Merge tag 'powerpc-5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Convert pseries & powernv to use MSI IRQ domains.

 - Rework the pseries CPU numbering so that CPUs that are removed, and
   later re-added, are given a CPU number on the same node as
   previously, when possible.

 - Add support for a new more flexible device-tree format for specifying
   NUMA distances.

 - Convert powerpc to GENERIC_PTDUMP.

 - Retire sbc8548 and sbc8641d board support.

 - Various other small features and fixes.

Thanks to Alexey Kardashevskiy, Aneesh Kumar K.V, Anton Blanchard,
Cédric Le Goater, Christophe Leroy, Emmanuel Gil Peyrot, Fabiano Rosas,
Fangrui Song, Finn Thain, Gautham R.  Shenoy, Hari Bathini, Joel
Stanley, Jordan Niethe, Kajol Jain, Laurent Dufour, Leonardo Bras, Lukas
Bulwahn, Marc Zyngier, Masahiro Yamada, Michal Suchanek, Nathan
Chancellor, Nicholas Piggin, Parth Shah, Paul Gortmaker, Pratik R.
Sampat, Randy Dunlap, Sebastian Andrzej Siewior, Srikar Dronamraju, Wan
Jiabing, Xiongwei Song, and Zheng Yongjun.

* tag 'powerpc-5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (154 commits)
  powerpc/bug: Cast to unsigned long before passing to inline asm
  powerpc/ptdump: Fix generic ptdump for 64-bit
  KVM: PPC: Fix clearing never mapped TCEs in realmode
  powerpc/pseries/iommu: Rename "direct window" to "dma window"
  powerpc/pseries/iommu: Make use of DDW for indirect mapping
  powerpc/pseries/iommu: Find existing DDW with given property name
  powerpc/pseries/iommu: Update remove_dma_window() to accept property name
  powerpc/pseries/iommu: Reorganize iommu_table_setparms*() with new helper
  powerpc/pseries/iommu: Add ddw_property_create() and refactor enable_ddw()
  powerpc/pseries/iommu: Allow DDW windows starting at 0x00
  powerpc/pseries/iommu: Add ddw_list_new_entry() helper
  powerpc/pseries/iommu: Add iommu_pseries_alloc_table() helper
  powerpc/kernel/iommu: Add new iommu_table_in_use() helper
  powerpc/pseries/iommu: Replace hard-coded page shift
  powerpc/numa: Update cpu_cpu_map on CPU online/offline
  powerpc/numa: Print debug statements only when required
  powerpc/numa: convert printk to pr_xxx
  powerpc/numa: Drop dbg in favour of pr_debug
  powerpc/smp: Enable CACHE domain for shared processor
  powerpc/smp: Update cpu_core_map on all PowerPc systems
  ...

39 files changed, 267 insertions, 245 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f66b63e81c3b..7be36c1e1db6 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -46,7 +46,8 @@ obj-y				:= cputable.o syscalls.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
 				   of_platform.o prom_parse.o firmware.o \
-				   hw_breakpoint_constraints.o interrupt.o
+				   hw_breakpoint_constraints.o interrupt.o \
+				   kdebugfs.o
 obj-y				+= ptrace/
 obj-$(CONFIG_PPC64)		+= setup_64.o \
 				   paca.o nvram_64.o note.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5bee245d832b..e563d3222d69 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -286,23 +286,16 @@ int main(void)
 	STACK_PT_REGS_OFFSET(_CCR, ccr);
 	STACK_PT_REGS_OFFSET(_XER, xer);
 	STACK_PT_REGS_OFFSET(_DAR, dar);
+	STACK_PT_REGS_OFFSET(_DEAR, dear);
 	STACK_PT_REGS_OFFSET(_DSISR, dsisr);
+	STACK_PT_REGS_OFFSET(_ESR, esr);
 	STACK_PT_REGS_OFFSET(ORIG_GPR3, orig_gpr3);
 	STACK_PT_REGS_OFFSET(RESULT, result);
 	STACK_PT_REGS_OFFSET(_TRAP, trap);
-#ifndef CONFIG_PPC64
-	/*
-	 * The PowerPC 400-class & Book-E processors have neither the DAR
-	 * nor the DSISR SPRs. Hence, we overload them to hold the similar
-	 * DEAR and ESR SPRs for such processors.  For critical interrupts
-	 * we use them to hold SRR0 and SRR1.
-	 */
-	STACK_PT_REGS_OFFSET(_DEAR, dar);
-	STACK_PT_REGS_OFFSET(_ESR, dsisr);
-#else /* CONFIG_PPC64 */
+#ifdef CONFIG_PPC64
 	STACK_PT_REGS_OFFSET(SOFTE, softe);
 	STACK_PT_REGS_OFFSET(_PPR, ppr);
-#endif /* CONFIG_PPC64 */
+#endif
 
 #ifdef CONFIG_PPC_PKEY
 	STACK_PT_REGS_OFFSET(STACK_REGS_AMR, amr);
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 6f903e9aa20b..cf1be75b7833 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -120,6 +120,7 @@ struct cache {
 	struct cpumask shared_cpu_map; /* online CPUs using this cache */
 	int type;                      /* split cache disambiguation */
 	int level;                     /* level not explicit in device tree */
+	int group_id;                  /* id of the group of threads that share this cache */
 	struct list_head list;         /* global list of cache objects */
 	struct cache *next_local;      /* next cache of >= level */
 };
@@ -142,22 +143,24 @@ static const char *cache_type_string(const struct cache *cache)
 }
 
 static void cache_init(struct cache *cache, int type, int level,
-		       struct device_node *ofnode)
+		       struct device_node *ofnode, int group_id)
 {
 	cache->type = type;
 	cache->level = level;
 	cache->ofnode = of_node_get(ofnode);
+	cache->group_id = group_id;
 	INIT_LIST_HEAD(&cache->list);
 	list_add(&cache->list, &cache_list);
 }
 
-static struct cache *new_cache(int type, int level, struct device_node *ofnode)
+static struct cache *new_cache(int type, int level,
+			       struct device_node *ofnode, int group_id)
 {
 	struct cache *cache;
 
