openwrt/target/linux/layerscape/patches-4.14/711-dpaa-bqman-support-layerscape.patch

From 371e99a257cb714f9a6027d6571cb1a43855d926 Mon Sep 17 00:00:00 2001
From: Biwen Li <biwen.li@nxp.com>
Date: Wed, 17 Apr 2019 18:58:24 +0800
Subject: [PATCH] dpaa-bqman: support layerscape

This is an integrated patch of dpaa-bqman for layerscape

Signed-off-by: Biwen Li <biwen.li@nxp.com>
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: Roy Pledge <roy.pledge@nxp.com>
Signed-off-by: Stuart Yoder <stuart.yoder@nxp.com>
Signed-off-by: Valentin Rothberg <valentinrothberg@gmail.com>
---
 drivers/soc/fsl/qbman/Kconfig       |   2 +-
 drivers/soc/fsl/qbman/bman.c        |  24 +++-
 drivers/soc/fsl/qbman/bman_ccsr.c   |  57 +++++++++-
 drivers/soc/fsl/qbman/bman_portal.c |  44 ++++++--
 drivers/soc/fsl/qbman/bman_priv.h   |   3 +
 drivers/soc/fsl/qbman/dpaa_sys.h    |   8 +-
 drivers/soc/fsl/qbman/qman.c        |  46 +++++++-
 drivers/soc/fsl/qbman/qman_ccsr.c   | 168 +++++++++++++++++++++++-----
 drivers/soc/fsl/qbman/qman_portal.c |  60 ++++++++--
 drivers/soc/fsl/qbman/qman_priv.h   |   5 +-
 drivers/soc/fsl/qbman/qman_test.h   |   2 -
 include/soc/fsl/bman.h              |  16 +++
 include/soc/fsl/qman.h              |  17 +++
 13 files changed, 390 insertions(+), 62 deletions(-)

--- a/drivers/soc/fsl/qbman/Kconfig
+++ b/drivers/soc/fsl/qbman/Kconfig
@@ -1,6 +1,6 @@
 menuconfig FSL_DPAA
 	bool "Freescale DPAA 1.x support"
-	depends on FSL_SOC_BOOKE
+	depends on (FSL_SOC_BOOKE || ARCH_LAYERSCAPE)
 	select GENERIC_ALLOCATOR
 	help
 	  The Freescale Data Path Acceleration Architecture (DPAA) is a set of
--- a/drivers/soc/fsl/qbman/bman.c
+++ b/drivers/soc/fsl/qbman/bman.c
@@ -35,6 +35,27 @@
 
 /* Portal register assists */
 
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+/* Cache-inhibited register offsets */
+#define BM_REG_RCR_PI_CINH	0x3000
+#define BM_REG_RCR_CI_CINH	0x3100
+#define BM_REG_RCR_ITR		0x3200
+#define BM_REG_CFG		0x3300
+#define BM_REG_SCN(n)		(0x3400 + ((n) << 6))
+#define BM_REG_ISR		0x3e00
+#define BM_REG_IER		0x3e40
+#define BM_REG_ISDR		0x3e80
+#define BM_REG_IIR		0x3ec0
+
+/* Cache-enabled register offsets */
+#define BM_CL_CR		0x0000
+#define BM_CL_RR0		0x0100
+#define BM_CL_RR1		0x0140
+#define BM_CL_RCR		0x1000
+#define BM_CL_RCR_PI_CENA	0x3000
+#define BM_CL_RCR_CI_CENA	0x3100
+
+#else
 /* Cache-inhibited register offsets */
 #define BM_REG_RCR_PI_CINH	0x0000
 #define BM_REG_RCR_CI_CINH	0x0004
@@ -53,6 +74,7 @@
 #define BM_CL_RCR		0x1000
 #define BM_CL_RCR_PI_CENA	0x3000
 #define BM_CL_RCR_CI_CENA	0x3100
+#endif
 
 /*
  * Portal modes.
@@ -607,7 +629,7 @@ int bman_p_irqsource_add(struct bman_por
 	unsigned long irqflags;
 
 	local_irq_save(irqflags);
-	set_bits(bits & BM_PIRQ_VISIBLE, &p->irq_sources);
+	p->irq_sources |= bits & BM_PIRQ_VISIBLE;
 	bm_out(&p->p, BM_REG_IER, p->irq_sources);
 	local_irq_restore(irqflags);
 	return 0;
--- a/drivers/soc/fsl/qbman/bman_ccsr.c
+++ b/drivers/soc/fsl/qbman/bman_ccsr.c
@@ -29,6 +29,7 @@
  */
 
