Merge remote-tracking branch 'lts/linux-4.4.y' into linux-linaro-lsk-v4.4

Conflicts:
	also change cpu_enable_uao in arch/arm64/include/asm/processor.h
	comment unmatch fixed in arch/arm64/kernel/suspend.c

Author: Alex Shi

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 36
+SUBLEVEL = 38
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

arch/arc/include/asm/delay.h

@@ -22,10 +22,11 @@
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
-	"	lp  1f	\n"
-	"	nop	\n"
-	"1:		\n"
-	: "+l"(loops));
+	"	mov lp_count, %0	\n"
+	"	lp  1f			\n"
+	"	nop			\n"
+	"1:				\n"
+	: : "r"(loops));
 }
 
 extern void __bad_udelay(void);

arch/arm64/include/asm/cpufeature.h

@@ -81,7 +81,7 @@ struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
 	bool (*matches)(const struct arm64_cpu_capabilities *);
-	void (*enable)(void *);		/* Called on all active CPUs */
+	int (*enable)(void *);		/* Called on all active CPUs */
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;

arch/arm64/include/asm/processor.h

@@ -190,7 +190,7 @@ static inline void spin_lock_prefetch(const void *ptr)
 
 #endif
 
-void cpu_enable_pan(void *__unused);
-void cpu_enable_uao(void *__unused);
+int cpu_enable_pan(void *__unused);
+int cpu_enable_uao(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */

arch/arm64/kernel/cpufeature.c

@@ -19,7 +19,9 @@
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
+#include <linux/cpumask.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -823,7 +825,13 @@ enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 
 	for (i = 0; caps[i].matches; i++)
 		if (caps[i].enable && cpus_have_cap(caps[i].capability))
-			on_each_cpu(caps[i].enable, NULL, true);
+			/*
+			 * Use stop_machine() as it schedules the work allowing
+			 * us to modify PSTATE, instead of on_each_cpu() which
+			 * uses an IPI, giving us a PSTATE that disappears when
+			 * we return.
+			 */
+			stop_machine(caps[i].enable, NULL, cpu_online_mask);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

arch/arm64/kernel/suspend.c

@@ -1,7 +1,9 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
@@ -88,11 +90,16 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		ret = fn(arg);
 
 		/*
-		 * Never gets here, unless the suspend finisher fails.
-		 * Successful cpu_suspend() should return from cpu_resume(),
-		 * returning through this code path is considered an error
-		 * If the return value is set to 0 force ret = -EOPNOTSUPP
-		 * to make sure a proper error condition is propagated
+		 * PSTATE was not saved over suspend/resume, re-enable any
+		 * detected features that might not have been set correctly.
+		 */
+		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+				CONFIG_ARM64_PAN));
+
+		/*
+		 * Restore HW breakpoint registers to sane values
+		 * before debug exceptions are possibly reenabled
+		 * through local_dbg_restore.
 		 */
 		if (!ret)
 			ret = -EOPNOTSUPP;

arch/arm64/mm/fault.c

@@ -29,7 +29,9 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/preempt.h>
 
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -641,9 +643,17 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 NOKPROBE_SYMBOL(do_debug_exception);
 
 #ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
 {
+	/*
+	 * We modify PSTATE. This won't work from irq context as the PSTATE
+	 * is discarded once we return from the exception.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
 	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+	asm(SET_PSTATE_PAN(1));
+	return 0;
 }
 #endif /* CONFIG_ARM64_PAN */
 
@@ -654,7 +664,7 @@ void cpu_enable_pan(void *__unused)
  * We need to enable the feature at runtime (instead of adding it to
  * PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
  */
-void cpu_enable_uao(void *__unused)
+int cpu_enable_uao(void *__unused)
 {
 	asm(SET_PSTATE_UAO(1));
 }

arch/sparc/kernel/signal_32.c

@@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv_and_exit;
 
 	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
@@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 
 	synchronize_user_stack();
 	sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
-	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;
 
 	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))

arch/sparc/mm/init_64.c

@@ -800,8 +800,10 @@ struct mdesc_mblock {
 };
 static struct mdesc_mblock *mblocks;
 static int num_mblocks;
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask);
 
-static unsigned long ra_to_pa(unsigned long addr)
+static unsigned long __init ra_to_pa(unsigned long addr)
 {
 	int i;
 
@@ -817,8 +819,11 @@ static unsigned long ra_to_pa(unsigned long addr)
 	return addr;
 }
 
-static int find_node(unsigned long addr)
+static int __init find_node(unsigned long addr)
 {
+	static bool search_mdesc = true;
+	static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
+	static int last_index;
 	int i;
 
 	addr = ra_to_pa(addr);
@@ -828,13 +833,30 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	/* The following condition has been observed on LDOM guests.*/
-	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
-		" rule. Some physical memory will be owned by node 0.");
-	return 0;
+	/* The following condition has been observed on LDOM guests because
+	 * node_masks only contains the best latency mask and value.
+	 * LDOM guest's mdesc can contain a single latency group to
+	 * cover multiple address range. Print warning message only if the
+	 * address cannot be found in node_masks nor mdesc.
+	 */
+	if ((search_mdesc) &&
+	    ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
+		/* find the available node in the mdesc */
+		last_index = find_numa_node_for_addr(addr, &last_mem_mask);
+		numadbg("find_node: latency group for address 0x%lx is %d\n",
+			addr, last_index);
+		if ((last_index < 0) || (last_index >= num_node_masks)) {
+			/* WARN_ONCE() and use default group 0 */
+			WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
+			search_mdesc = false;
+			last_index = 0;
+		}
+	}
+
+	return last_index;
 }
 
-static u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;
@@ -1158,6 +1180,41 @@ int __node_distance(int from, int to)
 	return numa_latency[from][to];
 }
 
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask)
+{
+	struct mdesc_handle *md = mdesc_grab();
+	u64 node, arc;
+	int i = 0;
+
+	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+	if (node == MDESC_NODE_NULL)
+		goto out;
+
+	mdesc_for_each_node_by_name(md, node, "group") {
+		mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
+			u64 target = mdesc_arc_target(md, arc);
+			struct mdesc_mlgroup *m = find_mlgroup(target);
+
+			if (!m)
+				continue;
+			if ((pa & m->mask) == m->match) {
+				if (pnode_mask) {
+					pnode_mask->mask = m->mask;
+					pnode_mask->val = m->match;
+				}
+				mdesc_release(md);
+				return i;
+			}
+		}
+		i++;
+	}
+
+out:
+	mdesc_release(md);
+	return -1;
+}
+
 static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 {
 	int i;

arch/x86/kernel/head_32.S

@@ -571,7 +571,7 @@ early_idt_handler_common:
 	movl %eax,%ds
 	movl %eax,%es
 
-	cmpl $(__KERNEL_CS),32(%esp)
+	cmpw $(__KERNEL_CS),32(%esp)
 	jne 10f
 
 	leal 28(%esp),%eax	# Pointer to %eip