Merge tag 'powerpc-4.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for STRICT_KERNEL_RWX on 64-bit server CPUs.

   - Platform support for FSP2 (476fpe) board

   - Enable ZONE_DEVICE on 64-bit server CPUs.

   - Generic & powerpc spin loop primitives to optimise busy waiting

   - Convert VDSO update function to use new update_vsyscall() interface

   - Optimisations to hypercall/syscall/context-switch paths

   - Improvements to the CPU idle code on Power8 and Power9.

  As well as many other fixes and improvements.

  Thanks to: Akshay Adiga, Andrew Donnellan, Andrew Jeffery, Anshuman
  Khandual, Anton Blanchard, Balbir Singh, Benjamin Herrenschmidt,
  Christophe Leroy, Christophe Lombard, Colin Ian King, Dan Carpenter,
  Gautham R. Shenoy, Hari Bathini, Ian Munsie, Ivan Mikhaylov, Javier
  Martinez Canillas, Madhavan Srinivasan, Masahiro Yamada, Matt Brown,
  Michael Neuling, Michal Suchanek, Murilo Opsfelder Araujo, Naveen N.
  Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pavel Machek,
  Russell Currey, Santosh Sivaraj, Stephen Rothwell, Thiago Jung
  Bauermann, Yang Li"

* tag 'powerpc-4.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (158 commits)
  powerpc/Kconfig: Enable STRICT_KERNEL_RWX for some configs
  powerpc/mm/radix: Implement STRICT_RWX/mark_rodata_ro() for Radix
  powerpc/mm/hash: Implement mark_rodata_ro() for hash
  powerpc/vmlinux.lds: Align __init_begin to 16M
  powerpc/lib/code-patching: Use alternate map for patch_instruction()
  powerpc/xmon: Add patch_instruction() support for xmon
  powerpc/kprobes/optprobes: Use patch_instruction()
  powerpc/kprobes: Move kprobes over to patch_instruction()
  powerpc/mm/radix: Fix execute permissions for interrupt_vectors
  powerpc/pseries: Fix passing of pp0 in updatepp() and updateboltedpp()
  powerpc/64s: Blacklist rtas entry/exit from kprobes
  powerpc/64s: Blacklist functions invoked on a trap
  powerpc/64s: Un-blacklist system_call() from kprobes
  powerpc/64s: Move system_call() symbol to just after setting MSR_EE
  powerpc/64s: Blacklist system_call() and system_call_common() from kprobes
  powerpc/64s: Convert .L__replay_interrupt_return to a local label
  powerpc64/elfv1: Only dereference function descriptor for non-text symbols
  cxl: Export library to support IBM XSL
  powerpc/dts: Use #include "..." to include local DT
  powerpc/perf/hv-24x7: Aggregate result elements on POWER9 SMT8
  ...

11 files changed, 369 insertions, 61 deletions

diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 12409a519cc5..37b0698b7193 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -32,18 +32,18 @@ static struct cpuidle_driver powernv_idle_driver = {
 	.owner            = THIS_MODULE,
 };
 
-static int max_idle_state;
-static struct cpuidle_state *cpuidle_state_table;
+static int max_idle_state __read_mostly;
+static struct cpuidle_state *cpuidle_state_table __read_mostly;
 
 struct stop_psscr_table {
 	u64 val;
 	u64 mask;
 };
 
-static struct stop_psscr_table stop_psscr_table[CPUIDLE_STATE_MAX];
+static struct stop_psscr_table stop_psscr_table[CPUIDLE_STATE_MAX] __read_mostly;
 
-static u64 snooze_timeout;
-static bool snooze_timeout_en;
+static u64 snooze_timeout __read_mostly;
+static bool snooze_timeout_en __read_mostly;
 
 static int snooze_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
@@ -51,21 +51,30 @@ static int snooze_loop(struct cpuidle_device *dev,
 {
 	u64 snooze_exit_time;
 
-	local_irq_enable();
 	set_thread_flag(TIF_POLLING_NRFLAG);
 
