Merge tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Enable THREAD_INFO_IN_TASK to move thread_info off the stack.

   - A big series from Christoph reworking our DMA code to use more of
     the generic infrastructure, as he said:
       "This series switches the powerpc port to use the generic swiotlb
        and noncoherent dma ops, and to use more generic code for the
        coherent direct mapping, as well as removing a lot of dead
        code."

   - Increase our vmalloc space to 512T with the Hash MMU on modern
     CPUs, allowing us to support machines with larger amounts of total
     RAM or distance between nodes.

   - Two series from Christophe, one to optimise TLB miss handlers on
     6xx, and another to optimise the way STRICT_KERNEL_RWX is
     implemented on some 32-bit CPUs.

   - Support for KCOV coverage instrumentation which means we can run
     syzkaller and discover even more bugs in our code.

  And as always many clean-ups, reworks and minor fixes etc.

  Thanks to: Alan Modra, Alexey Kardashevskiy, Alistair Popple, Andrea
  Arcangeli, Andrew Donnellan, Aneesh Kumar K.V, Aravinda Prasad, Balbir
  Singh, Brajeswar Ghosh, Breno Leitao, Christian Lamparter, Christian
  Zigotzky, Christophe Leroy, Christoph Hellwig, Corentin Labbe, Daniel
  Axtens, David Gibson, Diana Craciun, Firoz Khan, Gustavo A. R. Silva,
  Igor Stoppa, Joe Lawrence, Joel Stanley, Jonathan Neuschäfer, Jordan
  Niethe, Laurent Dufour, Madhavan Srinivasan, Mahesh Salgaonkar, Mark
  Cave-Ayland, Masahiro Yamada, Mathieu Malaterre, Matteo Croce, Meelis
  Roos, Michael W. Bringmann, Nathan Chancellor, Nathan Fontenot,
  Nicholas Piggin, Nick Desaulniers, Nicolai Stange, Oliver O'Halloran,
  Paul Mackerras, Peter Xu, PrasannaKumar Muralidharan, Qian Cai,
  Rashmica Gupta, Reza Arbab, Robert P. J. Day, Russell Currey,
  Sabyasachi Gupta, Sam Bobroff, Sandipan Das, Sergey Senozhatsky,
  Souptick Joarder, Stewart Smith, Tyrel Datwyler, Vaibhav Jain,
  YueHaibing"

* tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (200 commits)
  powerpc/32: Clear on-stack exception marker upon exception return
  powerpc: Remove export of save_stack_trace_tsk_reliable()
  powerpc/mm: fix "section_base" set but not used
  powerpc/mm: Fix "sz" set but not used warning
  powerpc/mm: Check secondary hash page table
  powerpc: remove nargs from __SYSCALL
  powerpc/64s: Fix unrelocated interrupt trampoline address test
  powerpc/powernv/ioda: Fix locked_vm counting for memory used by IOMMU tables
  powerpc/fsl: Fix the flush of branch predictor.
  powerpc/powernv: Make opal log only readable by root
  powerpc/xmon: Fix opcode being uninitialized in print_insn_powerpc
  powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C
  powerpc/64s: Fix data interrupts vs d-side MCE reentrancy
  powerpc/64s: Prepare to handle data interrupts vs d-side MCE reentrancy
  powerpc/64s: system reset interrupt preserve HSRRs
  powerpc/64s: Fix HV NMI vs HV interrupt recoverability test
  powerpc/mm/hash: Handle mmap_min_addr correctly in get_unmapped_area topdown search
  powerpc/hugetlb: Handle mmap_min_addr correctly in get_unmapped_area callback
  selftests/powerpc: Remove duplicate header
  powerpc sstep: Add support for modsd, modud instructions
  ...

39 files changed, 556 insertions, 850 deletions

diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 4a9a72d01c3c6..35be81fd2dc23 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -180,6 +180,7 @@ config CURRITUCK
 	depends on PPC_47x
 	select SWIOTLB
 	select 476FPE
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	help
 	  This option enables support for the IBM Currituck (476fpe) evaluation board
diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c
index e55933f9cd55f..a5e61e5c16e27 100644
--- a/arch/powerpc/platforms/44x/ppc476.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -34,6 +34,7 @@
 #include <asm/ppc4xx.h>
 #include <asm/mpic.h>
 #include <asm/mmu.h>
+#include <asm/swiotlb.h>
 
 #include <linux/pci.h>
 #include <linux/i2c.h>
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index f467247fd1c45..18422dbd061ad 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -47,7 +47,7 @@ static int __init warp_probe(void)
 	if (!of_machine_is_compatible("pika,warp"))
 		return 0;
 
-	/* For __dma_nommu_alloc_coherent */
+	/* For arch_dma_alloc */
 	ISA_DMA_THRESHOLD = ~0L;
 
 	return 1;
diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S
index 3d1ecd2117769..8137f77abad57 100644
--- a/arch/powerpc/platforms/83xx/suspend-asm.S
+++ b/arch/powerpc/platforms/83xx/suspend-asm.S
@@ -26,13 +26,13 @@
 #define SS_MSR		0x74
 #define SS_SDR1		0x78
 #define SS_LR		0x7c
-#define SS_SPRG		0x80 /* 4 SPRGs */
-#define SS_DBAT		0x90 /* 8 DBATs */
-#define SS_IBAT		0xd0 /* 8 IBATs */
-#define SS_TB		0x110
-#define SS_CR		0x118
-#define SS_GPREG	0x11c /* r12-r31 */
-#define STATE_SAVE_SIZE 0x16c
+#define SS_SPRG		0x80 /* 8 SPRGs */
+#define SS_DBAT		0xa0 /* 8 DBATs */
+#define SS_IBAT		0xe0 /* 8 IBATs */
+#define SS_TB		0x120
+#define SS_CR		0x128
+#define SS_GPREG	0x12c /* r12-r31 */
+#define STATE_SAVE_SIZE 0x17c
 
 	.section .data
 	.align	5
@@ -103,6 +103,16 @@ _GLOBAL(mpc83xx_enter_deep_sleep)
 	stw	r7, SS_SPRG+12(r3)
 	stw	r8, SS_SDR1(r3)
 
+	mfspr	r4, SPRN_SPRG4
+	mfspr	r5, SPRN_SPRG5
+	mfspr	r6, SPRN_SPRG6
+	mfspr	r7, SPRN_SPRG7
+
+	stw	r4, SS_SPRG+16(r3)
+	stw	r5, SS_SPRG+20(r3)
+	stw	r6, SS_SPRG+24(r3)
+	stw	r7, SS_SPRG+28(r3)
+
 	mfspr	r4, SPRN_DBAT0U
 	mfspr	r5, SPRN_DBAT0L
 	mfspr	r6, SPRN_DBAT1U
@@ -493,6 +503,16 @@ mpc83xx_deep_resume:
 	mtspr	SPRN_IBAT7U, r6
 	mtspr	SPRN_IBAT7L, r7
 
+	lwz	r4, SS_SPRG+16(r3)
+	lwz	r5, SS_SPRG+20(r3)
+	lwz	r6, SS_SPRG+24(r3)
+	lwz	r7, SS_SPRG+28(r3)
+
+	mtspr	SPRN_SPRG4, r4
+	mtspr	SPRN_SPRG5, r5
+	mtspr	SPRN_SPRG6, r6
+	mtspr	SPRN_SPRG7, r7
+
 	lwz	r4, SS_SPRG+0(r3)
 	lwz	r5, SS_SPRG+4(r3)
 	lwz	r6, SS_SPRG+8(r3)
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index b0dac307bebf9..785e9641220da 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -27,6 +27,7 @@
 #include <asm/udbg.h>
 #include <asm/mpic.h>
 #include <asm/ehv_pic.h>
+#include <asm/swiotlb.h>
 #include <soc/fsl/qe/qe_ic.h>
 
 #include <linux/of_platform.h>
@@ -223,7 +224,3 @@ define_machine(corenet_generic) {
 };
 
 machine_arch_initcall(corenet_generic, corenet_gen_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(corenet_generic, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index f29c6f0909f35..c64fa2483ea97 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -202,8 +202,6 @@ static int __init ge_imp3a_probe(void)
 
 machine_arch_initcall(ge_imp3a, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(ge_imp3a, swiotlb_setup_bus_notifier);
-
 define_machine(ge_imp3a) {
 	.name			= "GE_IMP3A",
 	.probe			= ge_imp3a_probe,
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 94a7f92c858ff..94194bad4954e 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -57,8 +57,6 @@ static void __init mpc8536_ds_setup_arch(void)
 
 machine_arch_initcall(mpc8536_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8536_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index dc9e035cc637a..b7e29ce1f266f 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -174,10 +174,6 @@ machine_arch_initcall(mpc8544_ds, mpc85xx_common_publish_devices);
 machine_arch_initcall(mpc8572_ds, mpc85xx_common_publish_devices);
 machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8544_ds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(mpc8572_ds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(p2020_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index d7e440e6dba3d..80939a425de59 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -367,10 +367,6 @@ machine_arch_initcall(mpc8568_mds, mpc85xx_publish_devices);
 machine_arch_initcall(mpc8569_mds, mpc85xx_publish_devices);
 machine_arch_initcall(p1021_mds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8568_mds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(mpc8569_mds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(p1021_mds, swiotlb_setup_bus_notifier);
-
 static void __init mpc85xx_mds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 78d13b364cd63..33ca373322e18 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -55,7 +55,6 @@ static void __init p1010_rdb_setup_arch(void)
 }
 
 machine_arch_initcall(p1010_rdb, mpc85xx_common_publish_devices);
-machine_arch_initcall(p1010_rdb, swiotlb_setup_bus_notifier);
 