 #include "bman_priv.h"
+#include <linux/iommu.h>
 
 u16 bman_ip_rev;
 EXPORT_SYMBOL(bman_ip_rev);
@@ -120,6 +121,7 @@ static void bm_set_memory(u64 ba, u32 si
  */
 static dma_addr_t fbpr_a;
 static size_t fbpr_sz;
+static int __bman_probed;
 
 static int bman_fbpr(struct reserved_mem *rmem)
 {
@@ -166,14 +168,24 @@ static irqreturn_t bman_isr(int irq, voi
 	return IRQ_HANDLED;
 }
 
+int bman_is_probed(void)
+{
+	return __bman_probed;
+}
+EXPORT_SYMBOL_GPL(bman_is_probed);
+
 static int fsl_bman_probe(struct platform_device *pdev)
 {
 	int ret, err_irq;
 	struct device *dev = &pdev->dev;
-	struct device_node *node = dev->of_node;
+	struct device_node *mem_node, *node = dev->of_node;
+	struct iommu_domain *domain;
 	struct resource *res;
 	u16 id, bm_pool_cnt;
 	u8 major, minor;
+	u64 size;
+
+	__bman_probed = -1;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
@@ -201,6 +213,47 @@ static int fsl_bman_probe(struct platfor
 		return -ENODEV;
 	}
 
+	/*
+	 * If FBPR memory wasn't defined using the qbman compatiable string
+	 * try using the of_reserved_mem_device method
+	 */
+	if (!fbpr_a) {
+		ret = of_reserved_mem_device_init(dev);
+		if (ret) {
+			dev_err(dev, "of_reserved_mem_device_init() failed 0x%x\n",
+				ret);
+			return -ENODEV;
+		}
+		mem_node = of_parse_phandle(dev->of_node, "memory-region", 0);
+		if (mem_node) {
+			ret = of_property_read_u64(mem_node, "size", &size);
+			if (ret) {
+				dev_err(dev, "FBPR: of_address_to_resource fails 0x%x\n",
+					ret);
+				return -ENODEV;
+			}
+			fbpr_sz = size;
+		} else {
+			dev_err(dev, "No memory-region found for FBPR\n");
+			return -ENODEV;
+		}
+		if (!dma_zalloc_coherent(dev, fbpr_sz, &fbpr_a, 0)) {
+			dev_err(dev, "Alloc FBPR memory failed\n");
+			return -ENODEV;
+		}
+	}
+
+	dev_dbg(dev, "Allocated FBPR 0x%llx 0x%zx\n", fbpr_a, fbpr_sz);
+
+	/* Create an 1-to-1 iommu mapping for FBPR area */
+	domain = iommu_get_domain_for_dev(dev);
+	if (domain) {
+		ret = iommu_map(domain, fbpr_a, fbpr_a, PAGE_ALIGN(fbpr_sz),
+				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
+		if (ret)
+			dev_warn(dev, "failed to iommu_map() %d\n", ret);
+	}
+
 	bm_set_memory(fbpr_a, fbpr_sz);
 
 	err_irq = platform_get_irq(pdev, 0);
@@ -240,6 +293,8 @@ static int fsl_bman_probe(struct platfor
 		return ret;
 	}
 
+	__bman_probed = 1;
+
 	return 0;
 };
 
--- a/drivers/soc/fsl/qbman/bman_portal.c
+++ b/drivers/soc/fsl/qbman/bman_portal.c
@@ -32,6 +32,7 @@
 
 static struct bman_portal *affine_bportals[NR_CPUS];
 static struct cpumask portal_cpus;
+static int __bman_portals_probed;
 /* protect bman global registers and global data shared among portals */
 static DEFINE_SPINLOCK(bman_lock);
 
@@ -85,6 +86,12 @@ static int bman_online_cpu(unsigned int
 	return 0;
 }
 
+int bman_portals_probed(void)
+{
+	return __bman_portals_probed;
+}
+EXPORT_SYMBOL_GPL(bman_portals_probed);
+
 static int bman_portal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -92,11 +99,21 @@ static int bman_portal_probe(struct plat
 	struct bm_portal_config *pcfg;
 	struct resource *addr_phys[2];
 	void __iomem *va;
-	int irq, cpu;
+	int irq, cpu, err;
+
+	err = bman_is_probed();
+	if (!err)
+		return -EPROBE_DEFER;
+	if (err < 0) {
+		dev_err(&pdev->dev, "failing probe due to bman probe error\n");
+		return -ENODEV;
+	}
 
 	pcfg = devm_kmalloc(dev, sizeof(*pcfg), GFP_KERNEL);
-	if (!pcfg)
+	if (!pcfg) {
+		__bman_portals_probed = -1;
 		return -ENOMEM;
+	}
 
 	pcfg->dev = dev;
 
