Merge remote-tracking branch 'origin/master' into perf/core

Further perf/core patches will depend on:

  d3f7b1bb2040 ("mm/gup: fix gup_fast with dynamic page table folding")

which is already in Linus' tree.

13 files changed, 108 insertions, 175 deletions

diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
index e172c3333a84..1a76f2d6f694 100644
--- a/arch/arc/kernel/ctx_sw.c
+++ b/arch/arc/kernel/ctx_sw.c
@@ -14,9 +14,6 @@
 #include <asm/asm-offsets.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
-#ifdef CONFIG_ARC_PLAT_EZNPS
-#include <plat/ctop.h>
-#endif
 
 #define KSP_WORD_OFF 	((TASK_THREAD + THREAD_KSP) / 4)
 
@@ -68,16 +65,9 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
 #ifndef CONFIG_SMP
 		"st  %2, [@_current_task]	\n\t"
 #else
-#ifdef CONFIG_ARC_PLAT_EZNPS
-		"lr   r24, [%4]		\n\t"
-#ifndef CONFIG_EZNPS_MTM_EXT
-		"lsr  r24, r24, 4		\n\t"
-#endif
-#else
 		"lr   r24, [identity]		\n\t"
 		"lsr  r24, r24, 8		\n\t"
 		"bmsk r24, r24, 7		\n\t"
-#endif
 		"add2 r24, @_current_task, r24	\n\t"
 		"st   %2,  [r24]		\n\t"
 #endif
@@ -115,9 +105,6 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
 
 		: "=r"(tmp)
 		: "n"(KSP_WORD_OFF), "r"(next), "r"(prev)
-#ifdef CONFIG_ARC_PLAT_EZNPS
-		, "i"(CTOP_AUX_LOGIC_GLOBAL_ID)
-#endif
 		: "blink"
 	);
 
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index fa86d13df5ed..721d465f1580 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -29,8 +29,6 @@ static void __init arc_set_early_base_baud(unsigned long dt_root)
 	else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp") ||
 		 of_flat_dt_is_compatible(dt_root, "snps,hsdk"))
 		arc_base_baud = 33333333;	/* Fixed 33MHz clk (AXS10x & HSDK) */
-	else if (of_flat_dt_is_compatible(dt_root, "ezchip,arc-nps"))
-		arc_base_baud = 800000000;      /* Fixed 800MHz clk (NPS) */
 	else
 		arc_base_baud = 50000000;	/* Fixed default 50MHz */
 }
diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c
index d04837d91b40..03f8b1be0c3a 100644
--- a/arch/arc/kernel/disasm.c
+++ b/arch/arc/kernel/disasm.c
@@ -339,7 +339,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state,
 
 	case op_LDWX_S:	/* LDWX_S c, [b, u6] */
 		state->x = 1;
-		/* intentional fall-through */
+		fallthrough;
 
 	case op_LDW_S:	/* LDW_S c, [b, u6] */
 		state->zz = 2;
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 17fd1ed700cc..9152782444b5 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -67,7 +67,22 @@
 	sr	r5, [ARC_REG_LPB_CTRL]
 1:
 #endif /* CONFIG_ARC_LPB_DISABLE */
-#endif
+
+	/* On HSDK, CCMs need to remapped super early */
+#ifdef CONFIG_ARC_SOC_HSDK
+	mov	r6, 0x60000000
+	lr	r5, [ARC_REG_ICCM_BUILD]
+	breq	r5, 0, 1f
+	sr	r6, [ARC_REG_AUX_ICCM]
+1:
+	lr	r5, [ARC_REG_DCCM_BUILD]
+	breq	r5, 0, 2f
+	sr	r6, [ARC_REG_AUX_DCCM]
+2:
+#endif	/* CONFIG_ARC_SOC_HSDK */
+
+#endif	/* CONFIG_ISA_ARCV2 */
+
 	; Config DSP_CTRL properly, so kernel may use integer multiply,
 	; multiply-accumulate, and divide operations
 	DSP_EARLY_INIT
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 7d3efe83cba7..cabef45f11df 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -388,6 +388,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 {
 