 	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (cache)
-		cache_init(cache, type, level, ofnode);
+		cache_init(cache, type, level, ofnode, group_id);
 
 	return cache;
 }
@@ -309,20 +312,24 @@ static struct cache *cache_find_first_sibling(struct cache *cache)
 		return cache;
 
 	list_for_each_entry(iter, &cache_list, list)
-		if (iter->ofnode == cache->ofnode && iter->next_local == cache)
+		if (iter->ofnode == cache->ofnode &&
+		    iter->group_id == cache->group_id &&
+		    iter->next_local == cache)
 			return iter;
 
 	return cache;
 }
 
-/* return the first cache on a local list matching node */
-static struct cache *cache_lookup_by_node(const struct device_node *node)
+/* return the first cache on a local list matching node and thread-group id */
+static struct cache *cache_lookup_by_node_group(const struct device_node *node,
+						int group_id)
 {
 	struct cache *cache = NULL;
 	struct cache *iter;
 
 	list_for_each_entry(iter, &cache_list, list) {
-		if (iter->ofnode != node)
+		if (iter->ofnode != node ||
+		    iter->group_id != group_id)
 			continue;
 		cache = cache_find_first_sibling(iter);
 		break;
@@ -352,14 +359,15 @@ static int cache_is_unified_d(const struct device_node *np)
 		CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
 }
 
-static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int group_id,
+						  int level)
 {
 	pr_debug("creating L%d ucache for %pOFP\n", level, node);
 
-	return new_cache(cache_is_unified_d(node), level, node);
+	return new_cache(cache_is_unified_d(node), level, node, group_id);
 }
 
-static struct cache *cache_do_one_devnode_split(struct device_node *node,
+static struct cache *cache_do_one_devnode_split(struct device_node *node, int group_id,
 						int level)
 {
 	struct cache *dcache, *icache;
@@ -367,8 +375,8 @@ static struct cache *cache_do_one_devnode_split(struct device_node *node,
 	pr_debug("creating L%d dcache and icache for %pOFP\n", level,
 		 node);
 
-	dcache = new_cache(CACHE_TYPE_DATA, level, node);
-	icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node);
+	dcache = new_cache(CACHE_TYPE_DATA, level, node, group_id);
+	icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node, group_id);
 
 	if (!dcache || !icache)
 		goto err;
@@ -382,31 +390,32 @@ err:
 	return NULL;
 }
 
-static struct cache *cache_do_one_devnode(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode(struct device_node *node, int group_id, int level)
 {
 	struct cache *cache;
 
 	if (cache_node_is_unified(node))
-		cache = cache_do_one_devnode_unified(node, level);
+		cache = cache_do_one_devnode_unified(node, group_id, level);
 	else
-		cache = cache_do_one_devnode_split(node, level);
+		cache = cache_do_one_devnode_split(node, group_id, level);
 
 	return cache;
 }
 
 static struct cache *cache_lookup_or_instantiate(struct device_node *node,
+						 int group_id,
 						 int level)
 {
 	struct cache *cache;
 
-	cache = cache_lookup_by_node(node);
+	cache = cache_lookup_by_node_group(node, group_id);
 
 	WARN_ONCE(cache && cache->level != level,
 		  "cache level mismatch on lookup (got %d, expected %d)\n",
 		  cache->level, level);
 
 	if (!cache)
-		cache = cache_do_one_devnode(node, level);
+		cache = cache_do_one_devnode(node, group_id, level);
 
 	return cache;
 }
@@ -443,7 +452,30 @@ static void do_subsidiary_caches_debugcheck(struct cache *cache)
 		  of_node_get_device_type(cache->ofnode));
 }
 
-static void do_subsidiary_caches(struct cache *cache)
+/*
+ * If sub-groups of threads in a core containing @cpu_id share the
+ * L@level-cache (information obtained via "ibm,thread-groups"
+ * device-tree property), then we identify the group by the first
+ * thread-sibling in the group. We define this to be the group-id.
+ *
+ * In the absence of any thread-group information for L@level-cache,
+ * this function returns -1.
+ */
+static int get_group_id(unsigned int cpu_id, int level)
+{
+	if (has_big_cores && level == 1)
+		return cpumask_first(per_cpu(thread_group_l1_cache_map,
+					     cpu_id));
+	else if (thread_group_shares_l2 && level == 2)
+		return cpumask_first(per_cpu(thread_group_l2_cache_map,
+					     cpu_id));
+	else if (thread_group_shares_l3 && level == 3)
+		return cpumask_first(per_cpu(thread_group_l3_cache_map,
+					     cpu_id));
+	return -1;
+}
+
+static void do_subsidiary_caches(struct cache *cache, unsigned int cpu_id)
 {
 	struct device_node *subcache_node;
 	int level = cache->level;
@@ -452,9 +484,11 @@ static void do_subsidiary_caches(struct cache *cache)
 
 	while ((subcache_node = of_find_next_cache_node(cache->ofnode))) {
 		struct cache *subcache;
+		int group_id;
 
 		level++;
-		subcache = cache_lookup_or_instantiate(subcache_node, level);
+		group_id = get_group_id(cpu_id, level);
+		subcache = cache_lookup_or_instantiate(subcache_node, group_id, level);
 		of_node_put(subcache_node);
 		if (!subcache)
 			break;
@@ -468,6 +502,7 @@ static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cpu_cache = NULL;
+	int group_id;
 
 	pr_debug("creating cache object(s) for CPU %i\n", cpu_id);
 
@@ -476,11 +511,13 @@ static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 	if (!cpu_node)
 		goto out;
 
-	cpu_cache = cache_lookup_or_instantiate(cpu_node, 1);
+	group_id = get_group_id(cpu_id, 1);
+
+	cpu_cache = cache_lookup_or_instantiate(cpu_node, group_id, 1);
 	if (!cpu_cache)
 		goto out;
 
-	do_subsidiary_caches(cpu_cache);
+	do_subsidiary_caches(cpu_cache, cpu_id);
 
 	cache_cpu_set(cpu_cache, cpu_id);
 out:
@@ -641,45 +678,6 @@ static ssize_t level_show(struct kobject *k, struct kobj_attribute *attr, char *
 static struct kobj_attribute cache_level_attr =
 	__ATTR(level, 0444, level_show, NULL);
 