@@ -104,14 +121,14 @@ static int bman_portal_probe(struct plat
 					     DPAA_PORTAL_CE);
 	if (!addr_phys[0]) {
 		dev_err(dev, "Can't get %pOF property 'reg::CE'\n", node);
-		return -ENXIO;
+		goto err_ioremap1;
 	}
 
 	addr_phys[1] = platform_get_resource(pdev, IORESOURCE_MEM,
 					     DPAA_PORTAL_CI);
 	if (!addr_phys[1]) {
 		dev_err(dev, "Can't get %pOF property 'reg::CI'\n", node);
-		return -ENXIO;
+		goto err_ioremap1;
 	}
 
 	pcfg->cpu = -1;
@@ -119,11 +136,18 @@ static int bman_portal_probe(struct plat
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0) {
 		dev_err(dev, "Can't get %pOF IRQ'\n", node);
-		return -ENXIO;
+		goto err_ioremap1;
 	}
 	pcfg->irq = irq;
 
-	va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]), 0);
+#ifdef CONFIG_PPC
+	/* PPC requires a cacheable/non-coherent mapping of the portal */
+	va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]),
+			  (pgprot_val(PAGE_KERNEL) & ~_PAGE_COHERENT));
+#else
+	/* For ARM we can use write combine mapping. */
+	va = ioremap_wc(addr_phys[0]->start, resource_size(addr_phys[0]));
+#endif
 	if (!va) {
 		dev_err(dev, "ioremap::CE failed\n");
 		goto err_ioremap1;
@@ -131,8 +155,7 @@ static int bman_portal_probe(struct plat
 
 	pcfg->addr_virt[DPAA_PORTAL_CE] = va;
 
-	va = ioremap_prot(addr_phys[1]->start, resource_size(addr_phys[1]),
-			  _PAGE_GUARDED | _PAGE_NO_CACHE);
+	va = ioremap(addr_phys[1]->start, resource_size(addr_phys[1]));
 	if (!va) {
 		dev_err(dev, "ioremap::CI failed\n");
 		goto err_ioremap2;
@@ -149,6 +172,9 @@ static int bman_portal_probe(struct plat
 	}
 
 	cpumask_set_cpu(cpu, &portal_cpus);
+	if (!__bman_portals_probed &&
+	    cpumask_weight(&portal_cpus) == num_online_cpus())
+		__bman_portals_probed = 1;
 	spin_unlock(&bman_lock);
 	pcfg->cpu = cpu;
 
@@ -168,6 +194,8 @@ err_portal_init:
 err_ioremap2:
 	iounmap(pcfg->addr_virt[DPAA_PORTAL_CE]);
 err_ioremap1:
+	 __bman_portals_probed = -1;
+
 	return -ENXIO;
 }
 
--- a/drivers/soc/fsl/qbman/bman_priv.h
+++ b/drivers/soc/fsl/qbman/bman_priv.h
@@ -33,6 +33,9 @@
 #include "dpaa_sys.h"
 
 #include <soc/fsl/bman.h>
+#include <linux/dma-contiguous.h>
+#include <linux/of_address.h>
+#include <linux/dma-mapping.h>
 
 /* Portal processing (interrupt) sources */
 #define BM_PIRQ_RCRI	0x00000002	/* RCR Ring (below threshold) */
--- a/drivers/soc/fsl/qbman/dpaa_sys.h
+++ b/drivers/soc/fsl/qbman/dpaa_sys.h
@@ -44,20 +44,18 @@
 #include <linux/prefetch.h>
 #include <linux/genalloc.h>
 #include <asm/cacheflush.h>
+#include <linux/io.h>
+#include <linux/delay.h>
 
 /* For 2-element tables related to cache-inhibited and cache-enabled mappings */
 #define DPAA_PORTAL_CE 0
 #define DPAA_PORTAL_CI 1
 