+	local_irq_enable();
+
 	snooze_exit_time = get_tb() + snooze_timeout;
 	ppc64_runlatch_off();
 	HMT_very_low();
 	while (!need_resched()) {
-		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time)
+		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) {
+			/*
+			 * Task has not woken up but we are exiting the polling
+			 * loop anyway. Require a barrier after polling is
+			 * cleared to order subsequent test of need_resched().
+			 */
+			clear_thread_flag(TIF_POLLING_NRFLAG);
+			smp_mb();
 			break;
+		}
 	}
 
 	HMT_medium();
 	ppc64_runlatch_on();
 	clear_thread_flag(TIF_POLLING_NRFLAG);
-	smp_mb();
+
 	return index;
 }
 
@@ -73,9 +82,8 @@ static int nap_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
 {
-	ppc64_runlatch_off();
-	power7_idle();
-	ppc64_runlatch_on();
+	power7_idle_type(PNV_THREAD_NAP);
+
 	return index;
 }
 
@@ -98,7 +106,8 @@ static int fastsleep_loop(struct cpuidle_device *dev,
 	new_lpcr &= ~LPCR_PECE1;
 
 	mtspr(SPRN_LPCR, new_lpcr);
-	power7_sleep();
+
+	power7_idle_type(PNV_THREAD_SLEEP);
 
 	mtspr(SPRN_LPCR, old_lpcr);
 
@@ -110,10 +119,8 @@ static int stop_loop(struct cpuidle_device *dev,
 		     struct cpuidle_driver *drv,
 		     int index)
 {
-	ppc64_runlatch_off();
-	power9_idle_stop(stop_psscr_table[index].val,
+	power9_idle_type(stop_psscr_table[index].val,
 			 stop_psscr_table[index].mask);
-	ppc64_runlatch_on();
 	return index;
 }
 
@@ -354,6 +361,7 @@ static int powernv_add_idle_states(void)
 
 	for (i = 0; i < dt_idle_states; i++) {
 		unsigned int exit_latency, target_residency;
+		bool stops_timebase = false;
 		/*
 		 * If an idle state has exit latency beyond
 		 * POWERNV_THRESHOLD_LATENCY_NS then don't use it
@@ -381,6 +389,9 @@ static int powernv_add_idle_states(void)
 			}
 		}
 
+		if (flags[i] & OPAL_PM_TIMEBASE_STOP)
+			stops_timebase = true;
+
 		/*
 		 * For nap and fastsleep, use default target_residency
 		 * values if f/w does not expose it.
@@ -392,8 +403,7 @@ static int powernv_add_idle_states(void)
 			add_powernv_state(nr_idle_states, "Nap",
 					  CPUIDLE_FLAG_NONE, nap_loop,
 					  target_residency, exit_latency, 0, 0);
-		} else if ((flags[i] & OPAL_PM_STOP_INST_FAST) &&
-				!(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
+		} else if (has_stop_states && !stops_timebase) {
 			add_powernv_state(nr_idle_states, names[i],
 					  CPUIDLE_FLAG_NONE, stop_loop,
 					  target_residency, exit_latency,
@@ -405,8 +415,8 @@ static int powernv_add_idle_states(void)
 		 * within this config dependency check.
 		 */
 #ifdef CONFIG_TICK_ONESHOT
-		if (flags[i] & OPAL_PM_SLEEP_ENABLED ||
-			flags[i] & OPAL_PM_SLEEP_ENABLED_ER1) {
+		else if (flags[i] & OPAL_PM_SLEEP_ENABLED ||
+			 flags[i] & OPAL_PM_SLEEP_ENABLED_ER1) {
 			if (!rc)
 				target_residency = 300000;
 			/* Add FASTSLEEP state */
@@ -414,14 +424,15 @@ static int powernv_add_idle_states(void)
 					  CPUIDLE_FLAG_TIMER_STOP,
 					  fastsleep_loop,
 					  target_residency, exit_latency, 0, 0);
-		} else if ((flags[i] & OPAL_PM_STOP_INST_DEEP) &&
-				(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
+		} else if (has_stop_states && stops_timebase) {
 			add_powernv_state(nr_idle_states, names[i],
 					  CPUIDLE_FLAG_TIMER_STOP, stop_loop,
 					  target_residency, exit_latency,
 					  psscr_val[i], psscr_mask[i]);
 		}
 #endif
+		else
+			continue;
 		nr_idle_states++;
 	}
 out:
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 166ccd711ec9..e9b3853d93ea 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -25,10 +25,10 @@ struct cpuidle_driver pseries_idle_driver = {
 	.owner            = THIS_MODULE,
 };
 
