio);
 
-	return !!(in_be32(&regs->cpdata) & pin_mask);
+	return !!(qe_ioread32be(&regs->cpdata) & pin_mask);
 }
 
 static void qe_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
@@ -74,7 +74,7 @@
 	else
 		qe_gc->cpdata &= ~pin_mask;
 
-	out_be32(&regs->cpdata, qe_gc->cpdata);
+	qe_iowrite32be(qe_gc->cpdata, &regs->cpdata);
 
 	spin_unlock_irqrestore(&qe_gc->lock, flags);
 }
@@ -101,7 +101,7 @@
 		}
 	}
 
-	out_be32(&regs->cpdata, qe_gc->cpdata);
+	qe_iowrite32be(qe_gc->cpdata, &regs->cpdata);
 
 	spin_unlock_irqrestore(&qe_gc->lock, flags);
 }
@@ -160,7 +160,6 @@
 {
 	struct qe_pin *qe_pin;
 	struct gpio_chip *gc;
-	struct of_mm_gpio_chip *mm_gc;
 	struct qe_gpio_chip *qe_gc;
 	int err;
 	unsigned long flags;
@@ -186,7 +185,6 @@
 		goto err0;
 	}
 
-	mm_gc = to_of_mm_gpio_chip(gc);
 	qe_gc = gpiochip_get_data(gc);
 
 	spin_lock_irqsave(&qe_gc->lock, flags);
@@ -255,11 +253,15 @@
 	spin_lock_irqsave(&qe_gc->lock, flags);
 
 	if (second_reg) {
-		clrsetbits_be32(&regs->cpdir2, mask2, sregs->cpdir2 & mask2);
-		clrsetbits_be32(&regs->cppar2, mask2, sregs->cppar2 & mask2);
+		qe_clrsetbits_be32(&regs->cpdir2, mask2,
+				   sregs->cpdir2 & mask2);
+		qe_clrsetbits_be32(&regs->cppar2, mask2,
+				   sregs->cppar2 & mask2);
 	} else {
-		clrsetbits_be32(&regs->cpdir1, mask2, sregs->cpdir1 & mask2);
-		clrsetbits_be32(&regs->cppar1, mask2, sregs->cppar1 & mask2);
+		qe_clrsetbits_be32(&regs->cpdir1, mask2,
+				   sregs->cpdir1 & mask2);
+		qe_clrsetbits_be32(&regs->cppar1, mask2,
+				   sregs->cppar1 & mask2);
 	}
 
 	if (sregs->cpdata & mask1)
@@ -267,8 +269,8 @@
 	else
 		qe_gc->cpdata &= ~mask1;
 
-	out_be32(&regs->cpdata, qe_gc->cpdata);
-	clrsetbits_be32(&regs->cpodr, mask1, sregs->cpodr & mask1);
+	qe_iowrite32be(qe_gc->cpdata, &regs->cpdata);
+	qe_clrsetbits_be32(&regs->cpodr, mask1, sregs->cpodr & mask1);
 
 	spin_unlock_irqrestore(&qe_gc->lock, flags);
 }
diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c
index 417df7e..2df20d6 100644
--- a/drivers/soc/fsl/qe/qe.c
+++ b/drivers/soc/fsl/qe/qe.c
@@ -22,16 +22,12 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/ioport.h>
+#include <linux/iopoll.h>
 #include <linux/crc32.h>
 #include <linux/mod_devicetable.h>
 #include <linux/of_platform.h>
-#include <asm/irq.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
 #include <soc/fsl/qe/immap_qe.h>
 #include <soc/fsl/qe/qe.h>
-#include <asm/prom.h>
-#include <asm/rheap.h>
 
 static void qe_snums_init(void);
 static int qe_sdma_init(void);
@@ -108,11 +104,12 @@
 {
 	unsigned long flags;
 	u8 mcn_shift = 0, dev_shift = 0;
-	u32 ret;
+	u32 val;
+	int ret;
 
 	spin_lock_irqsave(&qe_lock, flags);
 	if (cmd == QE_RESET) {
-		out_be32(&qe_immr->cp.cecr, (u32) (cmd | QE_CR_FLG));
+		qe_iowrite32be((u32)(cmd | QE_CR_FLG), &qe_immr->cp.cecr);
 	} else {
 		if (cmd == QE_ASSIGN_PAGE) {
 			/* Here device is the SNUM, not sub-block */
@@ -129,20 +126,18 @@
 				mcn_shift = QE_CR_MCN_NORMAL_SHIFT;
 		}
 
-		out_be32(&qe_immr->cp.cecdr, cmd_input);
-		out_be32(&qe_immr->cp.cecr,
-			 (cmd | QE_CR_FLG | ((u32) device << dev_shift) | (u32)
-			  mcn_protocol << mcn_shift));
+		qe_iowrite32be(cmd_input, &qe_immr->cp.cecdr);
+		qe_iowrite32be((cmd | QE_CR_FLG | ((u32)device << dev_shift) | (u32)mcn_protocol << mcn_shift),
+			       &qe_immr->cp.cecr);
 	}
 
 	/* wait for the QE_CR_FLG to clear */
-	ret = spin_event_timeout((in_be32(&qe_immr->cp.cecr) & QE_CR_FLG) == 0,
-			   100, 0);
-	/* On timeout (e.g. failure), the expression will be false (ret == 0),
-	   otherwise it will be true (ret == 1). */
+	ret = readx_poll_timeout_atomic(qe_ioread32be, &qe_immr->cp.cecr, val,
+					(val & QE_CR_FLG) == 0, 0, 100);
+	/* On timeout, ret is -ETIMEDOUT, otherwise it will be 0. */
 	spin_unlock_irqrestore(&qe_lock, flags);
 
-	return ret == 1;
+	return ret == 0;
 }
 EXPORT_SYMBOL(qe_issue_cmd);
 
@@ -164,8 +159,7 @@
 unsigned int qe_get_brg_clk(void)
 {
 	struct device_node *qe;
-	int size;
-	const u32 *prop;
+	u32 brg;
 	unsigned int mod;
 
 	if (brg_clk)
@@ -175,9 +169,8 @@
 	if (!qe)
 		return brg_clk;
 
-	prop = of_get_property(qe, "brg-frequency", &size);
-	if (prop && size == sizeof(*prop))
-		brg_clk = *prop;
+	if (!of_property_read_u32(qe, "brg-frequency", &brg))
+		brg_clk = brg;
 
 	of_node_put(qe);
 
@@ -197,6 +190,14 @@
 #define PVR_VER_836x	0x8083
 #define PVR_VER_832x	0x8084
 
+static bool qe_general4_errata(void)
+{
+#ifdef CONFIG_PPC32
+	return pvr_version_is(PVR_VER_836x) || pvr_version_is(PVR_VER_832x);
+#endif
+	return false;
+}
+
 /* Program the BRG to the given sampling rate and multiplier
  *
  * @brg: the BRG, QE_BRG1 - QE_BRG16
@@ -223,14 +224,14 @@
 	/* Errata QE_General4, which affects some MPC832x and MPC836x SOCs, says
 	   that the BRG divisor must be even if you're not using divide-by-16
 	   mode. */
-	if (pvr_version_is(PVR_VER_836x) || pvr_version_is(PVR_VER_832x))
+	if (qe_general4_errata())
 		if (!div16 && (divisor & 1) && (divisor > 3))
 			divisor++;
 
 	tempval = ((divisor - 1) << QE_BRGC_DIVISOR_SHIFT) |
 		QE_BRGC_ENABLE | div16;
 
-	out_be32(&qe_immr->brg.brgc[brg - QE_BRG1], tempval);
+	qe_iowrite32be(tempval, &qe_immr->brg.brgc[brg - QE_BRG1]);
 
 	return 0;
 }
@@ -364,22 +365,20 @@
 static int qe_sdma_init(void)
 {
 	struct sdma __iomem *sdma = &qe_immr->sdma;
-	static unsigned long sdma_buf_offset = (unsigned long)-ENOMEM;
-
-	if (!sdma)
-		return -ENODEV;
+	static s32 sdma_buf_offset = -ENOMEM;
 
 	/* allocate 2 internal temporary buffers (512 bytes size each) for
 	 * the SDMA */
-	if (IS_ERR_VALUE(sdma_buf_offset)) {
+	if (sdma_buf_offset < 0) {
 		sdma_buf_offset = qe_muram_alloc(512 * 2, 4096);
-		if (IS_ERR_VALUE(sdma_buf_offset))
+		if (sdma_buf_offset < 0)
 			return -ENOMEM;
 	}
 
-	out_be32(&sdma->sdebcr, (u32) sdma_buf_offset & QE_SDEBCR_BA_MASK);
- 	out_be32(&sdma->sdmr, (QE_SDMR_GLB_1_MSK |
- 					(0x1 << QE_SDMR_CEN_SHIFT)));
+	qe_iowrite32be((u32)sdma_buf_offset & QE_SDEBCR_BA_MASK,
+		       &sdma->sdebcr);
+	qe_iowrite32be((QE_SDMR_GLB_1_MSK | (0x1 << QE_SDMR_CEN_SHIFT)),
+		       &sdma->sdmr);
 
 	return 0;
 }
@@ -417,14 +416,14 @@
 			"uploading microcode '%s'\n", ucode->id);
 
 	/* Use auto-increment */
-	out_be32(&qe_immr->iram.iadd, be32_to_cpu(ucode->iram_offset) |
-		QE_IRAM_IADD_AIE | QE_IRAM_IADD_BADDR);
+	qe_iowrite32be(be32_to_cpu(ucode->iram_offset) | QE_IRAM_IADD_AIE | QE_IRAM_IADD_BADDR,
+		       &qe_immr->iram.iadd);
 
 	for (i = 0; i < be32_to_cpu(ucode->count); i++)
-		out_be32(&qe_immr->iram.idata, be32_to_cpu(code[i]));
+		qe_iowrite32be(be32_to_cpu(code[i]), &qe_immr->iram.idata);
 	
