Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/scottwood/linux into next

Freescale updates from Scott:

"Highlights include 8xx hugepage support, qbman fixes/cleanup, device
tree updates, and some misc cleanup."

47 files changed, 1040 insertions, 580 deletions

diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index fbbad6446741..c65aff0edf56 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -158,4 +158,5 @@ ti,tsc2003		I2C Touch-Screen Controller
 ti,tmp102		Low Power Digital Temperature Sensor with SMBUS/Two Wire Serial Interface
 ti,tmp103		Low Power Digital Temperature Sensor with SMBUS/Two Wire Serial Interface
 ti,tmp275		Digital Temperature Sensor
+winbond,w83793		Winbond/Nuvoton H/W Monitor
 winbond,wpct301		i2c trusted platform module (TPM)
diff --git a/arch/powerpc/boot/dts/fsl/t1023rdb.dts b/arch/powerpc/boot/dts/fsl/t1023rdb.dts
index 29757623e5ba..5ba6fbfca274 100644
--- a/arch/powerpc/boot/dts/fsl/t1023rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1023rdb.dts
@@ -41,6 +41,27 @@
 	#size-cells = <2>;
 	interrupt-parent = <&mpic>;
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		bman_fbpr: bman-fbpr {
+			size = <0 0x1000000>;
+			alignment = <0 0x1000000>;
+		};
+
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
+	};
+
 	ifc: localbus@ffe124000 {
 		reg = <0xf 0xfe124000 0 0x2000>;
 		ranges = <0 0 0xf 0xe8000000 0x08000000
@@ -72,6 +93,14 @@
 		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
 	};
 
+	bportals: bman-portals@ff4000000 {
+		ranges = <0x0 0xf 0xf4000000 0x2000000>;
+	};
+
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
index 6e0b4892a740..da2894c59479 100644
--- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -34,6 +34,21 @@
 
 #include <dt-bindings/thermal/thermal.h>
 
+&bman_fbpr {
+	compatible = "fsl,bman-fbpr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
@@ -180,6 +195,92 @@
 	};
 };
 
+&bportals {
+	#address-cells = <0x1>;
+	#size-cells = <0x1>;
+	compatible = "simple-bus";
+
+	bman-portal@0 {
+		cell-index = <0x0>;
+		compatible = "fsl,bman-portal";
+		reg = <0x0 0x4000>, <0x1000000 0x1000>;
+		interrupts = <105 2 0 0>;
+	};
+	bman-portal@4000 {
+		cell-index = <0x1>;
+		compatible = "fsl,bman-portal";
+		reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+		interrupts = <107 2 0 0>;
+	};
+	bman-portal@8000 {
+		cell-index = <2>;
+		compatible = "fsl,bman-portal";
+		reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+		interrupts = <109 2 0 0>;
+	};
+	bman-portal@c000 {
+		cell-index = <0x3>;
+		compatible = "fsl,bman-portal";
+		reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+		interrupts = <111 2 0 0>;
+	};
+	bman-portal@10000 {
+		cell-index = <0x4>;
+		compatible = "fsl,bman-portal";
+		reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+		interrupts = <113 2 0 0>;
+	};
+	bman-portal@14000 {
+		cell-index = <0x5>;
+		compatible = "fsl,bman-portal";
+		reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+		interrupts = <115 2 0 0>;
+	};
+};
+
+&qportals {
+	#address-cells = <0x1>;
+	#size-cells = <0x1>;
+	compatible = "simple-bus";
+
+	qportal0: qman-portal@0 {
+		compatible = "fsl,qman-portal";
+		reg = <0x0 0x4000>, <0x1000000 0x1000>;
+		interrupts = <104 0x2 0 0>;
+		cell-index = <0x0>;
+	};
+	qportal1: qman-portal@4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+		interrupts = <106 0x2 0 0>;
+		cell-index = <0x1>;
+	};
+	qportal2: qman-portal@8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+		interrupts = <108 0x2 0 0>;
+		cell-index = <0x2>;
+	};
+	qportal3: qman-portal@c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+		interrupts = <110 0x2 0 0>;
+		cell-index = <0x3>;
+	};
+	qportal4: qman-portal@10000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+		interrupts = <112 0x2 0 0>;
+		cell-index = <0x4>;
+	};
+	qportal5: qman-portal@14000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+		interrupts = <114 0x2 0 0>;
+		cell-index = <0x5>;
+	};
+};
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -413,6 +514,8 @@
 	};
 
 /include/ "qoriq-sec5.0-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
+/include/ "qoriq-bman1.dtsi"
 
 /include/ "qoriq-fman3l-0.dtsi"
 /include/ "qoriq-fman3-0-10g-0-best-effort.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/t1024qds.dts b/arch/powerpc/boot/dts/fsl/t1024qds.dts
index 772143da367f..d6858b7cd93f 100644
--- a/arch/powerpc/boot/dts/fsl/t1024qds.dts
+++ b/arch/powerpc/boot/dts/fsl/t1024qds.dts
@@ -41,6 +41,27 @@
 	#size-cells = <2>;
 	interrupt-parent = <&mpic>;
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		bman_fbpr: bman-fbpr {
+			size = <0 0x1000000>;
+			alignment = <0 0x1000000>;
+		};
+
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
+	};
+
 	ifc: localbus@ffe124000 {
 		reg = <0xf 0xfe124000 0 0x2000>;
 		ranges = <0 0 0xf 0xe8000000 0x08000000
@@ -80,6 +101,14 @@
 		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
 	};
 
+	bportals: bman-portals@ff4000000 {
+		ranges = <0x0 0xf 0xf4000000 0x2000000>;
+	};
+
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/fsl/t1024rdb.dts b/arch/powerpc/boot/dts/fsl/t1024rdb.dts
index 302cdd22b4bb..73a645324bc1 100644
--- a/arch/powerpc/boot/dts/fsl/t1024rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1024rdb.dts
@@ -41,6 +41,31 @@
 	#size-cells = <2>;
 	interrupt-parent = <&mpic>;
 
+	aliases {
+		sg_2500_aqr105_phy4 = &sg_2500_aqr105_phy4;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		bman_fbpr: bman-fbpr {
+			size = <0 0x1000000>;
+			alignment = <0 0x1000000>;
+		};
+
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
+	};
+
 	ifc: localbus@ffe124000 {
 		reg = <0xf 0xfe124000 0 0x2000>;
 		ranges = <0 0 0xf 0xe8000000 0x08000000
@@ -82,6 +107,14 @@
 		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
 	};
 
+	bportals: bman-portals@ff4000000 {
+		ranges = <0x0 0xf 0xf4000000 0x2000000>;
+	};
+
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts b/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts
index 2a5a90dd272e..fcd2aeb5b8ac 100644
--- a/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts
@@ -48,6 +48,58 @@
 					"fsl,deepsleep-cpld";
 		};
 	};
+
+	soc: soc@ffe000000 {
+		fman0: fman@400000 {
+			ethernet@e0000 {
+				phy-handle = <&phy_sgmii_0>;
+				phy-connection-type = "sgmii";
+			};
+
+			ethernet@e2000 {
+				phy-handle = <&phy_sgmii_1>;
+				phy-connection-type = "sgmii";
+			};
+
+			ethernet@e4000 {
+				phy-handle = <&phy_sgmii_2>;
+				phy-connection-type = "sgmii";
+			};
+
+			ethernet@e6000 {
+				phy-handle = <&phy_rgmii_0>;
+				phy-connection-type = "rgmii";
+			};
+
+			ethernet@e8000 {
+				phy-handle = <&phy_rgmii_1>;
+				phy-connection-type = "rgmii";
+			};
+
+			mdio0: mdio@fc000 {
+				phy_sgmii_0: ethernet-phy@02 {
+					reg = <0x02>;
+				};
+
+				phy_sgmii_1: ethernet-phy@03 {
+					reg = <0x03>;
+				};
+
+				phy_sgmii_2: ethernet-phy@01 {
+					reg = <0x01>;
+				};
+
+				phy_rgmii_0: ethernet-phy@04 {
+					reg = <0x04>;
+				};
+
+				phy_rgmii_1: ethernet-phy@05 {
+					reg = <0x05>;
+				};
+			};
+		};
+	};
+
 };
 
 #include "t1042si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/t4240rdb.dts b/arch/powerpc/boot/dts/fsl/t4240rdb.dts
index cc0a264b8acb..8166c660712a 100644
--- a/arch/powerpc/boot/dts/fsl/t4240rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t4240rdb.dts
@@ -125,6 +125,10 @@
 		};
 
 		i2c@118000 {
+			hwmon@2f {
+				compatible = "winbond,w83793";
+				reg = <0x2f>;
+			};
 			eeprom@52 {
 				compatible = "at24,24c256";
 				reg = <0x52>;
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index 1a61e81ab0cd..cc49c95494da 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -44,6 +44,7 @@ CONFIG_FORCE_MAX_ZONEORDER=13
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAME_WARN=1024
 CONFIG_FTL=y
+CONFIG_GPIO_GENERIC_PLATFORM=y
 CONFIG_HFS_FS=m
 CONFIG_HFSPLUS_FS=m
 CONFIG_HIGH_RES_TIMERS=y
@@ -104,8 +105,13 @@ CONFIG_PACKET=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_PERF_EVENTS=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POWER_SUPPLY=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_GPIO=y
+CONFIG_POWER_RESET_GPIO_RESTART=y
 CONFIG_QNX4FS_FS=m
 CONFIG_RCU_TRACE=y
+CONFIG_RESET_CONTROLLER=y
 CONFIG_ROOT_NFS=y
 CONFIG_SYSV_FS=m
 CONFIG_SYSVIPC=y
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 8e21bb492dca..d310546e5d9d 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -2,14 +2,42 @@
 #define _ASM_POWERPC_BOOK3S_32_PGALLOC_H
 
 #include <linux/threads.h>
+#include <linux/slab.h>
 
-/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
-#define MAX_PGTABLE_INDEX_SIZE	0
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation.  For PTE pages (which are linked to a struct
+ * page for now, and drawn from the main get_free_pages() pool), the
+ * allocation size will be (2^index_size * sizeof(pointer)) and
+ * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
 
 extern void __bad_pte(pmd_t *pmd);
 
-extern pgd_t *pgd_alloc(struct mm_struct *mm);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+extern struct kmem_cache *pgtable_cache[];
+#define PGT_CACHE(shift) ({				\
+			BUG_ON(!(shift));		\
+			pgtable_cache[(shift) - 1];	\
+		})
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
+}
 
 /*
  * We don't have any real pmd's, and this code never triggers because
@@ -68,8 +96,12 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 
 static inline void pgtable_free(void *table, unsigned index_size)
 {
-	BUG_ON(index_size); /* 32-bit doesn't use this */
-	free_page((unsigned long)table);
+	if (!index_size) {
+		free_page((unsigned long)table);
+	} else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
 }
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index dc58980f3ad9..012223638815 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -8,6 +8,23 @@
 /* And here we include common definitions */
 #include <asm/pte-common.h>
 
+#define PTE_INDEX_SIZE	PTE_SHIFT
+#define PMD_INDEX_SIZE	0
+#define PUD_INDEX_SIZE	0
+#define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
+
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+
+#ifndef __ASSEMBLY__
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE	0
+#define PUD_TABLE_SIZE	0
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+#endif	/* __ASSEMBLY__ */
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
 /*
  * The normal case is that PTEs are 32-bits and we have a 1-page
  * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
@@ -19,14 +36,10 @@
  * -Matt
  */
 /* PGDIR_SHIFT determines what a top-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-#define PTRS_PER_PTE	(1 << PTE_SHIFT)
-#define PTRS_PER_PMD	1
-#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
-
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 /*
  * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
@@ -82,12 +95,8 @@
 
 extern unsigned long ioremap_bot;
 
-/*
- * entries per page directory level: our page-table tree is two-level, so
- * we don't really have any PMD directory.
- */
-#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_SHIFT)
-#define PGD_TABLE_SIZE	(sizeof(pgd_t) << (32 - PGDIR_SHIFT))
+/* Bits to mask out from a PGD to get to the PUD page */
+#define PGD_MASKED_BITS		0
 
 #define pte_ERROR(e) \
 	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
@@ -284,15 +293,6 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-#ifndef CONFIG_PPC_4K_PAGES
-void pgtable_cache_init(void);
-#else
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-#endif
-
 extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 		      pmd_t **pmdp);
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index bbea0040320a..6cfc5dbdae03 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -800,9 +800,6 @@ extern struct page *pgd_page(pgd_t pgd);
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
-void pgtable_cache_init(void);
-
 static inline int map_kernel_page(unsigned long ea, unsigned long pa,
 				  unsigned long flags)
 {
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index c03e0a3dd4d8..ede215167d1a 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -51,12 +51,20 @@ static inline void __local_flush_hugetlb_page(struct vm_area_struct *vma,
 static inline pte_t *hugepd_page(hugepd_t hpd)
 {
 	BUG_ON(!hugepd_ok(hpd));
+#ifdef CONFIG_PPC_8xx
+	return (pte_t *)__va(hpd.pd & ~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK));
+#else
 	return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
+#endif
 }
 
 static inline unsigned int hugepd_shift(hugepd_t hpd)
 {
+#ifdef CONFIG_PPC_8xx
+	return ((hpd.pd & _PMD_PAGE_MASK) >> 1) + 17;
+#else
 	return hpd.pd & HUGEPD_SHIFT_MASK;
+#endif
 }
 
 #endif /* CONFIG_PPC_BOOK3S_64 */
@@ -99,7 +107,15 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 
 void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
 			    pte_t pte);
+#ifdef CONFIG_PPC_8xx
+static inline void flush_hugetlb_page(struct vm_area_struct *vma,
+				      unsigned long vmaddr)
+{
+	flush_tlb_page(vma, vmaddr);
+}
+#else
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+#endif
 
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
@@ -205,7 +221,8 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
  * are reserved early in the boot process by memblock instead of via
  * the .dts as on IBM platforms.
  */
-#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_FSL_BOOK3E)
+#if defined(CONFIG_HUGETLB_PAGE) && (defined(CONFIG_PPC_FSL_BOOK3E) || \
+    defined(CONFIG_PPC_8xx))
 extern void __init reserve_hugetlb_gpages(void);
 #else
 static inline void reserve_hugetlb_gpages(void)
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 3e0e4927811c..798b5bf91427 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -172,6 +172,41 @@ typedef struct {
 
