Merge tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for the kexec_file_load() syscall, which is a prereq for
     secure and trusted boot.

   - Prevent kernel execution of userspace on P9 Radix (similar to
     SMEP/PXN).

   - Sort the exception tables at build time, to save time at boot, and
     store them as relative offsets to save space in the kernel image &
     memory.

   - Allow building the kernel with thin archives, which should allow us
     to build an allyesconfig once some other fixes land.

   - Build fixes to allow us to correctly rebuild when changing the
     kernel endian from big to little or vice versa.

   - Plumbing so that we can avoid doing a full mm TLB flush on P9
     Radix.

   - Initial stack protector support (-fstack-protector).

   - Support for dumping the radix (aka. Linux) and hash page tables via
     debugfs.

   - Fix an oops in cxl coredump generation when cxl_get_fd() is used.

   - Freescale updates from Scott: "Highlights include 8xx hugepage
     support, qbman fixes/cleanup, device tree updates, and some misc
     cleanup."

   - Many and varied fixes and minor enhancements as always.

  Thanks to:
    Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anshuman
    Khandual, Anton Blanchard, Balbir Singh, Bartlomiej Zolnierkiewicz,
    Christophe Jaillet, Christophe Leroy, Denis Kirjanov, Elimar
    Riesebieter, Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff
    Levand, Jack Miller, Johan Hovold, Lars-Peter Clausen, Libin,
    Madhavan Srinivasan, Michael Neuling, Nathan Fontenot, Naveen N.
    Rao, Nicholas Piggin, Pan Xinhui, Peter Senna Tschudin, Rashmica
    Gupta, Rui Teng, Russell Currey, Scott Wood, Simon Guo, Suraj
    Jitindar Singh, Thiago Jung Bauermann, Tobias Klauser, Vaibhav Jain"

[ And thanks to Michael, who took time off from a new baby to get this
  pull request done.   - Linus ]

* tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (174 commits)
  powerpc/fsl/dts: add FMan node for t1042d4rdb
  powerpc/fsl/dts: add sg_2500_aqr105_phy4 alias on t1024rdb
  powerpc/fsl/dts: add QMan and BMan nodes on t1024
  powerpc/fsl/dts: add QMan and BMan nodes on t1023
  soc/fsl/qman: test: use DEFINE_SPINLOCK()
  powerpc/fsl-lbc: use DEFINE_SPINLOCK()
  powerpc/8xx: Implement support of hugepages
  powerpc: get hugetlbpage handling more generic
  powerpc: port 64 bits pgtable_cache to 32 bits
  powerpc/boot: Request no dynamic linker for boot wrapper
  soc/fsl/bman: Use resource_size instead of computation
  soc/fsl/qe: use builtin_platform_driver
  powerpc/fsl_pmc: use builtin_platform_driver
  powerpc/83xx/suspend: use builtin_platform_driver
  powerpc/ftrace: Fix the comments for ftrace_modify_code
  powerpc/perf: macros for power9 format encoding
  powerpc/perf: power9 raw event format encoding
  powerpc/perf: update attribute_group data structure
  powerpc/perf: factor out the event format field
  powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown
  ...

31 files changed, 1462 insertions, 2742 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1925341dbb9c..a3a6047fd395 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -19,6 +19,10 @@ CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 
+# -fstack-protector triggers protection checks in this code,
+# but it is being used too early to link to meaningful stack_chk logic.
+CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector)
+
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
 CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
@@ -58,8 +62,6 @@ obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
 obj-$(CONFIG_PPC_RTAS_DAEMON)	+= rtasd.o
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
-obj-$(CONFIG_IBMVIO)		+= vio.o
-obj-$(CONFIG_IBMEBUS)           += ibmebus.o
 obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
 				  eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
@@ -107,8 +109,9 @@ pci64-$(CONFIG_PPC64)		+= pci_dn.o pci-hotplug.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(BITS).o $(pci64-y) \
 				   pci-common.o pci_of_scan.o
 obj-$(CONFIG_PCI_MSI)		+= msi.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o crash.o \
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o crash.o \
 				   machine_kexec_$(BITS).o
+obj-$(CONFIG_KEXEC_FILE)	+= machine_kexec_file_$(BITS).o kexec_elf_$(BITS).o
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
@@ -128,7 +131,7 @@ obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM)	+= tm.o
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
 obj-$(CONFIG_PPC32)		+= $(obj32-y)
 
-ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
+ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE),)
 obj-y				+= ppc_save_regs.o
 endif
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 195a9fc8f81c..0601e6a7297c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -91,6 +91,9 @@ int main(void)
 	DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp));
 #endif
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+	DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary));
+#endif
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index f3e1f5d29dce..917188615bf5 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -96,6 +96,7 @@ _GLOBAL(__setup_cpu_power9)
 	mtlr	r11
 	beqlr
 	li	r0,0
+	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
 	mfspr	r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE)
@@ -116,6 +117,7 @@ _GLOBAL(__restore_cpu_power9)
 	mtlr	r11
 	beqlr
 	li	r0,0
+	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
 	mfspr   r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index f25731627d7f..8180bfd7ab93 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -372,7 +372,7 @@ static int eeh_phb_check_failure(struct eeh_pe *pe)
 	/* Find the PHB PE */
 	phb_pe = eeh_phb_pe_get(pe->phb);
 	if (!phb_pe) {
-		pr_warn("%s Can't find PE for PHB#%d\n",
+		pr_warn("%s Can't find PE for PHB#%x\n",
 			__func__, pe->phb->global_number);
 		return -EEXIST;
 	}
@@ -664,7 +664,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 	rc = eeh_ops->set_option(pe, function);
 	if (rc)
 		pr_warn("%s: Unexpected state change %d on "
-			"PHB#%d-PE#%x, err=%d\n",
+			"PHB#%x-PE#%x, err=%d\n",
 			__func__, function, pe->phb->global_number,
 			pe->addr, rc);
 
@@ -808,76 +808,67 @@ static void *eeh_set_dev_freset(void *data, void *flag)
 }
 
 /**
- * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second
+ * eeh_pe_reset_full - Complete a full reset process on the indicated PE
  * @pe: EEH PE
  *
- * Assert the PCI #RST line for 1/4 second.
+ * This function executes a full reset procedure on a PE, including setting
+ * the appropriate flags, performing a fundamental or hot reset, and then
+ * deactivating the reset status.  It is designed to be used within the EEH
+ * subsystem, as opposed to eeh_pe_reset which is exported to drivers and
+ * only performs a single operation at a time.
+ *
+ * This function will attempt to reset a PE three times before failing.
  */
-static void eeh_reset_pe_once(struct eeh_pe *pe)
+int eeh_pe_reset_full(struct eeh_pe *pe)
 {
+	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+	int reset_state = (EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+	int type = EEH_RESET_HOT;
 	unsigned int freset = 0;
+	int i, state, ret;
 
-	/* Determine type of EEH reset required for
-	 * Partitionable Endpoint, a hot-reset (1)
-	 * or a fundamental reset (3).
-	 * A fundamental reset required by any device under
-	 * Partitionable Endpoint trumps hot-reset.
+	/*
+	 * Determine the type of reset to perform - hot or fundamental.
+	 * Hot reset is the default operation, unless any device under the
+	 * PE requires a fundamental reset.
 	 */
 	eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset);
 
 	if (freset)
-		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
-	else
-		eeh_ops->reset(pe, EEH_RESET_HOT);
-
-	eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
-}
-
-/**
- * eeh_reset_pe - Reset the indicated PE
- * @pe: EEH PE
- *
- * This routine should be called to reset indicated device, including
- * PE. A PE might include multiple PCI devices and sometimes PCI bridges
- * might be involved as well.
- */
-int eeh_reset_pe(struct eeh_pe *pe)
-{
-	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
-	int i, state, ret;
+		type = EEH_RESET_FUNDAMENTAL;
 
-	/* Mark as reset and block config space */
-	eeh_pe_state_mark(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+	/* Mark the PE as in reset state and block config space accesses */
+	eeh_pe_state_mark(pe, reset_state);
 
-	/* Take three shots at resetting the bus */
+	/* Make three attempts at resetting the bus */
 	for (i = 0; i < 3; i++) {
-		eeh_reset_pe_once(pe);
+		ret = eeh_pe_reset(pe, type);
+		if (ret)
+			break;
 