 	/* Set I-RAM Ready Register */
-	out_be32(&qe_immr->iram.iready, be32_to_cpu(QE_IRAM_READY));
+	qe_iowrite32be(QE_IRAM_READY, &qe_immr->iram.iready);
 }
 
 /*
@@ -449,7 +448,7 @@
 	unsigned int i;
 	unsigned int j;
 	u32 crc;
-	size_t calc_size = sizeof(struct qe_firmware);
+	size_t calc_size;
 	size_t length;
 	const struct qe_header *hdr;
 
@@ -481,7 +480,7 @@
 	}
 
 	/* Validate the length and check if there's a CRC */
-	calc_size += (firmware->count - 1) * sizeof(struct qe_microcode);
+	calc_size = struct_size(firmware, microcode, firmware->count);
 
 	for (i = 0; i < firmware->count; i++)
 		/*
@@ -509,7 +508,7 @@
 	 * If the microcode calls for it, split the I-RAM.
 	 */
 	if (!firmware->split)
-		setbits16(&qe_immr->cp.cercr, QE_CP_CERCR_CIR);
+		qe_setbits_be16(&qe_immr->cp.cercr, QE_CP_CERCR_CIR);
 
 	if (firmware->soc.model)
 		printk(KERN_INFO
@@ -526,7 +525,7 @@
 	 */
 	memset(&qe_firmware_info, 0, sizeof(qe_firmware_info));
 	strlcpy(qe_firmware_info.id, firmware->id, sizeof(qe_firmware_info.id));
-	qe_firmware_info.extended_modes = firmware->extended_modes;
+	qe_firmware_info.extended_modes = be64_to_cpu(firmware->extended_modes);
 	memcpy(qe_firmware_info.vtraps, firmware->vtraps,
 		sizeof(firmware->vtraps));
 
@@ -543,11 +542,13 @@
 			u32 trap = be32_to_cpu(ucode->traps[j]);
 
 			if (trap)
-				out_be32(&qe_immr->rsp[i].tibcr[j], trap);
+				qe_iowrite32be(trap,
+					       &qe_immr->rsp[i].tibcr[j]);
 		}
 
 		/* Enable traps */
-		out_be32(&qe_immr->rsp[i].eccr, be32_to_cpu(ucode->eccr));
+		qe_iowrite32be(be32_to_cpu(ucode->eccr),
+			       &qe_immr->rsp[i].eccr);
 	}
 
 	qe_firmware_uploaded = 1;
@@ -565,11 +566,9 @@
 struct qe_firmware_info *qe_get_firmware_info(void)
 {
 	static int initialized;
-	struct property *prop;
 	struct device_node *qe;
 	struct device_node *fw = NULL;
 	const char *sprop;
-	unsigned int i;
 
 	/*
 	 * If we haven't checked yet, and a driver hasn't uploaded a firmware
@@ -603,20 +602,11 @@
 		strlcpy(qe_firmware_info.id, sprop,
 			sizeof(qe_firmware_info.id));
 
-	prop = of_find_property(fw, "extended-modes", NULL);
-	if (prop && (prop->length == sizeof(u64))) {
-		const u64 *iprop = prop->value;
+	of_property_read_u64(fw, "extended-modes",
+			     &qe_firmware_info.extended_modes);
 
-		qe_firmware_info.extended_modes = *iprop;
-	}
-
-	prop = of_find_property(fw, "virtual-traps", NULL);
-	if (prop && (prop->length == 32)) {
-		const u32 *iprop = prop->value;
-
-		for (i = 0; i < ARRAY_SIZE(qe_firmware_info.vtraps); i++)
-			qe_firmware_info.vtraps[i] = iprop[i];
-	}
+	of_property_read_u32_array(fw, "virtual-traps", qe_firmware_info.vtraps,
+				   ARRAY_SIZE(qe_firmware_info.vtraps));
 
 	of_node_put(fw);
 
@@ -627,17 +617,13 @@
 unsigned int qe_get_num_of_risc(void)
 {
 	struct device_node *qe;
-	int size;
 	unsigned int num_of_risc = 0;
-	const u32 *prop;
 
 	qe = qe_get_device_node();
 	if (!qe)
 		return num_of_risc;
 
-	prop = of_get_property(qe, "fsl,qe-num-riscs", &size);
-	if (prop && size == sizeof(*prop))
-		num_of_risc = *prop;
+	of_property_read_u32(qe, "fsl,qe-num-riscs", &num_of_risc);
 
 	of_node_put(qe);
 
diff --git a/drivers/soc/fsl/qe/qe_common.c b/drivers/soc/fsl/qe/qe_common.c
index 83e85e6..7507559 100644
--- a/drivers/soc/fsl/qe/qe_common.c
+++ b/drivers/soc/fsl/qe/qe_common.c
@@ -32,7 +32,7 @@
 
 struct muram_block {
 	struct list_head head;
-	unsigned long start;
+	s32 start;
 	int size;
 };
 
@@ -46,7 +46,7 @@
 {
 	struct device_node *np;
 	struct resource r;
-	u32 zero[OF_MAX_ADDR_CELLS] = {};
+	__be32 zero[OF_MAX_ADDR_CELLS] = {};
 	resource_size_t max = 0;
 	int i = 0;
 	int ret = 0;
@@ -110,34 +110,30 @@
  * @algo: algorithm for alloc.
  * @data: data for genalloc's algorithm.
  *
- * This function returns an offset into the muram area.
+ * This function returns a non-negative offset into the muram area, or
+ * a negative errno on failure.
  */
-static unsigned long cpm_muram_alloc_common(unsigned long size,
-		genpool_algo_t algo, void *data)
+static s32 cpm_muram_alloc_common(unsigned long size,
+				  genpool_algo_t algo, void *data)
 {
 	struct muram_block *entry;
-	unsigned long start;
+	s32 start;
 
-	if (!muram_pool && cpm_muram_init())
-		goto out2;
-
-	start = gen_pool_alloc_algo(muram_pool, size, algo, data);
-	if (!start)
-		goto out2;
-	start = start - GENPOOL_OFFSET;
-	memset_io(cpm_muram_addr(start), 0, size);
 	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry)
-		goto out1;
+		return -ENOMEM;
+	start = gen_pool_alloc_algo(muram_pool, size, algo, data);
+	if (!start) {
+		kfree(entry);
+		return -ENOMEM;
+	}
+	start = start - GENPOOL_OFFSET;
+	memset_io(cpm_muram_addr(start), 0, size);
 	entry->start = start;
 	entry->size = size;
 	list_add(&entry->head, &muram_block_list);
 
 	return start;
-out1:
-	gen_pool_free(muram_pool, start, size);
-out2:
-	return (unsigned long)-ENOMEM;
 }
 
 /*
@@ -145,13 +141,14 @@
  * @size: number of bytes to allocate
  * @align: requested alignment, in bytes
  *
- * This function returns an offset into the muram area.
+ * This function returns a non-negative offset into the muram area, or
+ * a negative errno on failure.
  * Use cpm_dpram_addr() to get the virtual address of the area.
  * Use cpm_muram_free() to free the allocation.
  */
-unsigned long cpm_muram_alloc(unsigned long size, unsigned long align)
+s32 cpm_muram_alloc(unsigned long size, unsigned long align)
 {
-	unsigned long start;
+	s32 start;
 	unsigned long flags;
 	struct genpool_data_align muram_pool_data;
 
@@ -168,12 +165,15 @@
  * cpm_muram_free - free a chunk of multi-user ram
  * @offset: The beginning of the chunk as returned by cpm_muram_alloc().
  */
-int cpm_muram_free(unsigned long offset)
+void cpm_muram_free(s32 offset)
 {
 	unsigned long flags;
 	int size;
 	struct muram_block *tmp;
 
+	if (offset < 0)
+		return;
+
 	size = 0;
 	spin_lock_irqsave(&cpm_muram_lock, flags);
 	list_for_each_entry(tmp, &muram_block_list, head) {
@@ -186,7 +186,6 @@
 	}
 	gen_pool_free(muram_pool, offset + GENPOOL_OFFSET, size);
 	spin_unlock_irqrestore(&cpm_muram_lock, flags);
-	return size;
 }
 EXPORT_SYMBOL(cpm_muram_free);
 
@@ -194,13 +193,14 @@
  * cpm_muram_alloc_fixed - reserve a specific region of multi-user ram
  * @offset: offset of allocation start address
  * @size: number of bytes to allocate
- * This function returns an offset into the muram area
+ * This function returns @offset if the area was available, a negative
+ * errno otherwise.
  * Use cpm_dpram_addr() to get the virtual address of the area.
  * Use cpm_muram_free() to free the allocation.
  */
-unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size)
+s32 cpm_muram_alloc_fixed(unsigned long offset, unsigned long size)
 {
-	unsigned long start;
+	s32 start;
 	unsigned long flags;
 	struct genpool_data_fixed muram_pool_data_fixed;
 
diff --git a/drivers/soc/fsl/qe/qe_ic.c b/drivers/soc/fsl/qe/qe_ic.c
index 9bac546..0390af9 100644
--- a/drivers/soc/fsl/qe/qe_ic.c
+++ b/drivers/soc/fsl/qe/qe_ic.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/errno.h>
+#include <linux/irq.h>
 #include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
@@ -24,9 +25,57 @@
 #include <linux/spinlock.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <soc/fsl/qe/qe_ic.h>
+#include <soc/fsl/qe/qe.h>
 