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
 #define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE))
+
+/* Page size definitions, common between 32 and 64-bit
+ *
+ *    shift : is the "PAGE_SHIFT" value for that page size
+ *    penc  : is the pte encoding mask
+ *
+ */
+struct mmu_psize_def {
+	unsigned int	shift;	/* number of bits */
+	unsigned int	enc;	/* PTE encoding */
+	unsigned int    ind;    /* Corresponding indirect page size shift */
+	unsigned int	flags;
+#define MMU_PAGE_SIZE_DIRECT	0x1	/* Supported as a direct size */
+#define MMU_PAGE_SIZE_INDIRECT	0x2	/* Supported as an indirect size */
+};
+
+extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+
+static inline int shift_to_mmu_psize(unsigned int shift)
+{
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+		if (mmu_psize_defs[psize].shift == shift)
+			return psize;
+	return -1;
+}
+
+static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
+{
+	if (mmu_psize_defs[mmu_psize].shift)
+		return mmu_psize_defs[mmu_psize].shift;
+	BUG();
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #if defined(CONFIG_PPC_4K_PAGES)
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 060b40b1bc3d..09304d2bec03 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -269,19 +269,20 @@ static inline bool early_radix_enabled(void)
 #define MMU_PAGE_64K	2
 #define MMU_PAGE_64K_AP	3	/* "Admixed pages" (hash64 only) */
 #define MMU_PAGE_256K	4
-#define MMU_PAGE_1M	5
-#define MMU_PAGE_2M	6
-#define MMU_PAGE_4M	7
-#define MMU_PAGE_8M	8
-#define MMU_PAGE_16M	9
-#define MMU_PAGE_64M	10
-#define MMU_PAGE_256M	11
-#define MMU_PAGE_1G	12
-#define MMU_PAGE_16G	13
-#define MMU_PAGE_64G	14
+#define MMU_PAGE_512K	5
+#define MMU_PAGE_1M	6
+#define MMU_PAGE_2M	7
+#define MMU_PAGE_4M	8
+#define MMU_PAGE_8M	9
+#define MMU_PAGE_16M	10
+#define MMU_PAGE_64M	11
+#define MMU_PAGE_256M	12
+#define MMU_PAGE_1G	13
+#define MMU_PAGE_16G	14
+#define MMU_PAGE_64G	15
 
 /* N.B. we need to change the type of hpte_page_sizes if this gets to be > 16 */
-#define MMU_PAGE_COUNT	15
+#define MMU_PAGE_COUNT	16
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/book3s/64/mmu.h>
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 76d6b9e0c8a9..633139291a48 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -2,14 +2,42 @@
 #define _ASM_POWERPC_PGALLOC_32_H
 
 #include <linux/threads.h>
+#include <linux/slab.h>
 
-/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
-#define MAX_PGTABLE_INDEX_SIZE	0
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation.  For PTE pages (which are linked to a struct
+ * page for now, and drawn from the main get_free_pages() pool), the
+ * allocation size will be (2^index_size * sizeof(pointer)) and
+ * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
 
 extern void __bad_pte(pmd_t *pmd);
 
-extern pgd_t *pgd_alloc(struct mm_struct *mm);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+extern struct kmem_cache *pgtable_cache[];
+#define PGT_CACHE(shift) ({				\
+			BUG_ON(!(shift));		\
+			pgtable_cache[(shift) - 1];	\
+		})
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
+}
 
 /*
  * We don't have any real pmd's, and this code never triggers because
@@ -68,8 +96,12 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 
 static inline void pgtable_free(void *table, unsigned index_size)
 {
-	BUG_ON(index_size); /* 32-bit doesn't use this */
-	free_page((unsigned long)table);
+	if (!index_size) {
+		free_page((unsigned long)table);
+	} else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
 }
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 65073fbc6707..ba9921bf202e 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -16,6 +16,23 @@ extern int icache_44x_need_flush;
 
 #endif /* __ASSEMBLY__ */
 
+#define PTE_INDEX_SIZE	PTE_SHIFT
+#define PMD_INDEX_SIZE	0
+#define PUD_INDEX_SIZE	0
+#define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
+
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+
+#ifndef __ASSEMBLY__
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE	0
+#define PUD_TABLE_SIZE	0
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+#endif	/* __ASSEMBLY__ */
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
 /*
  * The normal case is that PTEs are 32-bits and we have a 1-page
  * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
@@ -27,22 +44,12 @@ extern int icache_44x_need_flush;
  * -Matt
  */
 /* PGDIR_SHIFT determines what a top-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-/*
- * entries per page directory level: our page-table tree is two-level, so
- * we don't really have any PMD directory.
- */
-#ifndef __ASSEMBLY__
-#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_SHIFT)
-#define PGD_TABLE_SIZE	(sizeof(pgd_t) << (32 - PGDIR_SHIFT))
-#endif	/* __ASSEMBLY__ */
-
-#define PTRS_PER_PTE	(1 << PTE_SHIFT)
-#define PTRS_PER_PMD	1
-#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
+/* Bits to mask out from a PGD to get to the PUD page */
+#define PGD_MASKED_BITS		0
 
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 #define FIRST_USER_ADDRESS	0UL
@@ -329,15 +336,6 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-#ifndef CONFIG_PPC_4K_PAGES
-void pgtable_cache_init(void);
-#else
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-#endif
-
 extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 		      pmd_t **pmdp);
 
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 3742b1919661..b4df2734c078 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -49,6 +49,7 @@
 #define _PMD_BAD	0x0ff0
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
+#define _PMD_PAGE_512K	0x0004
 
 /* Until my rework is finished, 8xx still needs atomic PTE updates */
 #define PTE_ATOMIC_UPDATES	1
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 53a41b06a7b9..c7f927e67d14 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -347,8 +347,6 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)		__pte((x).val)
 
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
-void pgtable_cache_init(void);
 extern int map_kernel_page(unsigned long ea, unsigned long pa,
 			   unsigned long flags);
 extern int __meminit vmemmap_create_mapping(unsigned long start,
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 1263c22d60d8..172849727054 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -226,7 +226,11 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 #ifdef CONFIG_HUGETLB_PAGE
 static inline int hugepd_ok(hugepd_t hpd)
 {
+#ifdef CONFIG_PPC_8xx
+	return ((hpd.pd & 0x4) != 0);
+#else
 	return (hpd.pd > 0);
+#endif
 }
 
 static inline int pmd_huge(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 9bd87f269d6d..dd01212935ac 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -78,6 +78,8 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 
 unsigned long vmalloc_to_phys(void *vmalloc_addr);
 
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
+void pgtable_cache_init(void);
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index 0197e12f7d48..1f1636124a04 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -4,7 +4,7 @@
 #ifndef _ASM_POWERPC_REG_8xx_H
 #define _ASM_POWERPC_REG_8xx_H
 
-#include <asm/mmu-8xx.h>
+#include <asm/mmu.h>
 
 /* Cache control on the MPC8xx is provided through some additional
  * special purpose registers.
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index fb133a163263..1a9c99d3e5d8 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -73,6 +73,9 @@
 #define RPN_PATTERN	0x00f0
 #endif
 
+#define PAGE_SHIFT_512K		19
+#define PAGE_SHIFT_8M		23
+
 	__HEAD
 _ENTRY(_stext);
 _ENTRY(_start);
@@ -322,7 +325,7 @@ SystemCall:
 #endif
 
 InstructionTLBMiss:
-#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
+#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE)
 	mtspr	SPRN_SPRG_SCRATCH2, r3
 #endif
 	EXCEPTION_PROLOG_0
@@ -332,10 +335,12 @@ InstructionTLBMiss:
 	 */
 	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
 	INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10)
-#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
 	/* Only modules will cause ITLB Misses as we always
 	 * pin the first 8MB of kernel memory */
+#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE)
 	mfcr	r3
+#endif
+#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
 	IS_KERNEL(r11, r10)
 #endif
 	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
@@ -343,7 +348,6 @@ InstructionTLBMiss:
 	BRANCH_UNLESS_KERNEL(3f)
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 3:
-	mtcr	r3
 #endif
 	/* Insert level 1 index */
 	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
@@ -351,14 +355,25 @@ InstructionTLBMiss:
 
 	/* Extract level 2 index */
 	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+#ifdef CONFIG_HUGETLB_PAGE
+	mtcr	r11
+	bt-	28, 10f		/* bit 28 = Large page (8M) */
+	bt-	29, 20f		/* bit 29 = Large page (8M or 512k) */
+#endif
 	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
-
+4:
+#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE)
+	mtcr	r3
+#endif
 	/* Insert the APG into the TWC from the Linux PTE. */
 	rlwimi	r11, r10, 0, 25, 26
 	/* Load the MI_TWC with the attributes for this "segment." */
 	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
 
+#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
+	rlwimi	r10, r11, 1, MI_SPS16K
+#endif
 #ifdef CONFIG_SWAP
 	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
 	and	r11, r11, r10
@@ -371,16 +386,45 @@ InstructionTLBMiss:
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
+#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
+	rlwimi	r10, r11, 0, 0x0ff0	/* Set 24-27, clear 20-23 */
+#else
 	rlwimi	r10, r11, 0, 0x0ff8	/* Set 24-27, clear 20-23,28 */
+#endif
 	MTSPR_CPU6(SPRN_MI_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
-#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
+#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE)
 	mfspr	r3, SPRN_SPRG_SCRATCH2
 #endif
 	EXCEPTION_EPILOG_0
 	rfi
 
+#ifdef CONFIG_HUGETLB_PAGE
+10:	/* 8M pages */
+#ifdef CONFIG_PPC_16K_PAGES
+	/* Extract level 2 index */
+	rlwinm	r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29
+	/* Add level 2 base */
+	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1
+#else
+	/* Level 2 base */
+	rlwinm	r10, r11, 0, ~HUGEPD_SHIFT_MASK
+#endif
+	lwz	r10, 0(r10)	/* Get the pte */
+	rlwinm	r11, r11, 0, 0xf
+	b	4b
+
+20:	/* 512k pages */
+	/* Extract level 2 index */
+	rlwinm	r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29
+	/* Add level 2 base */
+	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
+	lwz	r10, 0(r10)	/* Get the pte */
+	rlwinm	r11, r11, 0, 0xf
+	b	4b
+#endif
+
 	. = 0x1200
 DataStoreTLBMiss:
 	mtspr	SPRN_SPRG_SCRATCH2, r3
@@ -407,7 +451,6 @@ _ENTRY(DTLBMiss_jmp)
 #endif
 	blt	cr7, DTLBMissLinear
 3:
-	mtcr	r3
 	mfspr	r10, SPRN_MD_EPN
 
 	/* Insert level 1 index */
@@ -418,8 +461,15 @@ _ENTRY(DTLBMiss_jmp)
 	 */
 	/* Extract level 2 index */
 	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+#ifdef CONFIG_HUGETLB_PAGE
+	mtcr	r11
+	bt-	28, 10f		/* bit 28 = Large page (8M) */
+	bt-	29, 20f		/* bit 29 = Large page (8M or 512k) */
+#endif
 	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
+4:
+	mtcr	r3
 
 	/* Insert the Guarded flag and APG into the TWC from the Linux PTE.
 	 * It is bit 26-27 of both the Linux PTE and the TWC (at least
@@ -434,6 +484,11 @@ _ENTRY(DTLBMiss_jmp)
 	rlwimi	r11, r10, 32-5, 30, 30
 	MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
 
+	/* In 4k pages mode, SPS (bit 28) in RPN must match PS[1] (bit 29)
+	 * In 16k pages mode, SPS is always 1 */
+#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
+	rlwimi	r10, r11, 1, MD_SPS16K
+#endif
 	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
 	 * We also need to know if the insn is a load/store, so:
 	 * Clear _PAGE_PRESENT and load that which will
@@ -455,7 +510,11 @@ _ENTRY(DTLBMiss_jmp)
 	 * of the MMU.
 	 */
 	li	r11, RPN_PATTERN
+#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
+	rlwimi	r10, r11, 0, 24, 27	/* Set 24-27 */
+#else
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
+#endif
 	rlwimi	r10, r11, 0, 20, 20	/* clear 20 */
 	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
 
@@ -465,6 +524,30 @@ _ENTRY(DTLBMiss_jmp)
 	EXCEPTION_EPILOG_0
 	rfi
 
+#ifdef CONFIG_HUGETLB_PAGE
+10:	/* 8M pages */
+	/* Extract level 2 index */
+#ifdef CONFIG_PPC_16K_PAGES
+	rlwinm	r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29
+	/* Add level 2 base */
+	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1
+#else
+	/* Level 2 base */
+	rlwinm	r10, r11, 0, ~HUGEPD_SHIFT_MASK
+#endif
+	lwz	r10, 0(r10)	/* Get the pte */
+	rlwinm	r11, r11, 0, 0xf
+	b	4b
+
+20:	/* 512k pages */
+	/* Extract level 2 index */
+	rlwinm	r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29
+	/* Add level 2 base */
+	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
+	lwz	r10, 0(r10)	/* Get the pte */
+	rlwinm	r11, r11, 0, 0xf
+	b	4b
+#endif
 
 /* This is an instruction TLB error on the MPC8xx.  This could be due
  * to many reasons, such as executing guarded memory or illegal instruction
@@ -586,6 +669,9 @@ _ENTRY(FixupDAR_cmp)
 	/* Insert level 1 index */
 3:	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
+	mtcr	r11
+	bt	28,200f		/* bit 28 = Large page (8M) */
+	bt	29,202f		/* bit 29 = Large page (8M or 512K) */
 	rlwinm	r11, r11,0,0,19	/* Extract page descriptor page address */
 	/* Insert level 2 index */
 	rlwimi	r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
@@ -611,6 +697,27 @@ _ENTRY(FixupDAR_cmp)
 141:	mfspr	r10,SPRN_SPRG_SCRATCH2
 	b	DARFixed	/* Nope, go back to normal TLB processing */
 