 /*
  * Called very early, device-tree isn't unflattened
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 9fb57f78cdbe3..1f1af0557470f 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -548,8 +548,6 @@ static void __init p1022_ds_setup_arch(void)
 
 machine_arch_initcall(p1022_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(p1022_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 276e00ab3dde9..fd9e3e7ef2347 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -128,8 +128,6 @@ static void __init p1022_rdk_setup_arch(void)
 
 machine_arch_initcall(p1022_rdk, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(p1022_rdk, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
index 27631c607f3d9..c52c8f9e83852 100644
--- a/arch/powerpc/platforms/85xx/qemu_e500.c
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -22,6 +22,7 @@
 #include <asm/time.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
+#include <asm/swiotlb.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 #include "smp.h"
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 17c6cd3d02e67..775a92353c832 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -121,7 +121,6 @@ static int __init declare_of_platform_devices(void)
 	return 0;
 }
 machine_arch_initcall(mpc86xx_hpcn, declare_of_platform_devices);
-machine_arch_initcall(mpc86xx_hpcn, swiotlb_setup_bus_notifier);
 
 define_machine(mpc86xx_hpcn) {
 	.name			= "MPC86xx HPCN",
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 8c7464c3f27fe..842b2c7e156ab 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -153,6 +153,11 @@ config E300C3_CPU
 	bool "e300c3 (831x)"
 	depends on PPC_BOOK3S_32
 
+config G4_CPU
+	bool "G4 (74xx)"
+	depends on PPC_BOOK3S_32
+	select ALTIVEC
+
 endchoice
 
 config TARGET_CPU_BOOL
@@ -171,6 +176,7 @@ config TARGET_CPU
 	default "860" if 860_CPU
 	default "e300c2" if E300C2_CPU
 	default "e300c3" if E300C3_CPU
+	default "G4" if G4_CPU
 
 config PPC_BOOK3S
 	def_bool y
@@ -402,6 +408,9 @@ config NOT_COHERENT_CACHE
 	bool
 	depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \
 		GAMECUBE_COMMON || AMIGAONE
+	select ARCH_HAS_DMA_COHERENT_TO_PFN
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	default n if PPC_47x
 	default y
 
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index af2a3c15e0ecc..54e012e1f720e 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -544,9 +544,10 @@ static struct cbe_iommu *cell_iommu_for_node(int nid)
 static unsigned long cell_dma_nommu_offset;
 
 static unsigned long dma_iommu_fixed_base;
+static bool cell_iommu_enabled;
 
 /* iommu_fixed_is_weak is set if booted with iommu_fixed=weak */
-static int iommu_fixed_is_weak;
+bool iommu_fixed_is_weak;
 
 static struct iommu_table *cell_get_iommu_table(struct device *dev)
 {
@@ -568,102 +569,19 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev)
 	return &window->table;
 }
 
-/* A coherent allocation implies strong ordering */
-
-static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
-				      dma_addr_t *dma_handle, gfp_t flag,
-				      unsigned long attrs)
-{
-	if (iommu_fixed_is_weak)
-		return iommu_alloc_coherent(dev, cell_get_iommu_table(dev),
-					    size, dma_handle,
-					    device_to_mask(dev), flag,
-					    dev_to_node(dev));
-	else
-		return dma_nommu_ops.alloc(dev, size, dma_handle, flag,
-					    attrs);
-}
-
-static void dma_fixed_free_coherent(struct device *dev, size_t size,
-				    void *vaddr, dma_addr_t dma_handle,
-				    unsigned long attrs)
-{
-	if (iommu_fixed_is_weak)
-		iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr,
-				    dma_handle);
-	else
-		dma_nommu_ops.free(dev, size, vaddr, dma_handle, attrs);
-}
-
-static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page,
-				     unsigned long offset, size_t size,
-				     enum dma_data_direction direction,
-				     unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_nommu_ops.map_page(dev, page, offset, size,
-					       direction, attrs);
-	else
-		return iommu_map_page(dev, cell_get_iommu_table(dev), page,
-				      offset, size, device_to_mask(dev),
-				      direction, attrs);
-}
-
-static void dma_fixed_unmap_page(struct device *dev, dma_addr_t dma_addr,
-				 size_t size, enum dma_data_direction direction,
-				 unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_nommu_ops.unmap_page(dev, dma_addr, size, direction,
-					  attrs);
-	else
-		iommu_unmap_page(cell_get_iommu_table(dev), dma_addr, size,
-				 direction, attrs);
-}
-
-static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg,
-			   int nents, enum dma_data_direction direction,
-			   unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_nommu_ops.map_sg(dev, sg, nents, direction, attrs);
-	else
-		return ppc_iommu_map_sg(dev, cell_get_iommu_table(dev), sg,
-					nents, device_to_mask(dev),
-					direction, attrs);
-}
-
-static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
-			       int nents, enum dma_data_direction direction,
-			       unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_nommu_ops.unmap_sg(dev, sg, nents, direction, attrs);
-	else
-		ppc_iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents,
-				   direction, attrs);
-}
-
-static int dma_suported_and_switch(struct device *dev, u64 dma_mask);
-
-static const struct dma_map_ops dma_iommu_fixed_ops = {
-	.alloc          = dma_fixed_alloc_coherent,
-	.free           = dma_fixed_free_coherent,
-	.map_sg         = dma_fixed_map_sg,
-	.unmap_sg       = dma_fixed_unmap_sg,
-	.dma_supported  = dma_suported_and_switch,
-	.map_page       = dma_fixed_map_page,
-	.unmap_page     = dma_fixed_unmap_page,
-};
+static u64 cell_iommu_get_fixed_address(struct device *dev);
 
 static void cell_dma_dev_setup(struct device *dev)
 {
-	if (get_pci_dma_ops() == &dma_iommu_ops)
+	if (cell_iommu_enabled) {
+		u64 addr = cell_iommu_get_fixed_address(dev);
+
+		if (addr != OF_BAD_ADDR)
+			dev->archdata.dma_offset = addr + dma_iommu_fixed_base;
 		set_iommu_table_base(dev, cell_get_iommu_table(dev));
-	else if (get_pci_dma_ops() == &dma_nommu_ops)
-		set_dma_offset(dev, cell_dma_nommu_offset);
-	else
-		BUG();
+	} else {
+		dev->archdata.dma_offset = cell_dma_nommu_offset;
+	}
 }
 
 static void cell_pci_dma_dev_setup(struct pci_dev *dev)
@@ -680,11 +598,9 @@ static int cell_of_bus_notify(struct notifier_block *nb, unsigned long action,
 	if (action != BUS_NOTIFY_ADD_DEVICE)
 		return 0;
 
-	/* We use the PCI DMA ops */
-	dev->dma_ops = get_pci_dma_ops();
-
+	if (cell_iommu_enabled)
+		dev->dma_ops = &dma_iommu_ops;
 	cell_dma_dev_setup(dev);
-
 	return 0;
 }
 
@@ -809,7 +725,6 @@ static int __init cell_iommu_init_disabled(void)
 	unsigned long base = 0, size;
 
 	/* When no iommu is present, we use direct DMA ops */
-	set_pci_dma_ops(&dma_nommu_ops);
 
 	/* First make sure all IOC translation is turned off */
 	cell_disable_iommus();
@@ -894,7 +809,11 @@ static u64 cell_iommu_get_fixed_address(struct device *dev)
 	const u32 *ranges = NULL;
 	int i, len, best, naddr, nsize, pna, range_size;
 
+	/* We can be called for platform devices that have no of_node */
 	np = of_node_get(dev->of_node);
+	if (!np)
+		goto out;
+
 	while (1) {
 		naddr = of_n_addr_cells(np);
 		nsize = of_n_size_cells(np);
@@ -945,27 +864,10 @@ out:
 	return dev_addr;
 }
 