-static unsigned int index_dir_to_cpu(struct cache_index_dir *index)
-{
-	struct kobject *index_dir_kobj = &index->kobj;
-	struct kobject *cache_dir_kobj = index_dir_kobj->parent;
-	struct kobject *cpu_dev_kobj = cache_dir_kobj->parent;
-	struct device *dev = kobj_to_dev(cpu_dev_kobj);
-
-	return dev->id;
-}
-
-/*
- * On big-core systems, each core has two groups of CPUs each of which
- * has its own L1-cache. The thread-siblings which share l1-cache with
- * @cpu can be obtained via cpu_smallcore_mask().
- *
- * On some big-core systems, the L2 cache is shared only between some
- * groups of siblings. This is already parsed and encoded in
- * cpu_l2_cache_mask().
- *
- * TODO: cache_lookup_or_instantiate() needs to be made aware of the
- *       "ibm,thread-groups" property so that cache->shared_cpu_map
- *       reflects the correct siblings on platforms that have this
- *       device-tree property. This helper function is only a stop-gap
- *       solution so that we report the correct siblings to the
- *       userspace via sysfs.
- */
-static const struct cpumask *get_shared_cpu_map(struct cache_index_dir *index, struct cache *cache)
-{
-	if (has_big_cores) {
-		int cpu = index_dir_to_cpu(index);
-		if (cache->level == 1)
-			return cpu_smallcore_mask(cpu);
-		if (cache->level == 2 && thread_group_shares_l2)
-			return cpu_l2_cache_mask(cpu);
-	}
-
-	return &cache->shared_cpu_map;
-}
-
 static ssize_t
 show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bool list)
 {
@@ -690,7 +688,7 @@ show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bo
 	index = kobj_to_cache_index_dir(k);
 	cache = index->cache;
 
-	mask = get_shared_cpu_map(index, cache);
+	mask = &cache->shared_cpu_map;
 
 	return cpumap_print_to_pagebuf(list, buf, mask);
 }
@@ -848,13 +846,15 @@ static struct cache *cache_lookup_by_cpu(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cache;
+	int group_id;
 
 	cpu_node = of_get_cpu_node(cpu_id, NULL);
 	WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
 	if (!cpu_node)
 		return NULL;
 
-	cache = cache_lookup_by_node(cpu_node);
+	group_id = get_group_id(cpu_id, 1);
+	cache = cache_lookup_by_node_group(cpu_node, group_id);
 	of_node_put(cpu_node);
 
 	return cache;
diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c
index cdc2dccb987d..64e423d2fe0f 100644
--- a/arch/powerpc/kernel/dawr.c
+++ b/arch/powerpc/kernel/dawr.c
@@ -9,7 +9,6 @@
 #include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/debugfs.h>
-#include <asm/debugfs.h>
 #include <asm/machdep.h>
 #include <asm/hvcall.h>
 
@@ -101,7 +100,7 @@ static int __init dawr_force_setup(void)
 	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
 		/* Turn DAWR off by default, but allow admin to turn it on */
 		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
-					   powerpc_debugfs_root,
+					   arch_debugfs_dir,
 					   &dawr_force_enable,
 					   &dawr_enable_fops);
 	}
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 3bbdcc86d01b..e9b597ed423c 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -21,9 +21,9 @@
 #include <linux/spinlock.h>
 #include <linux/export.h>
 #include <linux/of.h>
+#include <linux/debugfs.h>
 
 #include <linux/atomic.h>
-#include <asm/debugfs.h>
 #include <asm/eeh.h>
 #include <asm/eeh_event.h>
 #include <asm/io.h>
@@ -1901,24 +1901,24 @@ static int __init eeh_init_proc(void)
 		proc_create_single("powerpc/eeh", 0, NULL, proc_eeh_show);
 #ifdef CONFIG_DEBUG_FS
 		debugfs_create_file_unsafe("eeh_enable", 0600,
-					   powerpc_debugfs_root, NULL,
+					   arch_debugfs_dir, NULL,
 					   &eeh_enable_dbgfs_ops);
 		debugfs_create_u32("eeh_max_freezes", 0600,
-				powerpc_debugfs_root, &eeh_max_freezes);
+				arch_debugfs_dir, &eeh_max_freezes);
 		debugfs_create_bool("eeh_disable_recovery", 0600,
-				powerpc_debugfs_root,
+				arch_debugfs_dir,
 				&eeh_debugfs_no_recover);
 		debugfs_create_file_unsafe("eeh_dev_check", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_dev_check_fops);
 		debugfs_create_file_unsafe("eeh_dev_break", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_dev_break_fops);
 		debugfs_create_file_unsafe("eeh_force_recover", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_force_recover_fops);
 		debugfs_create_file_unsafe("eeh_dev_can_recover", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_dev_can_recover_fops);
 		eeh_cache_debugfs_init();
 #endif
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index bf3270426d82..9bdaaf7fddc9 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -12,8 +12,8 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
+#include <linux/debugfs.h>
 #include <asm/pci-bridge.h>
-#include <asm/debugfs.h>
 #include <asm/ppc-pci.h>
 
 
@@ -283,6 +283,6 @@ DEFINE_SHOW_ATTRIBUTE(eeh_addr_cache);
 void eeh_cache_debugfs_init(void)
 {
 	debugfs_create_file_unsafe("eeh_address_cache", 0400,
-			powerpc_debugfs_root, NULL,
+			arch_debugfs_dir, NULL,
 			&eeh_addr_cache_fops);
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 0273a1349006..61fdd53cdd9a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -161,10 +161,10 @@ ret_from_fork:
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
-	mtlr	r14
+	mtctr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
-	blrl
+	bctrl
 	li	r3,0
 	b	ret_from_syscall
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 15720f8661a1..70cff7b49e17 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -309,7 +309,7 @@ _GLOBAL(enter_rtas)
 	 */
 	lbz	r0,PACAIRQSOFTMASK(r13)
 1:	tdeqi	r0,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+	EMIT_WARN_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
 #endif
 