+	/* concat physical page address(r11) and page offset(r10) */
+200:
+#ifdef CONFIG_PPC_16K_PAGES
+	rlwinm	r11, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1
+	rlwimi	r11, r10, 32 - (PAGE_SHIFT_8M - 2), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29
+#else
+	rlwinm	r11, r10, 0, ~HUGEPD_SHIFT_MASK
+#endif
+	lwz	r11, 0(r11)	/* Get the pte */
+	/* concat physical page address(r11) and page offset(r10) */
+	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT_8M, 31
+	b	201b
+
+202:
+	rlwinm	r11, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
+	rlwimi	r11, r10, 32 - (PAGE_SHIFT_512K - 2), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29
+	lwz	r11, 0(r11)	/* Get the pte */
+	/* concat physical page address(r11) and page offset(r10) */
+	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT_512K, 31
+	b	201b
+
 144:	mfspr	r10, SPRN_DSISR
 	rlwinm	r10, r10,0,7,5	/* Clear store bit for buggy dcbst insn */
 	mtspr	SPRN_DSISR, r10
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 5784682d7b63..7414034df1c3 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -7,7 +7,8 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
 obj-y				:= fault.o mem.o pgtable.o mmap.o \
-				   init_$(BITS).o pgtable_$(BITS).o
+				   init_$(BITS).o pgtable_$(BITS).o \
+				   init-common.o
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
 				   tlb_nohash_low.o
 obj-$(CONFIG_PPC_BOOK3E)	+= tlb_low_$(BITS)e.o
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a5d3ecdabc44..289df38fb7e0 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -26,6 +26,8 @@
 #ifdef CONFIG_HUGETLB_PAGE
 
 #define PAGE_SHIFT_64K	16
+#define PAGE_SHIFT_512K	19
+#define PAGE_SHIFT_8M	23
 #define PAGE_SHIFT_16M	24
 #define PAGE_SHIFT_16G	34
 
@@ -38,7 +40,7 @@ unsigned int HPAGE_SHIFT;
  * implementations may have more than one gpage size, so we need multiple
  * arrays
  */
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 #define MAX_NUMBER_GPAGES	128
 struct psize_gpages {
 	u64 gpage_list[MAX_NUMBER_GPAGES];
@@ -64,14 +66,16 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 {
 	struct kmem_cache *cachep;
 	pte_t *new;
-
-#ifdef CONFIG_PPC_FSL_BOOK3E
 	int i;
-	int num_hugepd = 1 << (pshift - pdshift);
-	cachep = hugepte_cache;
-#else
-	cachep = PGT_CACHE(pdshift - pshift);
-#endif
+	int num_hugepd;
+
+	if (pshift >= pdshift) {
+		cachep = hugepte_cache;
+		num_hugepd = 1 << (pshift - pdshift);
+	} else {
+		cachep = PGT_CACHE(pdshift - pshift);
+		num_hugepd = 1;
+	}
 
 	new = kmem_cache_zalloc(cachep, GFP_KERNEL);
 
@@ -89,7 +93,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	smp_wmb();
 
 	spin_lock(&mm->page_table_lock);
-#ifdef CONFIG_PPC_FSL_BOOK3E
+
 	/*
 	 * We have multiple higher-level entries that point to the same
 	 * actual pte location.  Fill in each as we go and backtrack on error.
@@ -100,8 +104,18 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 		if (unlikely(!hugepd_none(*hpdp)))
 			break;
 		else
+#ifdef CONFIG_PPC_BOOK3S_64
+			hpdp->pd = __pa(new) |
+				   (shift_to_mmu_psize(pshift) << 2);
+#elif defined(CONFIG_PPC_8xx)
+			hpdp->pd = __pa(new) |
+				   (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
+							      _PMD_PAGE_512K) |
+				   _PMD_PRESENT;
+#else
 			/* We use the old format for PPC_FSL_BOOK3E */
 			hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+#endif
 	}
 	/* If we bailed from the for loop early, an error occurred, clean up */
 	if (i < num_hugepd) {
@@ -109,17 +123,6 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			hpdp->pd = 0;
 		kmem_cache_free(cachep, new);
 	}
-#else
-	if (!hugepd_none(*hpdp))
-		kmem_cache_free(cachep, new);
-	else {
-#ifdef CONFIG_PPC_BOOK3S_64
-		hpdp->pd = __pa(new) | (shift_to_mmu_psize(pshift) << 2);
-#else
-		hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
-#endif
-	}
-#endif
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
@@ -128,7 +131,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
  * These macros define how to determine which level of the page table holds
  * the hpdp.
  */
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 #define HUGEPD_PGD_SHIFT PGDIR_SHIFT
 #define HUGEPD_PUD_SHIFT PUD_SHIFT
 #else
@@ -136,7 +139,6 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 #define HUGEPD_PUD_SHIFT PMD_SHIFT
 #endif
 
-#ifdef CONFIG_PPC_BOOK3S_64
 /*
  * At this point we do the placement change only for BOOK3S 64. This would
  * possibly work on other subarchs.
@@ -153,6 +155,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 	addr &= ~(sz-1);
 	pg = pgd_offset(mm, addr);
 
+#ifdef CONFIG_PPC_BOOK3S_64
 	if (pshift == PGDIR_SHIFT)
 		/* 16GB huge page */
 		return (pte_t *) pg;
@@ -178,32 +181,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 				hpdp = (hugepd_t *)pm;
 		}
 	}
-	if (!hpdp)
-		return NULL;
-
-	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
-
-	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
-		return NULL;
-
-	return hugepte_offset(*hpdp, addr, pdshift);
-}
-
 #else
-
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	hugepd_t *hpdp = NULL;
-	unsigned pshift = __ffs(sz);
-	unsigned pdshift = PGDIR_SHIFT;
-
-	addr &= ~(sz-1);
-
-	pg = pgd_offset(mm, addr);
-
 	if (pshift >= HUGEPD_PGD_SHIFT) {
 		hpdp = (hugepd_t *)pg;
 	} else {
@@ -217,7 +195,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 			hpdp = (hugepd_t *)pm;
 		}
 	}
-
+#endif
 	if (!hpdp)
 		return NULL;
 
@@ -228,9 +206,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 
 	return hugepte_offset(*hpdp, addr, pdshift);
 }
-#endif
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 /* Build list of addresses of gigantic pages.  This function is used in early
  * boot before the buddy allocator is setup.
  */
@@ -310,7 +287,11 @@ static int __init do_gpage_early_setup(char *param, char *val,
 				npages = 0;
 			if (npages > MAX_NUMBER_GPAGES) {
 				pr_warn("MMU: %lu pages requested for page "
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
 					"size %llu KB, limiting to "
+#else
+					"size %u KB, limiting to "
+#endif
 					__stringify(MAX_NUMBER_GPAGES) "\n",
 					npages, size / 1024);
 				npages = MAX_NUMBER_GPAGES;
@@ -392,7 +373,7 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 }
 #endif
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 #define HUGEPD_FREELIST_SIZE \
 	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
 
@@ -442,6 +423,8 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
 	}
 	put_cpu_var(hugepd_freelist_cur);
 }
+#else
+static inline void hugepd_free(struct mmu_gather *tlb, void *hugepte) {}
 #endif
 
 static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
@@ -453,13 +436,11 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 
 	unsigned long pdmask = ~((1UL << pdshift) - 1);
 	unsigned int num_hugepd = 1;
+	unsigned int shift = hugepd_shift(*hpdp);
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
 	/* Note: On fsl the hpdp may be the first of several */
-	num_hugepd = (1 << (hugepd_shift(*hpdp) - pdshift));
-#else
-	unsigned int shift = hugepd_shift(*hpdp);
-#endif
+	if (shift > pdshift)
+		num_hugepd = 1 << (shift - pdshift);
 
 	start &= pdmask;
 	if (start < floor)
@@ -475,11 +456,10 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 	for (i = 0; i < num_hugepd; i++, hpdp++)
 		hpdp->pd = 0;
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
-	hugepd_free(tlb, hugepte);
-#else
-	pgtable_free_tlb(tlb, hugepte, pdshift - shift);
-#endif
+	if (shift >= pdshift)
+		hugepd_free(tlb, hugepte);
+	else
+		pgtable_free_tlb(tlb, hugepte, pdshift - shift);
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -492,6 +472,8 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 
 	start = addr;
 	do {
+		unsigned long more;
+
 		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
 		if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
@@ -502,15 +484,16 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 			WARN_ON(!pmd_none_or_clear_bad(pmd));
 			continue;
 		}
-#ifdef CONFIG_PPC_FSL_BOOK3E
 		/*
 		 * Increment next by the size of the huge mapping since
 		 * there may be more than one entry at this level for a
 		 * single hugepage, but all of them point to
 		 * the same kmem cache that holds the hugepte.
 		 */
-		next = addr + (1 << hugepd_shift(*(hugepd_t *)pmd));
-#endif
+		more = addr + (1 << hugepd_shift(*(hugepd_t *)pmd));
+		if (more > next)
+			next = more;
+
 		free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
 				  addr, next, floor, ceiling);
 	} while (addr = next, addr != end);
@@ -550,15 +533,17 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
 					       ceiling);
 		} else {
-#ifdef CONFIG_PPC_FSL_BOOK3E
+			unsigned long more;
 			/*
 			 * Increment next by the size of the huge mapping since
 			 * there may be more than one entry at this level for a
 			 * single hugepage, but all of them point to
 			 * the same kmem cache that holds the hugepte.
 			 */
-			next = addr + (1 << hugepd_shift(*(hugepd_t *)pud));
-#endif
+			more = addr + (1 << hugepd_shift(*(hugepd_t *)pud));
+			if (more > next)
+				next = more;
+
 			free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
 					  addr, next, floor, ceiling);
 		}
@@ -615,15 +600,17 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 				continue;
 			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
 		} else {
-#ifdef CONFIG_PPC_FSL_BOOK3E
+			unsigned long more;
 			/*
 			 * Increment next by the size of the huge mapping since
 			 * there may be more than one entry at the pgd level
 			 * for a single hugepage, but all of them point to the
 			 * same kmem cache that holds the hugepte.
 			 */
-			next = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
-#endif
+			more = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
+			if (more > next)
+				next = more;
+
 			free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
 					  addr, next, floor, ceiling);
 		}
@@ -753,12 +740,13 @@ static int __init add_huge_page_size(unsigned long long size)
 
 	/* Check that it is a page size supported by the hardware and
 	 * that it fits within pagetable and slice limits. */
-#ifdef CONFIG_PPC_FSL_BOOK3E
-	if ((size < PAGE_SIZE) || !is_power_of_4(size))
+	if (size <= PAGE_SIZE)
 		return -EINVAL;
-#else
-	if (!is_power_of_2(size)
-	    || (shift > SLICE_HIGH_SHIFT) || (shift <= PAGE_SHIFT))
+#if defined(CONFIG_PPC_FSL_BOOK3E)
+	if (!is_power_of_4(size))
+		return -EINVAL;
+#elif !defined(CONFIG_PPC_8xx)
+	if (!is_power_of_2(size) || (shift > SLICE_HIGH_SHIFT))
 		return -EINVAL;
 #endif
 
@@ -791,53 +779,15 @@ static int __init hugepage_setup_sz(char *str)
 }
 __setup("hugepagesz=", hugepage_setup_sz);
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
 struct kmem_cache *hugepte_cache;
 static int __init hugetlbpage_init(void)
 {
 	int psize;
 
-	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-		unsigned shift;
-
-		if (!mmu_psize_defs[psize].shift)
-			continue;
-
-		shift = mmu_psize_to_shift(psize);
-
-		/* Don't treat normal page sizes as huge... */
-		if (shift != PAGE_SHIFT)
-			if (add_huge_page_size(1ULL << shift) < 0)
-				continue;
-	}
-
-	/*
-	 * Create a kmem cache for hugeptes.  The bottom bits in the pte have
-	 * size information encoded in them, so align them to allow this
-	 */
-	hugepte_cache =  kmem_cache_create("hugepte-cache", sizeof(pte_t),
-					   HUGEPD_SHIFT_MASK + 1, 0, NULL);
-	if (hugepte_cache == NULL)
-		panic("%s: Unable to create kmem cache for hugeptes\n",
-		      __func__);
-
-	/* Default hpage size = 4M */
-	if (mmu_psize_defs[MMU_PAGE_4M].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_4M].shift;
-	else
-		panic("%s: Unable to set default huge page size\n", __func__);
-
-
-	return 0;
-}
-#else
-static int __init hugetlbpage_init(void)
-{
-	int psize;
-
+#if !defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_PPC_8xx)
 	if (!radix_enabled() && !mmu_has_feature(MMU_FTR_16M_PAGE))
 		return -ENODEV;
-
+#endif
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		unsigned shift;
 		unsigned pdshift;
@@ -850,9 +800,9 @@ static int __init hugetlbpage_init(void)
 		if (add_huge_page_size(1ULL << shift) < 0)
 			continue;
 
-		if (shift < PMD_SHIFT)
+		if (shift < HUGEPD_PUD_SHIFT)
 			pdshift = PMD_SHIFT;
-		else if (shift < PUD_SHIFT)
+		else if (shift < HUGEPD_PGD_SHIFT)
 			pdshift = PUD_SHIFT;
 		else
 			pdshift = PGDIR_SHIFT;
@@ -860,14 +810,38 @@ static int __init hugetlbpage_init(void)
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
 		 */
-		if (pdshift != shift) {
+		if (pdshift > shift) {
 			pgtable_cache_add(pdshift - shift, NULL);
 			if (!PGT_CACHE(pdshift - shift))
 				panic("hugetlbpage_init(): could not create "
 				      "pgtable cache for %d bit pagesize\n", shift);
 		}
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
+		else if (!hugepte_cache) {
+			/*
+			 * Create a kmem cache for hugeptes.  The bottom bits in
+			 * the pte have size information encoded in them, so
+			 * align them to allow this
+			 */
+			hugepte_cache = kmem_cache_create("hugepte-cache",
+							  sizeof(pte_t),
+							  HUGEPD_SHIFT_MASK + 1,
+							  0, NULL);
+			if (hugepte_cache == NULL)
+				panic("%s: Unable to create kmem cache "
+				      "for hugeptes\n", __func__);
+
+		}
+#endif
 	}
 