-#include "qe_ic.h"
+#define NR_QE_IC_INTS		64
+
+/* QE IC registers offset */
+#define QEIC_CICR		0x00
+#define QEIC_CIVEC		0x04
+#define QEIC_CIPXCC		0x10
+#define QEIC_CIPYCC		0x14
+#define QEIC_CIPWCC		0x18
+#define QEIC_CIPZCC		0x1c
+#define QEIC_CIMR		0x20
+#define QEIC_CRIMR		0x24
+#define QEIC_CIPRTA		0x30
+#define QEIC_CIPRTB		0x34
+#define QEIC_CHIVEC		0x60
+
+struct qe_ic {
+	/* Control registers offset */
+	__be32 __iomem *regs;
+
+	/* The remapper for this QEIC */
+	struct irq_domain *irqhost;
+
+	/* The "linux" controller struct */
+	struct irq_chip hc_irq;
+
+	/* VIRQ numbers of QE high/low irqs */
+	unsigned int virq_high;
+	unsigned int virq_low;
+};
+
+/*
+ * QE interrupt controller internal structure
+ */
+struct qe_ic_info {
+	/* Location of this source at the QIMR register */
+	u32	mask;
+
+	/* Mask register offset */
+	u32	mask_reg;
+
+	/*
+	 * For grouped interrupts sources - the interrupt code as
+	 * appears at the group priority register
+	 */
+	u8	pri_code;
+
+	/* Group priority register offset */
+	u32	pri_reg;
+};
 
 static DEFINE_RAW_SPINLOCK(qe_ic_lock);
 
@@ -171,15 +220,15 @@
 		},
 };
 
-static inline u32 qe_ic_read(volatile __be32  __iomem * base, unsigned int reg)
+static inline u32 qe_ic_read(__be32  __iomem *base, unsigned int reg)
 {
-	return in_be32(base + (reg >> 2));
+	return qe_ioread32be(base + (reg >> 2));
 }
 
-static inline void qe_ic_write(volatile __be32  __iomem * base, unsigned int reg,
+static inline void qe_ic_write(__be32  __iomem *base, unsigned int reg,
 			       u32 value)
 {
-	out_be32(base + (reg >> 2), value);
+	qe_iowrite32be(value, base + (reg >> 2));
 }
 
 static inline struct qe_ic *qe_ic_from_irq(unsigned int virq)
@@ -281,8 +330,8 @@
 	.xlate = irq_domain_xlate_onetwocell,
 };
 
-/* Return an interrupt vector or NO_IRQ if no interrupt is pending. */
-unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic)
+/* Return an interrupt vector or 0 if no interrupt is pending. */
+static unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic)
 {
 	int irq;
 
@@ -292,13 +341,13 @@
 	irq = qe_ic_read(qe_ic->regs, QEIC_CIVEC) >> 26;
 
 	if (irq == 0)
-		return NO_IRQ;
+		return 0;
 
 	return irq_linear_revmap(qe_ic->irqhost, irq);
 }
 
-/* Return an interrupt vector or NO_IRQ if no interrupt is pending. */
-unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic)
+/* Return an interrupt vector or 0 if no interrupt is pending. */
+static unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic)
 {
 	int irq;
 
@@ -308,18 +357,60 @@
 	irq = qe_ic_read(qe_ic->regs, QEIC_CHIVEC) >> 26;
 
 	if (irq == 0)
-		return NO_IRQ;
+		return 0;
 
 	return irq_linear_revmap(qe_ic->irqhost, irq);
 }
 
-void __init qe_ic_init(struct device_node *node, unsigned int flags,
-		       void (*low_handler)(struct irq_desc *desc),
-		       void (*high_handler)(struct irq_desc *desc))
+static void qe_ic_cascade_low(struct irq_desc *desc)
 {
+	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
+	unsigned int cascade_irq = qe_ic_get_low_irq(qe_ic);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	if (cascade_irq != 0)
+		generic_handle_irq(cascade_irq);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+}
+
+static void qe_ic_cascade_high(struct irq_desc *desc)
+{
+	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
+	unsigned int cascade_irq = qe_ic_get_high_irq(qe_ic);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	if (cascade_irq != 0)
+		generic_handle_irq(cascade_irq);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+}
+
+static void qe_ic_cascade_muxed_mpic(struct irq_desc *desc)
+{
+	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
+	unsigned int cascade_irq;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	cascade_irq = qe_ic_get_high_irq(qe_ic);
+	if (cascade_irq == 0)
+		cascade_irq = qe_ic_get_low_irq(qe_ic);
+
+	if (cascade_irq != 0)
+		generic_handle_irq(cascade_irq);
+
+	chip->irq_eoi(&desc->irq_data);
+}
+
+static void __init qe_ic_init(struct device_node *node)
+{
+	void (*low_handler)(struct irq_desc *desc);
+	void (*high_handler)(struct irq_desc *desc);
 	struct qe_ic *qe_ic;
 	struct resource res;
-	u32 temp = 0, ret, high_active = 0;
+	u32 ret;
 
 	ret = of_address_to_resource(node, 0, &res);
 	if (ret)
@@ -343,166 +434,42 @@
 	qe_ic->virq_high = irq_of_parse_and_map(node, 0);
 	qe_ic->virq_low = irq_of_parse_and_map(node, 1);
 
-	if (qe_ic->virq_low == NO_IRQ) {
+	if (!qe_ic->virq_low) {
 		printk(KERN_ERR "Failed to map QE_IC low IRQ\n");
 		kfree(qe_ic);
 		return;
 	}
-
-	/* default priority scheme is grouped. If spread mode is    */
-	/* required, configure cicr accordingly.                    */
-	if (flags & QE_IC_SPREADMODE_GRP_W)
-		temp |= CICR_GWCC;
-	if (flags & QE_IC_SPREADMODE_GRP_X)
-		temp |= CICR_GXCC;
-	if (flags & QE_IC_SPREADMODE_GRP_Y)
-		temp |= CICR_GYCC;
-	if (flags & QE_IC_SPREADMODE_GRP_Z)
-		temp |= CICR_GZCC;
-	if (flags & QE_IC_SPREADMODE_GRP_RISCA)
-		temp |= CICR_GRTA;
-	if (flags & QE_IC_SPREADMODE_GRP_RISCB)
-		temp |= CICR_GRTB;
-
-	/* choose destination signal for highest priority interrupt */
-	if (flags & QE_IC_HIGH_SIGNAL) {
-		temp |= (SIGNAL_HIGH << CICR_HPIT_SHIFT);
-		high_active = 1;
+	if (qe_ic->virq_high != qe_ic->virq_low) {
+		low_handler = qe_ic_cascade_low;
+		high_handler = qe_ic_cascade_high;
+	} else {
+		low_handler = qe_ic_cascade_muxed_mpic;
+		high_handler = NULL;
 	}
 
-	qe_ic_write(qe_ic->regs, QEIC_CICR, temp);
+	qe_ic_write(qe_ic->regs, QEIC_CICR, 0);
 
 	irq_set_handler_data(qe_ic->virq_low, qe_ic);
 	irq_set_chained_handler(qe_ic->virq_low, low_handler);
 
-	if (qe_ic->virq_high != NO_IRQ &&
-			qe_ic->virq_high != qe_ic->virq_low) {
+	if (qe_ic->virq_high && qe_ic->virq_high != qe_ic->virq_low) {
 		irq_set_handler_data(qe_ic->virq_high, qe_ic);
 		irq_set_chained_handler(qe_ic->virq_high, high_handler);
 	}
 }
 
-void qe_ic_set_highest_priority(unsigned int virq, int high)
+static int __init qe_ic_of_init(void)
 {
-	struct qe_ic *qe_ic = qe_ic_from_irq(virq);
-	unsigned int src = virq_to_hw(virq);
-	u32 temp = 0;
+	struct device_node *np;
 