-#if (L1_CACHE_BYTES != 32) && (L1_CACHE_BYTES != 64)
-#error "Unsupported Cacheline Size"
-#endif
-
 static inline void dpaa_flush(void *p)
 {
 #ifdef CONFIG_PPC
 	flush_dcache_range((unsigned long)p, (unsigned long)p+64);
-#elif defined(CONFIG_ARM32)
+#elif defined(CONFIG_ARM)
 	__cpuc_flush_dcache_area(p, 64);
 #elif defined(CONFIG_ARM64)
 	__flush_dcache_area(p, 64);
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -41,6 +41,43 @@
 
 /* Portal register assists */
 
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+/* Cache-inhibited register offsets */
+#define QM_REG_EQCR_PI_CINH	0x3000
+#define QM_REG_EQCR_CI_CINH	0x3040
+#define QM_REG_EQCR_ITR		0x3080
+#define QM_REG_DQRR_PI_CINH	0x3100
+#define QM_REG_DQRR_CI_CINH	0x3140
+#define QM_REG_DQRR_ITR		0x3180
+#define QM_REG_DQRR_DCAP	0x31C0
+#define QM_REG_DQRR_SDQCR	0x3200
+#define QM_REG_DQRR_VDQCR	0x3240
+#define QM_REG_DQRR_PDQCR	0x3280
+#define QM_REG_MR_PI_CINH	0x3300
+#define QM_REG_MR_CI_CINH	0x3340
+#define QM_REG_MR_ITR		0x3380
+#define QM_REG_CFG		0x3500
+#define QM_REG_ISR		0x3600
+#define QM_REG_IER		0x3640
+#define QM_REG_ISDR		0x3680
+#define QM_REG_IIR		0x36C0
+#define QM_REG_ITPR		0x3740
+
+/* Cache-enabled register offsets */
+#define QM_CL_EQCR		0x0000
+#define QM_CL_DQRR		0x1000
+#define QM_CL_MR		0x2000
+#define QM_CL_EQCR_PI_CENA	0x3000
+#define QM_CL_EQCR_CI_CENA	0x3040
+#define QM_CL_DQRR_PI_CENA	0x3100
+#define QM_CL_DQRR_CI_CENA	0x3140
+#define QM_CL_MR_PI_CENA	0x3300
+#define QM_CL_MR_CI_CENA	0x3340
+#define QM_CL_CR		0x3800
+#define QM_CL_RR0		0x3900
+#define QM_CL_RR1		0x3940
+
+#else
 /* Cache-inhibited register offsets */
 #define QM_REG_EQCR_PI_CINH	0x0000
 #define QM_REG_EQCR_CI_CINH	0x0004
@@ -75,6 +112,7 @@
 #define QM_CL_CR		0x3800
 #define QM_CL_RR0		0x3900
 #define QM_CL_RR1		0x3940
+#endif
 
 /*
  * BTW, the drivers (and h/w programming model) already obtain the required
@@ -909,12 +947,12 @@ static inline int qm_mc_result_timeout(s
 
 static inline void fq_set(struct qman_fq *fq, u32 mask)
 {
-	set_bits(mask, &fq->flags);
+	fq->flags |= mask;
 }
 
 static inline void fq_clear(struct qman_fq *fq, u32 mask)
 {
-	clear_bits(mask, &fq->flags);
+	fq->flags &= ~mask;
 }
 
 static inline int fq_isset(struct qman_fq *fq, u32 mask)
@@ -1567,7 +1605,7 @@ void qman_p_irqsource_add(struct qman_po
 	unsigned long irqflags;
 
 	local_irq_save(irqflags);
-	set_bits(bits & QM_PIRQ_VISIBLE, &p->irq_sources);
+	p->irq_sources |= bits & QM_PIRQ_VISIBLE;
 	qm_out(&p->p, QM_REG_IER, p->irq_sources);
 	local_irq_restore(irqflags);
 }
@@ -1590,7 +1628,7 @@ void qman_p_irqsource_remove(struct qman
 	 */
 	local_irq_save(irqflags);
 	bits &= QM_PIRQ_VISIBLE;
-	clear_bits(bits, &p->irq_sources);
+	p->irq_sources &= ~bits;
 	qm_out(&p->p, QM_REG_IER, p->irq_sources);
 	ier = qm_in(&p->p, QM_REG_IER);
 	/*
--- a/drivers/soc/fsl/qbman/qman_ccsr.c
+++ b/drivers/soc/fsl/qbman/qman_ccsr.c
@@ -29,6 +29,7 @@
  */
 