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
+	/* Default hpage size = 4M on FSL_BOOK3E and 512k on 8xx */
+	if (mmu_psize_defs[MMU_PAGE_4M].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_4M].shift;
+	else if (mmu_psize_defs[MMU_PAGE_512K].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_512K].shift;
+#else
 	/* Set default large page size. Currently, we pick 16M or 1M
 	 * depending on what is available
 	 */
@@ -877,11 +851,13 @@ static int __init hugetlbpage_init(void)
 		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
 	else if (mmu_psize_defs[MMU_PAGE_2M].shift)
 		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_2M].shift;
-
+#endif
+	else
+		panic("%s: Unable to set default huge page size\n", __func__);
 
 	return 0;
 }
-#endif
+
 arch_initcall(hugetlbpage_init);
 
 void flush_dcache_icache_hugepage(struct page *page)
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
new file mode 100644
index 000000000000..a175cd82ae8c
--- /dev/null
+++ b/arch/powerpc/mm/init-common.c
@@ -0,0 +1,107 @@
+/*
+ *  PowerPC version
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  Dave Engebretsen <engebret@us.ibm.com>
+ *      Rework for PPC64 port.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#undef DEBUG
+
+#include <linux/string.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+static void pgd_ctor(void *addr)
+{
+	memset(addr, 0, PGD_TABLE_SIZE);
+}
+
+static void pud_ctor(void *addr)
+{
+	memset(addr, 0, PUD_TABLE_SIZE);
+}
+
+static void pmd_ctor(void *addr)
+{
+	memset(addr, 0, PMD_TABLE_SIZE);
+}
+
+struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
+
+/*
+ * Create a kmem_cache() for pagetables.  This is not used for PTE
+ * pages - they're linked to struct page, come from the normal free
+ * pages pool and have a different entry size (see real_pte_t) to
+ * everything else.  Caches created by this function are used for all
+ * the higher level pagetables, and for hugepage pagetables.
+ */
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
+{
+	char *name;
+	unsigned long table_size = sizeof(void *) << shift;
+	unsigned long align = table_size;
+
+	/* When batching pgtable pointers for RCU freeing, we store
+	 * the index size in the low bits.  Table alignment must be
+	 * big enough to fit it.
+	 *
+	 * Likewise, hugeapge pagetable pointers contain a (different)
+	 * shift value in the low bits.  All tables must be aligned so
+	 * as to leave enough 0 bits in the address to contain it. */
+	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
+				     HUGEPD_SHIFT_MASK + 1);
+	struct kmem_cache *new;
+
+	/* It would be nice if this was a BUILD_BUG_ON(), but at the
+	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
+	 * constant expression, so so much for that. */
+	BUG_ON(!is_power_of_2(minalign));
+	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
+
+	if (PGT_CACHE(shift))
+		return; /* Already have a cache of this size */
+
+	align = max_t(unsigned long, align, minalign);
+	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
+	new = kmem_cache_create(name, table_size, align, 0, ctor);
+	kfree(name);
+	pgtable_cache[shift - 1] = new;
+	pr_debug("Allocated pgtable cache for order %d\n", shift);
+}
+
+
+void pgtable_cache_init(void)
+{
+	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
+
+	if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
+		pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	/*
+	 * In all current configs, when the PUD index exists it's the
+	 * same size as either the pgd or pmd index except with THP enabled
+	 * on book3s 64
+	 */
+	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
+		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
+
+	if (!PGT_CACHE(PGD_INDEX_SIZE))
+		panic("Couldn't allocate pgd cache");
+	if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
+		panic("Couldn't allocate pmd pgtable caches");
+	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
+		panic("Couldn't allocate pud pgtable caches");
+}
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 16ada1eb7e26..a000c3585390 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -80,83 +80,6 @@ EXPORT_SYMBOL_GPL(memstart_addr);
 phys_addr_t kernstart_addr;
 EXPORT_SYMBOL_GPL(kernstart_addr);
 
-static void pgd_ctor(void *addr)
-{
-	memset(addr, 0, PGD_TABLE_SIZE);
-}
-
-static void pud_ctor(void *addr)
-{
-	memset(addr, 0, PUD_TABLE_SIZE);
-}
-
-static void pmd_ctor(void *addr)
-{
-	memset(addr, 0, PMD_TABLE_SIZE);
-}
-
-struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
-
-/*
- * Create a kmem_cache() for pagetables.  This is not used for PTE
- * pages - they're linked to struct page, come from the normal free
- * pages pool and have a different entry size (see real_pte_t) to
- * everything else.  Caches created by this function are used for all
- * the higher level pagetables, and for hugepage pagetables.
- */
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
-{
-	char *name;
-	unsigned long table_size = sizeof(void *) << shift;
-	unsigned long align = table_size;
-
-	/* When batching pgtable pointers for RCU freeing, we store
-	 * the index size in the low bits.  Table alignment must be
-	 * big enough to fit it.
-	 *
-	 * Likewise, hugeapge pagetable pointers contain a (different)
-	 * shift value in the low bits.  All tables must be aligned so
-	 * as to leave enough 0 bits in the address to contain it. */
-	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
-				     HUGEPD_SHIFT_MASK + 1);
-	struct kmem_cache *new;
-
-	/* It would be nice if this was a BUILD_BUG_ON(), but at the
-	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
-	 * constant expression, so so much for that. */
-	BUG_ON(!is_power_of_2(minalign));
-	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
-
-	if (PGT_CACHE(shift))
-		return; /* Already have a cache of this size */
-
-	align = max_t(unsigned long, align, minalign);
-	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
-	new = kmem_cache_create(name, table_size, align, 0, ctor);
-	kfree(name);
-	pgtable_cache[shift - 1] = new;
-	pr_debug("Allocated pgtable cache for order %d\n", shift);
-}
-
-
-void pgtable_cache_init(void)
-{
-	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
-	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
-	/*
-	 * In all current configs, when the PUD index exists it's the
-	 * same size as either the pgd or pmd index except with THP enabled
-	 * on book3s 64
-	 */
-	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
-		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
-
-	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
-		panic("Couldn't allocate pgtable caches");
-	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
-		panic("Couldn't allocate pud pgtable caches");
-}
-
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Given an address within the vmemmap, determine the pfn of the page that
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 0ae0572bc239..a65c0b4c0669 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -42,43 +42,6 @@ EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
 
 extern char etext[], _stext[], _sinittext[], _einittext[];
 
-#define PGDIR_ORDER	(32 + PGD_T_LOG2 - PGDIR_SHIFT)
-
-#ifndef CONFIG_PPC_4K_PAGES
-static struct kmem_cache *pgtable_cache;
-
-void pgtable_cache_init(void)
-{
-	pgtable_cache = kmem_cache_create("PGDIR cache", 1 << PGDIR_ORDER,
-					  1 << PGDIR_ORDER, 0, NULL);
-	if (pgtable_cache == NULL)
-		panic("Couldn't allocate pgtable caches");
-}
-#endif
-
-pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	pgd_t *ret;
-
-	/* pgdir take page or two with 4K pages and a page fraction otherwise */
-#ifndef CONFIG_PPC_4K_PAGES
-	ret = kmem_cache_alloc(pgtable_cache, GFP_KERNEL | __GFP_ZERO);
-#else
-	ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
-			PGDIR_ORDER - PAGE_SHIFT);
-#endif
-	return ret;
-}
-
-void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-#ifndef CONFIG_PPC_4K_PAGES
-	kmem_cache_free(pgtable_cache, (void *)pgd);
-#else
-	free_pages((unsigned long)pgd, PGDIR_ORDER - PAGE_SHIFT);
-#endif
-}
-
 __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
 	pte_t *pte;
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 050badc0ebd3..ba28fcb98597 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -53,7 +53,7 @@
  * other sizes not listed here.   The .ind field is only used on MMUs that have
  * indirect page table entries.
  */
-#ifdef CONFIG_PPC_BOOK3E_MMU
+#if defined(CONFIG_PPC_BOOK3E_MMU) || defined(CONFIG_PPC_8xx)
 #ifdef CONFIG_PPC_FSL_BOOK3E
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 	[MMU_PAGE_4K] = {
@@ -85,6 +85,25 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 		.enc	= BOOK3E_PAGESZ_1GB,
 	},
 };
+#elif defined(CONFIG_PPC_8xx)
+struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
+	/* we only manage 4k and 16k pages as normal pages */
+#ifdef CONFIG_PPC_4K_PAGES
+	[MMU_PAGE_4K] = {
+		.shift	= 12,
+	},
+#else
+	[MMU_PAGE_16K] = {
+		.shift	= 14,
+	},
+#endif
+	[MMU_PAGE_512K] = {
+		.shift	= 19,
+	},
+	[MMU_PAGE_8M] = {
+		.shift	= 23,
+	},
+};
 #else
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 	[MMU_PAGE_4K] = {
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 24717d060008..08f92f6ed228 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -441,8 +441,4 @@ static struct platform_driver pmc_driver = {
 	.remove = pmc_remove
 };
 
-static int pmc_init(void)
-{
-	return platform_driver_register(&pmc_driver);
-}
-device_initcall(pmc_init);
+builtin_platform_driver(pmc_driver);
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 9dc1d28975b9..47b389dc4938 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -253,6 +253,8 @@ endif # PPC32
 config PPC_QEMU_E500
 	bool "QEMU generic e500 platform"
 	select DEFAULT_UIMAGE
+	select E500
+	select PPC_E500MC if PPC64
 	help
 	  This option enables support for running as a QEMU guest using
 	  QEMU's generic e500 machine.  This is not required if you're
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index 564d99bb2a26..80cbcb0ad9b1 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -130,6 +130,7 @@ config 8xx_CPU6
 
 config 8xx_CPU15
 	bool "CPU15 Silicon Errata"
+	depends on !HUGETLB_PAGE
 	default y
 	help
 	  This enables a workaround for erratum CPU15 on MPC8xx chips.
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index ca2da30ad2ab..6e89e5a8d4fb 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -34,6 +34,7 @@ config PPC_8xx
 	select FSL_SOC
 	select 8xx
 	select PPC_LIB_RHEAP
+	select SYS_SUPPORTS_HUGETLBFS
 
 config 40x
 	bool "AMCC 40x"
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index 424b67fdb57f..5340a483cf55 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -31,7 +31,7 @@
 #include <asm/prom.h>
 #include <asm/fsl_lbc.h>
 
-static spinlock_t fsl_lbc_lock = __SPIN_LOCK_UNLOCKED(fsl_lbc_lock);
+static DEFINE_SPINLOCK(fsl_lbc_lock);
 struct fsl_lbc_ctrl *fsl_lbc_ctrl_dev;
 EXPORT_SYMBOL(fsl_lbc_ctrl_dev);
 
diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c
index 1d6fd7c59fe9..232225e7f863 100644
--- a/arch/powerpc/sysdev/fsl_pmc.c
+++ b/arch/powerpc/sysdev/fsl_pmc.c
@@ -85,8 +85,4 @@ static struct platform_driver pmc_driver = {
 	.probe = pmc_probe,
 };
 
-static int __init pmc_init(void)
-{
-	return platform_driver_register(&pmc_driver);
-}
-device_initcall(pmc_init);
+builtin_platform_driver(pmc_driver);
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index d93056eedcb0..19101f9cfcfc 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -77,13 +77,10 @@ phys_addr_t get_immrbase(void)
 
 EXPORT_SYMBOL(get_immrbase);
 
-static u32 sysfreq = -1;
-
 u32 fsl_get_sys_freq(void)
 {
+	static u32 sysfreq = -1;
 	struct device_node *soc;
-	const u32 *prop;
-	int size;
 
 	if (sysfreq != -1)
 		return sysfreq;
@@ -92,12 +89,9 @@ u32 fsl_get_sys_freq(void)
 	if (!soc)
 		return -1;
 
-	prop = of_get_property(soc, "clock-frequency", &size);
-	if (!prop || size != sizeof(*prop) || *prop == 0)
-		prop = of_get_property(soc, "bus-frequency", &size);
-
-	if (prop && size == sizeof(*prop))
-		sysfreq = *prop;
+	of_property_read_u32(soc, "clock-frequency", &sysfreq);
+	if (sysfreq == -1 || !sysfreq)
+		of_property_read_u32(soc, "bus-frequency", &sysfreq);
 
 	of_node_put(soc);
 	return sysfreq;
@@ -106,23 +100,17 @@ EXPORT_SYMBOL(fsl_get_sys_freq);
 
 #if defined(CONFIG_CPM2) || defined(CONFIG_QUICC_ENGINE) || defined(CONFIG_8xx)
 
-static u32 brgfreq = -1;
-
 u32 get_brgfreq(void)
 {
+	static u32 brgfreq = -1;
 	struct device_node *node;
-	const unsigned int *prop;
-	int size;
 
 	if (brgfreq != -1)
 		return brgfreq;
 
 	node = of_find_compatible_node(NULL, NULL, "fsl,cpm-brg");
 	if (node) {
-		prop = of_get_property(node, "clock-frequency", &size);
-		if (prop && size == 4)
-			brgfreq = *prop;
-
+		of_property_read_u32(node, "clock-frequency", &brgfreq);
 		of_node_put(node);
 		return brgfreq;
 	}
@@ -135,15 +123,11 @@ u32 get_brgfreq(void)
 		node = of_find_node_by_type(NULL, "qe");
 
 	if (node) {
-		prop = of_get_property(node, "brg-frequency", &size);
-		if (prop && size == 4)
-			brgfreq = *prop;
-
-		if (brgfreq == -1 || brgfreq == 0) {
-			prop = of_get_property(node, "bus-frequency", &size);
-			if (prop && size == 4)
-				brgfreq = *prop / 2;
-		}
+		of_property_read_u32(node, "brg-frequency", &brgfreq);
+		if (brgfreq == -1 || !brgfreq)
+			if (!of_property_read_u32(node, "bus-frequency",
+						  &brgfreq))
+				brgfreq /= 2;
 		of_node_put(node);
 	}
 
@@ -152,10 +136,9 @@ u32 get_brgfreq(void)
 
 EXPORT_SYMBOL(get_brgfreq);
 