-static int max_idle_state;
-static struct cpuidle_state *cpuidle_state_table;
-static u64 snooze_timeout;
-static bool snooze_timeout_en;
+static int max_idle_state __read_mostly;
+static struct cpuidle_state *cpuidle_state_table __read_mostly;
+static u64 snooze_timeout __read_mostly;
+static bool snooze_timeout_en __read_mostly;
 
 static inline void idle_loop_prolog(unsigned long *in_purr)
 {
@@ -62,21 +62,29 @@ static int snooze_loop(struct cpuidle_device *dev,
 	unsigned long in_purr;
 	u64 snooze_exit_time;
 
+	set_thread_flag(TIF_POLLING_NRFLAG);
+
 	idle_loop_prolog(&in_purr);
 	local_irq_enable();
-	set_thread_flag(TIF_POLLING_NRFLAG);
 	snooze_exit_time = get_tb() + snooze_timeout;
 
 	while (!need_resched()) {
 		HMT_low();
 		HMT_very_low();
-		if (snooze_timeout_en && get_tb() > snooze_exit_time)
+		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) {
+			/*
+			 * Task has not woken up but we are exiting the polling
+			 * loop anyway. Require a barrier after polling is
+			 * cleared to order subsequent test of need_resched().
+			 */
+			clear_thread_flag(TIF_POLLING_NRFLAG);
+			smp_mb();
 			break;
+		}
 	}
 
 	HMT_medium();
 	clear_thread_flag(TIF_POLLING_NRFLAG);
-	smp_mb();
 
 	idle_loop_epilog(in_purr);
 
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index b75cf830d08a..93397cb05b15 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -11,11 +11,16 @@ config CXL_AFU_DRIVER_OPS
 	bool
 	default n
 
+config CXL_LIB
+	bool
+	default n
+
 config CXL
 	tristate "Support for IBM Coherent Accelerators (CXL)"
 	depends on PPC_POWERNV && PCI_MSI && EEH
 	select CXL_BASE
 	select CXL_AFU_DRIVER_OPS
+	select CXL_LIB
 	default m
 	help
 	  Select this option to enable driver support for IBM Coherent
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index c14fd6b65b5a..0b5fd749d96d 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -3,7 +3,7 @@ ccflags-$(CONFIG_PPC_WERROR)	+= -Werror
 
 cxl-y				+= main.o file.o irq.o fault.o native.o
 cxl-y				+= context.o sysfs.o pci.o trace.o
-cxl-y				+= vphb.o phb.o api.o
+cxl-y				+= vphb.o phb.o api.o cxllib.o
 cxl-$(CONFIG_PPC_PSERIES)	+= flash.o guest.o of.o hcalls.o
 cxl-$(CONFIG_DEBUG_FS)		+= debugfs.o
 obj-$(CONFIG_CXL)		+= cxl.o
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index a03f8e7535e5..b1afeccbb97f 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -1010,6 +1010,7 @@ static inline void cxl_debugfs_add_afu_regs_psl8(struct cxl_afu *afu, struct den
 
 void cxl_handle_fault(struct work_struct *work);
 void cxl_prefault(struct cxl_context *ctx, u64 wed);
+int cxl_handle_mm_fault(struct mm_struct *mm, u64 dsisr, u64 dar);
 
 struct cxl *get_cxl_adapter(int num);
 int cxl_alloc_sst(struct cxl_context *ctx);
@@ -1061,6 +1062,11 @@ int cxl_afu_slbia(struct cxl_afu *afu);
 int cxl_data_cache_flush(struct cxl *adapter);
 int cxl_afu_disable(struct cxl_afu *afu);
 int cxl_psl_purge(struct cxl_afu *afu);
+int cxl_calc_capp_routing(struct pci_dev *dev, u64 *chipid,
+			  u32 *phb_index, u64 *capp_unit_id);
+int cxl_slot_is_switched(struct pci_dev *dev);
+int cxl_get_xsl9_dsnctl(u64 capp_unit_id, u64 *reg);
+u64 cxl_calculate_sr(bool master, bool kernel, bool real_mode, bool p9);
 