-static int dma_suported_and_switch(struct device *dev, u64 dma_mask)
+static bool cell_pci_iommu_bypass_supported(struct pci_dev *pdev, u64 mask)
 {
-	if (dma_mask == DMA_BIT_MASK(64) &&
-	    cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR) {
-		u64 addr = cell_iommu_get_fixed_address(dev) +
-			dma_iommu_fixed_base;
-		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
-		dev_dbg(dev, "iommu: fixed addr = %llx\n", addr);
-		set_dma_ops(dev, &dma_iommu_fixed_ops);
-		set_dma_offset(dev, addr);
-		return 1;
-	}
-
-	if (dma_iommu_dma_supported(dev, dma_mask)) {
-		dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
-		set_dma_ops(dev, get_pci_dma_ops());
-		cell_dma_dev_setup(dev);
-		return 1;
-	}
-
-	return 0;
+	return mask == DMA_BIT_MASK(64) &&
+		cell_iommu_get_fixed_address(&pdev->dev) != OF_BAD_ADDR;
 }
 
 static void insert_16M_pte(unsigned long addr, unsigned long *ptab,
@@ -1119,9 +1021,8 @@ static int __init cell_iommu_fixed_mapping_init(void)
 		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
 	}
 
-	dma_iommu_ops.dma_supported = dma_suported_and_switch;
-	set_pci_dma_ops(&dma_iommu_ops);
-
+	cell_pci_controller_ops.iommu_bypass_supported =
+		cell_pci_iommu_bypass_supported;
 	return 0;
 }
 
@@ -1142,7 +1043,7 @@ static int __init setup_iommu_fixed(char *str)
 	pciep = of_find_node_by_type(NULL, "pcie-endpoint");
 
 	if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0))
-		iommu_fixed_is_weak = DMA_ATTR_WEAK_ORDERING;
+		iommu_fixed_is_weak = true;
 
 	of_node_put(pciep);
 
@@ -1150,26 +1051,6 @@ static int __init setup_iommu_fixed(char *str)
 }
 __setup("iommu_fixed=", setup_iommu_fixed);
 
-static u64 cell_dma_get_required_mask(struct device *dev)
-{
-	const struct dma_map_ops *dma_ops;
-
-	if (!dev->dma_mask)
-		return 0;
-
-	if (!iommu_fixed_disabled &&
-			cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR)
-		return DMA_BIT_MASK(64);
-
-	dma_ops = get_dma_ops(dev);
-	if (dma_ops->get_required_mask)
-		return dma_ops->get_required_mask(dev);
-
-	WARN_ONCE(1, "no get_required_mask in %p ops", dma_ops);
-
-	return DMA_BIT_MASK(64);
-}
-
 static int __init cell_iommu_init(void)
 {
 	struct device_node *np;
@@ -1186,10 +1067,9 @@ static int __init cell_iommu_init(void)
 
 	/* Setup various callbacks */
 	cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
-	ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
 
 	if (!iommu_fixed_disabled && cell_iommu_fixed_mapping_init() == 0)
-		goto bail;
+		goto done;
 
 	/* Create an iommu for each /axon node.  */
 	for_each_node_by_name(np, "axon") {
@@ -1206,10 +1086,10 @@ static int __init cell_iommu_init(void)
 			continue;
 		cell_iommu_init_one(np, SPIDER_DMA_OFFSET);
 	}
-
+ done:
 	/* Setup default PCI iommu ops */
 	set_pci_dma_ops(&dma_iommu_ops);
-
+	cell_iommu_enabled = true;
  bail:
 	/* Register callbacks on OF platform device addition/removal
 	 * to handle linking them to the right DMA operations
diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c
index 125f2a5f02de2..b5f35cbe9e217 100644
--- a/arch/powerpc/platforms/cell/spu_callbacks.c
+++ b/arch/powerpc/platforms/cell/spu_callbacks.c
@@ -34,7 +34,7 @@
  */
 
 static void *spu_syscall_table[] = {
-#define __SYSCALL(nr, entry, nargs) entry,
+#define __SYSCALL(nr, entry)	entry,
 #include <asm/syscall_table_spu.h>
 #undef __SYSCALL
 };
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index 263413a348230..b95d6afc39b57 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -26,7 +26,6 @@
 #include <linux/syscalls.h>
 #include <linux/rcupdate.h>
 #include <linux/binfmts.h>
-#include <linux/syscalls.h>
 
 #include <asm/spu.h>
 
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index ae8123edddc67..48c2477e7e2a2 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -2338,9 +2338,8 @@ static int spufs_switch_log_open(struct inode *inode, struct file *file)
 		goto out;
 	}
 
-	ctx->switch_log = kmalloc(sizeof(struct switch_log) +
-		SWITCH_LOG_BUFSIZE * sizeof(struct switch_log_entry),
-		GFP_KERNEL);
+	ctx->switch_log = kmalloc(struct_size(ctx->switch_log, log,
+				  SWITCH_LOG_BUFSIZE), GFP_KERNEL);
 
 	if (!ctx->switch_log) {
 		rc = -ENOMEM;
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index ecf703ee3a76d..235fe81aa2b1a 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -54,10 +54,6 @@
 static void __iomem *hw_ctrl;
 static void __iomem *hw_gpio;
 
-unsigned long wii_hole_start;
-unsigned long wii_hole_size;
-
-
 static int __init page_aligned(unsigned long x)
 {
 	return !(x & (PAGE_SIZE-1));
@@ -69,26 +65,6 @@ void __init wii_memory_fixups(void)
 
 	BUG_ON(memblock.memory.cnt != 2);
 	BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base));
-
-	/* determine hole */
-	wii_hole_start = ALIGN(p[0].base + p[0].size, PAGE_SIZE);
-	wii_hole_size = p[1].base - wii_hole_start;
-}
-
-unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
-{
-	unsigned long delta, size, bl;
-	unsigned long max_size = (256<<20);
-
-	/* MEM2 64MB@0x10000000 */
-	delta = wii_hole_start + wii_hole_size;
-	size = top - delta;
-	for (bl = 128<<10; bl < max_size; bl <<= 1) {
-		if (bl * 2 > size)
-			break;
-	}
-	setbat(4, PAGE_OFFSET+delta, delta, bl, PAGE_KERNEL_X);
-	return delta + bl;
 }
 
 static void __noreturn wii_spin(void)
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index f2971522fb4aa..bbeb6a1b03938 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -186,7 +186,7 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev)
 	 */
 	if (dev->vendor == 0x1959 && dev->device == 0xa007 &&
 	    !firmware_has_feature(FW_FEATURE_LPAR)) {
-		dev->dev.dma_ops = &dma_nommu_ops;
+		dev->dev.dma_ops = NULL;
 		/*
 		 * Set the coherent DMA mask to prevent the iommu
 		 * being used unnecessarily
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index c0532999f8540..46dd463faaa78 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -411,55 +411,6 @@ out:
 	return !!(srr1 & 0x2);
 }
 
-#ifdef CONFIG_PCMCIA
-static int pcmcia_notify(struct notifier_block *nb, unsigned long action,
-			 void *data)
-{
-	struct device *dev = data;
-	struct device *parent;
-	struct pcmcia_device *pdev = to_pcmcia_dev(dev);
-
-	/* We are only intereted in device addition */
-	if (action != BUS_NOTIFY_ADD_DEVICE)
-		return 0;
-
-	parent = pdev->socket->dev.parent;
-
-	/* We know electra_cf devices will always have of_node set, since
-	 * electra_cf is an of_platform driver.
-	 */
-	if (!parent->of_node)
-		return 0;
-
-	if (!of_device_is_compatible(parent->of_node, "electra-cf"))
-		return 0;
-
-	/* We use the direct ops for localbus */
-	dev->dma_ops = &dma_nommu_ops;
-
-	return 0;
-}
-
-static struct notifier_block pcmcia_notifier = {
-	.notifier_call = pcmcia_notify,
-};
-
-static inline void pasemi_pcmcia_init(void)
-{
-	extern struct bus_type pcmcia_bus_type;
-
-	bus_register_notifier(&pcmcia_bus_type, &pcmcia_notifier);
-}
-
-#else
-
-static inline void pasemi_pcmcia_init(void)
-{
-}
-
-#endif
-
-
 static const struct of_device_id pasemi_bus_ids[] = {
 	/* Unfortunately needed for legacy firmwares */
 	{ .type = "localbus", },
@@ -472,8 +423,6 @@ static const struct of_device_id pasemi_bus_ids[] = {
 
 static int __init pasemi_publish_devices(void)
 {
-	pasemi_pcmcia_init();
-
 	/* Publish OF platform devices for SDC and other non-PCI devices */
 	of_platform_bus_probe(NULL, pasemi_bus_ids, NULL);
 
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index b540ce8eec556..da2e99efbd04e 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o idle.o
-obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
+obj-y			+= setup.o opal-call.o opal-wrappers.o opal.o opal-async.o
+obj-y			+= idle.o opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
 obj-y			+= opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
 obj-y			+= opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
@@ -11,7 +11,6 @@ obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
-obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
 obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
 obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 35f699ebb6621..e52f9b06dd9c3 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -458,7 +458,8 @@ EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release);
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
+
+void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
 {
 	u64 pir = get_hard_smp_processor_id(cpu);
 