-	temp = qe_ic_read(qe_ic->regs, QEIC_CICR);
-
-	temp &= ~CICR_HP_MASK;
-	temp |= src << CICR_HP_SHIFT;
-
-	temp &= ~CICR_HPIT_MASK;
-	temp |= (high ? SIGNAL_HIGH : SIGNAL_LOW) << CICR_HPIT_SHIFT;
-
-	qe_ic_write(qe_ic->regs, QEIC_CICR, temp);
-}
-
-/* Set Priority level within its group, from 1 to 8 */
-int qe_ic_set_priority(unsigned int virq, unsigned int priority)
-{
-	struct qe_ic *qe_ic = qe_ic_from_irq(virq);
-	unsigned int src = virq_to_hw(virq);
-	u32 temp;
-
-	if (priority > 8 || priority == 0)
-		return -EINVAL;
-	if (WARN_ONCE(src >= ARRAY_SIZE(qe_ic_info),
-		      "%s: Invalid hw irq number for QEIC\n", __func__))
-		return -EINVAL;
-	if (qe_ic_info[src].pri_reg == 0)
-		return -EINVAL;
-
-	temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].pri_reg);
-
-	if (priority < 4) {
-		temp &= ~(0x7 << (32 - priority * 3));
-		temp |= qe_ic_info[src].pri_code << (32 - priority * 3);
-	} else {
-		temp &= ~(0x7 << (24 - priority * 3));
-		temp |= qe_ic_info[src].pri_code << (24 - priority * 3);
+	np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic");
+	if (!np) {
+		np = of_find_node_by_type(NULL, "qeic");
+		if (!np)
+			return -ENODEV;
 	}
-
-	qe_ic_write(qe_ic->regs, qe_ic_info[src].pri_reg, temp);
-
+	qe_ic_init(np);
+	of_node_put(np);
 	return 0;
 }
-
-/* Set a QE priority to use high irq, only priority 1~2 can use high irq */
-int qe_ic_set_high_priority(unsigned int virq, unsigned int priority, int high)
-{
-	struct qe_ic *qe_ic = qe_ic_from_irq(virq);
-	unsigned int src = virq_to_hw(virq);
-	u32 temp, control_reg = QEIC_CICNR, shift = 0;
-
-	if (priority > 2 || priority == 0)
-		return -EINVAL;
-	if (WARN_ONCE(src >= ARRAY_SIZE(qe_ic_info),
-		      "%s: Invalid hw irq number for QEIC\n", __func__))
-		return -EINVAL;
-
-	switch (qe_ic_info[src].pri_reg) {
-	case QEIC_CIPZCC:
-		shift = CICNR_ZCC1T_SHIFT;
-		break;
-	case QEIC_CIPWCC:
-		shift = CICNR_WCC1T_SHIFT;
-		break;
-	case QEIC_CIPYCC:
-		shift = CICNR_YCC1T_SHIFT;
-		break;
-	case QEIC_CIPXCC:
-		shift = CICNR_XCC1T_SHIFT;
-		break;
-	case QEIC_CIPRTA:
-		shift = CRICR_RTA1T_SHIFT;
-		control_reg = QEIC_CRICR;
-		break;
-	case QEIC_CIPRTB:
-		shift = CRICR_RTB1T_SHIFT;
-		control_reg = QEIC_CRICR;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	shift += (2 - priority) * 2;
-	temp = qe_ic_read(qe_ic->regs, control_reg);
-	temp &= ~(SIGNAL_MASK << shift);
-	temp |= (high ? SIGNAL_HIGH : SIGNAL_LOW) << shift;
-	qe_ic_write(qe_ic->regs, control_reg, temp);
-
-	return 0;
-}
-
-static struct bus_type qe_ic_subsys = {
-	.name = "qe_ic",
-	.dev_name = "qe_ic",
-};
-
-static struct device device_qe_ic = {
-	.id = 0,
-	.bus = &qe_ic_subsys,
-};
-
-static int __init init_qe_ic_sysfs(void)
-{
-	int rc;
-
-	printk(KERN_DEBUG "Registering qe_ic with sysfs...\n");
-
-	rc = subsys_system_register(&qe_ic_subsys, NULL);
-	if (rc) {
-		printk(KERN_ERR "Failed registering qe_ic sys class\n");
-		return -ENODEV;
-	}
-	rc = device_register(&device_qe_ic);
-	if (rc) {
-		printk(KERN_ERR "Failed registering qe_ic sys device\n");
-		return -ENODEV;
-	}
-	return 0;
-}
-
-subsys_initcall(init_qe_ic_sysfs);
+subsys_initcall(qe_ic_of_init);
diff --git a/drivers/soc/fsl/qe/qe_ic.h b/drivers/soc/fsl/qe/qe_ic.h
deleted file mode 100644
index 08c6956..0000000
--- a/drivers/soc/fsl/qe/qe_ic.h
+++ /dev/null
@@ -1,99 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * drivers/soc/fsl/qe/qe_ic.h
- *
- * QUICC ENGINE Interrupt Controller Header
- *
- * Copyright (C) 2006 Freescale Semiconductor, Inc. All rights reserved.
- *
- * Author: Li Yang <leoli@freescale.com>
- * Based on code from Shlomi Gridish <gridish@freescale.com>
- */
-#ifndef _POWERPC_SYSDEV_QE_IC_H
-#define _POWERPC_SYSDEV_QE_IC_H
-
-#include <soc/fsl/qe/qe_ic.h>
-
-#define NR_QE_IC_INTS		64
-
-/* QE IC registers offset */
-#define QEIC_CICR		0x00
-#define QEIC_CIVEC		0x04
-#define QEIC_CRIPNR		0x08
-#define QEIC_CIPNR		0x0c
-#define QEIC_CIPXCC		0x10
-#define QEIC_CIPYCC		0x14
-#define QEIC_CIPWCC		0x18
-#define QEIC_CIPZCC		0x1c
-#define QEIC_CIMR		0x20
-#define QEIC_CRIMR		0x24
-#define QEIC_CICNR		0x28
-#define QEIC_CIPRTA		0x30
-#define QEIC_CIPRTB		0x34
-#define QEIC_CRICR		0x3c
-#define QEIC_CHIVEC		0x60
-
-/* Interrupt priority registers */
-#define CIPCC_SHIFT_PRI0	29
-#define CIPCC_SHIFT_PRI1	26
-#define CIPCC_SHIFT_PRI2	23
-#define CIPCC_SHIFT_PRI3	20
-#define CIPCC_SHIFT_PRI4	13
-#define CIPCC_SHIFT_PRI5	10
-#define CIPCC_SHIFT_PRI6	7
-#define CIPCC_SHIFT_PRI7	4
-
-/* CICR priority modes */
-#define CICR_GWCC		0x00040000
-#define CICR_GXCC		0x00020000
-#define CICR_GYCC		0x00010000
-#define CICR_GZCC		0x00080000
-#define CICR_GRTA		0x00200000
-#define CICR_GRTB		0x00400000
-#define CICR_HPIT_SHIFT		8
-#define CICR_HPIT_MASK		0x00000300
-#define CICR_HP_SHIFT		24
-#define CICR_HP_MASK		0x3f000000
-
-/* CICNR */
-#define CICNR_WCC1T_SHIFT	20
-#define CICNR_ZCC1T_SHIFT	28
-#define CICNR_YCC1T_SHIFT	12
-#define CICNR_XCC1T_SHIFT	4
-
-/* CRICR */
-#define CRICR_RTA1T_SHIFT	20
-#define CRICR_RTB1T_SHIFT	28
-
-/* Signal indicator */
-#define SIGNAL_MASK		3
-#define SIGNAL_HIGH		2
-#define SIGNAL_LOW		0
-
-struct qe_ic {
-	/* Control registers offset */
-	volatile u32 __iomem *regs;
-
-	/* The remapper for this QEIC */
-	struct irq_domain *irqhost;
-
-	/* The "linux" controller struct */
-	struct irq_chip hc_irq;
-
-	/* VIRQ numbers of QE high/low irqs */
-	unsigned int virq_high;
-	unsigned int virq_low;
-};
-
-/*
- * QE interrupt controller internal structure
- */
-struct qe_ic_info {
-	u32	mask;	  /* location of this source at the QIMR register. */
-	u32	mask_reg; /* Mask register offset */
-	u8	pri_code; /* for grouped interrupts sources - the interrupt
-			     code as appears at the group priority register */
-	u32	pri_reg;  /* Group priority register offset */
-};
-
-#endif /* _POWERPC_SYSDEV_QE_IC_H */
diff --git a/drivers/soc/fsl/qe/qe_io.c b/drivers/soc/fsl/qe/qe_io.c
index 3657e29..1bb46d9 100644
--- a/drivers/soc/fsl/qe/qe_io.c
+++ b/drivers/soc/fsl/qe/qe_io.c
@@ -18,8 +18,6 @@
 
 #include <asm/io.h>
 #include <soc/fsl/qe/qe.h>
-#include <asm/prom.h>
-#include <sysdev/fsl_soc.h>
 
 #undef DEBUG
 
@@ -30,17 +28,18 @@
 {
 	struct resource res;
 	int ret;
-	const u32 *num_ports;
+	u32 num_ports;
 
 	/* Map Parallel I/O ports registers */
 	ret = of_address_to_resource(np, 0, &res);
 	if (ret)
 		return ret;
 	par_io = ioremap(res.start, resource_size(&res));
+	if (!par_io)
+		return -ENOMEM;
 
-	num_ports = of_get_property(np, "num-ports", NULL);
-	if (num_ports)
-		num_par_io_ports = *num_ports;
+	if (!of_property_read_u32(np, "num-ports", &num_ports))
+		num_par_io_ports = num_ports;
 
 	return 0;
 }
@@ -57,16 +56,16 @@
 	pin_mask1bit = (u32) (1 << (QE_PIO_PINS - (pin + 1)));
 
 	/* Set open drain, if required */
-	tmp_val = in_be32(&par_io->cpodr);
+	tmp_val = qe_ioread32be(&par_io->cpodr);
 	if (open_drain)
-		out_be32(&par_io->cpodr, pin_mask1bit | tmp_val);
+		qe_iowrite32be(pin_mask1bit | tmp_val, &par_io->cpodr);
 	else
-		out_be32(&par_io->cpodr, ~pin_mask1bit & tmp_val);
+		qe_iowrite32be(~pin_mask1bit & tmp_val, &par_io->cpodr);
 
 	/* define direction */
 	tmp_val = (pin > (QE_PIO_PINS / 2) - 1) ?
-		in_be32(&par_io->cpdir2) :
-		in_be32(&par_io->cpdir1);
+		qe_ioread32be(&par_io->cpdir2) :
+		qe_ioread32be(&par_io->cpdir1);
 
 	/* get all bits mask for 2 bit per port */
 	pin_mask2bits = (u32) (0x3 << (QE_PIO_PINS -
@@ -78,34 +77,30 @@
 