 	/* Hard-disable interrupts */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 1401787b0b93..711c66b76df1 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -545,8 +545,8 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	mfspr	r14,SPRN_DEAR
 	mfspr	r15,SPRN_ESR
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
+	std	r14,_DEAR(r1)
+	std	r15,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x300)
@@ -558,8 +558,8 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	li	r15,0
 	mr	r14,r10
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
+	std	r14,_DEAR(r1)
+	std	r15,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x400)
@@ -575,8 +575,8 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	mfspr	r14,SPRN_DEAR
 	mfspr	r15,SPRN_ESR
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
+	std	r14,_DEAR(r1)
+	std	r15,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x600)
@@ -587,7 +587,7 @@ __end_interrupts:
 	NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM,
 				PROLOG_ADDITION_1REG)
 	mfspr	r14,SPRN_ESR
-	std	r14,_DSISR(r1)
+	std	r14,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	EXCEPTION_COMMON(0x700)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
@@ -1057,8 +1057,8 @@ bad_stack_book3e:
 	std	r11,_CCR(r1)
 	mfspr	r10,SPRN_DEAR
 	mfspr	r11,SPRN_ESR
-	std	r10,_DAR(r1)
-	std	r11,_DSISR(r1)
+	std	r10,_DEAR(r1)
+	std	r11,_ESR(r1)
 	std	r0,GPR0(r1);		/* save r0 in stackframe */	    \
 	std	r2,GPR2(r1);		/* save r2 in stackframe */	    \
 	SAVE_4GPRS(3, r1);		/* save r3 - r6 in stackframe */    \
@@ -1127,7 +1127,7 @@ found_iprot:
  * r3 = MAS0_TLBSEL (for the iprot array)
  * r4 = SPRN_TLBnCFG
  */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r5,r7,27,31,31			/* extract MSR[IS] */
@@ -1196,7 +1196,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mfmsr	r6
 	xori	r6,r6,MSR_IS
 	mtspr	SPRN_SRR1,r6
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	mtspr	SPRN_SRR0,r6
@@ -1256,7 +1256,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
  * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
  */
 	/* Now we branch the new virtual address mapped by this entry */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	tovirt(r6,r6)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index b990075285f5..b7ceb041743c 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -24,8 +24,8 @@
 #include <linux/slab.h>
 #include <linux/cma.h>
 #include <linux/hugetlb.h>
+#include <linux/debugfs.h>
 
-#include <asm/debugfs.h>
 #include <asm/page.h>
 #include <asm/prom.h>
 #include <asm/fadump.h>
@@ -1557,7 +1557,7 @@ static void fadump_init_files(void)
 		return;
 	}
 
-	debugfs_create_file("fadump_region", 0444, powerpc_debugfs_root, NULL,
+	debugfs_create_file("fadump_region", 0444, arch_debugfs_dir, NULL,
 			    &fadump_region_fops);
 
 	if (fw_dump.dump_active) {
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 6010adcee16e..ba4afe3b5a9c 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -91,8 +91,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	isync
 	/* enable use of FP after return */
 #ifdef CONFIG_PPC32
-	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
-	tovirt(r5, r5)
+	addi	r5,r2,THREAD
 	lwz	r4,THREAD_FPEXC_MODE(r5)
 	ori	r9,r9,MSR_FP		/* enable FP for current */
 	or	r9,r9,r4
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index 8bccce6544b5..dedc17fac8f8 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 /* 1. Find the index of the entry we're executing in */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4				/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r4,r7,27,31,31			/* extract MSR[IS] */
@@ -85,7 +85,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	addi	r6,r6,10
 	slw	r6,r8,r6	/* convert to mask */
 
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r7
 
 	mfspr	r8,SPRN_MAS3
@@ -117,7 +117,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 
 	xori	r6,r4,1
 	slwi	r6,r6,5		/* setup new context with other address space */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r9
 	rlwimi	r7,r9,0,20,31
 	addi	r7,r7,(2f - 1b)
@@ -207,7 +207,7 @@ next_tlb_setup:
 
 	lis	r7,MSR_KERNEL@h
 	ori	r7,r7,MSR_KERNEL@l
-	bl	1f			/* Find our address */
+	bcl	20,31,$+4		/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
 	addi	r6,r6,(2f - 1b)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index ddc978a2d381..02d2928d1e01 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -70,7 +70,7 @@ _ENTRY(_start);
  * address.
  * r21 will be loaded with the physical runtime address of _stext
  */
-	bl	0f				/* Get our runtime address */
+	bcl	20,31,$+4			/* Get our runtime address */
 0:	mflr	r21				/* Make it accessible */
 	addis	r21,r21,(_stext - 0b)@ha
 	addi	r21,r21,(_stext - 0b)@l 	/* Get our current runtime base */
@@ -853,7 +853,7 @@ _GLOBAL(init_cpu_state)
 wmmucr:	mtspr	SPRN_MMUCR,r3			/* Put MMUCR */
 	sync
 
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -1045,7 +1045,7 @@ head_start_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r23
 	tlbsx	r23,0,r23
 	tlbre	r24,r23,0
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 79930b0bc781..f17ae2083733 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -712,6 +712,8 @@ _GLOBAL(copy_and_flush)
 	isync
 	blr
 
+_ASM_NOKPROBE_SYMBOL(copy_and_flush); /* Called in real mode */
+
 .align 8
 copy_to_here:
 
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 9a2f4265e6d2..0a9a0f301474 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -79,7 +79,7 @@ _ENTRY(_start);
 	mr	r23,r3
 	mr	r25,r4
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r8
 	addis	r3,r8,(is_second_reloc - 0b)@ha
 	lwz	r19,(is_second_reloc - 0b)@l(r3)
@@ -1132,7 +1132,7 @@ _GLOBAL(switch_to_as1)
 	bne	1b
 
 	/* Get the tlb entry used by the current running code */
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r4
 	tlbsx	0,r4
 
@@ -1166,7 +1166,7 @@ _GLOBAL(switch_to_as1)
 _GLOBAL(restore_to_as0)
 	mflr	r0
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r9
 	addi	r9,r9,1f - 0b
 
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 21a638aff72f..91a3be14808b 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -22,7 +22,6 @@
 #include <asm/processor.h>
 #include <asm/sstep.h>
 #include <asm/debug.h>
-#include <asm/debugfs.h>
 #include <asm/hvcall.h>
 #include <asm/inst.h>
 #include <linux/uaccess.h>
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 21bbd615ca41..a73f3f70a657 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -8,7 +8,6 @@
 #include <asm/asm-prototypes.h>
 #include <asm/kup.h>
 #include <asm/cputime.h>
-#include <asm/interrupt.h>
 #include <asm/hw_irq.h>
 #include <asm/interrupt.h>
 #include <asm/kprobes.h>
@@ -93,8 +92,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
 	user_exit_irqoff();
 
-	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
-		BUG_ON(!(regs->msr & MSR_RI));
+	BUG_ON(regs_is_unrecoverable(regs));
 	BUG_ON(!(regs->msr & MSR_PR));
 	BUG_ON(arch_irq_disabled_regs(regs));
 
@@ -463,9 +461,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
 {
 	unsigned long ret;
 
-	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
-		BUG_ON(!(regs->msr & MSR_RI));
-	BUG_ON(!(regs->msr & MSR_PR));
+	BUG_ON(regs_is_unrecoverable(regs));
 	BUG_ON(arch_irq_disabled_regs(regs));
 	CT_WARN_ON(ct_state() == CONTEXT_USER);
 