-static u32 fs_baudrate = -1;
-
 u32 get_baudrate(void)
 {
+	static u32 fs_baudrate = -1;
 	struct device_node *node;
 
 	if (fs_baudrate != -1)
@@ -163,12 +146,7 @@ u32 get_baudrate(void)
 
 	node = of_find_node_by_type(NULL, "serial");
 	if (node) {
-		int size;
-		const unsigned int *prop = of_get_property(node,
-				"current-speed", &size);
-
-		if (prop)
-			fs_baudrate = *prop;
+		of_property_read_u32(node, "current-speed", &fs_baudrate);
 		of_node_put(node);
 	}
 
diff --git a/drivers/soc/fsl/qbman/bman.c b/drivers/soc/fsl/qbman/bman.c
index ffa48fdbb1a9..a3d6d7cfa929 100644
--- a/drivers/soc/fsl/qbman/bman.c
+++ b/drivers/soc/fsl/qbman/bman.c
@@ -167,12 +167,12 @@ struct bm_portal {
 /* Cache-inhibited register access. */
 static inline u32 bm_in(struct bm_portal *p, u32 offset)
 {
-	return __raw_readl(p->addr.ci + offset);
+	return be32_to_cpu(__raw_readl(p->addr.ci + offset));
 }
 
 static inline void bm_out(struct bm_portal *p, u32 offset, u32 val)
 {
-	__raw_writel(val, p->addr.ci + offset);
+	__raw_writel(cpu_to_be32(val), p->addr.ci + offset);
 }
 
 /* Cache Enabled Portal Access */
@@ -188,7 +188,7 @@ static inline void bm_cl_touch_ro(struct bm_portal *p, u32 offset)
 
 static inline u32 bm_ce_in(struct bm_portal *p, u32 offset)
 {
-	return __raw_readl(p->addr.ce + offset);
+	return be32_to_cpu(__raw_readl(p->addr.ce + offset));
 }
 
 struct bman_portal {
@@ -391,7 +391,7 @@ static void bm_rcr_finish(struct bm_portal *portal)
 
 	i = bm_in(portal, BM_REG_RCR_PI_CINH) & (BM_RCR_SIZE - 1);
 	if (i != rcr_ptr2idx(rcr->cursor))
-		pr_crit("losing uncommited RCR entries\n");
+		pr_crit("losing uncommitted RCR entries\n");
 
 	i = bm_in(portal, BM_REG_RCR_CI_CINH) & (BM_RCR_SIZE - 1);
 	if (i != rcr->ci)
diff --git a/drivers/soc/fsl/qbman/bman_ccsr.c b/drivers/soc/fsl/qbman/bman_ccsr.c
index 9deb0524543f..a8e8389a6894 100644
--- a/drivers/soc/fsl/qbman/bman_ccsr.c
+++ b/drivers/soc/fsl/qbman/bman_ccsr.c
@@ -181,8 +181,7 @@ static int fsl_bman_probe(struct platform_device *pdev)
 			node->full_name);
 		return -ENXIO;
 	}
-	bm_ccsr_start = devm_ioremap(dev, res->start,
-				     res->end - res->start + 1);
+	bm_ccsr_start = devm_ioremap(dev, res->start, resource_size(res));
 	if (!bm_ccsr_start)
 		return -ENXIO;
 
diff --git a/drivers/soc/fsl/qbman/bman_portal.c b/drivers/soc/fsl/qbman/bman_portal.c
index 6579cc18811a..dd3f5d7617d2 100644
--- a/drivers/soc/fsl/qbman/bman_portal.c
+++ b/drivers/soc/fsl/qbman/bman_portal.c
@@ -146,15 +146,19 @@ static int bman_portal_probe(struct platform_device *pdev)
 	pcfg->irq = irq;
 
 	va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]), 0);
-	if (!va)
+	if (!va) {
+		dev_err(dev, "ioremap::CE failed\n");
 		goto err_ioremap1;
+	}
 
 	pcfg->addr_virt[DPAA_PORTAL_CE] = va;
 
 	va = ioremap_prot(addr_phys[1]->start, resource_size(addr_phys[1]),
 			  _PAGE_GUARDED | _PAGE_NO_CACHE);
-	if (!va)
+	if (!va) {
+		dev_err(dev, "ioremap::CI failed\n");
 		goto err_ioremap2;
+	}
 
 	pcfg->addr_virt[DPAA_PORTAL_CI] = va;
 
@@ -170,8 +174,10 @@ static int bman_portal_probe(struct platform_device *pdev)
 	spin_unlock(&bman_lock);
 	pcfg->cpu = cpu;
 
-	if (!init_pcfg(pcfg))
-		goto err_ioremap2;
+	if (!init_pcfg(pcfg)) {
+		dev_err(dev, "portal init failed\n");
+		goto err_portal_init;
+	}
 
 	/* clear irq affinity if assigned cpu is offline */
 	if (!cpu_online(cpu))
@@ -179,10 +185,11 @@ static int bman_portal_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_portal_init:
+	iounmap(pcfg->addr_virt[DPAA_PORTAL_CI]);
 err_ioremap2:
 	iounmap(pcfg->addr_virt[DPAA_PORTAL_CE]);
 err_ioremap1:
-	dev_err(dev, "ioremap failed\n");
 	return -ENXIO;
 }
 
diff --git a/drivers/soc/fsl/qbman/dpaa_sys.h b/drivers/soc/fsl/qbman/dpaa_sys.h
index b63fd72295c6..2eaf3184f61d 100644
--- a/drivers/soc/fsl/qbman/dpaa_sys.h
+++ b/drivers/soc/fsl/qbman/dpaa_sys.h
@@ -38,6 +38,7 @@
 #include <linux/kthread.h>
 #include <linux/vmalloc.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/prefetch.h>
 #include <linux/genalloc.h>
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 119054bc922b..6f509f68085e 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -140,10 +140,10 @@ enum qm_mr_cmode {		/* matches QCSP_CFG::MM */
 struct qm_eqcr_entry {
 	u8 _ncw_verb; /* writes to this are non-coherent */
 	u8 dca;
-	u16 seqnum;
-	u32 orp;	/* 24-bit */
-	u32 fqid;	/* 24-bit */
-	u32 tag;
+	__be16 seqnum;
+	u8 __reserved[4];
+	__be32 fqid;	/* 24-bit */
+	__be32 tag;
 	struct qm_fd fd;
 	u8 __reserved3[32];
 } __packed;
@@ -183,41 +183,22 @@ struct qm_mr {
 };
 
 /* MC (Management Command) command */
-/* "Query FQ" */
-struct qm_mcc_queryfq {
+/* "FQ" command layout */
+struct qm_mcc_fq {
 	u8 _ncw_verb;
 	u8 __reserved1[3];
-	u32 fqid;	/* 24-bit */
+	__be32 fqid;	/* 24-bit */
 	u8 __reserved2[56];
 } __packed;
-/* "Alter FQ State Commands " */
-struct qm_mcc_alterfq {
-	u8 _ncw_verb;
-	u8 __reserved1[3];
-	u32 fqid;	/* 24-bit */
-	u8 __reserved2;
-	u8 count;	/* number of consecutive FQID */
-	u8 __reserved3[10];
-	u32 context_b;	/* frame queue context b */
-	u8 __reserved4[40];
-} __packed;
 
-/* "Query CGR" */
-struct qm_mcc_querycgr {
+/* "CGR" command layout */
+struct qm_mcc_cgr {
 	u8 _ncw_verb;
 	u8 __reserved1[30];
 	u8 cgid;
 	u8 __reserved2[32];
 };
 
-struct qm_mcc_querywq {
-	u8 _ncw_verb;
-	u8 __reserved;
-	/* select channel if verb != QUERYWQ_DEDICATED */
-	u16 channel_wq; /* ignores wq (3 lsbits): _res[0-2] */
-	u8 __reserved2[60];
-} __packed;
-
 #define QM_MCC_VERB_VBIT		0x80
 #define QM_MCC_VERB_MASK		0x7f	/* where the verb contains; */
 #define QM_MCC_VERB_INITFQ_PARKED	0x40
@@ -243,12 +224,9 @@ union qm_mc_command {
 		u8 __reserved[63];
 	};
 	struct qm_mcc_initfq initfq;
-	struct qm_mcc_queryfq queryfq;
-	struct qm_mcc_alterfq alterfq;
 	struct qm_mcc_initcgr initcgr;
-	struct qm_mcc_querycgr querycgr;
-	struct qm_mcc_querywq querywq;
-	struct qm_mcc_queryfq_np queryfq_np;
+	struct qm_mcc_fq fq;
+	struct qm_mcc_cgr cgr;
 };
 
 /* MC (Management Command) result */
@@ -343,12 +321,12 @@ struct qm_portal {
 /* Cache-inhibited register access. */
 static inline u32 qm_in(struct qm_portal *p, u32 offset)
 {
-	return __raw_readl(p->addr.ci + offset);
+	return be32_to_cpu(__raw_readl(p->addr.ci + offset));
 }
 
 static inline void qm_out(struct qm_portal *p, u32 offset, u32 val)
 {
-	__raw_writel(val, p->addr.ci + offset);
+	__raw_writel(cpu_to_be32(val), p->addr.ci + offset);
 }
 
 /* Cache Enabled Portal Access */
@@ -364,7 +342,7 @@ static inline void qm_cl_touch_ro(struct qm_portal *p, u32 offset)
 
 static inline u32 qm_ce_in(struct qm_portal *p, u32 offset)
 {
-	return __raw_readl(p->addr.ce + offset);
+	return be32_to_cpu(__raw_readl(p->addr.ce + offset));
 }
 
 /* --- EQCR API --- */
@@ -443,7 +421,7 @@ static inline void qm_eqcr_finish(struct qm_portal *portal)
 
 	DPAA_ASSERT(!eqcr->busy);
 	if (pi != eqcr_ptr2idx(eqcr->cursor))
-		pr_crit("losing uncommited EQCR entries\n");
+		pr_crit("losing uncommitted EQCR entries\n");
 	if (ci != eqcr->ci)
 		pr_crit("missing existing EQCR completions\n");
 	if (eqcr->ci != eqcr_ptr2idx(eqcr->cursor))
@@ -492,8 +470,7 @@ static inline struct qm_eqcr_entry *qm_eqcr_start_stash(struct qm_portal
 static inline void eqcr_commit_checks(struct qm_eqcr *eqcr)
 {
 	DPAA_ASSERT(eqcr->busy);
-	DPAA_ASSERT(eqcr->cursor->orp == (eqcr->cursor->orp & 0x00ffffff));
-	DPAA_ASSERT(eqcr->cursor->fqid == (eqcr->cursor->fqid & 0x00ffffff));
+	DPAA_ASSERT(!(be32_to_cpu(eqcr->cursor->fqid) & ~QM_FQID_MASK));
 	DPAA_ASSERT(eqcr->available >= 1);
 }
 
@@ -962,8 +939,6 @@ struct qman_portal {
 	u32 sdqcr;
 	/* probing time config params for cpu-affine portals */
 	const struct qm_portal_config *config;
-	/* needed for providing a non-NULL device to dma_map_***() */
-	struct platform_device *pdev;
 	/* 2-element array. cgrs[0] is mask, cgrs[1] is snapshot. */
 	struct qman_cgrs *cgrs;
 	/* linked-list of CSCN handlers. */
@@ -1133,7 +1108,6 @@ static int qman_create_portal(struct qman_portal *portal,
 			      const struct qman_cgrs *cgrs)
 {
 	struct qm_portal *p;
-	char buf[16];
 	int ret;
 	u32 isdr;
 
@@ -1196,15 +1170,6 @@ static int qman_create_portal(struct qman_portal *portal,
 	portal->sdqcr = QM_SDQCR_SOURCE_CHANNELS | QM_SDQCR_COUNT_UPTO3 |
 			QM_SDQCR_DEDICATED_PRECEDENCE | QM_SDQCR_TYPE_PRIO_QOS |
 			QM_SDQCR_TOKEN_SET(0xab) | QM_SDQCR_CHANNELS_DEDICATED;
-	sprintf(buf, "qportal-%d", c->channel);
-	portal->pdev = platform_device_alloc(buf, -1);
-	if (!portal->pdev)
-		goto fail_devalloc;
-	if (dma_set_mask(&portal->pdev->dev, DMA_BIT_MASK(40)))
-		goto fail_devadd;
-	ret = platform_device_add(portal->pdev);
-	if (ret)
-		goto fail_devadd;
 	isdr = 0xffffffff;
 	qm_out(p, QM_REG_ISDR, isdr);
 	portal->irq_sources = 0;
@@ -1239,8 +1204,8 @@ static int qman_create_portal(struct qman_portal *portal,
 		/* special handling, drain just in case it's a few FQRNIs */
 		const union qm_mr_entry *e = qm_mr_current(p);
 
-		dev_err(c->dev, "MR dirty, VB 0x%x, rc 0x%x\n, addr 0x%x",
-			e->verb, e->ern.rc, e->ern.fd.addr_lo);
+		dev_err(c->dev, "MR dirty, VB 0x%x, rc 0x%x, addr 0x%llx\n",
+			e->verb, e->ern.rc, qm_fd_addr_get64(&e->ern.fd));
 		goto fail_dqrr_mr_empty;
 	}
 	/* Success */
@@ -1256,10 +1221,6 @@ fail_eqcr_empty:
 fail_affinity:
 	free_irq(c->irq, portal);
 fail_irq:
-	platform_device_del(portal->pdev);
-fail_devadd:
-	platform_device_put(portal->pdev);
-fail_devalloc:
 	kfree(portal->cgrs);
 fail_cgrs:
 	qm_mc_finish(p);
@@ -1321,9 +1282,6 @@ static void qman_destroy_portal(struct qman_portal *qm)
 	qm_dqrr_finish(&qm->p);
 	qm_eqcr_finish(&qm->p);
 
-	platform_device_del(qm->pdev);
-	platform_device_put(qm->pdev);
-
 	qm->config = NULL;
 }
 