-		/*
-		 * EEH_PE_ISOLATED is expected to be removed after
-		 * BAR restore.
-		 */
+		ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE);
+		if (ret)
+			break;
+
+		/* Wait until the PE is in a functioning state */
 		state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if ((state & flags) == flags) {
-			ret = 0;
-			goto out;
-		}
+		if ((state & active_flags) == active_flags)
+			break;
 
 		if (state < 0) {
-			pr_warn("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+			pr_warn("%s: Unrecoverable slot failure on PHB#%x-PE#%x",
 				__func__, pe->phb->global_number, pe->addr);
 			ret = -ENOTRECOVERABLE;
-			goto out;
+			break;
 		}
 
-		/* We might run out of credits */
+		/* Set error in case this is our last attempt */
 		ret = -EIO;
 		pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n",
 			__func__, state, pe->phb->global_number, pe->addr, (i + 1));
 	}
 
-out:
-	eeh_pe_state_clear(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+	eeh_pe_state_clear(pe, reset_state);
 	return ret;
 }
 
@@ -1601,6 +1592,7 @@ static int eeh_pe_reenable_devices(struct eeh_pe *pe)
 	return eeh_unfreeze_pe(pe, true);
 }
 
+
 /**
  * eeh_pe_reset - Issue PE reset according to specified type
  * @pe: EEH PE
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 5c31369435f2..d88573bdd090 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -588,7 +588,7 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 	eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
 
 	/* Issue reset */
-	ret = eeh_reset_pe(pe);
+	ret = eeh_pe_reset_full(pe);
 	if (ret) {
 		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		return ret;
@@ -659,7 +659,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	 * config accesses. So we prefer to block them. However, controlled
 	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
-	rc = eeh_reset_pe(pe);
+	rc = eeh_pe_reset_full(pe);
 	if (rc)
 		return rc;
 
@@ -734,7 +734,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 
 	frozen_bus = eeh_pe_bus_get(pe);
 	if (!frozen_bus) {
-		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
+		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
 		return;
 	}
@@ -878,7 +878,7 @@ excess_failures:
 	 * are due to poorly seated PCI cards. Only 10% or so are
 	 * due to actual, failed cards.
 	 */
-	pr_err("EEH: PHB#%d-PE#%x has failed %d times in the\n"
+	pr_err("EEH: PHB#%x-PE#%x has failed %d times in the\n"
 	       "last hour and has been permanently disabled.\n"
 	       "Please try reseating or replacing it.\n",
 		pe->phb->global_number, pe->addr,
@@ -886,7 +886,7 @@ excess_failures:
 	goto perm_error;
 
 hard_fail:
-	pr_err("EEH: Unable to recover from failure from PHB#%d-PE#%x.\n"
+	pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n"
 	       "Please try reseating or replacing it\n",
 		pe->phb->global_number, pe->addr);
 
@@ -1000,7 +1000,7 @@ static void eeh_handle_special_event(void)
 				bus = eeh_pe_bus_get(phb_pe);
 				if (!bus) {
 					pr_err("%s: Cannot find PCI bus for "
-					       "PHB#%d-PE#%x\n",
+					       "PHB#%x-PE#%x\n",
 					       __func__,
 					       pe->phb->global_number,
 					       pe->addr);
diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
index 82e7327e3cd0..accbf8b5fd46 100644
--- a/arch/powerpc/kernel/eeh_event.c
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -75,11 +75,11 @@ static int eeh_event_handler(void * dummy)
 		if (pe) {
 			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
 			if (pe->type & EEH_PE_PHB)
-				pr_info("EEH: Detected error on PHB#%d\n",
+				pr_info("EEH: Detected error on PHB#%x\n",
 					 pe->phb->global_number);
 			else
 				pr_info("EEH: Detected PCI bus error on "
-					"PHB#%d-PE#%x\n",
+					"PHB#%x-PE#%x\n",
 					pe->phb->global_number, pe->addr);
 			eeh_handle_event(pe);
 			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index de7d091c4c31..cc4b206f77e4 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -104,7 +104,7 @@ int eeh_phb_pe_create(struct pci_controller *phb)
 	/* Put it into the list */
 	list_add_tail(&pe->child, &eeh_phb_pe);
 