 	ri->ret_addr = (kprobe_opcode_t *) regs->blink;
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->blink = (unsigned long)&kretprobe_trampoline;
@@ -396,58 +397,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 static int __kprobes trampoline_probe_handler(struct kprobe *p,
 					      struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address) {
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-		}
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-	regs->ret = orig_ret_address;
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
+	regs->ret = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 
 	/* By returning a non zero value, we are telling the kprobe handler
 	 * that we don't want the post_handler to run
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 661fd842ea97..145722f80c9b 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -562,7 +562,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, has_interrupts;
+	int i, has_interrupts, irq = -1;
 	int counter_size;	/* in bits */
 
 	union cc_name {
@@ -638,22 +638,25 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	};
 
 	if (has_interrupts) {
-		int irq = platform_get_irq(pdev, 0);
+		irq = platform_get_irq(pdev, 0);
+		if (irq >= 0) {
+			int ret;
 
-		if (irq < 0) {
-			pr_err("Cannot get IRQ number for the platform\n");
-			return -ENODEV;
-		}
+			arc_pmu->irq = irq;
 
-		arc_pmu->irq = irq;
+			/* intc map function ensures irq_set_percpu_devid() called */
+			ret = request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
+						 this_cpu_ptr(&arc_pmu_cpu));
 
-		/* intc map function ensures irq_set_percpu_devid() called */
-		request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
-				   this_cpu_ptr(&arc_pmu_cpu));
+			if (!ret)
+				on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
+			else
+				irq = -1;
+		}
 
-		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
+	}
 
-	} else
+	if (irq == -1)
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
 	/*
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index efeba1fe7252..37f724ad5e39 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -116,17 +116,6 @@ void arch_cpu_idle(void)
 		:"I"(arg)); /* can't be "r" has to be embedded const */
 }
 
-#elif defined(CONFIG_EZNPS_MTM_EXT)	/* ARC700 variant in NPS */
-
-void arch_cpu_idle(void)
-{
-	/* only the calling HW thread needs to sleep */
-	__asm__ __volatile__(
-		".word %0	\n"
-		:
-		:"i"(CTOP_INST_HWSCHD_WFT_IE12));
-}
-
 #else	/* ARC700 */
 
 void arch_cpu_idle(void)
@@ -278,10 +267,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long usp)
 	 */
 	regs->status32 = STATUS_U_MASK | STATUS_L_MASK | ISA_INIT_STATUS_BITS;
 
-#ifdef CONFIG_EZNPS_MTM_EXT
-	regs->eflags = 0;
-#endif
-
 	fpu_init_task(regs);
 
 	/* bogus seed values for debugging */
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 3d57ed0d8535..2be55fb96d87 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -321,7 +321,7 @@ static void arc_restart_syscall(struct k_sigaction *ka, struct pt_regs *regs)
 			regs->r0 = -EINTR;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 
 	case -ERESTARTNOINTR:
 		/*
@@ -394,6 +394,6 @@ void do_notify_resume(struct pt_regs *regs)
 	 * ASM glue gaurantees that this is only called when returning to
 	 * user mode
 	 */
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index eca35e02ce06..52906d314537 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -226,7 +226,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	}
 
 	if (!cpu_online(cpu)) {
-		pr_info("Timeout: CPU%u FAILED to comeup !!!\n", cpu);
+		pr_info("Timeout: CPU%u FAILED to come up !!!\n", cpu);
 		return -1;
 	}
 
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index feba91c9d969..f73da203b170 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -38,15 +38,27 @@
 