 void cxl_native_irq_dump_regs_psl9(struct cxl_context *ctx);
 void cxl_native_irq_dump_regs_psl8(struct cxl_context *ctx);
diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c
new file mode 100644
index 000000000000..5dba23ca2e5f
--- /dev/null
+++ b/drivers/misc/cxl/cxllib.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright 2017 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/hugetlb.h>
+#include <linux/sched/mm.h>
+#include <asm/pnv-pci.h>
+#include <misc/cxllib.h>
+
+#include "cxl.h"
+
+#define CXL_INVALID_DRA                 ~0ull
+#define CXL_DUMMY_READ_SIZE             128
+#define CXL_DUMMY_READ_ALIGN            8
+#define CXL_CAPI_WINDOW_START           0x2000000000000ull
+#define CXL_CAPI_WINDOW_LOG_SIZE        48
+#define CXL_XSL_CONFIG_CURRENT_VERSION  CXL_XSL_CONFIG_VERSION1
+
+
+bool cxllib_slot_is_supported(struct pci_dev *dev, unsigned long flags)
+{
+	int rc;
+	u32 phb_index;
+	u64 chip_id, capp_unit_id;
+
+	/* No flags currently supported */
+	if (flags)
+		return false;
+
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return false;
+
+	if (!cxl_is_power9())
+		return false;
+
+	if (cxl_slot_is_switched(dev))
+		return false;
+
+	/* on p9, some pci slots are not connected to a CAPP unit */
+	rc = cxl_calc_capp_routing(dev, &chip_id, &phb_index, &capp_unit_id);
+	if (rc)
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(cxllib_slot_is_supported);
+
+static DEFINE_MUTEX(dra_mutex);
+static u64 dummy_read_addr = CXL_INVALID_DRA;
+
+static int allocate_dummy_read_buf(void)
+{
+	u64 buf, vaddr;
+	size_t buf_size;
+
+	/*
+	 * Dummy read buffer is 128-byte long, aligned on a
+	 * 256-byte boundary and we need the physical address.
+	 */
+	buf_size = CXL_DUMMY_READ_SIZE + (1ull << CXL_DUMMY_READ_ALIGN);
+	buf = (u64) kzalloc(buf_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	vaddr = (buf + (1ull << CXL_DUMMY_READ_ALIGN) - 1) &
+					(~0ull << CXL_DUMMY_READ_ALIGN);
+
+	WARN((vaddr + CXL_DUMMY_READ_SIZE) > (buf + buf_size),
+		"Dummy read buffer alignment issue");
+	dummy_read_addr = virt_to_phys((void *) vaddr);
+	return 0;
+}
+
+int cxllib_get_xsl_config(struct pci_dev *dev, struct cxllib_xsl_config *cfg)
+{
+	int rc;
+	u32 phb_index;
+	u64 chip_id, capp_unit_id;
+
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return -EINVAL;
+
+	mutex_lock(&dra_mutex);
+	if (dummy_read_addr == CXL_INVALID_DRA) {
+		rc = allocate_dummy_read_buf();
+		if (rc) {
+			mutex_unlock(&dra_mutex);
+			return rc;
+		}
+	}
+	mutex_unlock(&dra_mutex);
+
+	rc = cxl_calc_capp_routing(dev, &chip_id, &phb_index, &capp_unit_id);
+	if (rc)
+		return rc;
+
+	rc = cxl_get_xsl9_dsnctl(capp_unit_id, &cfg->dsnctl);
+	if (rc)
+		return rc;
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
+		/* workaround for DD1 - nbwind = capiind */
+		cfg->dsnctl |= ((u64)0x02 << (63-47));
+	}
+
+	cfg->version  = CXL_XSL_CONFIG_CURRENT_VERSION;
+	cfg->log_bar_size = CXL_CAPI_WINDOW_LOG_SIZE;
+	cfg->bar_addr = CXL_CAPI_WINDOW_START;
+	cfg->dra = dummy_read_addr;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxllib_get_xsl_config);
+
+int cxllib_switch_phb_mode(struct pci_dev *dev, enum cxllib_mode mode,
+			unsigned long flags)
+{
+	int rc = 0;
+
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return -EINVAL;