 	/* clear and set 2 bits mask */
 	if (pin > (QE_PIO_PINS / 2) - 1) {
-		out_be32(&par_io->cpdir2,
-			 ~pin_mask2bits & tmp_val);
+		qe_iowrite32be(~pin_mask2bits & tmp_val, &par_io->cpdir2);
 		tmp_val &= ~pin_mask2bits;
-		out_be32(&par_io->cpdir2, new_mask2bits | tmp_val);
+		qe_iowrite32be(new_mask2bits | tmp_val, &par_io->cpdir2);
 	} else {
-		out_be32(&par_io->cpdir1,
-			 ~pin_mask2bits & tmp_val);
+		qe_iowrite32be(~pin_mask2bits & tmp_val, &par_io->cpdir1);
 		tmp_val &= ~pin_mask2bits;
-		out_be32(&par_io->cpdir1, new_mask2bits | tmp_val);
+		qe_iowrite32be(new_mask2bits | tmp_val, &par_io->cpdir1);
 	}
 	/* define pin assignment */
 	tmp_val = (pin > (QE_PIO_PINS / 2) - 1) ?
-		in_be32(&par_io->cppar2) :
-		in_be32(&par_io->cppar1);
+		qe_ioread32be(&par_io->cppar2) :
+		qe_ioread32be(&par_io->cppar1);
 
 	new_mask2bits = (u32) (assignment << (QE_PIO_PINS -
 			(pin % (QE_PIO_PINS / 2) + 1) * 2));
 	/* clear and set 2 bits mask */
 	if (pin > (QE_PIO_PINS / 2) - 1) {
-		out_be32(&par_io->cppar2,
-			 ~pin_mask2bits & tmp_val);
+		qe_iowrite32be(~pin_mask2bits & tmp_val, &par_io->cppar2);
 		tmp_val &= ~pin_mask2bits;
-		out_be32(&par_io->cppar2, new_mask2bits | tmp_val);
+		qe_iowrite32be(new_mask2bits | tmp_val, &par_io->cppar2);
 	} else {
-		out_be32(&par_io->cppar1,
-			 ~pin_mask2bits & tmp_val);
+		qe_iowrite32be(~pin_mask2bits & tmp_val, &par_io->cppar1);
 		tmp_val &= ~pin_mask2bits;
-		out_be32(&par_io->cppar1, new_mask2bits | tmp_val);
+		qe_iowrite32be(new_mask2bits | tmp_val, &par_io->cppar1);
 	}
 }
 EXPORT_SYMBOL(__par_io_config_pin);
@@ -133,12 +128,12 @@
 	/* calculate pin location */
 	pin_mask = (u32) (1 << (QE_PIO_PINS - 1 - pin));
 
-	tmp_val = in_be32(&par_io[port].cpdata);
+	tmp_val = qe_ioread32be(&par_io[port].cpdata);
 
 	if (val == 0)		/* clear */
-		out_be32(&par_io[port].cpdata, ~pin_mask & tmp_val);
+		qe_iowrite32be(~pin_mask & tmp_val, &par_io[port].cpdata);
 	else			/* set */
-		out_be32(&par_io[port].cpdata, pin_mask | tmp_val);
+		qe_iowrite32be(pin_mask | tmp_val, &par_io[port].cpdata);
 
 	return 0;
 }
@@ -147,23 +142,20 @@
 int par_io_of_config(struct device_node *np)
 {
 	struct device_node *pio;
-	const phandle *ph;
 	int pio_map_len;
-	const unsigned int *pio_map;
+	const __be32 *pio_map;
 
 	if (par_io == NULL) {
 		printk(KERN_ERR "par_io not initialized\n");
 		return -1;
 	}
 
-	ph = of_get_property(np, "pio-handle", NULL);
-	if (ph == NULL) {
+	pio = of_parse_phandle(np, "pio-handle", 0);
+	if (pio == NULL) {
 		printk(KERN_ERR "pio-handle not available\n");
 		return -1;
 	}
 
-	pio = of_find_node_by_phandle(*ph);
-
 	pio_map = of_get_property(pio, "pio-map", &pio_map_len);
 	if (pio_map == NULL) {
 		printk(KERN_ERR "pio-map is not set!\n");
@@ -176,9 +168,15 @@
 	}
 
 	while (pio_map_len > 0) {
-		par_io_config_pin((u8) pio_map[0], (u8) pio_map[1],
-				(int) pio_map[2], (int) pio_map[3],
-				(int) pio_map[4], (int) pio_map[5]);
+		u8 port        = be32_to_cpu(pio_map[0]);
+		u8 pin         = be32_to_cpu(pio_map[1]);
+		int dir        = be32_to_cpu(pio_map[2]);
+		int open_drain = be32_to_cpu(pio_map[3]);
+		int assignment = be32_to_cpu(pio_map[4]);
+		int has_irq    = be32_to_cpu(pio_map[5]);
+
+		par_io_config_pin(port, pin, dir, open_drain,
+				  assignment, has_irq);
 		pio_map += 6;
 		pio_map_len -= 6;
 	}
diff --git a/drivers/soc/fsl/qe/qe_tdm.c b/drivers/soc/fsl/qe/qe_tdm.c
index e37ebc3..7d7d78d 100644
--- a/drivers/soc/fsl/qe/qe_tdm.c
+++ b/drivers/soc/fsl/qe/qe_tdm.c
@@ -169,10 +169,10 @@
 				    &siram[siram_entry_id * 32 + 0x200 +  i]);
 	}
 
-	setbits16(&siram[(siram_entry_id * 32) + (utdm->num_of_ts - 1)],
-		  SIR_LAST);
-	setbits16(&siram[(siram_entry_id * 32) + 0x200 + (utdm->num_of_ts - 1)],
-		  SIR_LAST);
+	qe_setbits_be16(&siram[(siram_entry_id * 32) + (utdm->num_of_ts - 1)],
+			SIR_LAST);
+	qe_setbits_be16(&siram[(siram_entry_id * 32) + 0x200 + (utdm->num_of_ts - 1)],
+			SIR_LAST);
 
 	/* Set SIxMR register */
 	sixmr = SIMR_SAD(siram_entry_id);
diff --git a/drivers/soc/fsl/qe/ucc.c b/drivers/soc/fsl/qe/ucc.c
index 024d239..21dbcd7 100644
--- a/drivers/soc/fsl/qe/ucc.c
+++ b/drivers/soc/fsl/qe/ucc.c
@@ -15,7 +15,6 @@
 #include <linux/spinlock.h>
 #include <linux/export.h>
 
-#include <asm/irq.h>
 #include <asm/io.h>
 #include <soc/fsl/qe/immap_qe.h>
 #include <soc/fsl/qe/qe.h>
@@ -35,8 +34,8 @@
 		return -EINVAL;
 
 	spin_lock_irqsave(&cmxgcr_lock, flags);
-	clrsetbits_be32(&qe_immr->qmx.cmxgcr, QE_CMXGCR_MII_ENET_MNG,
-		ucc_num << QE_CMXGCR_MII_ENET_MNG_SHIFT);
+	qe_clrsetbits_be32(&qe_immr->qmx.cmxgcr, QE_CMXGCR_MII_ENET_MNG,
+			   ucc_num << QE_CMXGCR_MII_ENET_MNG_SHIFT);
 	spin_unlock_irqrestore(&cmxgcr_lock, flags);
 
 	return 0;
@@ -80,8 +79,8 @@
 		return -EINVAL;
 	}
 
-	clrsetbits_8(guemr, UCC_GUEMR_MODE_MASK,
-		UCC_GUEMR_SET_RESERVED3 | speed);
+	qe_clrsetbits_8(guemr, UCC_GUEMR_MODE_MASK,
+			UCC_GUEMR_SET_RESERVED3 | speed);
 
 	return 0;
 }
@@ -109,9 +108,9 @@
 	get_cmxucr_reg(ucc_num, &cmxucr, &reg_num, &shift);
 
 	if (set)
-		setbits32(cmxucr, mask << shift);
+		qe_setbits_be32(cmxucr, mask << shift);
 	else
-		clrbits32(cmxucr, mask << shift);
+		qe_clrbits_be32(cmxucr, mask << shift);
 
 	return 0;
 }
@@ -207,8 +206,8 @@
 	if (mode == COMM_DIR_RX)
 		shift += 4;
 
-	clrsetbits_be32(cmxucr, QE_CMXUCR_TX_CLK_SRC_MASK << shift,
-		clock_bits << shift);
+	qe_clrsetbits_be32(cmxucr, QE_CMXUCR_TX_CLK_SRC_MASK << shift,
+			   clock_bits << shift);
 
 	return 0;
 }
@@ -520,11 +519,11 @@
 	int clock_bits;
 	u32 shift;
 	struct qe_mux __iomem *qe_mux_reg;
-	 __be32 __iomem *cmxs1cr;
+	__be32 __iomem *cmxs1cr;
 
 	qe_mux_reg = &qe_immr->qmx;
 
-	if (tdm_num > 7 || tdm_num < 0)
+	if (tdm_num > 7)
 		return -EINVAL;
 
 	/* The communications direction must be RX or TX */
@@ -540,8 +539,8 @@
 	cmxs1cr = (tdm_num < 4) ? &qe_mux_reg->cmxsi1cr_l :
 				  &qe_mux_reg->cmxsi1cr_h;
 
-	qe_clrsetbits32(cmxs1cr, QE_CMXUCR_TX_CLK_SRC_MASK << shift,
-			clock_bits << shift);
+	qe_clrsetbits_be32(cmxs1cr, QE_CMXUCR_TX_CLK_SRC_MASK << shift,
+			   clock_bits << shift);
 
 	return 0;
 }
@@ -633,7 +632,7 @@
 {
 	int source;
 	u32 shift;
-	struct qe_mux *qe_mux_reg;
+	struct qe_mux __iomem *qe_mux_reg;
 
 	qe_mux_reg = &qe_immr->qmx;
 
@@ -650,9 +649,9 @@
 
 	shift = ucc_get_tdm_sync_shift(mode, tdm_num);
 