 #include "qman_priv.h"
+#include <linux/iommu.h>
 
 u16 qman_ip_rev;
 EXPORT_SYMBOL(qman_ip_rev);
@@ -273,6 +274,7 @@ static const struct qman_error_info_mdat
 static u32 __iomem *qm_ccsr_start;
 /* A SDQCR mask comprising all the available/visible pool channels */
 static u32 qm_pools_sdqcr;
+static int __qman_probed;
 
 static inline u32 qm_ccsr_in(u32 offset)
 {
@@ -401,21 +403,42 @@ static int qm_init_pfdr(struct device *d
 }
 
 /*
- * Ideally we would use the DMA API to turn rmem->base into a DMA address
- * (especially if iommu translations ever get involved).  Unfortunately, the
- * DMA API currently does not allow mapping anything that is not backed with
- * a struct page.
+ * QMan needs two global memory areas initialized at boot time:
+ *  1) FQD: Frame Queue Descriptors used to manage frame queues
+ *  2) PFDR: Packed Frame Queue Descriptor Records used to store frames
+ * Both areas are reserved using the device tree reserved memory framework
+ * and the addresses and sizes are initialized when the QMan device is probed
  */
 static dma_addr_t fqd_a, pfdr_a;
 static size_t fqd_sz, pfdr_sz;
 
+#ifdef CONFIG_PPC
+/*
+ * Support for PPC Device Tree backward compatibility when compatiable
+ * string is set to fsl-qman-fqd and fsl-qman-pfdr
+ */
+static int zero_priv_mem(phys_addr_t addr, size_t sz)
+{
+	/* map as cacheable, non-guarded */
+	void __iomem *tmpp = ioremap_prot(addr, sz, 0);
+
+	if (!tmpp)
+		return -ENOMEM;
+
+	memset_io(tmpp, 0, sz);
+	flush_dcache_range((unsigned long)tmpp,
+			   (unsigned long)tmpp + sz);
+	iounmap(tmpp);
+
+	return 0;
+}
+
 static int qman_fqd(struct reserved_mem *rmem)
 {
 	fqd_a = rmem->base;
 	fqd_sz = rmem->size;
 
 	WARN_ON(!(fqd_a && fqd_sz));
-
 	return 0;
 }
 RESERVEDMEM_OF_DECLARE(qman_fqd, "fsl,qman-fqd", qman_fqd);
@@ -431,32 +454,13 @@ static int qman_pfdr(struct reserved_mem
 }
 RESERVEDMEM_OF_DECLARE(qman_pfdr, "fsl,qman-pfdr", qman_pfdr);
 
+#endif
+
 static unsigned int qm_get_fqid_maxcnt(void)
 {
 	return fqd_sz / 64;
 }
 
-/*
- * Flush this memory range from data cache so that QMAN originated
- * transactions for this memory region could be marked non-coherent.
- */
-static int zero_priv_mem(struct device *dev, struct device_node *node,
-			 phys_addr_t addr, size_t sz)
-{
-	/* map as cacheable, non-guarded */
-	void __iomem *tmpp = ioremap_prot(addr, sz, 0);
-
-	if (!tmpp)
-		return -ENOMEM;
-
-	memset_io(tmpp, 0, sz);
-	flush_dcache_range((unsigned long)tmpp,
-			   (unsigned long)tmpp + sz);
-	iounmap(tmpp);
-
-	return 0;
-}
-
 static void log_edata_bits(struct device *dev, u32 bit_count)
 {
 	u32 i, j, mask = 0xffffffff;
@@ -595,6 +599,7 @@ static int qman_init_ccsr(struct device
 #define LIO_CFG_LIODN_MASK 0x0fff0000
 void qman_liodn_fixup(u16 channel)
 {
+#ifdef CONFIG_PPC
 	static int done;
 	static u32 liodn_offset;
 	u32 before, after;
@@ -614,6 +619,7 @@ void qman_liodn_fixup(u16 channel)
 		qm_ccsr_out(REG_REV3_QCSP_LIO_CFG(idx), after);
 	else
 		qm_ccsr_out(REG_QCSP_LIO_CFG(idx), after);
+#endif
 }
 
 #define IO_CFG_SDEST_MASK 0x00ff0000
@@ -684,14 +690,24 @@ static int qman_resource_init(struct dev
 	return 0;
 }
 