+
+	switch (mode) {
+	case CXL_MODE_PCI:
+		/*
+		 * We currently don't support going back to PCI mode
+		 * However, we'll turn the invalidations off, so that
+		 * the firmware doesn't have to ack them and can do
+		 * things like reset, etc.. with no worries.
+		 * So always return EPERM (can't go back to PCI) or
+		 * EBUSY if we couldn't even turn off snooping
+		 */
+		rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_OFF);
+		if (rc)
+			rc = -EBUSY;
+		else
+			rc = -EPERM;
+		break;
+	case CXL_MODE_CXL:
+		/* DMA only supported on TVT1 for the time being */
+		if (flags != CXL_MODE_DMA_TVT1)
+			return -EINVAL;
+		rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_DMA_TVT1);
+		if (rc)
+			return rc;
+		rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_ON);
+		break;
+	default:
+		rc = -EINVAL;
+	}
+	return rc;
+}
+EXPORT_SYMBOL_GPL(cxllib_switch_phb_mode);
+
+/*
+ * When switching the PHB to capi mode, the TVT#1 entry for
+ * the Partitionable Endpoint is set in bypass mode, like
+ * in PCI mode.
+ * Configure the device dma to use TVT#1, which is done
+ * by calling dma_set_mask() with a mask large enough.
+ */
+int cxllib_set_device_dma(struct pci_dev *dev, unsigned long flags)
+{
+	int rc;
+
+	if (flags)
+		return -EINVAL;
+
+	rc = dma_set_mask(&dev->dev, DMA_BIT_MASK(64));
+	return rc;
+}
+EXPORT_SYMBOL_GPL(cxllib_set_device_dma);
+
+int cxllib_get_PE_attributes(struct task_struct *task,
+			     unsigned long translation_mode,
+			     struct cxllib_pe_attributes *attr)
+{
+	struct mm_struct *mm = NULL;
+
+	if (translation_mode != CXL_TRANSLATED_MODE &&
+		translation_mode != CXL_REAL_MODE)
+		return -EINVAL;
+
+	attr->sr = cxl_calculate_sr(false,
+				task == NULL,
+				translation_mode == CXL_REAL_MODE,
+				true);
+	attr->lpid = mfspr(SPRN_LPID);
+	if (task) {
+		mm = get_task_mm(task);
+		if (mm == NULL)
+			return -EINVAL;
+		/*
+		 * Caller is keeping a reference on mm_users for as long
+		 * as XSL uses the memory context
+		 */
+		attr->pid = mm->context.id;
+		mmput(mm);
+	} else {
+		attr->pid = 0;
+	}
+	attr->tid = 0;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxllib_get_PE_attributes);
+
+int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags)
+{
+	int rc;
+	u64 dar;
+	struct vm_area_struct *vma = NULL;
+	unsigned long page_size;
+
+	if (mm == NULL)
+		return -EFAULT;
+
+	down_read(&mm->mmap_sem);
+
+	for (dar = addr; dar < addr + size; dar += page_size) {
+		if (!vma || dar < vma->vm_start || dar > vma->vm_end) {
+			vma = find_vma(mm, addr);
+			if (!vma) {
+				pr_err("Can't find vma for addr %016llx\n", addr);
+				rc = -EFAULT;
+				goto out;
+			}
+			/* get the size of the pages allocated */
+			page_size = vma_kernel_pagesize(vma);
+		}
+
+		rc = cxl_handle_mm_fault(mm, flags, dar);
+		if (rc) {
+			pr_err("cxl_handle_mm_fault failed %d", rc);
+			rc = -EFAULT;
+			goto out;
+		}
+	}
+	rc = 0;
+out:
+	up_read(&mm->mmap_sem);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(cxllib_handle_fault);
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index c79e39bad7a4..6eed7d03e2b5 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -132,18 +132,15 @@ static int cxl_handle_segment_miss(struct cxl_context *ctx,
 	return IRQ_HANDLED;
 }
 