@@ -481,20 +482,6 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 {
 	unsigned long srr1;
 	u32 idle_states = pnv_get_supported_cpuidle_states();
-	u64 lpcr_val;
-
-	/*
-	 * We don't want to take decrementer interrupts while we are
-	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
-	 * LPCR_PECE_HVEE on P9) enabled as to let IPIs in.
-	 *
-	 * If the CPU gets woken up by a special wakeup, ensure that
-	 * the SLW engine sets LPCR with decrementer bit cleared, else
-	 * the CPU will come back to the kernel due to a spurious
-	 * wakeup.
-	 */
-	lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
-	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
 
 	__ppc64_runlatch_off();
 
@@ -526,16 +513,6 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 
 	__ppc64_runlatch_on();
 
-	/*
-	 * Re-enable decrementer interrupts in LPCR.
-	 *
-	 * Further, we want stop states to be woken up by decrementer
-	 * for non-hotplug cases. So program the LPCR via stop api as
-	 * well.
-	 */
-	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
-	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
-
 	return srr1;
 }
 #endif
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 3f58c7dbd581e..dc23d9d2a7d9a 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -28,10 +28,6 @@
  */
 static DEFINE_SPINLOCK(npu_context_lock);
 
-/*
- * Other types of TCE cache invalidation are not functional in the
- * hardware.
- */
 static struct pci_dev *get_pci_dev(struct device_node *dn)
 {
 	struct pci_dn *pdn = PCI_DN(dn);
@@ -220,7 +216,7 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe)
 	 * their parent device so drivers shouldn't be doing DMA
 	 * operations directly on these devices.
 	 */
-	set_dma_ops(&npe->pdev->dev, NULL);
+	set_dma_ops(&npe->pdev->dev, &dma_dummy_ops);
 }
 
 /*
@@ -917,15 +913,6 @@ static void pnv_npu2_mn_release(struct mmu_notifier *mn,
 	mmio_invalidate(npu_context, 0, ~0UL);
 }
 
-static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
-				struct mm_struct *mm,
-				unsigned long address,
-				pte_t pte)
-{
-	struct npu_context *npu_context = mn_to_npu_context(mn);
-	mmio_invalidate(npu_context, address, PAGE_SIZE);
-}
-
 static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
 					struct mm_struct *mm,
 					unsigned long start, unsigned long end)
@@ -936,7 +923,6 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
 
 static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
 	.release = pnv_npu2_mn_release,
-	.change_pte = pnv_npu2_mn_change_pte,
 	.invalidate_range = pnv_npu2_mn_invalidate_range,
 };
 
diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c
new file mode 100644
index 0000000000000..578757d403ab8
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-call.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/percpu.h>
+#include <linux/jump_label.h>
+#include <asm/opal-api.h>
+#include <asm/trace.h>
+#include <asm/asm-prototypes.h>
+
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * Since the tracing code might execute OPAL calls we need to guard against
+ * recursion.
+ */
+static DEFINE_PER_CPU(unsigned int, opal_trace_depth);
+
+static void __trace_opal_entry(s64 a0, s64 a1, s64 a2, s64 a3,
+			       s64 a4, s64 a5, s64 a6, s64 a7,
+			       unsigned long opcode)
+{
+	unsigned int *depth;
+	unsigned long args[8];
+
+	depth = this_cpu_ptr(&opal_trace_depth);
+
+	if (*depth)
+		return;
+
+	args[0] = a0;
+	args[1] = a1;
+	args[2] = a2;
+	args[3] = a3;
+	args[4] = a4;
+	args[5] = a5;
+	args[6] = a6;
+	args[7] = a7;
+
+	(*depth)++;
+	trace_opal_entry(opcode, &args[0]);
+	(*depth)--;
+}
+
+static void __trace_opal_exit(unsigned long opcode, unsigned long retval)
+{
+	unsigned int *depth;
+
+	depth = this_cpu_ptr(&opal_trace_depth);
+
+	if (*depth)
+		return;
+
+	(*depth)++;
+	trace_opal_exit(opcode, retval);
+	(*depth)--;
+}
+
+static DEFINE_STATIC_KEY_FALSE(opal_tracepoint_key);
+
+int opal_tracepoint_regfunc(void)
+{
+	static_branch_inc(&opal_tracepoint_key);
+	return 0;
+}
+
+void opal_tracepoint_unregfunc(void)
+{
+	static_branch_dec(&opal_tracepoint_key);
+}
+
+static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3,
+			     s64 a4, s64 a5, s64 a6, s64 a7,
+			      unsigned long opcode, unsigned long msr)
+{
+	s64 ret;
+
+	__trace_opal_entry(a0, a1, a2, a3, a4, a5, a6, a7, opcode);
+	ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	__trace_opal_exit(opcode, ret);
+
+	return ret;
+}
+
+#define DO_TRACE (static_branch_unlikely(&opal_tracepoint_key))
+
+#else /* CONFIG_TRACEPOINTS */
+
+static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3,
+			     s64 a4, s64 a5, s64 a6, s64 a7,
+			      unsigned long opcode, unsigned long msr)
+{
+}
+
+#define DO_TRACE false
+#endif /* CONFIG_TRACEPOINTS */
+
+static int64_t opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
+	     int64_t a4, int64_t a5, int64_t a6, int64_t a7, int64_t opcode)
+{
+	unsigned long flags;
+	unsigned long msr = mfmsr();
+	bool mmu = (msr & (MSR_IR|MSR_DR));
+	int64_t ret;
+
+	msr &= ~MSR_EE;
+
+	if (unlikely(!mmu))
+		return __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+
+	local_save_flags(flags);
+	hard_irq_disable();
+
+	if (DO_TRACE) {
+		ret = __opal_call_trace(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	} else {
+		ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	}
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+#define OPAL_CALL(name, opcode)					\
+int64_t name(int64_t a0, int64_t a1, int64_t a2, int64_t a3,	\
+	     int64_t a4, int64_t a5, int64_t a6, int64_t a7)	\
+{								\
+	return opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode); \
+}
+
+OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
+OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
+OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
+OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
+OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
+OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
+OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
+OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
+OPAL_CALL(opal_cec_reboot2,			OPAL_CEC_REBOOT2);
+OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
+OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
+OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
+OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
+OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
+OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
+OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
+OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
+OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
+OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
+OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
+OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
+OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
+OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
+OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
+OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
+OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
+OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
+OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
+OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
+OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
+OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
+OPAL_CALL(opal_pci_map_pe_mmio_window,		OPAL_PCI_MAP_PE_MMIO_WINDOW);
+OPAL_CALL(opal_pci_set_phb_table_memory,	OPAL_PCI_SET_PHB_TABLE_MEMORY);
+OPAL_CALL(opal_pci_set_pe,			OPAL_PCI_SET_PE);
+OPAL_CALL(opal_pci_set_peltv,			OPAL_PCI_SET_PELTV);
+OPAL_CALL(opal_pci_set_mve,			OPAL_PCI_SET_MVE);
+OPAL_CALL(opal_pci_set_mve_enable,		OPAL_PCI_SET_MVE_ENABLE);
+OPAL_CALL(opal_pci_get_xive_reissue,		OPAL_PCI_GET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_reissue,		OPAL_PCI_SET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_pe,			OPAL_PCI_SET_XIVE_PE);
+OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
+OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
+OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
+OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
+OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
+OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
+OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
+OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
+OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
+OPAL_CALL(opal_pci_get_hub_diag_data,		OPAL_PCI_GET_HUB_DIAG_DATA);
+OPAL_CALL(opal_pci_get_phb_diag_data,		OPAL_PCI_GET_PHB_DIAG_DATA);
+OPAL_CALL(opal_pci_fence_phb,			OPAL_PCI_FENCE_PHB);
+OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
+OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
+OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
+OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
+OPAL_CALL(opal_get_dpo_status,			OPAL_GET_DPO_STATUS);
+OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
+OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
+OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
+OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
+OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
+OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
+OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
+OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
+OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
+OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
+OPAL_CALL(opal_reinit_cpus,			OPAL_REINIT_CPUS);
+OPAL_CALL(opal_read_elog,			OPAL_ELOG_READ);
+OPAL_CALL(opal_send_ack_elog,			OPAL_ELOG_ACK);
+OPAL_CALL(opal_get_elog_size,			OPAL_ELOG_SIZE);
+OPAL_CALL(opal_resend_pending_logs,		OPAL_ELOG_RESEND);
+OPAL_CALL(opal_write_elog,			OPAL_ELOG_WRITE);
+OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
+OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
+OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
+OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
+OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
+OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
+OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
+OPAL_CALL(opal_dump_read,			OPAL_DUMP_READ);
+OPAL_CALL(opal_dump_ack,			OPAL_DUMP_ACK);
+OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
+OPAL_CALL(opal_write_oppanel_async,		OPAL_WRITE_OPPANEL_ASYNC);
+OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
+OPAL_CALL(opal_dump_resend_notification,	OPAL_DUMP_RESEND);
+OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
+OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
+OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
+OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
+OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
+OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
+OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
+OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
+OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
+OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CAPI_MODE);
+OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
+OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
+OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
+OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
+OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
+OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
+OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
+OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
+OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
+OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
+OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
+OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
+OPAL_CALL(opal_get_device_tree,			OPAL_GET_DEVICE_TREE);
+OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
+OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
+OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
+OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
+OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
+OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
+OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
+OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
+OPAL_CALL(opal_nmmu_set_ptcr,			OPAL_NMMU_SET_PTCR);
+OPAL_CALL(opal_xive_reset,			OPAL_XIVE_RESET);
+OPAL_CALL(opal_xive_get_irq_info,		OPAL_XIVE_GET_IRQ_INFO);
+OPAL_CALL(opal_xive_get_irq_config,		OPAL_XIVE_GET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_set_irq_config,		OPAL_XIVE_SET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_get_queue_info,		OPAL_XIVE_GET_QUEUE_INFO);
+OPAL_CALL(opal_xive_set_queue_info,		OPAL_XIVE_SET_QUEUE_INFO);
+OPAL_CALL(opal_xive_donate_page,		OPAL_XIVE_DONATE_PAGE);
+OPAL_CALL(opal_xive_alloc_vp_block,		OPAL_XIVE_ALLOCATE_VP_BLOCK);
+OPAL_CALL(opal_xive_free_vp_block,		OPAL_XIVE_FREE_VP_BLOCK);
+OPAL_CALL(opal_xive_allocate_irq,		OPAL_XIVE_ALLOCATE_IRQ);
+OPAL_CALL(opal_xive_free_irq,			OPAL_XIVE_FREE_IRQ);
+OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
+OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
+OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
+OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
+OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
+OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
+OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
+OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
+OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
+OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);
+OPAL_CALL(opal_imc_counters_stop,		OPAL_IMC_COUNTERS_STOP);
+OPAL_CALL(opal_pci_set_p2p,			OPAL_PCI_SET_P2P);
+OPAL_CALL(opal_get_powercap,			OPAL_GET_POWERCAP);
+OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
+OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
+OPAL_CALL(opal_quiesce,				OPAL_QUIESCE);
+OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
+OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
+OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
+OPAL_CALL(opal_pci_get_pbcq_tunnel_bar,		OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
+OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,		OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
+OPAL_CALL(opal_sensor_read_u64,			OPAL_SENSOR_READ_U64);
+OPAL_CALL(opal_sensor_group_enable,		OPAL_SENSOR_GROUP_ENABLE);
+OPAL_CALL(opal_nx_coproc_init,			OPAL_NX_COPROC_INIT);
diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c
index acd3206dfae34..06628c71cef69 100644
--- a/arch/powerpc/platforms/powernv/opal-msglog.c
+++ b/arch/powerpc/platforms/powernv/opal-msglog.c
@@ -98,7 +98,7 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
 }
 