 #ifdef CONFIG_ARC_DW2_UNWIND
 
-static void seed_unwind_frame_info(struct task_struct *tsk,
-				   struct pt_regs *regs,
-				   struct unwind_frame_info *frame_info)
+static int
+seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs,
+		       struct unwind_frame_info *frame_info)
 {
-	/*
-	 * synchronous unwinding (e.g. dump_stack)
-	 *  - uses current values of SP and friends
-	 */
-	if (tsk == NULL && regs == NULL) {
+	if (regs) {
+		/*
+		 * Asynchronous unwinding of intr/exception
+		 *  - Just uses the pt_regs passed
+		 */
+		frame_info->task = tsk;
+
+		frame_info->regs.r27 = regs->fp;
+		frame_info->regs.r28 = regs->sp;
+		frame_info->regs.r31 = regs->blink;
+		frame_info->regs.r63 = regs->ret;
+		frame_info->call_frame = 0;
+	} else if (tsk == NULL || tsk == current) {
+		/*
+		 * synchronous unwinding (e.g. dump_stack)
+		 *  - uses current values of SP and friends
+		 */
 		unsigned long fp, sp, blink, ret;
 		frame_info->task = current;
 
@@ -63,13 +75,17 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 		frame_info->regs.r31 = blink;
 		frame_info->regs.r63 = ret;
 		frame_info->call_frame = 0;
-	} else if (regs == NULL) {
+	} else {
 		/*
-		 * Asynchronous unwinding of sleeping task
-		 *  - Gets SP etc from task's pt_regs (saved bottom of kernel
-		 *    mode stack of task)
+		 * Asynchronous unwinding of a likely sleeping task
+		 *  - first ensure it is actually sleeping
+		 *  - if so, it will be in __switch_to, kernel mode SP of task
+		 *    is safe-kept and BLINK at a well known location in there
 		 */
 
+		if (tsk->state == TASK_RUNNING)
+			return -1;
+
 		frame_info->task = tsk;
 
 		frame_info->regs.r27 = TSK_K_FP(tsk);
@@ -90,19 +106,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 		frame_info->regs.r28 += 60;
 		frame_info->call_frame = 0;
 
-	} else {
-		/*
-		 * Asynchronous unwinding of intr/exception
-		 *  - Just uses the pt_regs passed
-		 */
-		frame_info->task = tsk;
-
-		frame_info->regs.r27 = regs->fp;
-		frame_info->regs.r28 = regs->sp;
-		frame_info->regs.r31 = regs->blink;
-		frame_info->regs.r63 = regs->ret;
-		frame_info->call_frame = 0;
 	}
+	return 0;
 }
 
 #endif
@@ -112,11 +117,12 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 		int (*consumer_fn) (unsigned int, void *), void *arg)
 {
 #ifdef CONFIG_ARC_DW2_UNWIND
-	int ret = 0;
+	int ret = 0, cnt = 0;
 	unsigned int address;
 	struct unwind_frame_info frame_info;
 
-	seed_unwind_frame_info(tsk, regs, &frame_info);
+	if (seed_unwind_frame_info(tsk, regs, &frame_info))
+		return 0;
 
 	while (1) {
 		address = UNW_PC(&frame_info);
@@ -132,6 +138,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 			break;
 
 		frame_info.regs.r63 = frame_info.regs.r31;
+
+		if (cnt++ > 128) {
+			printk("unwinder looping too long, aborting !\n");
+			return 0;
+		}
 	}
 
 	return address;		/* return the last address it saw */
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 28e8bf04b253..a331bb5d8319 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -18,44 +18,37 @@
 
 #define ARC_PATH_MAX	256
 
-/*
- * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
- *   -Prints 3 regs per line and a CR.
- *   -To continue, callee regs right after scratch, special handling of CR
- */
-static noinline void print_reg_file(long *reg_rev, int start_num)
+static noinline void print_regs_scratch(struct pt_regs *regs)
 {
-	unsigned int i;
-	char buf[512];
-	int n = 0, len = sizeof(buf);
-
-	for (i = start_num; i < start_num + 13; i++) {
-		n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t",
-			       i, (unsigned long)*reg_rev);
-
-		if (((i + 1) % 3) == 0)
-			n += scnprintf(buf + n, len - n, "\n");
-
-		/* because pt_regs has regs reversed: r12..r0, r25..r13 */
-		if (is_isa_arcv2() && start_num == 0)
-			reg_rev++;
-		else
-			reg_rev--;
-	}
-
-	if (start_num != 0)
-		n += scnprintf(buf + n, len - n, "\n\n");
+	pr_cont("BTA: 0x%08lx\n SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
+		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
+	pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
+		regs->lp_start, regs->lp_end, regs->lp_count);
 