-static void cxl_handle_page_fault(struct cxl_context *ctx,
-				  struct mm_struct *mm, u64 dsisr, u64 dar)
+int cxl_handle_mm_fault(struct mm_struct *mm, u64 dsisr, u64 dar)
 {
 	unsigned flt = 0;
 	int result;
 	unsigned long access, flags, inv_flags = 0;
 
-	trace_cxl_pte_miss(ctx, dsisr, dar);
-
 	if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
 		pr_devel("copro_handle_mm_fault failed: %#x\n", result);
-		return cxl_ack_ae(ctx);
+		return result;
 	}
 
 	if (!radix_enabled()) {
@@ -155,9 +152,8 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
 		if (dsisr & CXL_PSL_DSISR_An_S)
 			access |= _PAGE_WRITE;
 
-		access |= _PAGE_PRIVILEGED;
-		if ((!ctx->kernel) || (REGION_ID(dar) == USER_REGION_ID))
-			access &= ~_PAGE_PRIVILEGED;
+		if (!mm && (REGION_ID(dar) != USER_REGION_ID))
+			access |= _PAGE_PRIVILEGED;
 
 		if (dsisr & DSISR_NOHPTE)
 			inv_flags |= HPTE_NOHPTE_UPDATE;
@@ -166,8 +162,21 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
 		hash_page_mm(mm, dar, access, 0x300, inv_flags);
 		local_irq_restore(flags);
 	}
-	pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);
-	cxl_ops->ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
+	return 0;
+}
+
+static void cxl_handle_page_fault(struct cxl_context *ctx,
+				  struct mm_struct *mm,
+				  u64 dsisr, u64 dar)
+{
+	trace_cxl_pte_miss(ctx, dsisr, dar);
+
+	if (cxl_handle_mm_fault(mm, dsisr, dar)) {
+		cxl_ack_ae(ctx);
+	} else {
+		pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);
+		cxl_ops->ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
+	}
 }
 
 /*
diff --git a/drivers/misc/cxl/flash.c b/drivers/misc/cxl/flash.c
index 7c61c70ba3f6..3aa216bf0939 100644
--- a/drivers/misc/cxl/flash.c
+++ b/drivers/misc/cxl/flash.c
@@ -401,8 +401,10 @@ static int device_open(struct inode *inode, struct file *file)
 	if (down_interruptible(&sem) != 0)
 		return -EPERM;
 
-	if (!(adapter = get_cxl_adapter(adapter_num)))
-		return -ENODEV;
+	if (!(adapter = get_cxl_adapter(adapter_num))) {
+		rc = -ENODEV;
+		goto err_unlock;
+	}
 
 	file->private_data = adapter;
 	continue_token = 0;
@@ -446,6 +448,8 @@ err1:
 		free_page((unsigned long) le);
 err:
 	put_device(&adapter->dev);
+err_unlock:
+	up(&sem);
 
 	return rc;
 }
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 2b2f8894149d..4a82c313cf71 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -586,17 +586,17 @@ err:
 #define set_endian(sr) ((sr) &= ~(CXL_PSL_SR_An_LE))
 #endif
 
-static u64 calculate_sr(struct cxl_context *ctx)
+u64 cxl_calculate_sr(bool master, bool kernel, bool real_mode, bool p9)
 {
 	u64 sr = 0;
 
 	set_endian(sr);
-	if (ctx->master)
+	if (master)
 		sr |= CXL_PSL_SR_An_MP;
 	if (mfspr(SPRN_LPCR) & LPCR_TC)
 		sr |= CXL_PSL_SR_An_TC;
-	if (ctx->kernel) {
-		if (!ctx->real_mode)
+	if (kernel) {
+		if (!real_mode)
 			sr |= CXL_PSL_SR_An_R;
 		sr |= (mfmsr() & MSR_SF) | CXL_PSL_SR_An_HV;
 	} else {
@@ -608,7 +608,7 @@ static u64 calculate_sr(struct cxl_context *ctx)
 		if (!test_tsk_thread_flag(current, TIF_32BIT))
 			sr |= CXL_PSL_SR_An_SF;
 	}
-	if (cxl_is_power9()) {
+	if (p9) {
 		if (radix_enabled())
 			sr |= CXL_PSL_SR_An_XLAT_ror;
 		else
@@ -617,6 +617,12 @@ static u64 calculate_sr(struct cxl_context *ctx)
 	return sr;
 }
 