 static struct bin_attribute opal_msglog_attr = {
-	.attr = {.name = "msglog", .mode = 0444},
+	.attr = {.name = "msglog", .mode = 0400},
 	.read = opal_msglog_read
 };
 
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index f4875fe3f8ff2..7d2052d8af9d7 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -17,317 +17,51 @@
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
-	.section	".text"
-
-#ifdef CONFIG_TRACEPOINTS
-#ifdef CONFIG_JUMP_LABEL
-#define OPAL_BRANCH(LABEL)					\
-	ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key)
-#else
-
-	.section	".toc","aw"
-
-	.globl opal_tracepoint_refcount
-opal_tracepoint_refcount:
-	.8byte	0
-
-	.section	".text"
-
-/*
- * We branch around this in early init by using an unconditional cpu
- * feature.
- */
-#define OPAL_BRANCH(LABEL)					\
-BEGIN_FTR_SECTION;						\
-	b	1f;						\
-END_FTR_SECTION(0, 1);						\
-	ld	r11,opal_tracepoint_refcount@toc(r2);		\
-	cmpdi	r11,0;						\
-	bne-	LABEL;						\
-1:
-
-#endif
-
-#else
-#define OPAL_BRANCH(LABEL)
-#endif
+	.section ".text"
 
 /*
- * DO_OPAL_CALL assumes:
- * r0  = opal call token
- * r12 = msr
- * LR has been saved
+ * r3-r10		- OPAL call arguments
+ * STK_PARAM(R11)	- OPAL opcode
+ * STK_PARAM(R12)	- MSR to restore
  */
-#define DO_OPAL_CALL()			\
-	mfcr	r11;			\
-	stw	r11,8(r1);		\
-	li	r11,0;			\
-	ori	r11,r11,MSR_EE;		\
-	std	r12,PACASAVEDMSR(r13);	\
-	andc	r12,r12,r11;		\
-	mtmsrd	r12,1;			\
-	LOAD_REG_ADDR(r11,opal_return);	\
-	mtlr	r11;			\
-	li	r11,MSR_DR|MSR_IR|MSR_LE;\
-	andc	r12,r12,r11;		\
-	mtspr	SPRN_HSRR1,r12;		\
-	LOAD_REG_ADDR(r11,opal);	\
-	ld	r12,8(r11);		\
-	ld	r2,0(r11);		\
-	mtspr	SPRN_HSRR0,r12;		\
+_GLOBAL_TOC(__opal_call)
+	mflr	r0
+	std	r0,PPC_LR_STKOFF(r1)
+	ld	r12,STK_PARAM(R12)(r1)
+	li	r0,MSR_IR|MSR_DR|MSR_LE
+	andc	r12,r12,r0
+	LOAD_REG_ADDR(r11, opal_return)
+	mtlr	r11
+	LOAD_REG_ADDR(r11, opal)
+	ld	r2,0(r11)
+	ld	r11,8(r11)
+	mtspr	SPRN_HSRR0,r11
+	mtspr	SPRN_HSRR1,r12
+	/* set token to r0 */
+	ld	r0,STK_PARAM(R11)(r1)
 	hrfid
-
-#define OPAL_CALL(name, token)		\
- _GLOBAL_TOC(name);			\
-	mfmsr	r12;			\
-	mflr	r0;			\
-	andi.	r11,r12,MSR_IR|MSR_DR; 	\
-	std	r0,PPC_LR_STKOFF(r1);	\
-	li	r0,token;		\
-	beq	opal_real_call;         \
-	OPAL_BRANCH(opal_tracepoint_entry) \
-	DO_OPAL_CALL()
-
-
 opal_return:
 	/*
-	 * Fixup endian on OPAL return... we should be able to simplify
-	 * this by instead converting the below trampoline to a set of
-	 * bytes (always BE) since MSR:LE will end up fixed up as a side
-	 * effect of the rfid.
+	 * Restore MSR on OPAL return. The MSR is set to big-endian.
 	 */
-	FIXUP_ENDIAN_HV
-	ld	r2,PACATOC(r13);
-	lwz	r4,8(r1);
-	ld	r5,PPC_LR_STKOFF(r1);
-	ld	r6,PACASAVEDMSR(r13);
-	mtcr	r4;
-	mtspr	SPRN_HSRR0,r5;
-	mtspr	SPRN_HSRR1,r6;
-	hrfid
-
-opal_real_call:
-	mfcr	r11
-	stw	r11,8(r1)
-	/* Set opal return address */
-	LOAD_REG_ADDR(r11, opal_return_realmode)
-	mtlr	r11
-	li	r11,MSR_LE
-	andc	r12,r12,r11
-	mtspr	SPRN_HSRR1,r12
-	LOAD_REG_ADDR(r11,opal)
-	ld	r12,8(r11)
-	ld	r2,0(r11)
-	mtspr	SPRN_HSRR0,r12
-	hrfid
-
-opal_return_realmode:
-	FIXUP_ENDIAN_HV
-	ld	r2,PACATOC(r13);
-	lwz	r11,8(r1);
-	ld	r12,PPC_LR_STKOFF(r1)
-	mtcr	r11;
-	mtlr	r12
-	blr
-
-#ifdef CONFIG_TRACEPOINTS
-opal_tracepoint_entry:
-	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r0,STK_REG(R23)(r1)
-	std	r3,STK_REG(R24)(r1)
-	std	r4,STK_REG(R25)(r1)
-	std	r5,STK_REG(R26)(r1)
-	std	r6,STK_REG(R27)(r1)
-	std	r7,STK_REG(R28)(r1)
-	std	r8,STK_REG(R29)(r1)
-	std	r9,STK_REG(R30)(r1)
-	std	r10,STK_REG(R31)(r1)
-	mr	r3,r0
-	addi	r4,r1,STK_REG(R24)
-	bl	__trace_opal_entry
-	ld	r0,STK_REG(R23)(r1)
-	ld	r3,STK_REG(R24)(r1)
-	ld	r4,STK_REG(R25)(r1)
-	ld	r5,STK_REG(R26)(r1)
-	ld	r6,STK_REG(R27)(r1)
-	ld	r7,STK_REG(R28)(r1)
-	ld	r8,STK_REG(R29)(r1)
-	ld	r9,STK_REG(R30)(r1)
-	ld	r10,STK_REG(R31)(r1)
-
-	/* setup LR so we return via tracepoint_return */
-	LOAD_REG_ADDR(r11,opal_tracepoint_return)
-	std	r11,16(r1)
-
-	mfmsr	r12
-	DO_OPAL_CALL()
-
-opal_tracepoint_return:
-	std	r3,STK_REG(R31)(r1)
-	mr	r4,r3
-	ld	r3,STK_REG(R23)(r1)
-	bl	__trace_opal_exit
-	ld	r3,STK_REG(R31)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-	ld	r0,16(r1)
+#ifdef __BIG_ENDIAN__
+	ld	r11,STK_PARAM(R12)(r1)
+	mtmsrd	r11
+#else
+	/* Endian can only be switched with rfi, must byte reverse MSR load */
+	.short 0x4039	 /* li r10,STK_PARAM(R12)		*/
+	.byte (STK_PARAM(R12) >> 8) & 0xff
+	.byte STK_PARAM(R12) & 0xff
+
+	.long 0x280c6a7d /* ldbrx r11,r10,r1			*/
+	.long 0x05009f42 /* bcl 20,31,$+4			*/
+	.long 0xa602487d /* mflr r10				*/
+	.long 0x14004a39 /* addi r10,r10,20			*/
+	.long 0xa64b5a7d /* mthsrr0 r10				*/
+	.long 0xa64b7b7d /* mthsrr1 r11				*/
+	.long 0x2402004c /* hrfid				*/
+#endif
+	ld	r2,PACATOC(r13)
+	ld	r0,PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
-#endif
-
-
-OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
-OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
-OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
-OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
-OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
-OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
-OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
-OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
-OPAL_CALL(opal_cec_reboot2,			OPAL_CEC_REBOOT2);
-OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
-OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
-OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
-OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
-OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
-OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
-OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
-OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
-OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
-OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
-OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
-OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
-OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
-OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
-OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
-OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
-OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
-OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
-OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
-OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
-OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
-OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
-OPAL_CALL(opal_pci_map_pe_mmio_window,		OPAL_PCI_MAP_PE_MMIO_WINDOW);
-OPAL_CALL(opal_pci_set_phb_table_memory,	OPAL_PCI_SET_PHB_TABLE_MEMORY);
-OPAL_CALL(opal_pci_set_pe,			OPAL_PCI_SET_PE);
-OPAL_CALL(opal_pci_set_peltv,			OPAL_PCI_SET_PELTV);
-OPAL_CALL(opal_pci_set_mve,			OPAL_PCI_SET_MVE);
-OPAL_CALL(opal_pci_set_mve_enable,		OPAL_PCI_SET_MVE_ENABLE);
-OPAL_CALL(opal_pci_get_xive_reissue,		OPAL_PCI_GET_XIVE_REISSUE);
-OPAL_CALL(opal_pci_set_xive_reissue,		OPAL_PCI_SET_XIVE_REISSUE);
-OPAL_CALL(opal_pci_set_xive_pe,			OPAL_PCI_SET_XIVE_PE);
-OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
-OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
-OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
-OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
-OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
-OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
-OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
-OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
-OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
-OPAL_CALL(opal_pci_get_hub_diag_data,		OPAL_PCI_GET_HUB_DIAG_DATA);
-OPAL_CALL(opal_pci_get_phb_diag_data,		OPAL_PCI_GET_PHB_DIAG_DATA);
-OPAL_CALL(opal_pci_fence_phb,			OPAL_PCI_FENCE_PHB);
-OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
-OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
-OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
-OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
-OPAL_CALL(opal_get_dpo_status,			OPAL_GET_DPO_STATUS);
-OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
-OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
-OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
-OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
-OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
-OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
-OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
-OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
-OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
-OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
-OPAL_CALL(opal_reinit_cpus,			OPAL_REINIT_CPUS);
-OPAL_CALL(opal_read_elog,			OPAL_ELOG_READ);
-OPAL_CALL(opal_send_ack_elog,			OPAL_ELOG_ACK);
-OPAL_CALL(opal_get_elog_size,			OPAL_ELOG_SIZE);
-OPAL_CALL(opal_resend_pending_logs,		OPAL_ELOG_RESEND);
-OPAL_CALL(opal_write_elog,			OPAL_ELOG_WRITE);
-OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
-OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
-OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
-OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
-OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
-OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
-OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
-OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
-OPAL_CALL(opal_dump_read,			OPAL_DUMP_READ);
-OPAL_CALL(opal_dump_ack,			OPAL_DUMP_ACK);
-OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
-OPAL_CALL(opal_write_oppanel_async,		OPAL_WRITE_OPPANEL_ASYNC);
-OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
-OPAL_CALL(opal_dump_resend_notification,	OPAL_DUMP_RESEND);
-OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
-OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
-OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
-OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
-OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
-OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
-OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
-OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
-OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
-OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CAPI_MODE);
-OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
-OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
-OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
-OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
-OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
-OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
-OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
-OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
-OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
-OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
-OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
-OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
-OPAL_CALL(opal_get_device_tree,			OPAL_GET_DEVICE_TREE);
-OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
-OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
-OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
-OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
-OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
-OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
-OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
-OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
-OPAL_CALL(opal_nmmu_set_ptcr,			OPAL_NMMU_SET_PTCR);
-OPAL_CALL(opal_xive_reset,			OPAL_XIVE_RESET);
-OPAL_CALL(opal_xive_get_irq_info,		OPAL_XIVE_GET_IRQ_INFO);
-OPAL_CALL(opal_xive_get_irq_config,		OPAL_XIVE_GET_IRQ_CONFIG);
-OPAL_CALL(opal_xive_set_irq_config,		OPAL_XIVE_SET_IRQ_CONFIG);
-OPAL_CALL(opal_xive_get_queue_info,		OPAL_XIVE_GET_QUEUE_INFO);
-OPAL_CALL(opal_xive_set_queue_info,		OPAL_XIVE_SET_QUEUE_INFO);
-OPAL_CALL(opal_xive_donate_page,		OPAL_XIVE_DONATE_PAGE);
-OPAL_CALL(opal_xive_alloc_vp_block,		OPAL_XIVE_ALLOCATE_VP_BLOCK);
-OPAL_CALL(opal_xive_free_vp_block,		OPAL_XIVE_FREE_VP_BLOCK);
-OPAL_CALL(opal_xive_allocate_irq,		OPAL_XIVE_ALLOCATE_IRQ);
-OPAL_CALL(opal_xive_free_irq,			OPAL_XIVE_FREE_IRQ);
-OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
-OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
-OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
-OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
-OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
-OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
-OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
-OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
-OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
-OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);
-OPAL_CALL(opal_imc_counters_stop,		OPAL_IMC_COUNTERS_STOP);
-OPAL_CALL(opal_pci_set_p2p,			OPAL_PCI_SET_P2P);
-OPAL_CALL(opal_get_powercap,			OPAL_GET_POWERCAP);
-OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
-OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
-OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
-OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
-OPAL_CALL(opal_quiesce,				OPAL_QUIESCE);
-OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
-OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
-OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
-OPAL_CALL(opal_pci_get_pbcq_tunnel_bar,		OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
-OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,		OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
-OPAL_CALL(opal_sensor_read_u64,			OPAL_SENSOR_READ_U64);
-OPAL_CALL(opal_sensor_group_enable,		OPAL_SENSOR_GROUP_ENABLE);
-OPAL_CALL(opal_nx_coproc_init,			OPAL_NX_COPROC_INIT);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 79586f1275213..2ca3ba95f8aaf 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -26,7 +26,6 @@
 #include <linux/memblock.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
-#include <linux/printk.h>
 #include <linux/kmsg_dump.h>
 #include <linux/console.h>
 #include <linux/sched/debug.h>
@@ -587,7 +586,7 @@ int opal_machine_check(struct pt_regs *regs)
 		       evt.version);
 		return 0;
 	}
-	machine_check_print_event_info(&evt, user_mode(regs));
+	machine_check_print_event_info(&evt, user_mode(regs), false);
 
 	if (opal_recover_mce(regs, &evt))
 		return 1;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index 697449afb3f77..e28f03e1eb5eb 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -313,7 +313,6 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 			page_shift);
 	tbl->it_level_size = 1ULL << (level_shift - 3);
 	tbl->it_indirect_levels = levels - 1;
-	tbl->it_allocated_size = total_allocated;
 	tbl->it_userspace = uas;
 	tbl->it_nid = nid;
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 145373f0e5dc0..fa6af52b5219f 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1748,7 +1748,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+	pdev->dev.archdata.dma_offset = pe->tce_bypass_base;
 	set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
 	/*
 	 * Note: iommu_add_device() will fail here as
@@ -1758,31 +1758,6 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 	 */
 }
 
-static bool pnv_pci_ioda_pe_single_vendor(struct pnv_ioda_pe *pe)
-{
-	unsigned short vendor = 0;
-	struct pci_dev *pdev;
-
-	if (pe->device_count == 1)
-		return true;
-
-	/* pe->pdev should be set if it's a single device, pe->pbus if not */
-	if (!pe->pbus)
-		return true;
-
-	list_for_each_entry(pdev, &pe->pbus->devices, bus_list) {
-		if (!vendor) {
-			vendor = pdev->vendor;
-			continue;
-		}
-
-		if (pdev->vendor != vendor)
-			return false;
-	}
-
-	return true;
-}
-
 /*
  * Reconfigure TVE#0 to be usable as 64-bit DMA space.
  *
@@ -1852,88 +1827,45 @@ err:
 	return -EIO;
 }
 