-	pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number);
+	pr_debug("EEH: Add PE for PHB#%x\n", phb->global_number);
 
 	return 0;
 }
@@ -333,7 +333,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 
 	/* Check if the PE number is valid */
 	if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) {
-		pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%d\n",
+		pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%x\n",
 		       __func__, edev->config_addr, edev->phb->global_number);
 		return -EINVAL;
 	}
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 3841d749a430..5742dbdbee46 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -674,7 +674,11 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_SPEFSCR,r0		/* restore SPEFSCR reg */
 END_FTR_SECTION_IFSET(CPU_FTR_SPE)
 #endif /* CONFIG_SPE */
-
+#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
+	lwz	r0,TSK_STACK_CANARY(r2)
+	lis	r4,__stack_chk_guard@ha
+	stw	r0,__stack_chk_guard@l(r4)
+#endif
 	lwz	r0,_CCR(r1)
 	mtcrf	0xFF,r0
 	/* r3-r12 are destroyed -- Cort */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 38a1f96430e1..45b453e4d0c8 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -923,10 +923,10 @@ kernel_dbg_exc:
 			        PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x340)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /*
  * An interrupt came in while soft-disabled; We mark paca->irq_happened
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 1ba82ea90230..d39d6118c6e9 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1408,7 +1408,7 @@ USE_TEXT_SECTION()
 /*
  * Hash table stuff
  */
-	.align	7
+	.balign	IFETCH_ALIGN_BYTES
 do_hash_page:
 #ifdef CONFIG_PPC_STD_MMU_64
 	andis.	r0,r4,0xa410		/* weird error? */
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index a95639b8d4ac..5c9f50c1aa99 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -47,13 +47,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
 	unsigned int replaced;
 
 	/*
-	 * Note: Due to modules and __init, code can
-	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing. We do this by using the
-	 *  probe_kernel_* functions.
-	 *
-	 * No real locking needed, this code is run through
-	 * kstop_machine, or before SMP starts.
+	 * Note:
+	 * We are paranoid about modifying text, as if a bug was to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with probe_kernel_*(), and make
+	 * sure what we read is what we expected it to be before modifying it.
 	 */
 
 	/* read the text we want to modify */
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 04c546e20cc0..1dc5eae2ced3 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -107,12 +107,19 @@ __secondary_hold_acknowledge:
 	 * crash_kernel region.  The loader is responsible for
 	 * observing the alignment requirement.
 	 */
+
+#ifdef CONFIG_RELOCATABLE_TEST
+#define RUN_AT_LOAD_DEFAULT 1		/* Test relocation, do not copy to 0 */
+#else
+#define RUN_AT_LOAD_DEFAULT 0x72756e30  /* "run0" -- relocate to 0 by default */
+#endif
+
 	/* Do not move this variable as kexec-tools knows about it. */
 	. = 0x5c
 	.globl	__run_at_load
 __run_at_load:
 DEFINE_FIXED_SYMBOL(__run_at_load)
-	.long	0x72756e30	/* "run0" -- relocate to 0 by default */
+	.long	RUN_AT_LOAD_DEFAULT
 #endif
 
 	. = 0x60
@@ -153,7 +160,7 @@ __secondary_hold:
 	cmpdi	0,r12,0
 	beq	100b
 
-#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
+#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
 #ifdef CONFIG_PPC_BOOK3E
 	tovirt(r12,r12)
 #endif
@@ -214,9 +221,9 @@ booting_thread_hwid:
  */
 _GLOBAL(book3e_start_thread)
 	LOAD_REG_IMMEDIATE(r5, MSR_KERNEL)
-	cmpi	0, r3, 0
+	cmpwi	r3, 0
 	beq	10f
-	cmpi	0, r3, 1
+	cmpwi	r3, 1
 	beq	11f
 	/* If the thread id is invalid, just exit. */
 	b	13f
@@ -241,9 +248,9 @@ _GLOBAL(book3e_start_thread)
  * r3 = the thread physical id
  */
 _GLOBAL(book3e_stop_thread)
-	cmpi	0, r3, 0
+	cmpwi	r3, 0
 	beq	10f
-	cmpi	0, r3, 1
+	cmpwi	r3, 1
 	beq	10f
 	/* If the thread id is invalid, just exit. */
 	b	13f
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/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
deleted file mode 100644
index 6ca9a2ffaac7..000000000000
--- a/arch/powerpc/kernel/ibmebus.c
+++ /dev/null
@@ -1,759 +0,0 @@
-/*
- * IBM PowerPC IBM eBus Infrastructure Support.
- *
- * Copyright (c) 2005 IBM Corporation
- *  Joachim Fenkes <fenkes@de.ibm.com>