@@ -496,10 +492,8 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 	bool stack_store = current_thread_info()->flags &
 						_TIF_EMULATE_STACK_STORE;
 
-	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x) &&
-	    unlikely(!(regs->msr & MSR_RI)))
+	if (regs_is_unrecoverable(regs))
 		unrecoverable_exception(regs);
-	BUG_ON(regs->msr & MSR_PR);
 	/*
 	 * CT_WARN_ON comes here via program_check_exception,
 	 * so avoid recursion.
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 30b7736f0896..07093b7cdcb9 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -688,32 +688,24 @@ static void iommu_table_reserve_pages(struct iommu_table *tbl,
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
 
-	tbl->it_reserved_start = res_start;
-	tbl->it_reserved_end = res_end;
-
-	/* Check if res_start..res_end isn't empty and overlaps the table */
-	if (res_start && res_end &&
-			(tbl->it_offset + tbl->it_size < res_start ||
-			 res_end < tbl->it_offset))
-		return;
+	if (res_start < tbl->it_offset)
+		res_start = tbl->it_offset;
 
-	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
-		set_bit(i - tbl->it_offset, tbl->it_map);
-}
+	if (res_end > (tbl->it_offset + tbl->it_size))
+		res_end = tbl->it_offset + tbl->it_size;
 
-static void iommu_table_release_pages(struct iommu_table *tbl)
-{
-	int i;
+	/* Check if res_start..res_end is a valid range in the table */
+	if (res_start >= res_end) {
+		tbl->it_reserved_start = tbl->it_offset;
+		tbl->it_reserved_end = tbl->it_offset;
+		return;
+	}
 
-	/*
-	 * In case we have reserved the first bit, we should not emit
-	 * the warning below.
-	 */
-	if (tbl->it_offset == 0)
-		clear_bit(0, tbl->it_map);
+	tbl->it_reserved_start = res_start;
+	tbl->it_reserved_end = res_end;
 
 	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
-		clear_bit(i - tbl->it_offset, tbl->it_map);
+		set_bit(i - tbl->it_offset, tbl->it_map);
 }
 
 /*
@@ -777,6 +769,22 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
 	return tbl;
 }
 
+bool iommu_table_in_use(struct iommu_table *tbl)
+{
+	unsigned long start = 0, end;
+
+	/* ignore reserved bit0 */
+	if (tbl->it_offset == 0)
+		start = 1;
+	end = tbl->it_reserved_start - tbl->it_offset;
+	if (find_next_bit(tbl->it_map, end, start) != end)
+		return true;
+
+	start = tbl->it_reserved_end - tbl->it_offset;
+	end = tbl->it_size;
+	return find_next_bit(tbl->it_map, end, start) != end;
+}
+
 static void iommu_table_free(struct kref *kref)
 {
 	struct iommu_table *tbl;
@@ -793,10 +801,8 @@ static void iommu_table_free(struct kref *kref)
 
 	iommu_debugfs_del(tbl);
 
-	iommu_table_release_pages(tbl);
-
 	/* verify that table contains no entries */
-	if (!bitmap_empty(tbl->it_map, tbl->it_size))
+	if (iommu_table_in_use(tbl))
 		pr_warn("%s: Unexpected TCEs\n", __func__);
 
 	/* free bitmap */
@@ -1097,14 +1103,9 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	for (i = 0; i < tbl->nr_pools; i++)
 		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
 
-	iommu_table_release_pages(tbl);
-
-	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
+	if (iommu_table_in_use(tbl)) {
 		pr_err("iommu_tce: it_map is not empty");
 		ret = -EBUSY;
-		/* Undo iommu_table_release_pages, i.e. restore bit#0, etc */
-		iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
-				tbl->it_reserved_end);
 	} else {
 		memset(tbl->it_map, 0xff, sz);
 	}
diff --git a/arch/powerpc/kernel/kdebugfs.c b/arch/powerpc/kernel/kdebugfs.c
new file mode 100644
index 000000000000..36d3124d5a8b
--- /dev/null
+++ b/arch/powerpc/kernel/kdebugfs.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/init.h>
+
+struct dentry *arch_debugfs_dir;
+EXPORT_SYMBOL(arch_debugfs_dir);
+
+static int __init arch_kdebugfs_init(void)
+{
+	arch_debugfs_dir = debugfs_create_dir("powerpc", NULL);
+	return 0;
+}
+arch_initcall(arch_kdebugfs_init);
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 5be96feccb55..fb7de3543c03 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -29,7 +29,7 @@ _GLOBAL(reloc_offset)
 	li	r3, 0
 _GLOBAL(add_reloc_offset)
 	mflr	r0
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	PPC_LL	r4,(2f-1b)(r5)
 	subf	r5,r4,r5
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 39ab15419592..e5127b19fec2 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -67,7 +67,7 @@ _GLOBAL(reloc_got2)
 	srwi.	r8,r8,2
 	beqlr
 	mtctr	r8
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r0
 	lis	r4,1b@ha
 	addi	r4,r4,1b@l
@@ -237,7 +237,7 @@ _GLOBAL(copy_page)
 	addi	r3,r3,-4
 
 0:	twnei	r5, 0	/* WARN if r3 is not cache aligned */
-	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
+	EMIT_WARN_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
 
 	addi	r4,r4,-4
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4b761a18a74d..d38a019b38e1 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -255,7 +255,7 @@ _GLOBAL(scom970_write)
  * Physical (hardware) cpu id should be in r3.
  */
 _GLOBAL(kexec_wait)
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	addi	r5,r5,kexec_flag-1b
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 001e90cd8948..c3573430919d 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/vgaarb.h>
 #include <linux/numa.h>
+#include <linux/msi.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -1060,11 +1061,16 @@ void pcibios_bus_add_device(struct pci_dev *dev)
 
 int pcibios_add_device(struct pci_dev *dev)
 {
+	struct irq_domain *d;
+
 #ifdef CONFIG_PCI_IOV
 	if (ppc_md.pcibios_fixup_sriov)
 		ppc_md.pcibios_fixup_sriov(dev);
 #endif /* CONFIG_PCI_IOV */
 