+static u64 calculate_sr(struct cxl_context *ctx)
+{
+	return cxl_calculate_sr(ctx->master, ctx->kernel, ctx->real_mode,
+				cxl_is_power9());
+}
+
 static void update_ivtes_directed(struct cxl_context *ctx)
 {
 	bool need_update = (ctx->status == STARTED);
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 1eb9859809bf..d18b3d9292fd 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -375,7 +375,7 @@ static u64 get_capp_unit_id(struct device_node *np, u32 phb_index)
 	return 0;
 }
 
-static int calc_capp_routing(struct pci_dev *dev, u64 *chipid,
+int cxl_calc_capp_routing(struct pci_dev *dev, u64 *chipid,
 			     u32 *phb_index, u64 *capp_unit_id)
 {
 	int rc;
@@ -408,17 +408,9 @@ static int calc_capp_routing(struct pci_dev *dev, u64 *chipid,
 	return 0;
 }
 
-static int init_implementation_adapter_regs_psl9(struct cxl *adapter, struct pci_dev *dev)
+int cxl_get_xsl9_dsnctl(u64 capp_unit_id, u64 *reg)
 {
-	u64 xsl_dsnctl, psl_fircntl;
-	u64 chipid;
-	u32 phb_index;
-	u64 capp_unit_id;
-	int rc;
-
-	rc = calc_capp_routing(dev, &chipid, &phb_index, &capp_unit_id);
-	if (rc)
-		return rc;
+	u64 xsl_dsnctl;
 
 	/*
 	 * CAPI Identifier bits [0:7]
@@ -454,6 +446,27 @@ static int init_implementation_adapter_regs_psl9(struct cxl *adapter, struct pci
 		xsl_dsnctl |= ((u64)0x04 << (63-55));
 	}
 
+	*reg = xsl_dsnctl;
+	return 0;
+}
+
+static int init_implementation_adapter_regs_psl9(struct cxl *adapter,
+						 struct pci_dev *dev)
+{
+	u64 xsl_dsnctl, psl_fircntl;
+	u64 chipid;
+	u32 phb_index;
+	u64 capp_unit_id;
+	int rc;
+
+	rc = cxl_calc_capp_routing(dev, &chipid, &phb_index, &capp_unit_id);
+	if (rc)
+		return rc;
+
+	rc = cxl_get_xsl9_dsnctl(capp_unit_id, &xsl_dsnctl);
+	if (rc)
+		return rc;
+
 	cxl_p1_write(adapter, CXL_XSL9_DSNCTL, xsl_dsnctl);
 
 	/* Set fir_cntl to recommended value for production env */
@@ -505,7 +518,7 @@ static int init_implementation_adapter_regs_psl8(struct cxl *adapter, struct pci
 	u64 capp_unit_id;
 	int rc;
 
-	rc = calc_capp_routing(dev, &chipid, &phb_index, &capp_unit_id);
+	rc = cxl_calc_capp_routing(dev, &chipid, &phb_index, &capp_unit_id);
 	if (rc)
 		return rc;
 
@@ -538,7 +551,7 @@ static int init_implementation_adapter_regs_xsl(struct cxl *adapter, struct pci_
 	u64 capp_unit_id;
 	int rc;
 
-	rc = calc_capp_routing(dev, &chipid, &phb_index, &capp_unit_id);
+	rc = cxl_calc_capp_routing(dev, &chipid, &phb_index, &capp_unit_id);
 	if (rc)
 		return rc;
 
@@ -1897,7 +1910,7 @@ static void cxl_pci_remove_adapter(struct cxl *adapter)
 
 #define CXL_MAX_PCIEX_PARENT 2
 
-static int cxl_slot_is_switched(struct pci_dev *dev)
+int cxl_slot_is_switched(struct pci_dev *dev)
 {
 	struct device_node *np;
 	int depth = 0;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 8b9049dac094..e6e31a16f68f 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1688,7 +1688,7 @@ config MEN_A21_WDT
 
 config WATCHDOG_RTAS
 	tristate "RTAS watchdog"
-	depends on PPC_RTAS || (PPC64 && COMPILE_TEST)
+	depends on PPC_RTAS
 	help
 	  This driver adds watchdog support for the RTAS watchdog.