-	qe_clrsetbits32(&qe_mux_reg->cmxsi1syr,
-			QE_CMXUCR_TX_CLK_SRC_MASK << shift,
-			source << shift);
+	qe_clrsetbits_be32(&qe_mux_reg->cmxsi1syr,
+			   QE_CMXUCR_TX_CLK_SRC_MASK << shift,
+			   source << shift);
 
 	return 0;
 }
diff --git a/drivers/soc/fsl/qe/ucc_fast.c b/drivers/soc/fsl/qe/ucc_fast.c
index af4d80e..ad6193e 100644
--- a/drivers/soc/fsl/qe/ucc_fast.c
+++ b/drivers/soc/fsl/qe/ucc_fast.c
@@ -29,41 +29,42 @@
 	printk(KERN_INFO "Base address: 0x%p\n", uccf->uf_regs);
 
 	printk(KERN_INFO "gumr  : addr=0x%p, val=0x%08x\n",
-		  &uccf->uf_regs->gumr, in_be32(&uccf->uf_regs->gumr));
+		  &uccf->uf_regs->gumr, qe_ioread32be(&uccf->uf_regs->gumr));
 	printk(KERN_INFO "upsmr : addr=0x%p, val=0x%08x\n",
-		  &uccf->uf_regs->upsmr, in_be32(&uccf->uf_regs->upsmr));
+		  &uccf->uf_regs->upsmr, qe_ioread32be(&uccf->uf_regs->upsmr));
 	printk(KERN_INFO "utodr : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->utodr, in_be16(&uccf->uf_regs->utodr));
+		  &uccf->uf_regs->utodr, qe_ioread16be(&uccf->uf_regs->utodr));
 	printk(KERN_INFO "udsr  : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->udsr, in_be16(&uccf->uf_regs->udsr));
+		  &uccf->uf_regs->udsr, qe_ioread16be(&uccf->uf_regs->udsr));
 	printk(KERN_INFO "ucce  : addr=0x%p, val=0x%08x\n",
-		  &uccf->uf_regs->ucce, in_be32(&uccf->uf_regs->ucce));
+		  &uccf->uf_regs->ucce, qe_ioread32be(&uccf->uf_regs->ucce));
 	printk(KERN_INFO "uccm  : addr=0x%p, val=0x%08x\n",
-		  &uccf->uf_regs->uccm, in_be32(&uccf->uf_regs->uccm));
+		  &uccf->uf_regs->uccm, qe_ioread32be(&uccf->uf_regs->uccm));
 	printk(KERN_INFO "uccs  : addr=0x%p, val=0x%02x\n",
-		  &uccf->uf_regs->uccs, in_8(&uccf->uf_regs->uccs));
+		  &uccf->uf_regs->uccs, qe_ioread8(&uccf->uf_regs->uccs));
 	printk(KERN_INFO "urfb  : addr=0x%p, val=0x%08x\n",
-		  &uccf->uf_regs->urfb, in_be32(&uccf->uf_regs->urfb));
+		  &uccf->uf_regs->urfb, qe_ioread32be(&uccf->uf_regs->urfb));
 	printk(KERN_INFO "urfs  : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->urfs, in_be16(&uccf->uf_regs->urfs));
+		  &uccf->uf_regs->urfs, qe_ioread16be(&uccf->uf_regs->urfs));
 	printk(KERN_INFO "urfet : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->urfet, in_be16(&uccf->uf_regs->urfet));
+		  &uccf->uf_regs->urfet, qe_ioread16be(&uccf->uf_regs->urfet));
 	printk(KERN_INFO "urfset: addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->urfset, in_be16(&uccf->uf_regs->urfset));
+		  &uccf->uf_regs->urfset,
+		  qe_ioread16be(&uccf->uf_regs->urfset));
 	printk(KERN_INFO "utfb  : addr=0x%p, val=0x%08x\n",
-		  &uccf->uf_regs->utfb, in_be32(&uccf->uf_regs->utfb));
+		  &uccf->uf_regs->utfb, qe_ioread32be(&uccf->uf_regs->utfb));
 	printk(KERN_INFO "utfs  : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->utfs, in_be16(&uccf->uf_regs->utfs));
+		  &uccf->uf_regs->utfs, qe_ioread16be(&uccf->uf_regs->utfs));
 	printk(KERN_INFO "utfet : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->utfet, in_be16(&uccf->uf_regs->utfet));
+		  &uccf->uf_regs->utfet, qe_ioread16be(&uccf->uf_regs->utfet));
 	printk(KERN_INFO "utftt : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->utftt, in_be16(&uccf->uf_regs->utftt));
+		  &uccf->uf_regs->utftt, qe_ioread16be(&uccf->uf_regs->utftt));
 	printk(KERN_INFO "utpt  : addr=0x%p, val=0x%04x\n",
-		  &uccf->uf_regs->utpt, in_be16(&uccf->uf_regs->utpt));
+		  &uccf->uf_regs->utpt, qe_ioread16be(&uccf->uf_regs->utpt));
 	printk(KERN_INFO "urtry : addr=0x%p, val=0x%08x\n",
-		  &uccf->uf_regs->urtry, in_be32(&uccf->uf_regs->urtry));
+		  &uccf->uf_regs->urtry, qe_ioread32be(&uccf->uf_regs->urtry));
 	printk(KERN_INFO "guemr : addr=0x%p, val=0x%02x\n",
-		  &uccf->uf_regs->guemr, in_8(&uccf->uf_regs->guemr));
+		  &uccf->uf_regs->guemr, qe_ioread8(&uccf->uf_regs->guemr));
 }
 EXPORT_SYMBOL(ucc_fast_dump_regs);
 
@@ -85,7 +86,7 @@
 
 void ucc_fast_transmit_on_demand(struct ucc_fast_private * uccf)
 {
-	out_be16(&uccf->uf_regs->utodr, UCC_FAST_TOD);
+	qe_iowrite16be(UCC_FAST_TOD, &uccf->uf_regs->utodr);
 }
 EXPORT_SYMBOL(ucc_fast_transmit_on_demand);
 
@@ -97,7 +98,7 @@
 	uf_regs = uccf->uf_regs;
 
 	/* Enable reception and/or transmission on this UCC. */
-	gumr = in_be32(&uf_regs->gumr);
+	gumr = qe_ioread32be(&uf_regs->gumr);
 	if (mode & COMM_DIR_TX) {
 		gumr |= UCC_FAST_GUMR_ENT;
 		uccf->enabled_tx = 1;
@@ -106,7 +107,7 @@
 		gumr |= UCC_FAST_GUMR_ENR;
 		uccf->enabled_rx = 1;
 	}
-	out_be32(&uf_regs->gumr, gumr);
+	qe_iowrite32be(gumr, &uf_regs->gumr);
 }
 EXPORT_SYMBOL(ucc_fast_enable);
 
@@ -118,7 +119,7 @@
 	uf_regs = uccf->uf_regs;
 
 	/* Disable reception and/or transmission on this UCC. */
-	gumr = in_be32(&uf_regs->gumr);
+	gumr = qe_ioread32be(&uf_regs->gumr);
 	if (mode & COMM_DIR_TX) {
 		gumr &= ~UCC_FAST_GUMR_ENT;
 		uccf->enabled_tx = 0;
@@ -127,7 +128,7 @@
 		gumr &= ~UCC_FAST_GUMR_ENR;
 		uccf->enabled_rx = 0;
 	}
-	out_be32(&uf_regs->gumr, gumr);
+	qe_iowrite32be(gumr, &uf_regs->gumr);
 }
 EXPORT_SYMBOL(ucc_fast_disable);
 
@@ -196,6 +197,8 @@
 			__func__);
 		return -ENOMEM;
 	}
+	uccf->ucc_fast_tx_virtual_fifo_base_offset = -1;
+	uccf->ucc_fast_rx_virtual_fifo_base_offset = -1;
 
 	/* Fill fast UCC structure */
 	uccf->uf_info = uf_info;
@@ -259,15 +262,14 @@
 	gumr |= uf_info->tenc;
 	gumr |= uf_info->tcrc;
 	gumr |= uf_info->mode;
-	out_be32(&uf_regs->gumr, gumr);
+	qe_iowrite32be(gumr, &uf_regs->gumr);
 
 	/* Allocate memory for Tx Virtual Fifo */
 	uccf->ucc_fast_tx_virtual_fifo_base_offset =
 	    qe_muram_alloc(uf_info->utfs, UCC_FAST_VIRT_FIFO_REGS_ALIGNMENT);
-	if (IS_ERR_VALUE(uccf->ucc_fast_tx_virtual_fifo_base_offset)) {
+	if (uccf->ucc_fast_tx_virtual_fifo_base_offset < 0) {
 		printk(KERN_ERR "%s: cannot allocate MURAM for TX FIFO\n",
 			__func__);
-		uccf->ucc_fast_tx_virtual_fifo_base_offset = 0;
 		ucc_fast_free(uccf);
 		return -ENOMEM;
 	}
@@ -277,24 +279,25 @@
 		qe_muram_alloc(uf_info->urfs +
 			   UCC_FAST_RECEIVE_VIRTUAL_FIFO_SIZE_FUDGE_FACTOR,
 			   UCC_FAST_VIRT_FIFO_REGS_ALIGNMENT);
-	if (IS_ERR_VALUE(uccf->ucc_fast_rx_virtual_fifo_base_offset)) {
+	if (uccf->ucc_fast_rx_virtual_fifo_base_offset < 0) {
 		printk(KERN_ERR "%s: cannot allocate MURAM for RX FIFO\n",
 			__func__);
-		uccf->ucc_fast_rx_virtual_fifo_base_offset = 0;
 		ucc_fast_free(uccf);
 		return -ENOMEM;
 	}
 