-static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
+		u64 dma_mask)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
-	uint64_t top;
-	bool bypass = false;
-	s64 rc;
 
 	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
 		return -ENODEV;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	if (pe->tce_bypass_enabled) {
-		top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
-		bypass = (dma_mask >= top);
+		u64 top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+		if (dma_mask >= top)
+			return true;
 	}
 
-	if (bypass) {
-		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
-		set_dma_ops(&pdev->dev, &dma_nommu_ops);
-	} else {
-		/*
-		 * If the device can't set the TCE bypass bit but still wants
-		 * to access 4GB or more, on PHB3 we can reconfigure TVE#0 to
-		 * bypass the 32-bit region and be usable for 64-bit DMAs.
-		 * The device needs to be able to address all of this space.
-		 */
-		if (dma_mask >> 32 &&
-		    dma_mask > (memory_hotplug_max() + (1ULL << 32)) &&
-		    pnv_pci_ioda_pe_single_vendor(pe) &&
-		    phb->model == PNV_PHB_MODEL_PHB3) {
-			/* Configure the bypass mode */
-			rc = pnv_pci_ioda_dma_64bit_bypass(pe);
-			if (rc)
-				return rc;
-			/* 4GB offset bypasses 32-bit space */
-			set_dma_offset(&pdev->dev, (1ULL << 32));
-			set_dma_ops(&pdev->dev, &dma_nommu_ops);
-		} else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) {
-			/*
-			 * Fail the request if a DMA mask between 32 and 64 bits
-			 * was requested but couldn't be fulfilled. Ideally we
-			 * would do this for 64-bits but historically we have
-			 * always fallen back to 32-bits.
-			 */
-			return -ENOMEM;
-		} else {
-			dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
-			set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		}
+	/*
+	 * If the device can't set the TCE bypass bit but still wants
+	 * to access 4GB or more, on PHB3 we can reconfigure TVE#0 to
+	 * bypass the 32-bit region and be usable for 64-bit DMAs.
+	 * The device needs to be able to address all of this space.
+	 */
+	if (dma_mask >> 32 &&
+	    dma_mask > (memory_hotplug_max() + (1ULL << 32)) &&
+	    /* pe->pdev should be set if it's a single device, pe->pbus if not */
+	    (pe->device_count == 1 || !pe->pbus) &&
+	    phb->model == PNV_PHB_MODEL_PHB3) {
+		/* Configure the bypass mode */
+		s64 rc = pnv_pci_ioda_dma_64bit_bypass(pe);
+		if (rc)
+			return rc;
+		/* 4GB offset bypasses 32-bit space */
+		pdev->dev.archdata.dma_offset = (1ULL << 32);
+		return true;
 	}
-	*pdev->dev.dma_mask = dma_mask;
 
-	/* Update peer npu devices */
-	pnv_npu_try_dma_set_bypass(pdev, bypass);
-
-	return 0;
-}
-
-static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-	struct pnv_ioda_pe *pe;
-	u64 end, mask;
-
-	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-		return 0;
-
-	pe = &phb->ioda.pe_array[pdn->pe_number];
-	if (!pe->tce_bypass_enabled)
-		return __dma_get_required_mask(&pdev->dev);
-
-
-	end = pe->tce_bypass_base + memblock_end_of_DRAM();
-	mask = 1ULL << (fls64(end) - 1);
-	mask += mask - 1;
-
-	return mask;
+	return false;
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
@@ -1942,7 +1874,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
-		set_dma_offset(&dev->dev, pe->tce_bypass_base);
+		dev->dev.archdata.dma_offset = pe->tce_bypass_base;
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
@@ -2594,8 +2526,13 @@ static long pnv_pci_ioda2_create_table_userspace(
 		int num, __u32 page_shift, __u64 window_size, __u32 levels,
 		struct iommu_table **ptbl)
 {
-	return pnv_pci_ioda2_create_table(table_group,
+	long ret = pnv_pci_ioda2_create_table(table_group,
 			num, page_shift, window_size, levels, true, ptbl);
+
+	if (!ret)
+		(*ptbl)->it_allocated_size = pnv_pci_ioda2_get_table_size(
+				page_shift, window_size, levels);
+	return ret;
 }
 
 static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
@@ -3661,6 +3598,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.dma_bus_setup		= pnv_pci_dma_bus_setup,
+	.iommu_bypass_supported	= pnv_pci_ioda_iommu_bypass_supported,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
 	.enable_device_hook	= pnv_pci_enable_device_hook,
@@ -3668,19 +3606,9 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.window_alignment	= pnv_pci_window_alignment,
 	.setup_bridge		= pnv_pci_setup_bridge,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.dma_set_mask		= pnv_pci_ioda_dma_set_mask,
-	.dma_get_required_mask	= pnv_pci_ioda_dma_get_required_mask,
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
-static int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask)
-{
-	dev_err_once(&npdev->dev,
-			"%s operation unsupported for NVLink devices\n",
-			__func__);
-	return -EPERM;
-}
-
 static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
@@ -3688,7 +3616,6 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.enable_device_hook	= pnv_pci_enable_device_hook,
 	.window_alignment	= pnv_pci_window_alignment,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.dma_set_mask		= pnv_npu_dma_set_mask,
 	.shutdown		= pnv_pci_ioda_shutdown,
 	.disable_device		= pnv_npu_disable_device,
 };
@@ -3946,9 +3873,12 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 * shutdown PCI devices correctly. We already got IODA table
 	 * cleaned out. So we have to issue PHB reset to stop all PCI
 	 * transactions from previous kernel. The ppc_pci_reset_phbs
-	 * kernel parameter will force this reset too.
+	 * kernel parameter will force this reset too. Additionally,
+	 * if the IODA reset above failed then use a bigger hammer.
+	 * This can happen if we get a PHB fatal error in very early
+	 * boot.
 	 */
-	if (is_kdump_kernel() || pci_reset_phbs) {
+	if (is_kdump_kernel() || pci_reset_phbs || rc) {
 		pr_info("  Issue PHB reset ...\n");
 		pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
 		pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 0d354e19ef926..db09c7022635b 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -39,6 +39,7 @@
 #include <asm/cpuidle.h>
 #include <asm/kexec.h>
 #include <asm/reg.h>
+#include <asm/powernv.h>
 
 #include "powernv.h"
 
@@ -153,6 +154,7 @@ static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
 	unsigned long srr1, wmask;
+	u64 lpcr_val;
 
 	/* Standard hot unplug procedure */
 	/*
@@ -174,6 +176,19 @@ static void pnv_smp_cpu_kill_self(void)
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		wmask = SRR1_WAKEMASK_P8;
 
+	/*
+	 * We don't want to take decrementer interrupts while we are
+	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
+	 * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in.
+	 *
+	 * If the CPU gets woken up by a special wakeup, ensure that
+	 * the SLW engine sets LPCR with decrementer bit cleared, else
+	 * the CPU will come back to the kernel due to a spurious
+	 * wakeup.
+	 */
+	lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
+	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
+
 	while (!generic_check_cpu_restart(cpu)) {
 		/*
 		 * Clear IPI flag, since we don't handle IPIs while
@@ -246,6 +261,16 @@ static void pnv_smp_cpu_kill_self(void)
 
 	}
 
+	/*
+	 * Re-enable decrementer interrupts in LPCR.
+	 *
+	 * Further, we want stop states to be woken up by decrementer
+	 * for non-hotplug cases. So program the LPCR via stop api as
+	 * well.
+	 */
+	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
+	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
+
 	DBG("CPU%d coming online...\n", cpu);
 }
 
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e7075aaff1bb6..59587b75493db 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -354,9 +354,7 @@ static int ps3_setup_storage_dev(const struct ps3_repository_device *repo,
 		 repo->dev_index, repo->dev_type, port, blk_size, num_blocks,
 		 num_regions);
 
-	p = kzalloc(sizeof(struct ps3_storage_device) +
-		    num_regions * sizeof(struct ps3_storage_region),
-		    GFP_KERNEL);
+	p = kzalloc(struct_size(p, regions, num_regions), GFP_KERNEL);
 	if (!p) {
 		result = -ENOMEM;
 		goto fail_malloc;
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index f5387ad822798..4d65c53800206 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -205,11 +205,11 @@ static const struct os_area_db_id os_area_db_id_rtc_diff = {
  *  3) The number of seconds from 1970 to 2000.
  */
 
-struct saved_params {
+static struct saved_params {
 	unsigned int valid;
 	s64 rtc_diff;
 	unsigned int av_multi_out;
-} static saved_params;
+} saved_params;
 
 static struct property property_rtc_diff = {
 	.name = "linux,rtc_diff",
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 5cc35d6b94b6c..7c227e784247c 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -37,12 +37,12 @@ static struct device ps3_system_bus = {
 };
 