+int qman_is_probed(void)
+{
+	return __qman_probed;
+}
+EXPORT_SYMBOL_GPL(qman_is_probed);
+
 static int fsl_qman_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct device_node *node = dev->of_node;
+	struct device_node *mem_node, *node = dev->of_node;
+	struct iommu_domain *domain;
 	struct resource *res;
 	int ret, err_irq;
 	u16 id;
 	u8 major, minor;
+	u64 size;
+
+	__qman_probed = -1;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
@@ -717,6 +733,8 @@ static int fsl_qman_probe(struct platfor
 		qman_ip_rev = QMAN_REV30;
 	else if (major == 3 && minor == 1)
 		qman_ip_rev = QMAN_REV31;
+	else if (major == 3 && minor == 2)
+		qman_ip_rev = QMAN_REV32;
 	else {
 		dev_err(dev, "Unknown QMan version\n");
 		return -ENODEV;
@@ -727,10 +745,96 @@ static int fsl_qman_probe(struct platfor
 		qm_channel_caam = QMAN_CHANNEL_CAAM_REV3;
 	}
 
-	ret = zero_priv_mem(dev, node, fqd_a, fqd_sz);
-	WARN_ON(ret);
-	if (ret)
-		return -ENODEV;
+	if (fqd_a) {
+#ifdef CONFIG_PPC
+		/*
+		 * For PPC backward DT compatibility
+		 * FQD memory MUST be zero'd by software
+		 */
+		zero_priv_mem(fqd_a, fqd_sz);
+#else
+		WARN(1, "Unexpected archiceture using non shared-dma-mem reservations");
+#endif
+	} else {
+		/*
+		 * Order of memory regions is assumed as FQD followed by PFDR
+		 * in order to ensure allocations from the correct regions the
+		 * driver initializes then allocates each piece in order
+		 */
+		ret = of_reserved_mem_device_init_by_idx(dev, dev->of_node, 0);
+		if (ret) {
+			dev_err(dev, "of_reserved_mem_device_init_by_idx(0) failed 0x%x\n",
+				ret);
+			return -ENODEV;
+		}
+		mem_node = of_parse_phandle(dev->of_node, "memory-region", 0);
+		if (mem_node) {
+			ret = of_property_read_u64(mem_node, "size", &size);
+			if (ret) {
+				dev_err(dev, "FQD: of_address_to_resource fails 0x%x\n",
+					ret);
+				return -ENODEV;
+			}
+			fqd_sz = size;
+		} else {
+			dev_err(dev, "No memory-region found for FQD\n");
+			return -ENODEV;
+		}
+		if (!dma_zalloc_coherent(dev, fqd_sz, &fqd_a, 0)) {
+			dev_err(dev, "Alloc FQD memory failed\n");
+			return -ENODEV;
+		}
+
+		/*
+		 * Disassociate the FQD reserved memory area from the device
+		 * because a device can only have one DMA memory area. This
+		 * should be fine since the memory is allocated and initialized
+		 * and only ever accessed by the QMan device from now on
+		 */
+		of_reserved_mem_device_release(dev);
+	}
+	dev_dbg(dev, "Allocated FQD 0x%llx 0x%zx\n", fqd_a, fqd_sz);
+
+	if (!pfdr_a) {
+		/* Setup PFDR memory */
+		ret = of_reserved_mem_device_init_by_idx(dev, dev->of_node, 1);
+		if (ret) {
+			dev_err(dev, "of_reserved_mem_device_init(1) failed 0x%x\n",
+			ret);
+			return -ENODEV;
+		}
+		mem_node = of_parse_phandle(dev->of_node, "memory-region", 1);
+		if (mem_node) {
+			ret = of_property_read_u64(mem_node, "size", &size);
+			if (ret) {
+				dev_err(dev, "PFDR: of_address_to_resource fails 0x%x\n",
+					ret);
+				return -ENODEV;
+			}
+			pfdr_sz = size;
+		} else {
+			dev_err(dev, "No memory-region found for PFDR\n");
+			return -ENODEV;
+		}
+		if (!dma_zalloc_coherent(dev, pfdr_sz, &pfdr_a, 0)) {
+			dev_err(dev, "Alloc PFDR Failed size 0x%zx\n", pfdr_sz);
+			return -ENODEV;
+		}
+	}
+	dev_info(dev, "Allocated PFDR 0x%llx 0x%zx\n", pfdr_a, pfdr_sz);
+
+	/* Create an 1-to-1 iommu mapping for fqd and pfdr areas */
+	domain = iommu_get_domain_for_dev(dev);
+	if (domain) {
+		ret = iommu_map(domain, fqd_a, fqd_a, PAGE_ALIGN(fqd_sz),
+				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
+		if (ret)
+			dev_warn(dev, "iommu_map(fqd) failed %d\n", ret);
+		ret = iommu_map(domain, pfdr_a, pfdr_a, PAGE_ALIGN(pfdr_sz),
+				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
+		if (ret)
+			dev_warn(dev, "iommu_map(pfdr) failed %d\n", ret);
+	}
 
 	ret = qman_init_ccsr(dev);
 	if (ret) {
@@ -793,6 +897,8 @@ static int fsl_qman_probe(struct platfor
 	if (ret)
 		return ret;
 