 	/* Set Virtual Fifo registers */
-	out_be16(&uf_regs->urfs, uf_info->urfs);
-	out_be16(&uf_regs->urfet, uf_info->urfet);
-	out_be16(&uf_regs->urfset, uf_info->urfset);
-	out_be16(&uf_regs->utfs, uf_info->utfs);
-	out_be16(&uf_regs->utfet, uf_info->utfet);
-	out_be16(&uf_regs->utftt, uf_info->utftt);
+	qe_iowrite16be(uf_info->urfs, &uf_regs->urfs);
+	qe_iowrite16be(uf_info->urfet, &uf_regs->urfet);
+	qe_iowrite16be(uf_info->urfset, &uf_regs->urfset);
+	qe_iowrite16be(uf_info->utfs, &uf_regs->utfs);
+	qe_iowrite16be(uf_info->utfet, &uf_regs->utfet);
+	qe_iowrite16be(uf_info->utftt, &uf_regs->utftt);
 	/* utfb, urfb are offsets from MURAM base */
-	out_be32(&uf_regs->utfb, uccf->ucc_fast_tx_virtual_fifo_base_offset);
-	out_be32(&uf_regs->urfb, uccf->ucc_fast_rx_virtual_fifo_base_offset);
+	qe_iowrite32be(uccf->ucc_fast_tx_virtual_fifo_base_offset,
+		       &uf_regs->utfb);
+	qe_iowrite32be(uccf->ucc_fast_rx_virtual_fifo_base_offset,
+		       &uf_regs->urfb);
 
 	/* Mux clocking */
 	/* Grant Support */
@@ -362,14 +365,14 @@
 	}
 
 	/* Set interrupt mask register at UCC level. */
-	out_be32(&uf_regs->uccm, uf_info->uccm_mask);
+	qe_iowrite32be(uf_info->uccm_mask, &uf_regs->uccm);
 
 	/* First, clear anything pending at UCC level,
 	 * otherwise, old garbage may come through
 	 * as soon as the dam is opened. */
 
 	/* Writing '1' clears */
-	out_be32(&uf_regs->ucce, 0xffffffff);
+	qe_iowrite32be(0xffffffff, &uf_regs->ucce);
 
 	*uccf_ret = uccf;
 	return 0;
@@ -381,11 +384,8 @@
 	if (!uccf)
 		return;
 
-	if (uccf->ucc_fast_tx_virtual_fifo_base_offset)
-		qe_muram_free(uccf->ucc_fast_tx_virtual_fifo_base_offset);
-
-	if (uccf->ucc_fast_rx_virtual_fifo_base_offset)
-		qe_muram_free(uccf->ucc_fast_rx_virtual_fifo_base_offset);
+	qe_muram_free(uccf->ucc_fast_tx_virtual_fifo_base_offset);
+	qe_muram_free(uccf->ucc_fast_rx_virtual_fifo_base_offset);
 
 	if (uccf->uf_regs)
 		iounmap(uccf->uf_regs);
diff --git a/drivers/soc/fsl/qe/ucc_slow.c b/drivers/soc/fsl/qe/ucc_slow.c
index 34f0ec3..7e11be4 100644
--- a/drivers/soc/fsl/qe/ucc_slow.c
+++ b/drivers/soc/fsl/qe/ucc_slow.c
@@ -72,13 +72,13 @@
 
 void ucc_slow_enable(struct ucc_slow_private * uccs, enum comm_dir mode)
 {
-	struct ucc_slow *us_regs;
+	struct ucc_slow __iomem *us_regs;
 	u32 gumr_l;
 
 	us_regs = uccs->us_regs;
 
 	/* Enable reception and/or transmission on this UCC. */
-	gumr_l = in_be32(&us_regs->gumr_l);
+	gumr_l = qe_ioread32be(&us_regs->gumr_l);
 	if (mode & COMM_DIR_TX) {
 		gumr_l |= UCC_SLOW_GUMR_L_ENT;
 		uccs->enabled_tx = 1;
@@ -87,19 +87,19 @@
 		gumr_l |= UCC_SLOW_GUMR_L_ENR;
 		uccs->enabled_rx = 1;
 	}
-	out_be32(&us_regs->gumr_l, gumr_l);
+	qe_iowrite32be(gumr_l, &us_regs->gumr_l);
 }
 EXPORT_SYMBOL(ucc_slow_enable);
 
 void ucc_slow_disable(struct ucc_slow_private * uccs, enum comm_dir mode)
 {
-	struct ucc_slow *us_regs;
+	struct ucc_slow __iomem *us_regs;
 	u32 gumr_l;
 
 	us_regs = uccs->us_regs;
 
 	/* Disable reception and/or transmission on this UCC. */
-	gumr_l = in_be32(&us_regs->gumr_l);
+	gumr_l = qe_ioread32be(&us_regs->gumr_l);
 	if (mode & COMM_DIR_TX) {
 		gumr_l &= ~UCC_SLOW_GUMR_L_ENT;
 		uccs->enabled_tx = 0;
@@ -108,7 +108,7 @@
 		gumr_l &= ~UCC_SLOW_GUMR_L_ENR;
 		uccs->enabled_rx = 0;
 	}
-	out_be32(&us_regs->gumr_l, gumr_l);
+	qe_iowrite32be(gumr_l, &us_regs->gumr_l);
 }
 EXPORT_SYMBOL(ucc_slow_disable);
 
@@ -122,7 +122,7 @@
 	u32 i;
 	struct ucc_slow __iomem *us_regs;
 	u32 gumr;
-	struct qe_bd *bd;
+	struct qe_bd __iomem *bd;
 	u32 id;
 	u32 command;
 	int ret = 0;
@@ -154,6 +154,9 @@
 			__func__);
 		return -ENOMEM;
 	}
+	uccs->rx_base_offset = -1;
+	uccs->tx_base_offset = -1;
+	uccs->us_pram_offset = -1;
 
 	/* Fill slow UCC structure */
 	uccs->us_info = us_info;
@@ -165,21 +168,14 @@
 		return -ENOMEM;
 	}
 
-	uccs->saved_uccm = 0;
-	uccs->p_rx_frame = 0;
 	us_regs = uccs->us_regs;
-	uccs->p_ucce = (u16 *) & (us_regs->ucce);
-	uccs->p_uccm = (u16 *) & (us_regs->uccm);
-#ifdef STATISTICS
-	uccs->rx_frames = 0;
-	uccs->tx_frames = 0;
-	uccs->rx_discarded = 0;
-#endif				/* STATISTICS */
+	uccs->p_ucce = &us_regs->ucce;
+	uccs->p_uccm = &us_regs->uccm;
 
 	/* Get PRAM base */
 	uccs->us_pram_offset =
 		qe_muram_alloc(UCC_SLOW_PRAM_SIZE, ALIGNMENT_OF_UCC_SLOW_PRAM);
-	if (IS_ERR_VALUE(uccs->us_pram_offset)) {
+	if (uccs->us_pram_offset < 0) {
 		printk(KERN_ERR "%s: cannot allocate MURAM for PRAM", __func__);
 		ucc_slow_free(uccs);
 		return -ENOMEM;
@@ -198,7 +194,7 @@
 		return ret;
 	}
 
-	out_be16(&uccs->us_pram->mrblr, us_info->max_rx_buf_length);
+	qe_iowrite16be(us_info->max_rx_buf_length, &uccs->us_pram->mrblr);
 
 	INIT_LIST_HEAD(&uccs->confQ);
 
@@ -206,10 +202,9 @@
 	uccs->rx_base_offset =
 		qe_muram_alloc(us_info->rx_bd_ring_len * sizeof(struct qe_bd),
 				QE_ALIGNMENT_OF_BD);
-	if (IS_ERR_VALUE(uccs->rx_base_offset)) {
+	if (uccs->rx_base_offset < 0) {
 		printk(KERN_ERR "%s: cannot allocate %u RX BDs\n", __func__,
 			us_info->rx_bd_ring_len);
-		uccs->rx_base_offset = 0;
 		ucc_slow_free(uccs);
 		return -ENOMEM;
 	}
@@ -217,9 +212,8 @@
 	uccs->tx_base_offset =
 		qe_muram_alloc(us_info->tx_bd_ring_len * sizeof(struct qe_bd),
 			QE_ALIGNMENT_OF_BD);
-	if (IS_ERR_VALUE(uccs->tx_base_offset)) {
+	if (uccs->tx_base_offset < 0) {
 		printk(KERN_ERR "%s: cannot allocate TX BDs", __func__);
-		uccs->tx_base_offset = 0;
 		ucc_slow_free(uccs);
 		return -ENOMEM;
 	}
@@ -228,27 +222,27 @@
 	bd = uccs->confBd = uccs->tx_bd = qe_muram_addr(uccs->tx_base_offset);
 	for (i = 0; i < us_info->tx_bd_ring_len - 1; i++) {
 		/* clear bd buffer */
-		out_be32(&bd->buf, 0);
+		qe_iowrite32be(0, &bd->buf);
 		/* set bd status and length */
-		out_be32((u32 *) bd, 0);
+		qe_iowrite32be(0, (u32 __iomem *)bd);
 		bd++;
 	}
 	/* for last BD set Wrap bit */
-	out_be32(&bd->buf, 0);
-	out_be32((u32 *) bd, cpu_to_be32(T_W));
+	qe_iowrite32be(0, &bd->buf);
+	qe_iowrite32be(T_W, (u32 __iomem *)bd);
 