-	/* To continue printing callee regs on same line as scratch regs */
-	if (start_num == 0)
-		pr_info("%s", buf);
-	else
-		pr_cont("%s\n", buf);
+	pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n"	\
+		"r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n"	\
+		"r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n"	\
+		"r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n"	\
+		"r12: 0x%08lx\t",
+		regs->r0, regs->r1, regs->r2,
+		regs->r3, regs->r4, regs->r5,
+		regs->r6, regs->r7, regs->r8,
+		regs->r9, regs->r10, regs->r11,
+		regs->r12);
 }
 
-static void show_callee_regs(struct callee_regs *cregs)
+static void print_regs_callee(struct callee_regs *regs)
 {
-	print_reg_file(&(cregs->r13), 13);
+	pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n"			\
+		"r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n"	\
+		"r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n"	\
+		"r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n"	\
+		"r24: 0x%08lx\tr25: 0x%08lx\n",
+		regs->r13, regs->r14,
+		regs->r15, regs->r16, regs->r17,
+		regs->r18, regs->r19, regs->r20,
+		regs->r21, regs->r22, regs->r23,
+		regs->r24, regs->r25);
 }
 
 static void print_task_path_n_nm(struct task_struct *tsk)
@@ -175,7 +168,7 @@ static void show_ecr_verbose(struct pt_regs *regs)
 void show_regs(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
-	struct callee_regs *cregs;
+	struct callee_regs *cregs = (struct callee_regs *)tsk->thread.callee_reg;
 
 	/*
 	 * generic code calls us with preemption disabled, but some calls
@@ -204,25 +197,15 @@ void show_regs(struct pt_regs *regs)
 			STS_BIT(regs, A2), STS_BIT(regs, A1),
 			STS_BIT(regs, E2), STS_BIT(regs, E1));
 #else
-	pr_cont(" [%2s%2s%2s%2s]",
+	pr_cont(" [%2s%2s%2s%2s]   ",
 			STS_BIT(regs, IE),
 			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
 			STS_BIT(regs, DE), STS_BIT(regs, AE));
 #endif
-	pr_cont("  BTA: 0x%08lx\n  SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
-		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
-	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
-		regs->lp_start, regs->lp_end, regs->lp_count);
-
-	/* print regs->r0 thru regs->r12
-	 * Sequential printing was generating horrible code
-	 */
-	print_reg_file(&(regs->r0), 0);
 
-	/* If Callee regs were saved, display them too */
-	cregs = (struct callee_regs *)current->thread.callee_reg;
+	print_regs_scratch(regs);
 	if (cregs)
-		show_callee_regs(cregs);
+		print_regs_callee(cregs);
 
 	preempt_disable();
 }
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index f87758a6851b..74ad4256022e 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -572,7 +572,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end,
 #else
 		BUILD_BUG_ON(sizeof(u32) != sizeof(value));
 #endif
-		/* Fall through */
+		fallthrough;
 	case DW_EH_PE_native:
 		if (end < (const void *)(ptr.pul + 1))
 			return 0;
@@ -827,7 +827,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc,
 			case DW_CFA_def_cfa:
 				state->cfa.reg = get_uleb128(&ptr.p8, end);
 				unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg);
-				/* fall through */
+				fallthrough;
 			case DW_CFA_def_cfa_offset:
 				state->cfa.offs = get_uleb128(&ptr.p8, end);
 				unw_debug("cfa_def_cfa_offset: 0x%lx ",
@@ -835,7 +835,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc,
 				break;
 			case DW_CFA_def_cfa_sf:
 				state->cfa.reg = get_uleb128(&ptr.p8, end);
-				/* fall through */
+				fallthrough;
 			case DW_CFA_def_cfa_offset_sf:
 				state->cfa.offs = get_sleb128(&ptr.p8, end)
 				    * state->dataAlign;
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 54139a6f469b..33ce59d91461 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -122,6 +122,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	ELF_DETAILS
 	DISCARDS
 
 	.arcextmap 0 : {