+	__qman_probed = 1;
+
 	return 0;
 }
 
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -29,6 +29,7 @@
  */
 
 #include "qman_priv.h"
+#include <linux/iommu.h>
 
 struct qman_portal *qman_dma_portal;
 EXPORT_SYMBOL(qman_dma_portal);
@@ -38,6 +39,7 @@ EXPORT_SYMBOL(qman_dma_portal);
 #define CONFIG_FSL_DPA_PIRQ_FAST  1
 
 static struct cpumask portal_cpus;
+static int __qman_portals_probed;
 /* protect qman global registers and global data shared among portals */
 static DEFINE_SPINLOCK(qman_lock);
 
@@ -218,19 +220,36 @@ static int qman_online_cpu(unsigned int
 	return 0;
 }
 
+int qman_portals_probed(void)
+{
+	return __qman_portals_probed;
+}
+EXPORT_SYMBOL_GPL(qman_portals_probed);
+
 static int qman_portal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *node = dev->of_node;
+	struct iommu_domain *domain;
 	struct qm_portal_config *pcfg;
 	struct resource *addr_phys[2];
 	void __iomem *va;
 	int irq, cpu, err;
 	u32 val;
 
+	err = qman_is_probed();
+	if (!err)
+		return -EPROBE_DEFER;
+	if (err < 0) {
+		dev_err(&pdev->dev, "failing probe due to qman probe error\n");
+		return -ENODEV;
+	}
+
 	pcfg = devm_kmalloc(dev, sizeof(*pcfg), GFP_KERNEL);
-	if (!pcfg)
+	if (!pcfg) {
+		__qman_portals_probed = -1;
 		return -ENOMEM;
+	}
 
 	pcfg->dev = dev;
 
@@ -238,19 +257,20 @@ static int qman_portal_probe(struct plat
 					     DPAA_PORTAL_CE);
 	if (!addr_phys[0]) {
 		dev_err(dev, "Can't get %pOF property 'reg::CE'\n", node);
-		return -ENXIO;
+		goto err_ioremap1;
 	}
 
 	addr_phys[1] = platform_get_resource(pdev, IORESOURCE_MEM,
 					     DPAA_PORTAL_CI);
 	if (!addr_phys[1]) {
 		dev_err(dev, "Can't get %pOF property 'reg::CI'\n", node);
-		return -ENXIO;
+		goto err_ioremap1;
 	}
 
 	err = of_property_read_u32(node, "cell-index", &val);
 	if (err) {
 		dev_err(dev, "Can't get %pOF property 'cell-index'\n", node);
+		__qman_portals_probed = -1;
 		return err;
 	}
 	pcfg->channel = val;
@@ -258,11 +278,18 @@ static int qman_portal_probe(struct plat
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0) {
 		dev_err(dev, "Can't get %pOF IRQ\n", node);
-		return -ENXIO;
+		goto err_ioremap1;
 	}
 	pcfg->irq = irq;
 
-	va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]), 0);
+#ifdef CONFIG_PPC
+	/* PPC requires a cacheable/non-coherent mapping of the portal */
+	va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]),
+			  (pgprot_val(PAGE_KERNEL) & ~_PAGE_COHERENT));
+#else
+	/* For ARM we can use write combine mapping. */
+	va = ioremap_wc(addr_phys[0]->start, resource_size(addr_phys[0]));
+#endif
 	if (!va) {
 		dev_err(dev, "ioremap::CE failed\n");
 		goto err_ioremap1;
@@ -270,8 +297,7 @@ static int qman_portal_probe(struct plat
 
 	pcfg->addr_virt[DPAA_PORTAL_CE] = va;
 
-	va = ioremap_prot(addr_phys[1]->start, resource_size(addr_phys[1]),
-			  _PAGE_GUARDED | _PAGE_NO_CACHE);
+	va = ioremap(addr_phys[1]->start, resource_size(addr_phys[1]));
 	if (!va) {
 		dev_err(dev, "ioremap::CI failed\n");
 		goto err_ioremap2;
@@ -279,6 +305,21 @@ static int qman_portal_probe(struct plat
 
 	pcfg->addr_virt[DPAA_PORTAL_CI] = va;
 