 	/* Init Rx bds */
 	bd = uccs->rx_bd = qe_muram_addr(uccs->rx_base_offset);
 	for (i = 0; i < us_info->rx_bd_ring_len - 1; i++) {
 		/* set bd status and length */
-		out_be32((u32*)bd, 0);
+		qe_iowrite32be(0, (u32 __iomem *)bd);
 		/* clear bd buffer */
-		out_be32(&bd->buf, 0);
+		qe_iowrite32be(0, &bd->buf);
 		bd++;
 	}
 	/* for last BD set Wrap bit */
-	out_be32((u32*)bd, cpu_to_be32(R_W));
-	out_be32(&bd->buf, 0);
+	qe_iowrite32be(R_W, (u32 __iomem *)bd);
+	qe_iowrite32be(0, &bd->buf);
 
 	/* Set GUMR (For more details see the hardware spec.). */
 	/* gumr_h */
@@ -269,11 +263,11 @@
 		gumr |= UCC_SLOW_GUMR_H_TXSY;
 	if (us_info->rtsm)
 		gumr |= UCC_SLOW_GUMR_H_RTSM;
-	out_be32(&us_regs->gumr_h, gumr);
+	qe_iowrite32be(gumr, &us_regs->gumr_h);
 
 	/* gumr_l */
-	gumr = us_info->tdcr | us_info->rdcr | us_info->tenc | us_info->renc |
-		us_info->diag | us_info->mode;
+	gumr = (u32)us_info->tdcr | (u32)us_info->rdcr | (u32)us_info->tenc |
+	       (u32)us_info->renc | (u32)us_info->diag | (u32)us_info->mode;
 	if (us_info->tci)
 		gumr |= UCC_SLOW_GUMR_L_TCI;
 	if (us_info->rinv)
@@ -282,18 +276,18 @@
 		gumr |= UCC_SLOW_GUMR_L_TINV;
 	if (us_info->tend)
 		gumr |= UCC_SLOW_GUMR_L_TEND;
-	out_be32(&us_regs->gumr_l, gumr);
+	qe_iowrite32be(gumr, &us_regs->gumr_l);
 
 	/* Function code registers */
 
 	/* if the data is in cachable memory, the 'global' */
 	/* in the function code should be set. */
-	uccs->us_pram->tbmr = UCC_BMR_BO_BE;
-	uccs->us_pram->rbmr = UCC_BMR_BO_BE;
+	qe_iowrite8(UCC_BMR_BO_BE, &uccs->us_pram->tbmr);
+	qe_iowrite8(UCC_BMR_BO_BE, &uccs->us_pram->rbmr);
 
 	/* rbase, tbase are offsets from MURAM base */
-	out_be16(&uccs->us_pram->rbase, uccs->rx_base_offset);
-	out_be16(&uccs->us_pram->tbase, uccs->tx_base_offset);
+	qe_iowrite16be(uccs->rx_base_offset, &uccs->us_pram->rbase);
+	qe_iowrite16be(uccs->tx_base_offset, &uccs->us_pram->tbase);
 
 	/* Mux clocking */
 	/* Grant Support */
@@ -323,14 +317,14 @@
 	}
 
 	/* Set interrupt mask register at UCC level. */
-	out_be16(&us_regs->uccm, us_info->uccm_mask);
+	qe_iowrite16be(us_info->uccm_mask, &us_regs->uccm);
 
 	/* First, clear anything pending at UCC level,
 	 * otherwise, old garbage may come through
 	 * as soon as the dam is opened. */
 
 	/* Writing '1' clears */
-	out_be16(&us_regs->ucce, 0xffff);
+	qe_iowrite16be(0xffff, &us_regs->ucce);
 
 	/* Issue QE Init command */
 	if (us_info->init_tx && us_info->init_rx)
@@ -352,14 +346,9 @@
 	if (!uccs)
 		return;
 
-	if (uccs->rx_base_offset)
-		qe_muram_free(uccs->rx_base_offset);
-
-	if (uccs->tx_base_offset)
-		qe_muram_free(uccs->tx_base_offset);
-
-	if (uccs->us_pram)
-		qe_muram_free(uccs->us_pram_offset);
+	qe_muram_free(uccs->rx_base_offset);
+	qe_muram_free(uccs->tx_base_offset);
+	qe_muram_free(uccs->us_pram_offset);
 
 	if (uccs->us_regs)
 		iounmap(uccs->us_regs);
diff --git a/drivers/soc/fsl/qe/usb.c b/drivers/soc/fsl/qe/usb.c
index 32d8269..890f236 100644
--- a/drivers/soc/fsl/qe/usb.c
+++ b/drivers/soc/fsl/qe/usb.c
@@ -43,7 +43,7 @@
 
 	spin_lock_irqsave(&cmxgcr_lock, flags);
 
-	clrsetbits_be32(&mux->cmxgcr, QE_CMXGCR_USBCS, val);
+	qe_clrsetbits_be32(&mux->cmxgcr, QE_CMXGCR_USBCS, val);
 
 	spin_unlock_irqrestore(&cmxgcr_lock, flags);
 
diff --git a/drivers/soc/fsl/rcpm.c b/drivers/soc/fsl/rcpm.c
new file mode 100644
index 0000000..a093dbe
--- /dev/null
+++ b/drivers/soc/fsl/rcpm.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// rcpm.c - Freescale QorIQ RCPM driver
+//
+// Copyright 2019 NXP
+//
+// Author: Ran Wang <ran.wang_1@nxp.com>
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/suspend.h>
+#include <linux/kernel.h>
+
+#define RCPM_WAKEUP_CELL_MAX_SIZE	7
+
+struct rcpm {
+	unsigned int	wakeup_cells;
+	void __iomem	*ippdexpcr_base;
+	bool		little_endian;
+};
+
+/**
+ * rcpm_pm_prepare - performs device-level tasks associated with power
+ * management, such as programming related to the wakeup source control.
+ * @dev: Device to handle.
+ *
+ */
+static int rcpm_pm_prepare(struct device *dev)
+{
+	int i, ret, idx;
+	void __iomem *base;
+	struct wakeup_source	*ws;
+	struct rcpm		*rcpm;
+	struct device_node	*np = dev->of_node;
+	u32 value[RCPM_WAKEUP_CELL_MAX_SIZE + 1];
+	u32 setting[RCPM_WAKEUP_CELL_MAX_SIZE] = {0};
+
+	rcpm = dev_get_drvdata(dev);
+	if (!rcpm)
+		return -EINVAL;
+
+	base = rcpm->ippdexpcr_base;
+	idx = wakeup_sources_read_lock();
+
+	/* Begin with first registered wakeup source */
+	for_each_wakeup_source(ws) {
+
+		/* skip object which is not attached to device */
+		if (!ws->dev || !ws->dev->parent)
+			continue;
+
+		ret = device_property_read_u32_array(ws->dev->parent,
+				"fsl,rcpm-wakeup", value,
+				rcpm->wakeup_cells + 1);
+
+		/*  Wakeup source should refer to current rcpm device */
+		if (ret || (np->phandle != value[0]))
+			continue;
+
+		/* Property "#fsl,rcpm-wakeup-cells" of rcpm node defines the
+		 * number of IPPDEXPCR register cells, and "fsl,rcpm-wakeup"
+		 * of wakeup source IP contains an integer array: <phandle to
+		 * RCPM node, IPPDEXPCR0 setting, IPPDEXPCR1 setting,
+		 * IPPDEXPCR2 setting, etc>.
+		 *
+		 * So we will go thought them to collect setting data.
+		 */
+		for (i = 0; i < rcpm->wakeup_cells; i++)
+			setting[i] |= value[i + 1];
+	}
+
+	wakeup_sources_read_unlock(idx);
+
+	/* Program all IPPDEXPCRn once */
+	for (i = 0; i < rcpm->wakeup_cells; i++) {
+		u32 tmp = setting[i];
+		void __iomem *address = base + i * 4;
+
+		if (!tmp)
+			continue;
+
+		/* We can only OR related bits */
+		if (rcpm->little_endian) {
+			tmp |= ioread32(address);
+			iowrite32(tmp, address);
+		} else {
+			tmp |= ioread32be(address);
+			iowrite32be(tmp, address);
+		}
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops rcpm_pm_ops = {
+	.prepare =  rcpm_pm_prepare,
+};
+
+static int rcpm_probe(struct platform_device *pdev)
+{
+	struct device	*dev = &pdev->dev;
+	struct resource *r;
+	struct rcpm	*rcpm;
+	int ret;
+
+	rcpm = devm_kzalloc(dev, sizeof(*rcpm), GFP_KERNEL);
+	if (!rcpm)
+		return -ENOMEM;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r)
+		return -ENODEV;
+
+	rcpm->ippdexpcr_base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(rcpm->ippdexpcr_base)) {
+		ret =  PTR_ERR(rcpm->ippdexpcr_base);
+		return ret;
+	}
+
+	rcpm->little_endian = device_property_read_bool(
+			&pdev->dev, "little-endian");
+
+	ret = device_property_read_u32(&pdev->dev,
+			"#fsl,rcpm-wakeup-cells", &rcpm->wakeup_cells);
+	if (ret)
+		return ret;
+
+	dev_set_drvdata(&pdev->dev, rcpm);
+
+	return 0;
+}
+
+static const struct of_device_id rcpm_of_match[] = {
+	{ .compatible = "fsl,qoriq-rcpm-2.1+", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, rcpm_of_match);
+
+static struct platform_driver rcpm_driver = {
+	.driver = {
+		.name = "rcpm",
+		.of_match_table = rcpm_of_match,
+		.pm	= &rcpm_pm_ops,
+	},
+	.probe = rcpm_probe,
+};
+
+module_platform_driver(rcpm_driver);