@@ -1428,7 +1386,7 @@ static void qm_mr_process_task(struct work_struct *work)
 			case QM_MR_VERB_FQRN:
 			case QM_MR_VERB_FQRL:
 				/* Lookup in the retirement table */
-				fq = fqid_to_fq(msg->fq.fqid);
+				fq = fqid_to_fq(qm_fqid_get(&msg->fq));
 				if (WARN_ON(!fq))
 					break;
 				fq_state_change(p, fq, msg, verb);
@@ -1437,7 +1395,7 @@ static void qm_mr_process_task(struct work_struct *work)
 				break;
 			case QM_MR_VERB_FQPN:
 				/* Parked */
-				fq = tag_to_fq(msg->fq.contextB);
+				fq = tag_to_fq(be32_to_cpu(msg->fq.context_b));
 				fq_state_change(p, fq, msg, verb);
 				if (fq->cb.fqs)
 					fq->cb.fqs(p, fq, msg);
@@ -1451,7 +1409,7 @@ static void qm_mr_process_task(struct work_struct *work)
 			}
 		} else {
 			/* Its a software ERN */
-			fq = tag_to_fq(msg->ern.tag);
+			fq = tag_to_fq(be32_to_cpu(msg->ern.tag));
 			fq->cb.ern(p, fq, msg);
 		}
 		num++;
@@ -1536,7 +1494,7 @@ static inline unsigned int __poll_portal_fast(struct qman_portal *p,
 
 		if (dq->stat & QM_DQRR_STAT_UNSCHEDULED) {
 			/*
-			 * VDQCR: don't trust contextB as the FQ may have
+			 * VDQCR: don't trust context_b as the FQ may have
 			 * been configured for h/w consumption and we're
 			 * draining it post-retirement.
 			 */
@@ -1562,8 +1520,8 @@ static inline unsigned int __poll_portal_fast(struct qman_portal *p,
 			if (dq->stat & QM_DQRR_STAT_DQCR_EXPIRED)
 				clear_vdqcr(p, fq);
 		} else {
-			/* SDQCR: contextB points to the FQ */
-			fq = tag_to_fq(dq->contextB);
+			/* SDQCR: context_b points to the FQ */
+			fq = tag_to_fq(be32_to_cpu(dq->context_b));
 			/* Now let the callback do its stuff */
 			res = fq->cb.dqrr(p, fq, dq);
 			/*
@@ -1780,9 +1738,9 @@ int qman_init_fq(struct qman_fq *fq, u32 flags, struct qm_mcc_initfq *opts)
 	if (fq_isset(fq, QMAN_FQ_FLAG_NO_MODIFY))
 		return -EINVAL;
 #endif
-	if (opts && (opts->we_mask & QM_INITFQ_WE_OAC)) {
+	if (opts && (be16_to_cpu(opts->we_mask) & QM_INITFQ_WE_OAC)) {
 		/* And can't be set at the same time as TDTHRESH */
-		if (opts->we_mask & QM_INITFQ_WE_TDTHRESH)
+		if (be16_to_cpu(opts->we_mask) & QM_INITFQ_WE_TDTHRESH)
 			return -EINVAL;
 	}
 	/* Issue an INITFQ_[PARKED|SCHED] management command */
@@ -1796,37 +1754,49 @@ int qman_init_fq(struct qman_fq *fq, u32 flags, struct qm_mcc_initfq *opts)
 	mcc = qm_mc_start(&p->p);
 	if (opts)
 		mcc->initfq = *opts;
-	mcc->initfq.fqid = fq->fqid;
+	qm_fqid_set(&mcc->fq, fq->fqid);
 	mcc->initfq.count = 0;
 	/*
-	 * If the FQ does *not* have the TO_DCPORTAL flag, contextB is set as a
+	 * If the FQ does *not* have the TO_DCPORTAL flag, context_b is set as a
 	 * demux pointer. Otherwise, the caller-provided value is allowed to
 	 * stand, don't overwrite it.
 	 */
 	if (fq_isclear(fq, QMAN_FQ_FLAG_TO_DCPORTAL)) {
 		dma_addr_t phys_fq;
 
-		mcc->initfq.we_mask |= QM_INITFQ_WE_CONTEXTB;
-		mcc->initfq.fqd.context_b = fq_to_tag(fq);
+		mcc->initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CONTEXTB);
+		mcc->initfq.fqd.context_b = cpu_to_be32(fq_to_tag(fq));
 		/*
 		 *  and the physical address - NB, if the user wasn't trying to
 		 * set CONTEXTA, clear the stashing settings.
 		 */
-		if (!(mcc->initfq.we_mask & QM_INITFQ_WE_CONTEXTA)) {
-			mcc->initfq.we_mask |= QM_INITFQ_WE_CONTEXTA;
+		if (!(be16_to_cpu(mcc->initfq.we_mask) &
+				  QM_INITFQ_WE_CONTEXTA)) {
+			mcc->initfq.we_mask |=
+				cpu_to_be16(QM_INITFQ_WE_CONTEXTA);
 			memset(&mcc->initfq.fqd.context_a, 0,
 				sizeof(mcc->initfq.fqd.context_a));
 		} else {
-			phys_fq = dma_map_single(&p->pdev->dev, fq, sizeof(*fq),
-						 DMA_TO_DEVICE);
+			struct qman_portal *p = qman_dma_portal;
+
+			phys_fq = dma_map_single(p->config->dev, fq,
+						 sizeof(*fq), DMA_TO_DEVICE);
+			if (dma_mapping_error(p->config->dev, phys_fq)) {
+				dev_err(p->config->dev, "dma_mapping failed\n");
+				ret = -EIO;
+				goto out;
+			}
+
 			qm_fqd_stashing_set64(&mcc->initfq.fqd, phys_fq);
 		}
 	}
 	if (flags & QMAN_INITFQ_FLAG_LOCAL) {
 		int wq = 0;
 
-		if (!(mcc->initfq.we_mask & QM_INITFQ_WE_DESTWQ)) {
-			mcc->initfq.we_mask |= QM_INITFQ_WE_DESTWQ;
+		if (!(be16_to_cpu(mcc->initfq.we_mask) &
+				  QM_INITFQ_WE_DESTWQ)) {
+			mcc->initfq.we_mask |=
+				cpu_to_be16(QM_INITFQ_WE_DESTWQ);
 			wq = 4;
 		}
 		qm_fqd_set_destwq(&mcc->initfq.fqd, p->config->channel, wq);
@@ -1845,13 +1815,13 @@ int qman_init_fq(struct qman_fq *fq, u32 flags, struct qm_mcc_initfq *opts)
 		goto out;
 	}
 	if (opts) {
-		if (opts->we_mask & QM_INITFQ_WE_FQCTRL) {
-			if (opts->fqd.fq_ctrl & QM_FQCTRL_CGE)
+		if (be16_to_cpu(opts->we_mask) & QM_INITFQ_WE_FQCTRL) {
+			if (be16_to_cpu(opts->fqd.fq_ctrl) & QM_FQCTRL_CGE)
 				fq_set(fq, QMAN_FQ_STATE_CGR_EN);
 			else
 				fq_clear(fq, QMAN_FQ_STATE_CGR_EN);
 		}
-		if (opts->we_mask & QM_INITFQ_WE_CGID)
+		if (be16_to_cpu(opts->we_mask) & QM_INITFQ_WE_CGID)
 			fq->cgr_groupid = opts->fqd.cgid;
 	}
 	fq->state = (flags & QMAN_INITFQ_FLAG_SCHED) ?
@@ -1884,7 +1854,7 @@ int qman_schedule_fq(struct qman_fq *fq)
 		goto out;
 	}
 	mcc = qm_mc_start(&p->p);
-	mcc->alterfq.fqid = fq->fqid;
+	qm_fqid_set(&mcc->fq, fq->fqid);
 	qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_SCHED);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		dev_err(p->config->dev, "ALTER_SCHED timeout\n");
@@ -1927,7 +1897,7 @@ int qman_retire_fq(struct qman_fq *fq, u32 *flags)
 		goto out;
 	}
 	mcc = qm_mc_start(&p->p);
-	mcc->alterfq.fqid = fq->fqid;
+	qm_fqid_set(&mcc->fq, fq->fqid);
 	qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_RETIRE);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		dev_crit(p->config->dev, "ALTER_RETIRE timeout\n");
@@ -1970,8 +1940,8 @@ int qman_retire_fq(struct qman_fq *fq, u32 *flags)
 
 			msg.verb = QM_MR_VERB_FQRNI;
 			msg.fq.fqs = mcr->alterfq.fqs;
-			msg.fq.fqid = fq->fqid;
-			msg.fq.contextB = fq_to_tag(fq);
+			qm_fqid_set(&msg.fq, fq->fqid);
+			msg.fq.context_b = cpu_to_be32(fq_to_tag(fq));
 			fq->cb.fqs(p, fq, &msg);
 		}
 	} else if (res == QM_MCR_RESULT_PENDING) {
@@ -2006,7 +1976,7 @@ int qman_oos_fq(struct qman_fq *fq)
 		goto out;
 	}
 	mcc = qm_mc_start(&p->p);
-	mcc->alterfq.fqid = fq->fqid;
+	qm_fqid_set(&mcc->fq, fq->fqid);
 	qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_OOS);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		ret = -ETIMEDOUT;
@@ -2032,7 +2002,7 @@ int qman_query_fq(struct qman_fq *fq, struct qm_fqd *fqd)
 	int ret = 0;
 
 	mcc = qm_mc_start(&p->p);
-	mcc->queryfq.fqid = fq->fqid;
+	qm_fqid_set(&mcc->fq, fq->fqid);
 	qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		ret = -ETIMEDOUT;
@@ -2058,7 +2028,7 @@ static int qman_query_fq_np(struct qman_fq *fq,
 	int ret = 0;
 
 	mcc = qm_mc_start(&p->p);
-	mcc->queryfq.fqid = fq->fqid;
+	qm_fqid_set(&mcc->fq, fq->fqid);
 	qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ_NP);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		ret = -ETIMEDOUT;
@@ -2086,7 +2056,7 @@ static int qman_query_cgr(struct qman_cgr *cgr,
 	int ret = 0;
 
 	mcc = qm_mc_start(&p->p);
-	mcc->querycgr.cgid = cgr->cgrid;
+	mcc->cgr.cgid = cgr->cgrid;
 	qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCGR);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		ret = -ETIMEDOUT;
@@ -2239,8 +2209,8 @@ int qman_enqueue(struct qman_fq *fq, const struct qm_fd *fd)
 	if (unlikely(!eq))
 		goto out;
 
-	eq->fqid = fq->fqid;
-	eq->tag = fq_to_tag(fq);
+	qm_fqid_set(eq, fq->fqid);
+	eq->tag = cpu_to_be32(fq_to_tag(fq));
 	eq->fd = *fd;
 
 	qm_eqcr_pvb_commit(&p->p, QM_EQCR_VERB_CMD_ENQUEUE);
@@ -2282,7 +2252,24 @@ out:
 }
 
 #define PORTAL_IDX(n)	(n->config->channel - QM_CHANNEL_SWPORTAL0)
-#define TARG_MASK(n)	(BIT(31) >> PORTAL_IDX(n))
+
+/* congestion state change notification target update control */
+static void qm_cgr_cscn_targ_set(struct __qm_mc_cgr *cgr, int pi, u32 val)
+{
+	if (qman_ip_rev >= QMAN_REV30)
+		cgr->cscn_targ_upd_ctrl = cpu_to_be16(pi |
+					QM_CGR_TARG_UDP_CTRL_WRITE_BIT);
+	else
+		cgr->cscn_targ = cpu_to_be32(val | QM_CGR_TARG_PORTAL(pi));
+}
+
+static void qm_cgr_cscn_targ_clear(struct __qm_mc_cgr *cgr, int pi, u32 val)
+{
+	if (qman_ip_rev >= QMAN_REV30)
+		cgr->cscn_targ_upd_ctrl = cpu_to_be16(pi);
+	else
+		cgr->cscn_targ = cpu_to_be32(val & ~QM_CGR_TARG_PORTAL(pi));
+}
 
 static u8 qman_cgr_cpus[CGR_NUM];
 
@@ -2305,7 +2292,6 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags,
 		    struct qm_mcc_initcgr *opts)
 {
 	struct qm_mcr_querycgr cgr_state;
-	struct qm_mcc_initcgr local_opts = {};
 	int ret;
 	struct qman_portal *p;
 
@@ -2327,22 +2313,18 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags,
 	spin_lock(&p->cgr_lock);
 
 	if (opts) {
+		struct qm_mcc_initcgr local_opts = *opts;
+
 		ret = qman_query_cgr(cgr, &cgr_state);
 		if (ret)
 			goto out;
-		if (opts)
-			local_opts = *opts;
-		if ((qman_ip_rev & 0xFF00) >= QMAN_REV30)
-			local_opts.cgr.cscn_targ_upd_ctrl =
-				QM_CGR_TARG_UDP_CTRL_WRITE_BIT | PORTAL_IDX(p);
-		else
-			/* Overwrite TARG */
-			local_opts.cgr.cscn_targ = cgr_state.cgr.cscn_targ |
-						   TARG_MASK(p);
-		local_opts.we_mask |= QM_CGR_WE_CSCN_TARG;
+
+		qm_cgr_cscn_targ_set(&local_opts.cgr, PORTAL_IDX(p),
+				     be32_to_cpu(cgr_state.cgr.cscn_targ));
+		local_opts.we_mask |= cpu_to_be16(QM_CGR_WE_CSCN_TARG);
 