+	d = dev_get_msi_domain(&dev->bus->dev);
+	if (d)
+		dev_set_msi_domain(&dev->dev, d);
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 185beb290580..50436b52c213 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1499,7 +1499,7 @@ static void __show_regs(struct pt_regs *regs)
 	    trap == INTERRUPT_DATA_STORAGE ||
 	    trap == INTERRUPT_ALIGNMENT) {
 		if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
-			pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+			pr_cont("DEAR: "REG" ESR: "REG" ", regs->dear, regs->esr);
 		else
 			pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
 	}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f620e04dc9bf..44b2cdc0aae3 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -640,7 +640,9 @@ static void __init early_reserve_mem(void)
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-#ifdef CONFIG_PPC32
+	if (!IS_ENABLED(CONFIG_PPC32))
+		return;
+
 	/* 
 	 * Handle the case where we might be booting from an old kexec
 	 * image that setup the mem_rsvmap as pairs of 32-bit values
@@ -661,7 +663,6 @@ static void __init early_reserve_mem(void)
 		}
 		return;
 	}
-#endif
 }
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a5bf355ce1d6..95a42d49e291 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1096,7 +1096,8 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 #else
 		0,
 #endif
-		.associativity = OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN),
+		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN) |
+		OV5_FEAT(OV5_FORM2_AFFINITY),
 		.bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
 		.micro_checkpoint = 0,
 		.reserved0 = 0,
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 0a0a33eb0d28..7c7093c17c45 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -373,8 +373,12 @@ void __init pt_regs_check(void)
 		     offsetof(struct user_pt_regs, trap));
 	BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
 		     offsetof(struct user_pt_regs, dar));
+	BUILD_BUG_ON(offsetof(struct pt_regs, dear) !=
+		     offsetof(struct user_pt_regs, dar));
 	BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
 		     offsetof(struct user_pt_regs, dsisr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, esr) !=
+		     offsetof(struct user_pt_regs, dsisr));
 	BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
 		     offsetof(struct user_pt_regs, result));
 
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
index 10e96f3e22fe..0508c14b4c28 100644
--- a/arch/powerpc/kernel/reloc_32.S
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -30,7 +30,7 @@ R_PPC_RELATIVE = 22
 _GLOBAL(relocate)
 
 	mflr	r0		/* Save our LR */
-	bl	0f		/* Find our current runtime address */
+	bcl	20,31,$+4	/* Find our current runtime address */
 0:	mflr	r12		/* Make it accessible */
 	mtlr	r0
 
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 8561dfb33f24..32ee17753eb4 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -429,7 +429,7 @@ static void rtas_event_scan(struct work_struct *w)
 
 	do_event_scan();
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	/* raw_ OK because just using CPU as starting point. */
 	cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
@@ -451,7 +451,7 @@ static void rtas_event_scan(struct work_struct *w)
 	schedule_delayed_work_on(cpu, &event_scan_work,
 		__round_jiffies_relative(event_scan_delay, cpu));
 
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index cc51fa52e783..1a998490fe60 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -11,10 +11,10 @@
 #include <linux/nospec.h>
 #include <linux/prctl.h>
 #include <linux/seq_buf.h>
+#include <linux/debugfs.h>
 
 #include <asm/asm-prototypes.h>
 #include <asm/code-patching.h>
-#include <asm/debugfs.h>
 #include <asm/security_features.h>
 #include <asm/setup.h>
 #include <asm/inst.h>
@@ -106,7 +106,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_barrier_nospec, barrier_nospec_get,
 static __init int barrier_nospec_debugfs_init(void)
 {
 	debugfs_create_file_unsafe("barrier_nospec", 0600,
-				   powerpc_debugfs_root, NULL,
+				   arch_debugfs_dir, NULL,
 				   &fops_barrier_nospec);
 	return 0;
 }
@@ -114,7 +114,7 @@ device_initcall(barrier_nospec_debugfs_init);
 
 static __init int security_feature_debugfs_init(void)
 {
-	debugfs_create_x64("security_features", 0400, powerpc_debugfs_root,
+	debugfs_create_x64("security_features", 0400, arch_debugfs_dir,
 			   &powerpc_security_features);
 	return 0;
 }
@@ -420,7 +420,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set,
 
 static __init int stf_barrier_debugfs_init(void)
 {
-	debugfs_create_file_unsafe("stf_barrier", 0600, powerpc_debugfs_root,
+	debugfs_create_file_unsafe("stf_barrier", 0600, arch_debugfs_dir,
 				   NULL, &fops_stf_barrier);
 	return 0;
 }
@@ -748,7 +748,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get,
 static __init int count_cache_flush_debugfs_init(void)
 {
 	debugfs_create_file_unsafe("count_cache_flush", 0600,
-				   powerpc_debugfs_root, NULL,
+				   arch_debugfs_dir, NULL,
 				   &fops_count_cache_flush);
 	return 0;
 }
@@ -834,9 +834,9 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set
 
 static __init int rfi_flush_debugfs_init(void)
 {
-	debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
-	debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
-	debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush);
+	debugfs_create_file("rfi_flush", 0600, arch_debugfs_dir, NULL, &fops_rfi_flush);
+	debugfs_create_file("entry_flush", 0600, arch_debugfs_dir, NULL, &fops_entry_flush);
+	debugfs_create_file("uaccess_flush", 0600, arch_debugfs_dir, NULL, &fops_uaccess_flush);
 	return 0;
 }
 device_initcall(rfi_flush_debugfs_init);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index aa9c2d01424a..b1e43b69a559 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -33,7 +33,6 @@
 #include <linux/of_platform.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
-#include <asm/debugfs.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/prom.h>
@@ -773,18 +772,6 @@ static int __init check_cache_coherency(void)
 late_initcall(check_cache_coherency);
 #endif /* CONFIG_CHECK_CACHE_COHERENCY */
 
-#ifdef CONFIG_DEBUG_FS
-struct dentry *powerpc_debugfs_root;
-EXPORT_SYMBOL(powerpc_debugfs_root);
-
-static int powerpc_debugfs_init(void)
-{
-	powerpc_debugfs_root = debugfs_create_dir("powerpc", NULL);
-	return 0;
-}
-arch_initcall(powerpc_debugfs_init);
-#endif
-
 void ppc_printk_progress(char *s, unsigned short hex)
 {
 	pr_info("%s\n", s);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1ff258f6c76c..eaa79a0996d1 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -32,7 +32,6 @@
 #include <linux/nmi.h>
 #include <linux/pgtable.h>
 
-#include <asm/debugfs.h>
 #include <asm/kvm_guest.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 447b78a87c8f..9cc7d3dbf439 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -78,6 +78,7 @@ struct task_struct *secondary_current;
 bool has_big_cores;
 bool coregroup_enabled;
 bool thread_group_shares_l2;
+bool thread_group_shares_l3;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -101,7 +102,7 @@ enum {
 