 /* FIXME: need device usage counters! */
-struct {
+static struct {
 	struct mutex mutex;
 	int sb_11; /* usb 0 */
 	int sb_12; /* usb 0 */
 	int gpu;
-} static usage_hack;
+} usage_hack;
 
 static int ps3_is_device(struct ps3_system_bus_device *dev, u64 bus_id,
 			 u64 dev_id)
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 2f8e62163602b..97feb6e79f1a7 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -802,6 +802,25 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add)
 	return rc;
 }
 
+int dlpar_cpu_readd(int cpu)
+{
+	struct device_node *dn;
+	struct device *dev;
+	u32 drc_index;
+	int rc;
+
+	dev = get_cpu_device(cpu);
+	dn = dev->of_node;
+
+	rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index);
+
+	rc = dlpar_cpu_remove_by_index(drc_index);
+	if (!rc)
+		rc = dlpar_cpu_add(drc_index);
+
+	return rc;
+}
+
 int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 {
 	u32 count, drc_index;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 8fc8fe0b98485..36eb1ddbac695 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -978,7 +978,7 @@ static phys_addr_t ddw_memory_hotplug_max(void)
  * pdn: the parent pe node with the ibm,dma_window property
  * Future: also check if we can remap the base window for our base page size
  *
- * returns the dma offset for use by dma_set_mask
+ * returns the dma offset for use by the direct mapped DMA code.
  */
 static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
@@ -1198,87 +1198,37 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	iommu_add_device(pci->table_group, &dev->dev);
 }
 
-static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
+static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 {
-	bool ddw_enabled = false;
-	struct device_node *pdn, *dn;
-	struct pci_dev *pdev;
+	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
 	const __be32 *dma_window = NULL;
-	u64 dma_offset;
-
-	if (!dev->dma_mask)
-		return -EIO;
-
-	if (!dev_is_pci(dev))
-		goto check_mask;
-
-	pdev = to_pci_dev(dev);
 
 	/* only attempt to use a new window if 64-bit DMA is requested */
-	if (!disable_ddw && dma_mask == DMA_BIT_MASK(64)) {
-		dn = pci_device_to_OF_node(pdev);
-		dev_dbg(dev, "node is %pOF\n", dn);
+	if (dma_mask < DMA_BIT_MASK(64))
+		return false;
 
-		/*
-		 * the device tree might contain the dma-window properties
-		 * per-device and not necessarily for the bus. So we need to
-		 * search upwards in the tree until we either hit a dma-window
-		 * property, OR find a parent with a table already allocated.
-		 */
-		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
-				pdn = pdn->parent) {
-			dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
-			if (dma_window)
-				break;
-		}
-		if (pdn && PCI_DN(pdn)) {
-			dma_offset = enable_ddw(pdev, pdn);
-			if (dma_offset != 0) {
-				dev_info(dev, "Using 64-bit direct DMA at offset %llx\n", dma_offset);
-				set_dma_offset(dev, dma_offset);
-				set_dma_ops(dev, &dma_nommu_ops);
-				ddw_enabled = true;
-			}
-		}
-	}
+	dev_dbg(&pdev->dev, "node is %pOF\n", dn);
 
-	/* fall back on iommu ops */
-	if (!ddw_enabled && get_dma_ops(dev) != &dma_iommu_ops) {
-		dev_info(dev, "Restoring 32-bit DMA via iommu\n");
-		set_dma_ops(dev, &dma_iommu_ops);
+	/*
+	 * the device tree might contain the dma-window properties
+	 * per-device and not necessarily for the bus. So we need to
+	 * search upwards in the tree until we either hit a dma-window
+	 * property, OR find a parent with a table already allocated.
+	 */
+	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
+			pdn = pdn->parent) {
+		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
+		if (dma_window)
+			break;
 	}
 
-check_mask:
-	if (!dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-
-static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	if (!disable_ddw && dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct device_node *dn;
-
-		dn = pci_device_to_OF_node(pdev);
-
-		/* search upwards for ibm,dma-window */
-		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->table_group;
-				dn = dn->parent)
-			if (of_get_property(dn, "ibm,dma-window", NULL))
-				break;
-		/* if there is a ibm,ddw-applicable property require 64 bits */
-		if (dn && PCI_DN(dn) &&
-				of_get_property(dn, "ibm,ddw-applicable", NULL))
-			return DMA_BIT_MASK(64);
+	if (pdn && PCI_DN(pdn)) {
+		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
+		if (pdev->dev.archdata.dma_offset)
+			return true;
 	}
 
-	return dma_iommu_ops.get_required_mask(dev);
+	return false;
 }
 
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
@@ -1373,8 +1323,9 @@ void iommu_init_early_pSeries(void)
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
-		ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
-		ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
+		if (!disable_ddw)
+			pseries_pci_controller_ops.iommu_bypass_supported =
+				iommu_bypass_supported_pSeriesLP;
 	} else {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 794487313cc8d..e73c7e30efe63 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -475,6 +475,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 		splpar_dispatch_data(m);
 
 		seq_printf(m, "purr=%ld\n", get_purr());
+		seq_printf(m, "tbr=%ld\n", mftb());
 	} else {		/* non SPLPAR case */
 
 		seq_printf(m, "system_active_processors=%d\n",
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 1fad4649735bd..141795275ccb1 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -492,7 +492,9 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
 		return NULL;
 	}
 
-	ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
+	ret = iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
+				    dma_handle, dev->coherent_dma_mask, flag,
+				    dev_to_node(dev));
 	if (unlikely(ret == NULL)) {
 		vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 		atomic_inc(&viodev->cmo.allocs_failed);
@@ -507,8 +509,7 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 
-	dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
-
+	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
 
@@ -518,22 +519,22 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
                                          unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	dma_addr_t ret = DMA_MAPPING_ERROR;
 
-	tbl = get_iommu_table_base(dev);
-	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
-
-	ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs);
-	if (unlikely(dma_mapping_error(dev, ret))) {
-		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
-		atomic_inc(&viodev->cmo.allocs_failed);
-	}
-
+	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))))
+		goto out_fail;
+	ret = iommu_map_page(dev, tbl, page, offset, size, device_to_mask(dev),
+			direction, attrs);
+	if (unlikely(ret == DMA_MAPPING_ERROR))
+		goto out_deallocate;
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return DMA_MAPPING_ERROR;
 }
 
 static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
@@ -542,11 +543,9 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				     unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
-
-	tbl = get_iommu_table_base(dev);
-	dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs);
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 
+	iommu_unmap_page(tbl, dma_handle, size, direction, attrs);
 	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 }
 
@@ -555,34 +554,32 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
                                 unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	int ret, count;
 	size_t alloc_size = 0;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
-	if (vio_cmo_alloc(viodev, alloc_size)) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return 0;
-	}
-
-	ret = dma_iommu_ops.map_sg(dev, sglist, nelems, direction, attrs);
-
-	if (unlikely(!ret)) {
-		vio_cmo_dealloc(viodev, alloc_size);
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
+	if (vio_cmo_alloc(viodev, alloc_size))
+		goto out_fail;
+	ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, device_to_mask(dev),
+			direction, attrs);
+	if (unlikely(!ret))
+		goto out_deallocate;
 
 	for_each_sg(sglist, sgl, ret, count)
 		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
-
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, alloc_size);
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return 0;
 }
 
 static void vio_dma_iommu_unmap_sg(struct device *dev,
@@ -591,40 +588,27 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 		unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	size_t alloc_size = 0;
 	int count;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 
-	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
-
+	ppc_iommu_unmap_sg(tbl, sglist, nelems, direction, attrs);
 	vio_cmo_dealloc(viodev, alloc_size);
 }
 
-static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
-{
-        return dma_iommu_ops.dma_supported(dev, mask);
-}
-
-static u64 vio_dma_get_required_mask(struct device *dev)
-{
-        return dma_iommu_ops.get_required_mask(dev);
-}
-
 static const struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc             = vio_dma_iommu_alloc_coherent,
 	.free              = vio_dma_iommu_free_coherent,
-	.mmap		   = dma_nommu_mmap_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
 	.map_page          = vio_dma_iommu_map_page,
 	.unmap_page        = vio_dma_iommu_unmap_page,
-	.dma_supported     = vio_dma_iommu_dma_supported,
-	.get_required_mask = vio_dma_get_required_mask,
+	.dma_supported     = dma_iommu_dma_supported,
+	.get_required_mask = dma_iommu_get_required_mask,
 };
 
 /**
@@ -1715,3 +1699,10 @@ int vio_disable_interrupts(struct vio_dev *dev)
 }
 EXPORT_SYMBOL(vio_disable_interrupts);
 #endif /* CONFIG_PPC_PSERIES */
+
+static int __init vio_init(void)
+{
+	dma_debug_add_bus(&vio_bus_type);
+	return 0;
+}
+fs_initcall(vio_init);