 		/* send init if flags indicate so */
-		if (opts && (flags & QMAN_CGR_FLAG_USE_INIT))
+		if (flags & QMAN_CGR_FLAG_USE_INIT)
 			ret = qm_modify_cgr(cgr, QMAN_CGR_FLAG_USE_INIT,
 					    &local_opts);
 		else
@@ -2405,13 +2387,11 @@ int qman_delete_cgr(struct qman_cgr *cgr)
 		list_add(&cgr->node, &p->cgr_cbs);
 		goto release_lock;
 	}
-	/* Overwrite TARG */
-	local_opts.we_mask = QM_CGR_WE_CSCN_TARG;
-	if ((qman_ip_rev & 0xFF00) >= QMAN_REV30)
-		local_opts.cgr.cscn_targ_upd_ctrl = PORTAL_IDX(p);
-	else
-		local_opts.cgr.cscn_targ = cgr_state.cgr.cscn_targ &
-							 ~(TARG_MASK(p));
+
+	local_opts.we_mask = cpu_to_be16(QM_CGR_WE_CSCN_TARG);
+	qm_cgr_cscn_targ_clear(&local_opts.cgr, PORTAL_IDX(p),
+			       be32_to_cpu(cgr_state.cgr.cscn_targ));
+
 	ret = qm_modify_cgr(cgr, 0, &local_opts);
 	if (ret)
 		/* add back to the list */
@@ -2501,7 +2481,7 @@ static int _qm_dqrr_consume_and_match(struct qm_portal *p, u32 fqid, int s,
 	} while (wait && !dqrr);
 
 	while (dqrr) {
-		if (dqrr->fqid == fqid && (dqrr->stat & s))
+		if (qm_fqid_get(dqrr) == fqid && (dqrr->stat & s))
 			found = 1;
 		qm_dqrr_cdc_consume_1ptr(p, dqrr, 0);
 		qm_dqrr_pvb_update(p);
@@ -2537,7 +2517,7 @@ static int qman_shutdown_fq(u32 fqid)
 	dev = p->config->dev;
 	/* Determine the state of the FQID */
 	mcc = qm_mc_start(&p->p);
-	mcc->queryfq_np.fqid = fqid;
+	qm_fqid_set(&mcc->fq, fqid);
 	qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ_NP);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		dev_err(dev, "QUERYFQ_NP timeout\n");
@@ -2552,7 +2532,7 @@ static int qman_shutdown_fq(u32 fqid)
 
 	/* Query which channel the FQ is using */
 	mcc = qm_mc_start(&p->p);
-	mcc->queryfq.fqid = fqid;
+	qm_fqid_set(&mcc->fq, fqid);
 	qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ);
 	if (!qm_mc_result_timeout(&p->p, &mcr)) {
 		dev_err(dev, "QUERYFQ timeout\n");
@@ -2572,7 +2552,7 @@ static int qman_shutdown_fq(u32 fqid)
 	case QM_MCR_NP_STATE_PARKED:
 		orl_empty = 0;
 		mcc = qm_mc_start(&p->p);
-		mcc->alterfq.fqid = fqid;
+		qm_fqid_set(&mcc->fq, fqid);
 		qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_RETIRE);
 		if (!qm_mc_result_timeout(&p->p, &mcr)) {
 			dev_err(dev, "QUERYFQ_NP timeout\n");
@@ -2667,7 +2647,7 @@ static int qman_shutdown_fq(u32 fqid)
 			cpu_relax();
 		}
 		mcc = qm_mc_start(&p->p);
-		mcc->alterfq.fqid = fqid;
+		qm_fqid_set(&mcc->fq, fqid);
 		qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_OOS);
 		if (!qm_mc_result_timeout(&p->p, &mcr)) {
 			ret = -ETIMEDOUT;
@@ -2687,7 +2667,7 @@ static int qman_shutdown_fq(u32 fqid)
 	case QM_MCR_NP_STATE_RETIRED:
 		/* Send OOS Command */
 		mcc = qm_mc_start(&p->p);
-		mcc->alterfq.fqid = fqid;
+		qm_fqid_set(&mcc->fq, fqid);
 		qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_OOS);
 		if (!qm_mc_result_timeout(&p->p, &mcr)) {
 			ret = -ETIMEDOUT;
@@ -2722,6 +2702,7 @@ const struct qm_portal_config *qman_get_qm_portal_config(
 {
 	return portal->config;
 }
+EXPORT_SYMBOL(qman_get_qm_portal_config);
 
 struct gen_pool *qm_fqalloc; /* FQID allocator */
 struct gen_pool *qm_qpalloc; /* pool-channel allocator */
@@ -2789,15 +2770,18 @@ static int qpool_cleanup(u32 qp)
 		struct qm_mcr_queryfq_np np;
 
 		err = qman_query_fq_np(&fq, &np);
-		if (err)
+		if (err == -ERANGE)
 			/* FQID range exceeded, found no problems */
 			return 0;
+		else if (WARN_ON(err))
+			return err;
+
 		if ((np.state & QM_MCR_NP_STATE_MASK) != QM_MCR_NP_STATE_OOS) {
 			struct qm_fqd fqd;
 
 			err = qman_query_fq(&fq, &fqd);
 			if (WARN_ON(err))
-				return 0;
+				return err;
 			if (qm_fqd_get_chan(&fqd) == qp) {
 				/* The channel is the FQ's target, clean it */
 				err = qman_shutdown_fq(fq.fqid);
@@ -2836,7 +2820,7 @@ static int cgr_cleanup(u32 cgrid)
 	 * error, looking for non-OOS FQDs whose CGR is the CGR being released
 	 */
 	struct qman_fq fq = {
-		.fqid = 1
+		.fqid = QM_FQID_RANGE_START
 	};
 	int err;
 
@@ -2844,16 +2828,19 @@ static int cgr_cleanup(u32 cgrid)
 		struct qm_mcr_queryfq_np np;
 
 		err = qman_query_fq_np(&fq, &np);
-		if (err)
+		if (err == -ERANGE)
 			/* FQID range exceeded, found no problems */
 			return 0;
+		else if (WARN_ON(err))
+			return err;
+
 		if ((np.state & QM_MCR_NP_STATE_MASK) != QM_MCR_NP_STATE_OOS) {
 			struct qm_fqd fqd;
 
 			err = qman_query_fq(&fq, &fqd);
 			if (WARN_ON(err))
-				return 0;
-			if ((fqd.fq_ctrl & QM_FQCTRL_CGE) &&
+				return err;
+			if (be16_to_cpu(fqd.fq_ctrl) & QM_FQCTRL_CGE &&
 			    fqd.cgid == cgrid) {
 				pr_err("CRGID 0x%x is being used by FQID 0x%x, CGR will be leaked\n",
 				       cgrid, fq.fqid);
diff --git a/drivers/soc/fsl/qbman/qman_ccsr.c b/drivers/soc/fsl/qbman/qman_ccsr.c
index 0cace9e0077e..f4e6e70de259 100644
--- a/drivers/soc/fsl/qbman/qman_ccsr.c
+++ b/drivers/soc/fsl/qbman/qman_ccsr.c
@@ -444,6 +444,9 @@ static int zero_priv_mem(struct device *dev, struct device_node *node,
 	/* 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);
diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
index 148614388fca..c9a9bcb1aea2 100644
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -30,6 +30,9 @@
 
 #include "qman_priv.h"
 
+struct qman_portal *qman_dma_portal;
+EXPORT_SYMBOL(qman_dma_portal);
+
 /* Enable portal interupts (as opposed to polling mode) */
 #define CONFIG_FSL_DPA_PIRQ_SLOW  1
 #define CONFIG_FSL_DPA_PIRQ_FAST  1
@@ -150,6 +153,10 @@ static struct qman_portal *init_pcfg(struct qm_portal_config *pcfg)
 		/* all assigned portals are initialized now */
 		qman_init_cgr_all();
 	}
+
+	if (!qman_dma_portal)
+		qman_dma_portal = p;
+
 	spin_unlock(&qman_lock);
 
 	dev_info(pcfg->dev, "Portal initialised, cpu %d\n", pcfg->cpu);
@@ -238,9 +245,9 @@ static int qman_portal_probe(struct platform_device *pdev)
 	struct device_node *node = dev->of_node;
 	struct qm_portal_config *pcfg;
 	struct resource *addr_phys[2];
-	const u32 *channel;
 	void __iomem *va;
-	int irq, len, cpu;
+	int irq, cpu, err;
+	u32 val;
 
 	pcfg = devm_kmalloc(dev, sizeof(*pcfg), GFP_KERNEL);
 	if (!pcfg)
@@ -264,13 +271,13 @@ static int qman_portal_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	channel = of_get_property(node, "cell-index", &len);
-	if (!channel || (len != 4)) {
+	err = of_property_read_u32(node, "cell-index", &val);
+	if (err) {
 		dev_err(dev, "Can't get %s property 'cell-index'\n",
 			node->full_name);
-		return -ENXIO;
+		return err;
 	}
-	pcfg->channel = *channel;
+	pcfg->channel = val;
 	pcfg->cpu = -1;
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0) {
@@ -280,15 +287,19 @@ static int qman_portal_probe(struct platform_device *pdev)
 	pcfg->irq = irq;
 
 	va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]), 0);
-	if (!va)
+	if (!va) {
+		dev_err(dev, "ioremap::CE failed\n");
 		goto err_ioremap1;
+	}
 
 	pcfg->addr_virt[DPAA_PORTAL_CE] = va;
 
 	va = ioremap_prot(addr_phys[1]->start, resource_size(addr_phys[1]),
 			  _PAGE_GUARDED | _PAGE_NO_CACHE);
-	if (!va)
+	if (!va) {
+		dev_err(dev, "ioremap::CI failed\n");
 		goto err_ioremap2;
+	}
 
 	pcfg->addr_virt[DPAA_PORTAL_CI] = va;
 
@@ -306,8 +317,15 @@ static int qman_portal_probe(struct platform_device *pdev)
 	spin_unlock(&qman_lock);
 	pcfg->cpu = cpu;
 
-	if (!init_pcfg(pcfg))
-		goto err_ioremap2;
+	if (dma_set_mask(dev, DMA_BIT_MASK(40))) {
+		dev_err(dev, "dma_set_mask() failed\n");
+		goto err_portal_init;
+	}
+
+	if (!init_pcfg(pcfg)) {
+		dev_err(dev, "portal init failed\n");
+		goto err_portal_init;
+	}
 
 	/* clear irq affinity if assigned cpu is offline */
 	if (!cpu_online(cpu))
@@ -315,10 +333,11 @@ static int qman_portal_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_portal_init:
+	iounmap(pcfg->addr_virt[DPAA_PORTAL_CI]);
 err_ioremap2:
 	iounmap(pcfg->addr_virt[DPAA_PORTAL_CE]);
 err_ioremap1:
-	dev_err(dev, "ioremap failed\n");
 	return -ENXIO;
 }
 
diff --git a/drivers/soc/fsl/qbman/qman_priv.h b/drivers/soc/fsl/qbman/qman_priv.h
index 5cf821e623a9..53685b59718e 100644
--- a/drivers/soc/fsl/qbman/qman_priv.h
+++ b/drivers/soc/fsl/qbman/qman_priv.h
@@ -73,29 +73,23 @@ struct qm_mcr_querycgr {
 	struct __qm_mc_cgr cgr; /* CGR fields */
 	u8 __reserved2[6];
 	u8 i_bcnt_hi;	/* high 8-bits of 40-bit "Instant" */
-	u32 i_bcnt_lo;	/* low 32-bits of 40-bit */
+	__be32 i_bcnt_lo;	/* low 32-bits of 40-bit */
 	u8 __reserved3[3];
 	u8 a_bcnt_hi;	/* high 8-bits of 40-bit "Average" */
-	u32 a_bcnt_lo;	/* low 32-bits of 40-bit */
-	u32 cscn_targ_swp[4];
+	__be32 a_bcnt_lo;	/* low 32-bits of 40-bit */
+	__be32 cscn_targ_swp[4];
 } __packed;
 
 static inline u64 qm_mcr_querycgr_i_get64(const struct qm_mcr_querycgr *q)
 {
-	return ((u64)q->i_bcnt_hi << 32) | (u64)q->i_bcnt_lo;
+	return ((u64)q->i_bcnt_hi << 32) | be32_to_cpu(q->i_bcnt_lo);
 }
 static inline u64 qm_mcr_querycgr_a_get64(const struct qm_mcr_querycgr *q)
 {
-	return ((u64)q->a_bcnt_hi << 32) | (u64)q->a_bcnt_lo;
+	return ((u64)q->a_bcnt_hi << 32) | be32_to_cpu(q->a_bcnt_lo);
 }
 
 /* "Query FQ Non-Programmable Fields" */
-struct qm_mcc_queryfq_np {
-	u8 _ncw_verb;
-	u8 __reserved1[3];
-	u32 fqid;	/* 24-bit */
-	u8 __reserved2[56];
-} __packed;
 
 struct qm_mcr_queryfq_np {
 	u8 verb;
@@ -367,5 +361,6 @@ int qman_alloc_fq_table(u32 num_fqids);
 #define QM_PIRQ_VISIBLE	(QM_PIRQ_SLOW | QM_PIRQ_DQRI)
 
 extern struct qman_portal *affine_portals[NR_CPUS];
+extern struct qman_portal *qman_dma_portal;
 const struct qm_portal_config *qman_get_qm_portal_config(
 						struct qman_portal *portal);
diff --git a/drivers/soc/fsl/qbman/qman_test_api.c b/drivers/soc/fsl/qbman/qman_test_api.c
index 6880ff17f45e..2895d062cf51 100644
--- a/drivers/soc/fsl/qbman/qman_test_api.c
+++ b/drivers/soc/fsl/qbman/qman_test_api.c
@@ -65,7 +65,7 @@ static void fd_init(struct qm_fd *fd)
 {
 	qm_fd_addr_set64(fd, 0xabdeadbeefLLU);
 	qm_fd_set_contig_big(fd, 0x0000ffff);
-	fd->cmd = 0xfeedf00d;
+	fd->cmd = cpu_to_be32(0xfeedf00d);
 }
 
 static void fd_inc(struct qm_fd *fd)
@@ -86,26 +86,19 @@ static void fd_inc(struct qm_fd *fd)
 	len--;
 	qm_fd_set_param(fd, fmt, off, len);
 
-	fd->cmd++;
+	fd->cmd = cpu_to_be32(be32_to_cpu(fd->cmd) + 1);
 }
 
 /* The only part of the 'fd' we can't memcmp() is the ppid */
-static int fd_cmp(const struct qm_fd *a, const struct qm_fd *b)
+static bool fd_neq(const struct qm_fd *a, const struct qm_fd *b)
 {
-	int r = (qm_fd_addr_get64(a) == qm_fd_addr_get64(b)) ? 0 : -1;
+	bool neq = qm_fd_addr_get64(a) != qm_fd_addr_get64(b);
 
-	if (!r) {
-		enum qm_fd_format fmt_a, fmt_b;
+	neq |= qm_fd_get_format(a) != qm_fd_get_format(b);
+	neq |= a->cfg != b->cfg;
+	neq |= a->cmd != b->cmd;
 
-		fmt_a = qm_fd_get_format(a);
-		fmt_b = qm_fd_get_format(b);
-		r = fmt_a - fmt_b;
-	}
-	if (!r)
-		r = a->cfg - b->cfg;
-	if (!r)
-		r = a->cmd - b->cmd;
-	return r;
+	return neq;
 }
 