+	/* Create an 1-to-1 iommu mapping for cena portal area */
+	domain = iommu_get_domain_for_dev(dev);
+	if (domain) {
+		/*
+		 * Note: not mapping this as cacheable triggers the infamous
+		 * QMan CIDE error.
+		 */
+		err = iommu_map(domain,
+				addr_phys[0]->start, addr_phys[0]->start,
+				PAGE_ALIGN(resource_size(addr_phys[0])),
+				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
+		if (err)
+			dev_warn(dev, "failed to iommu_map() %d\n", err);
+	}
+
 	pcfg->pools = qm_get_pools_sdqcr();
 
 	spin_lock(&qman_lock);
@@ -290,6 +331,9 @@ static int qman_portal_probe(struct plat
 	}
 
 	cpumask_set_cpu(cpu, &portal_cpus);
+	if (!__qman_portals_probed &&
+	    cpumask_weight(&portal_cpus) == num_online_cpus())
+		__qman_portals_probed = 1;
 	spin_unlock(&qman_lock);
 	pcfg->cpu = cpu;
 
@@ -314,6 +358,8 @@ err_portal_init:
 err_ioremap2:
 	iounmap(pcfg->addr_virt[DPAA_PORTAL_CE]);
 err_ioremap1:
+	__qman_portals_probed = -1;
+
 	return -ENXIO;
 }
 
--- a/drivers/soc/fsl/qbman/qman_priv.h
+++ b/drivers/soc/fsl/qbman/qman_priv.h
@@ -28,13 +28,13 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include "dpaa_sys.h"
 
 #include <soc/fsl/qman.h>
 #include <linux/dma-mapping.h>
 #include <linux/iommu.h>
+#include <linux/dma-contiguous.h>
+#include <linux/of_address.h>
 
 #if defined(CONFIG_FSL_PAMU)
 #include <asm/fsl_pamu_stash.h>
@@ -187,6 +187,7 @@ struct qm_portal_config {
 #define QMAN_REV20 0x0200
 #define QMAN_REV30 0x0300
 #define QMAN_REV31 0x0301
+#define QMAN_REV32 0x0302
 extern u16 qman_ip_rev; /* 0 if uninitialised, otherwise QMAN_REVx */
 
 #define QM_FQID_RANGE_START 1 /* FQID 0 reserved for internal use */
--- a/drivers/soc/fsl/qbman/qman_test.h
+++ b/drivers/soc/fsl/qbman/qman_test.h
@@ -30,7 +30,5 @@
 
 #include "qman_priv.h"
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 int qman_test_stash(void);
 int qman_test_api(void);
--- a/include/soc/fsl/bman.h
+++ b/include/soc/fsl/bman.h
@@ -126,4 +126,20 @@ int bman_release(struct bman_pool *pool,
  */
 int bman_acquire(struct bman_pool *pool, struct bm_buffer *bufs, u8 num);
 
+/**
+ * bman_is_probed - Check if bman is probed
+ *
+ * Returns 1 if the bman driver successfully probed, -1 if the bman driver
+ * failed to probe or 0 if the bman driver did not probed yet.
+ */
+int bman_is_probed(void);
+/**
+ * bman_portals_probed - Check if all cpu bound bman portals are probed
+ *
+ * Returns 1 if all the required cpu bound bman portals successfully probed,
+ * -1 if probe errors appeared or 0 if the bman portals did not yet finished
+ * probing.
+ */
+int bman_portals_probed(void);
+
 #endif	/* __FSL_BMAN_H */
--- a/include/soc/fsl/qman.h
+++ b/include/soc/fsl/qman.h
@@ -1186,4 +1186,21 @@ int qman_alloc_cgrid_range(u32 *result,
  */
 int qman_release_cgrid(u32 id);
 
+/**
+ * qman_is_probed - Check if qman is probed
+ *
+ * Returns 1 if the qman driver successfully probed, -1 if the qman driver
+ * failed to probe or 0 if the qman driver did not probed yet.
+ */
+int qman_is_probed(void);
+
+/**
+ * qman_portals_probed - Check if all cpu bound qman portals are probed
+ *
+ * Returns 1 if all the required cpu bound qman portals successfully probed,
+ * -1 if probe errors appeared or 0 if the qman portals did not yet finished
+ * probing.
+ */
+int qman_portals_probed(void);
+
 #endif	/* __FSL_QMAN_H */