 #define MAX_THREAD_LIST_SIZE	8
 #define THREAD_GROUP_SHARE_L1   1
-#define THREAD_GROUP_SHARE_L2   2
+#define THREAD_GROUP_SHARE_L2_L3 2
 struct thread_groups {
 	unsigned int property;
 	unsigned int nr_groups;
@@ -122,14 +123,20 @@ static struct thread_groups_list tgl[NR_CPUS] __initdata;
  * On big-cores system, thread_group_l1_cache_map for each CPU corresponds to
  * the set its siblings that share the L1-cache.
  */
-static DEFINE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
 
 /*
  * On some big-cores system, thread_group_l2_cache_map for each CPU
  * corresponds to the set its siblings within the core that share the
  * L2-cache.
  */
-static DEFINE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
+
+/*
+ * On P10, thread_group_l3_cache_map for each CPU is equal to the
+ * thread_group_l2_cache_map
+ */
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l3_cache_map);
 
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
@@ -889,19 +896,41 @@ out:
 	return tg;
 }
 
+static int update_mask_from_threadgroup(cpumask_var_t *mask, struct thread_groups *tg, int cpu, int cpu_group_start)
+{
+	int first_thread = cpu_first_thread_sibling(cpu);
+	int i;
+
+	zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cpu));
+
+	for (i = first_thread; i < first_thread + threads_per_core; i++) {
+		int i_group_start = get_cpu_thread_group_start(i, tg);
+
+		if (unlikely(i_group_start == -1)) {
+			WARN_ON_ONCE(1);
+			return -ENODATA;
+		}
+
+		if (i_group_start == cpu_group_start)
+			cpumask_set_cpu(i, *mask);
+	}
+
+	return 0;
+}
+
 static int __init init_thread_group_cache_map(int cpu, int cache_property)
 
 {
-	int first_thread = cpu_first_thread_sibling(cpu);
-	int i, cpu_group_start = -1, err = 0;
+	int cpu_group_start = -1, err = 0;
 	struct thread_groups *tg = NULL;
 	cpumask_var_t *mask = NULL;
 
 	if (cache_property != THREAD_GROUP_SHARE_L1 &&
-	    cache_property != THREAD_GROUP_SHARE_L2)
+	    cache_property != THREAD_GROUP_SHARE_L2_L3)
 		return -EINVAL;
 
 	tg = get_thread_groups(cpu, cache_property, &err);
+
 	if (!tg)
 		return err;
 
@@ -912,25 +941,18 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
 		return -ENODATA;
 	}
 
-	if (cache_property == THREAD_GROUP_SHARE_L1)
+	if (cache_property == THREAD_GROUP_SHARE_L1) {
 		mask = &per_cpu(thread_group_l1_cache_map, cpu);
-	else if (cache_property == THREAD_GROUP_SHARE_L2)
+		update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+	}
+	else if (cache_property == THREAD_GROUP_SHARE_L2_L3) {
 		mask = &per_cpu(thread_group_l2_cache_map, cpu);
-
-	zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cpu));
-
-	for (i = first_thread; i < first_thread + threads_per_core; i++) {
-		int i_group_start = get_cpu_thread_group_start(i, tg);
-
-		if (unlikely(i_group_start == -1)) {
-			WARN_ON_ONCE(1);
-			return -ENODATA;
-		}
-
-		if (i_group_start == cpu_group_start)
-			cpumask_set_cpu(i, *mask);
+		update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+		mask = &per_cpu(thread_group_l3_cache_map, cpu);
+		update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
 	}
 
+
 	return 0;
 }
 
@@ -1020,14 +1042,16 @@ static int __init init_big_cores(void)
 	has_big_cores = true;
 
 	for_each_possible_cpu(cpu) {
-		int err = init_thread_group_cache_map(cpu, THREAD_GROUP_SHARE_L2);
+		int err = init_thread_group_cache_map(cpu, THREAD_GROUP_SHARE_L2_L3);
 
 		if (err)
 			return err;
 	}
 
 	thread_group_shares_l2 = true;
-	pr_debug("L2 cache only shared by the threads in the small core\n");
+	thread_group_shares_l3 = true;
+	pr_debug("L2/L3 cache only shared by the threads in the small core\n");
+
 	return 0;
 }
 
@@ -1085,7 +1109,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 
 	if (cpu_to_chip_id(boot_cpuid) != -1) {
-		int idx = num_possible_cpus() / threads_per_core;
+		int idx = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
 
 		/*
 		 * All threads of a core will all belong to the same core,
@@ -1376,7 +1400,7 @@ static bool update_mask_by_l2(int cpu, cpumask_var_t *mask)
 	l2_cache = cpu_to_l2cache(cpu);
 	if (!l2_cache || !*mask) {
 		/* Assume only core siblings share cache with this CPU */
-		for_each_cpu(i, submask_fn(cpu))
+		for_each_cpu(i, cpu_sibling_mask(cpu))
 			set_cpus_related(cpu, i, cpu_l2_cache_mask);
 
 		return false;
@@ -1418,6 +1442,8 @@ static void remove_cpu_from_masks(int cpu)
 	struct cpumask *(*mask_fn)(int) = cpu_sibling_mask;
 	int i;
 
+	unmap_cpu_from_node(cpu);
+
 	if (shared_caches)
 		mask_fn = cpu_l2_cache_mask;
 
@@ -1502,7 +1528,9 @@ static void add_cpu_to_masks(int cpu)
 	 * This CPU will not be in the online mask yet so we need to manually
 	 * add it to it's own thread sibling mask.
 	 */
+	map_cpu_to_node(cpu, cpu_to_node(cpu));
 	cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+	cpumask_set_cpu(cpu, cpu_core_mask(cpu));
 
 	for (i = first_thread; i < first_thread + threads_per_core; i++)
 		if (cpu_online(i))
@@ -1520,11 +1548,6 @@ static void add_cpu_to_masks(int cpu)
 	if (chip_id_lookup_table && ret)
 		chip_id = cpu_to_chip_id(cpu);
 
-	if (chip_id == -1) {
-		cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu));
-		goto out;
-	}
-
 	if (shared_caches)
 		submask_fn = cpu_l2_cache_mask;
 
@@ -1534,6 +1557,10 @@ static void add_cpu_to_masks(int cpu)
 	/* Skip all CPUs already part of current CPU core mask */
 	cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
 