 /* test */
@@ -217,12 +210,12 @@ static enum qman_cb_dqrr_result cb_dqrr(struct qman_portal *p,
 					struct qman_fq *fq,
 					const struct qm_dqrr_entry *dq)
 {
-	if (WARN_ON(fd_cmp(&fd_dq, &dq->fd))) {
+	if (WARN_ON(fd_neq(&fd_dq, &dq->fd))) {
 		pr_err("BADNESS: dequeued frame doesn't match;\n");
 		return qman_cb_dqrr_consume;
 	}
 	fd_inc(&fd_dq);
-	if (!(dq->stat & QM_DQRR_STAT_UNSCHEDULED) && !fd_cmp(&fd_dq, &fd)) {
+	if (!(dq->stat & QM_DQRR_STAT_UNSCHEDULED) && !fd_neq(&fd_dq, &fd)) {
 		sdqcr_complete = 1;
 		wake_up(&waitqueue);
 	}
diff --git a/drivers/soc/fsl/qbman/qman_test_stash.c b/drivers/soc/fsl/qbman/qman_test_stash.c
index 43cf66ba42f5..e87b65403b67 100644
--- a/drivers/soc/fsl/qbman/qman_test_stash.c
+++ b/drivers/soc/fsl/qbman/qman_test_stash.c
@@ -175,7 +175,7 @@ static DEFINE_PER_CPU(struct hp_cpu, hp_cpus);
 
 /* links together the hp_cpu structs, in first-come first-serve order. */
 static LIST_HEAD(hp_cpu_list);
-static spinlock_t hp_lock = __SPIN_LOCK_UNLOCKED(hp_lock);
+static DEFINE_SPINLOCK(hp_lock);
 
 static unsigned int hp_cpu_list_length;
 
@@ -191,6 +191,9 @@ static void *__frame_ptr;
 static u32 *frame_ptr;
 static dma_addr_t frame_dma;
 
+/* needed for dma_map*() */
+static const struct qm_portal_config *pcfg;
+
 /* the main function waits on this */
 static DECLARE_WAIT_QUEUE_HEAD(queue);
 
@@ -210,16 +213,14 @@ static int allocate_frame_data(void)
 {
 	u32 lfsr = HP_FIRST_WORD;
 	int loop;
-	struct platform_device *pdev = platform_device_alloc("foobar", -1);
 
-	if (!pdev) {
-		pr_crit("platform_device_alloc() failed");
-		return -EIO;
-	}
-	if (platform_device_add(pdev)) {
-		pr_crit("platform_device_add() failed");
+	if (!qman_dma_portal) {
+		pr_crit("portal not available\n");
 		return -EIO;
 	}
+
+	pcfg = qman_get_qm_portal_config(qman_dma_portal);
+
 	__frame_ptr = kmalloc(4 * HP_NUM_WORDS, GFP_KERNEL);
 	if (!__frame_ptr)
 		return -ENOMEM;
@@ -229,15 +230,22 @@ static int allocate_frame_data(void)
 		frame_ptr[loop] = lfsr;
 		lfsr = do_lfsr(lfsr);
 	}
-	frame_dma = dma_map_single(&pdev->dev, frame_ptr, 4 * HP_NUM_WORDS,
+
+	frame_dma = dma_map_single(pcfg->dev, frame_ptr, 4 * HP_NUM_WORDS,
 				   DMA_BIDIRECTIONAL);
-	platform_device_del(pdev);
-	platform_device_put(pdev);
+	if (dma_mapping_error(pcfg->dev, frame_dma)) {
+		pr_crit("dma mapping failure\n");
+		kfree(__frame_ptr);
+		return -EIO;
+	}
+
 	return 0;
 }
 
 static void deallocate_frame_data(void)
 {
+	dma_unmap_single(pcfg->dev, frame_dma, 4 * HP_NUM_WORDS,
+			 DMA_BIDIRECTIONAL);
 	kfree(__frame_ptr);
 }
 
@@ -249,7 +257,8 @@ static inline int process_frame_data(struct hp_handler *handler,
 	int loop;
 
 	if (qm_fd_addr_get64(fd) != handler->addr) {
-		pr_crit("bad frame address");
+		pr_crit("bad frame address, [%llX != %llX]\n",
+			qm_fd_addr_get64(fd), handler->addr);
 		return -EIO;
 	}
 	for (loop = 0; loop < HP_NUM_WORDS; loop++, p++) {
@@ -397,8 +406,9 @@ static int init_handler(void *h)
 		goto failed;
 	}
 	memset(&opts, 0, sizeof(opts));
-	opts.we_mask = QM_INITFQ_WE_FQCTRL | QM_INITFQ_WE_CONTEXTA;
-	opts.fqd.fq_ctrl = QM_FQCTRL_CTXASTASHING;
+	opts.we_mask = cpu_to_be16(QM_INITFQ_WE_FQCTRL |
+				   QM_INITFQ_WE_CONTEXTA);
+	opts.fqd.fq_ctrl = cpu_to_be16(QM_FQCTRL_CTXASTASHING);
 	qm_fqd_set_stashing(&opts.fqd, 0, STASH_DATA_CL, STASH_CTX_CL);
 	err = qman_init_fq(&handler->rx, QMAN_INITFQ_FLAG_SCHED |
 			   QMAN_INITFQ_FLAG_LOCAL, &opts);
diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c
index 2707a827261b..ade168f5328e 100644
--- a/drivers/soc/fsl/qe/qe.c
+++ b/drivers/soc/fsl/qe/qe.c
@@ -717,9 +717,5 @@ static struct platform_driver qe_driver = {
 	.resume = qe_resume,
 };
 
-static int __init qe_drv_init(void)
-{
-	return platform_driver_register(&qe_driver);
-}
-device_initcall(qe_drv_init);
+builtin_platform_driver(qe_driver);
 #endif /* defined(CONFIG_SUSPEND) && defined(CONFIG_PPC_85xx) */
diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h
index 37f3eb001a16..3d4df74a96de 100644
--- a/include/soc/fsl/qman.h
+++ b/include/soc/fsl/qman.h
@@ -244,11 +244,11 @@ static inline int qm_sg_entry_get_off(const struct qm_sg_entry *sg)
 struct qm_dqrr_entry {
 	u8 verb;
 	u8 stat;
-	u16 seqnum;	/* 15-bit */
+	__be16 seqnum;	/* 15-bit */
 	u8 tok;
 	u8 __reserved2[3];
-	u32 fqid;	/* 24-bit */
-	u32 contextB;
+	__be32 fqid;	/* 24-bit */
+	__be32 context_b;
 	struct qm_fd fd;
 	u8 __reserved4[32];
 } __packed;
@@ -262,6 +262,11 @@ struct qm_dqrr_entry {
 #define QM_DQRR_STAT_UNSCHEDULED	0x02	/* Unscheduled dequeue */
 #define QM_DQRR_STAT_DQCR_EXPIRED	0x01	/* VDQCR or PDQCR expired*/
 
+/* 'fqid' is a 24-bit field in every h/w descriptor */
+#define QM_FQID_MASK	GENMASK(23, 0)
+#define qm_fqid_set(p, v) ((p)->fqid = cpu_to_be32((v) & QM_FQID_MASK))
+#define qm_fqid_get(p)    (be32_to_cpu((p)->fqid) & QM_FQID_MASK)
+
 /* "ERN Message Response" */
 /* "FQ State Change Notification" */
 union qm_mr_entry {
@@ -272,12 +277,11 @@ union qm_mr_entry {
 	struct {
 		u8 verb;
 		u8 dca;
-		u16 seqnum;
+		__be16 seqnum;
 		u8 rc;		/* Rej Code: 8-bit */
-		u8 orp_hi;	/* ORP: 24-bit */
-		u16 orp_lo;
-		u32 fqid;	/* 24-bit */
-		u32 tag;
+		u8 __reserved[3];
+		__be32 fqid;	/* 24-bit */
+		__be32 tag;
 		struct qm_fd fd;
 		u8 __reserved1[32];
 	} __packed ern;
@@ -285,8 +289,8 @@ union qm_mr_entry {
 		u8 verb;
 		u8 fqs;		/* Frame Queue Status */
 		u8 __reserved1[6];
-		u32 fqid;	/* 24-bit */
-		u32 contextB;
+		__be32 fqid;	/* 24-bit */
+		__be32 context_b;
 		u8 __reserved2[48];
 	} __packed fq;		/* FQRN/FQRNI/FQRL/FQPN */
 };
@@ -405,13 +409,13 @@ static inline u64 qm_fqd_context_a_get64(const struct qm_fqd *fqd)
 
 static inline void qm_fqd_stashing_set64(struct qm_fqd *fqd, u64 addr)
 {
-	fqd->context_a.context_hi = upper_32_bits(addr);
-	fqd->context_a.context_lo = lower_32_bits(addr);
+	fqd->context_a.context_hi = cpu_to_be16(upper_32_bits(addr));
+	fqd->context_a.context_lo = cpu_to_be32(lower_32_bits(addr));
 }
 
 static inline void qm_fqd_context_a_set64(struct qm_fqd *fqd, u64 addr)
 {
-	fqd->context_a.hi = cpu_to_be16(upper_32_bits(addr));
+	fqd->context_a.hi = cpu_to_be32(upper_32_bits(addr));
 	fqd->context_a.lo = cpu_to_be32(lower_32_bits(addr));
 }
 
@@ -521,7 +525,7 @@ static inline int qm_fqd_get_wq(const struct qm_fqd *fqd)
  */
 struct qm_cgr_wr_parm {
 	/* MA[24-31], Mn[19-23], SA[12-18], Sn[6-11], Pn[0-5] */
-	u32 word;
+	__be32 word;
 };
 /*
  * This struct represents the 13-bit "CS_THRES" CGR field. In the corresponding
@@ -532,7 +536,7 @@ struct qm_cgr_wr_parm {
  */
 struct qm_cgr_cs_thres {
 	/* _res[13-15], TA[5-12], Tn[0-4] */
-	u16 word;
+	__be16 word;
 };
 /*
  * This identical structure of CGR fields is present in the "Init/Modify CGR"
@@ -549,10 +553,10 @@ struct __qm_mc_cgr {
 	u8 cscn_en;	/* boolean, use QM_CGR_EN */
 	union {
 		struct {
-			u16 cscn_targ_upd_ctrl; /* use QM_CSCN_TARG_UDP_ */
-			u16 cscn_targ_dcp_low;	/* CSCN_TARG_DCP low-16bits */
+			__be16 cscn_targ_upd_ctrl; /* use QM_CGR_TARG_UDP_* */
+			__be16 cscn_targ_dcp_low;
 		};
-		u32 cscn_targ;	/* use QM_CGR_TARG_* */
+		__be32 cscn_targ;	/* use QM_CGR_TARG_* */
 	};
 	u8 cstd_en;	/* boolean, use QM_CGR_EN */
 	u8 cs;		/* boolean, only used in query response */
@@ -568,7 +572,9 @@ struct __qm_mc_cgr {
 /* Convert CGR thresholds to/from "cs_thres" format */
 static inline u64 qm_cgr_cs_thres_get64(const struct qm_cgr_cs_thres *th)
 {
-	return ((th->word >> 5) & 0xff) << (th->word & 0x1f);
+	int thres = be16_to_cpu(th->word);
+
+	return ((thres >> 5) & 0xff) << (thres & 0x1f);
 }
 
 static inline int qm_cgr_cs_thres_set64(struct qm_cgr_cs_thres *th, u64 val,
@@ -584,23 +590,23 @@ static inline int qm_cgr_cs_thres_set64(struct qm_cgr_cs_thres *th, u64 val,
 		if (roundup && oddbit)
 			val++;
 	}
-	th->word = ((val & 0xff) << 5) | (e & 0x1f);
+	th->word = cpu_to_be16(((val & 0xff) << 5) | (e & 0x1f));
 	return 0;
 }
 
 /* "Initialize FQ" */
 struct qm_mcc_initfq {
 	u8 __reserved1[2];
-	u16 we_mask;	/* Write Enable Mask */
-	u32 fqid;	/* 24-bit */
-	u16 count;	/* Initialises 'count+1' FQDs */
+	__be16 we_mask;	/* Write Enable Mask */
+	__be32 fqid;	/* 24-bit */
+	__be16 count;	/* Initialises 'count+1' FQDs */
 	struct qm_fqd fqd; /* the FQD fields go here */
 	u8 __reserved2[30];
 } __packed;
 /* "Initialize/Modify CGR" */
 struct qm_mcc_initcgr {
 	u8 __reserve1[2];
-	u16 we_mask;	/* Write Enable Mask */
+	__be16 we_mask;	/* Write Enable Mask */
 	struct __qm_mc_cgr cgr;	/* CGR fields */
 	u8 __reserved2[2];
 	u8 cgid;
@@ -654,7 +660,7 @@ struct qman_cgr;
 /*
  * This enum, and the callback type that returns it, are used when handling
  * dequeued frames via DQRR. Note that for "null" callbacks registered with the
- * portal object (for handling dequeues that do not demux because contextB is
+ * portal object (for handling dequeues that do not demux because context_b is
  * NULL), the return value *MUST* be qman_cb_dqrr_consume.
  */
 enum qman_cb_dqrr_result {
@@ -859,11 +865,11 @@ void qman_p_static_dequeue_add(struct qman_portal *p, u32 pools);
  * qman_fq" for more info). NO_MODIFY is only intended for enqueuing to
  * pre-existing frame-queues that aren't to be otherwise interfered with, it
  * prevents all other modifications to the frame queue. The TO_DCPORTAL flag
- * causes the driver to honour any contextB modifications requested in the
+ * causes the driver to honour any context_b modifications requested in the
  * qm_init_fq() API, as this indicates the frame queue will be consumed by a
  * direct-connect portal (PME, CAAM, or Fman). When frame queues are consumed by
- * software portals, the contextB field is controlled by the driver and can't be
- * modified by the caller.
+ * software portals, the context_b field is controlled by the driver and can't
+ * be modified by the caller.
  */
 int qman_create_fq(u32 fqid, u32 flags, struct qman_fq *fq);