Merge branch 'fixes' into next

Merge our fixes branch, a few of them are tripping people up while
working on top of next, and we also have a dependency between the CXL
fixes and new CXL code we want to merge into next.

7 files changed, 152 insertions, 33 deletions

diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index fcc7588a96d6..4c7656dc4e04 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/jump_label.h>
+#include <linux/libfdt.h>
 #include <linux/memblock.h>
 #include <linux/printk.h>
 #include <linux/sched.h>
@@ -642,7 +643,6 @@ static struct dt_cpu_feature_match __initdata
 	{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
-	{"subcore", feat_enable, CPU_FTR_SUBCORE},
 	{"no-execute", feat_enable, 0},
 	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
 	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
@@ -671,12 +671,24 @@ static struct dt_cpu_feature_match __initdata
 	{"wait-v3", feat_enable, 0},
 };
 
-/* XXX: how to configure this? Default + boot time? */
-#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN
-#define CPU_FEATURE_ENABLE_UNKNOWN 1
-#else
-#define CPU_FEATURE_ENABLE_UNKNOWN 0
-#endif
+static bool __initdata using_dt_cpu_ftrs;
+static bool __initdata enable_unknown = true;
+
+static int __init dt_cpu_ftrs_parse(char *str)
+{
+	if (!str)
+		return 0;
+
+	if (!strcmp(str, "off"))
+		using_dt_cpu_ftrs = false;
+	else if (!strcmp(str, "known"))
+		enable_unknown = false;
+	else
+		return 1;
+
+	return 0;
+}
+early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse);
 
 static void __init cpufeatures_setup_start(u32 isa)
 {
@@ -707,7 +719,7 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
 		}
 	}
 
-	if (!known && CPU_FEATURE_ENABLE_UNKNOWN) {
+	if (!known && enable_unknown) {
 		if (!feat_try_enable_unknown(f)) {
 			pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
 				f->name);
@@ -756,6 +768,26 @@ static void __init cpufeatures_setup_finished(void)
 		cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
 }
 
+static int __init disabled_on_cmdline(void)
+{
+	unsigned long root, chosen;
+	const char *p;
+
+	root = of_get_flat_dt_root();
+	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+	if (chosen == -FDT_ERR_NOTFOUND)
+		return false;
+
+	p = of_get_flat_dt_prop(chosen, "bootargs", NULL);
+	if (!p)
+		return false;
+
+	if (strstr(p, "dt_cpu_ftrs=off"))
+		return true;
+
+	return false;
+}
+
 static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
 					int depth, void *data)
 {
@@ -766,8 +798,6 @@ static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
 	return 0;
 }
 
-static bool __initdata using_dt_cpu_ftrs = false;
-
 bool __init dt_cpu_ftrs_in_use(void)
 {
 	return using_dt_cpu_ftrs;
@@ -775,6 +805,8 @@ bool __init dt_cpu_ftrs_in_use(void)
 
 bool __init dt_cpu_ftrs_init(void *fdt)
 {
+	using_dt_cpu_ftrs = false;
+
 	/* Setup and verify the FDT, if it fails we just bail */
 	if (!early_init_dt_verify(fdt))
 		return false;
@@ -782,6 +814,9 @@ bool __init dt_cpu_ftrs_init(void *fdt)
 	if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
 		return false;
 
+	if (disabled_on_cmdline())
+		return false;
+
 	cpufeatures_setup_cpu();
 
 	using_dt_cpu_ftrs = true;
@@ -1027,5 +1062,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
 
 void __init dt_cpu_ftrs_scan(void)
 {
+	if (!using_dt_cpu_ftrs)
+		return;
+
 	of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL);
 }
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 02a82777fd5b..fb4ffc773082 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1452,10 +1452,8 @@ USE_TEXT_SECTION()
 	.balign	IFETCH_ALIGN_BYTES
 do_hash_page:
 #ifdef CONFIG_PPC_STD_MMU_64
-	andis.	r0,r4,0xa410		/* weird error? */
+	andis.	r0,r4,0xa450		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
-	andis.  r0,r4,DSISR_DABRMATCH@h
-	bne-    handle_dabr_fault
 	CURRENT_THREAD_INFO(r11, r1)
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
@@ -1479,11 +1477,16 @@ do_hash_page:
 
 	/* Error */
 	blt-	13f
+
+	/* Reload DSISR into r4 for the DABR check below */
+	ld      r4,_DSISR(r1)
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
-11:	ld	r4,_DAR(r1)
+11:	andis.  r0,r4,DSISR_DABRMATCH@h
+	bne-    handle_dabr_fault
+	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_page_fault
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index fc4343514bed..01addfb0ed0a 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -43,6 +43,12 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
 
+int is_current_kprobe_addr(unsigned long addr)
+{
+	struct kprobe *p = kprobe_running();
+	return (p && (unsigned long)p->addr == addr) ? 1 : 0;
+}
+
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	return  (addr >= (unsigned long)__kprobes_text_start &&
@@ -617,6 +623,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
 #endif
 