+	/* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+	if (chip_id == -1)
+		cpumask_and(mask, mask, cpu_cpu_mask(cpu));
+
 	for_each_cpu(i, mask) {
 		if (chip_id == cpu_to_chip_id(i)) {
 			or_cpumasks_related(cpu, i, submask_fn, cpu_core_mask);
@@ -1543,7 +1570,6 @@ static void add_cpu_to_masks(int cpu)
 		}
 	}
 
-out:
 	free_cpumask_var(mask);
 }
 
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 2b0d04a1b7d2..9e4a4a7af380 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -8,6 +8,7 @@
  * Copyright 2018 Nick Piggin, Michael Ellerman, IBM Corp.
  */
 
+#include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/module.h>
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index bf4ae0f0e36c..825931e400df 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -41,20 +41,13 @@ static inline long do_mmap2(unsigned long addr, size_t len,
 			unsigned long prot, unsigned long flags,
 			unsigned long fd, unsigned long off, int shift)
 {
-	long ret = -EINVAL;
-
 	if (!arch_validate_prot(prot, addr))
-		goto out;
+		return -EINVAL;
 
-	if (shift) {
-		if (off & ((1 << shift) - 1))
-			goto out;
-		off >>= shift;
-	}
+	if (!IS_ALIGNED(off, 1 << shift))
+		return -EINVAL;
 
-	ret = ksys_mmap_pgoff(addr, len, prot, flags, fd, off);
-out:
-	return ret;
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> shift);
 }
 
 SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index b9a047d92ec0..8e83d19fe8fa 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -164,7 +164,7 @@ static void tau_work_func(struct work_struct *work)
 	queue_work(tau_workq, work);
 }
 
-DECLARE_WORK(tau_work, tau_work_func);
+static DECLARE_WORK(tau_work, tau_work_func);
 
 /*
  * setup the TAU
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index c487ba5a6e11..934d8ae66cc6 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -31,6 +31,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/cputime.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
@@ -52,8 +53,6 @@
 #include <linux/irq_work.h>
 #include <linux/of_clk.h>
 #include <linux/suspend.h>
-#include <linux/sched/cputime.h>
-#include <linux/sched/clock.h>
 #include <linux/processor.h>
 #include <asm/trace.h>
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index cd5f633c9b1b..4390f8d72126 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -37,10 +37,10 @@
 #include <linux/smp.h>
 #include <linux/console.h>
 #include <linux/kmsg_dump.h>
+#include <linux/debugfs.h>
 
 #include <asm/emulated_ops.h>
 #include <linux/uaccess.h>
-#include <asm/debugfs.h>
 #include <asm/interrupt.h>
 #include <asm/io.h>
 #include <asm/machdep.h>
@@ -427,7 +427,7 @@ void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
 	return;
 
 nonrecoverable:
-	regs_set_return_msr(regs, regs->msr & ~MSR_RI);
+	regs_set_unrecoverable(regs);
 #endif
 }
 DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
@@ -497,7 +497,7 @@ out:
 		die("Unrecoverable nested System Reset", regs, SIGABRT);
 #endif
 	/* Must die if the interrupt is not recoverable */
-	if (!(regs->msr & MSR_RI)) {
+	if (regs_is_unrecoverable(regs)) {
 		/* For the reason explained in die_mce, nmi_exit before die */
 		nmi_exit();
 		die("Unrecoverable System Reset", regs, SIGABRT);
@@ -549,7 +549,7 @@ static inline int check_io_access(struct pt_regs *regs)
 			printk(KERN_DEBUG "%s bad port %lx at %p\n",
 			       (*nip & 0x100)? "OUT to": "IN from",
 			       regs->gpr[rb] - _IO_BASE, nip);
-			regs_set_return_msr(regs, regs->msr | MSR_RI);
+			regs_set_recoverable(regs);
 			regs_set_return_ip(regs, extable_fixup(entry));
 			return 1;
 		}
@@ -561,7 +561,7 @@ static inline int check_io_access(struct pt_regs *regs)
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 /* On 4xx, the reason for the machine check or program exception
    is in the ESR. */
-#define get_reason(regs)	((regs)->dsisr)
+#define get_reason(regs)	((regs)->esr)
 #define REASON_FP		ESR_FP
 #define REASON_ILLEGAL		(ESR_PIL | ESR_PUO)
 #define REASON_PRIVILEGED	ESR_PPR
@@ -839,7 +839,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
 
 bail:
 	/* Must die if the interrupt is not recoverable */
-	if (!(regs->msr & MSR_RI))
+	if (regs_is_unrecoverable(regs))
 		die_mce("Unrecoverable Machine check", regs, SIGBUS);
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -1481,8 +1481,13 @@ static void do_program_check(struct pt_regs *regs)
 
 		if (!(regs->msr & MSR_PR) &&  /* not user-mode */
 		    report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
-			regs_add_return_ip(regs, 4);
-			return;
+			const struct exception_table_entry *entry;
+
+			entry = search_exception_tables(bugaddr);
+			if (entry) {
+				regs_set_return_ip(regs, extable_fixup(entry) + regs->nip - bugaddr);
+				return;
+			}
 		}
 		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
 		return;
@@ -2271,7 +2276,7 @@ static int __init ppc_warn_emulated_init(void)
 	struct ppc_emulated_entry *entries = (void *)&ppc_emulated;
 
 	dir = debugfs_create_dir("emulated_instructions",
-				 powerpc_debugfs_root);
+				 arch_debugfs_dir);
 
 	debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated);
 
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index fc120fac1910..ba03eedfdcd8 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -65,9 +65,8 @@ _GLOBAL(load_up_altivec)
 1:
 	/* enable use of VMX after return */
 #ifdef CONFIG_PPC32
-	mfspr	r5,SPRN_SPRG_THREAD		/* current task's THREAD (phys) */
+	addi	r5,r2,THREAD
 	oris	r9,r9,MSR_VEC@h
-	tovirt(r5, r5)
 #else
 	ld	r4,PACACURRENT(r13)
 	addi	r5,r4,THREAD		/* Get THREAD */
@@ -81,7 +80,6 @@ _GLOBAL(load_up_altivec)
 	li	r4,1
 	stb	r4,THREAD_LOAD_VEC(r5)
 	addi	r6,r5,THREAD_VRSTATE
-	li	r4,1
 	li	r10,VRSTATE_VSCR
 	stw	r4,THREAD_USED_VR(r5)
 	lvx	v0,r10,r6