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -642,6 +657,8 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 6273b5d5baec..9f3e2c932dcc 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1697,6 +1697,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
+	current->thread.load_fp = 0;
 	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 	current->thread.fp_save_area = NULL;
 #ifdef CONFIG_ALTIVEC
@@ -1705,6 +1706,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.vr_save_area = NULL;
 	current->thread.vrsave = 0;
 	current->thread.used_vr = 0;
+	current->thread.load_vec = 0;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_SPE
 	memset(current->thread.evr, 0, sizeof(current->thread.evr));
@@ -1716,6 +1718,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfhar = 0;
 	current->thread.tm_texasr = 0;
 	current->thread.tm_tfiar = 0;
+	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
 EXPORT_SYMBOL(start_thread);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 096dee58b9c1..94a948207cd2 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -932,7 +932,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_PPC_MM_SLICES
 #ifdef CONFIG_PPC64
-	init_mm.context.addr_limit = TASK_SIZE_128TB;
+	init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 #else
 #error	"context.addr_limit not initialized."
 #endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f35ff9dea4fb..4640f6d64f8b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -616,6 +616,24 @@ void __init exc_lvl_early_init(void)
 #endif
 
 /*
+ * Emergency stacks are used for a range of things, from asynchronous
+ * NMIs (system reset, machine check) to synchronous, process context.
+ * We set preempt_count to zero, even though that isn't necessarily correct. To
+ * get the right value we'd need to copy it from the previous thread_info, but
+ * doing that might fault causing more problems.
+ * TODO: what to do with accounting?
+ */
+static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
+{
+	ti->task = NULL;
+	ti->cpu = cpu;
+	ti->preempt_count = 0;
+	ti->local_flags = 0;
+	ti->flags = 0;
+	klp_init_thread_info(ti);
+}
+
+/*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled. Exclusive emergency
  * stack for machine checks.
@@ -633,24 +651,31 @@ void __init emergency_stack_init(void)
 	 * Since we use these as temporary stacks during secondary CPU
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
+	 *
+	 * The IRQ stacks allocated elsewhere in this file are zeroed and
+	 * initialized in kernel/irq.c. These are initialized here in order
+	 * to have emergency stacks available as early as possible.
 	 */
 	limit = min(safe_stack_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
@@ -661,7 +686,7 @@ void __init emergency_stack_init(void)
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
 				    __pa(MAX_DMA_ADDRESS));
 }
 
@@ -672,7 +697,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size)
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	if (cpu_to_node(from) == cpu_to_node(to))
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
 		return LOCAL_DISTANCE;
 	else
 		return REMOTE_DISTANCE;
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 7c933a99f5d5..c98e90b4ea7b 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -45,10 +45,14 @@ _GLOBAL(ftrace_caller)
 	stdu	r1,-SWITCH_FRAME_SIZE(r1)
 
 	/* Save all gprs to pt_regs */
-	SAVE_8GPRS(0,r1)
-	SAVE_8GPRS(8,r1)
-	SAVE_8GPRS(16,r1)
-	SAVE_8GPRS(24,r1)
+	SAVE_GPR(0, r1)
+	SAVE_10GPRS(2, r1)
+	SAVE_10GPRS(12, r1)
+	SAVE_10GPRS(22, r1)
+
+	/* Save previous stack pointer (r1) */
+	addi	r8, r1, SWITCH_FRAME_SIZE
+	std	r8, GPR1(r1)
 
 	/* Load special regs for save below */
 	mfmsr   r8
@@ -95,18 +99,44 @@ ftrace_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load ctr with the possibly modified NIP */
-	ld	r3, _NIP(r1)
-	mtctr	r3
+	/* Load the possibly modified NIP */
+	ld	r15, _NIP(r1)
+
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14,r3		/* has NIP been altered? */
+	cmpd	r14, r15	/* has NIP been altered? */
+#endif
+
+#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
+	/* NIP has not been altered, skip over further checks */
+	beq	1f
+
+	/* Check if there is an active kprobe on us */
+	subi	r3, r14, 4
+	bl	is_current_kprobe_addr
+	nop
+
+	/*
+	 * If r3 == 1, then this is a kprobe/jprobe.
+	 * else, this is livepatched function.
+	 *
+	 * The conditional branch for livepatch_handler below will use the
+	 * result of this comparison. For kprobe/jprobe, we just need to branch to
+	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
+	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
+	 * CR0[EQ] = (r3 == 1).
+	 */
+	cmpdi	r3, 1
+1:
 #endif
 
+	/* Load CTR with the possibly modified NIP */
+	mtctr	r15
+
 	/* Restore gprs */
-	REST_8GPRS(0,r1)
-	REST_8GPRS(8,r1)
-	REST_8GPRS(16,r1)
-	REST_8GPRS(24,r1)
+	REST_GPR(0,r1)
+	REST_10GPRS(2,r1)
+	REST_10GPRS(12,r1)
+	REST_10GPRS(22,r1)
 
 	/* Restore possibly modified LR */
 	ld	r0, _LINK(r1)
@@ -119,7 +149,10 @@ ftrace_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /* Based on the cmpd above, if the NIP was altered handle livepatch */
+        /*
+	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
+	 * not on a kprobe/jprobe, then handle livepatch.
+	 */
 	bne-	livepatch_handler
 #endif