Merge tag 's390-5.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Vasily Gorbik:

 - Adjust PMU device drivers registration to avoid WARN_ON and few other
   perf improvements.

 - Enhance tracing in vfio-ccw.

 - Few stack unwinder fixes and improvements, convert get_wchan custom
   stack unwinding to generic api usage.

 - Fixes for mm helpers issues uncovered with tests validating
   architecture page table helpers.

 - Fix noexec bit handling when hardware doesn't support it.

 - Fix memleak and unsigned value compared with zero bugs in crypto
   code. Minor code simplification.

 - Fix crash during kdump with kasan enabled kernel.

 - Switch bug and alternatives from asm to asm_inline to improve
   inlining decisions.

 - Use 'depends on cc-option' for MARCH and TUNE options in Kconfig, add
   z13s and z14 ZR1 to TUNE descriptions.

 - Minor head64.S simplification.

 - Fix physical to logical CPU map for SMT.

 - Several cleanups in qdio code.

 - Other minor cleanups and fixes all over the code.

* tag 's390-5.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (41 commits)
  s390/cpumf: Adjust registration of s390 PMU device drivers
  s390/smp: fix physical to logical CPU map for SMT
  s390/early: move access registers setup in C code
  s390/head64: remove unnecessary vdso_per_cpu_data setup
  s390/early: move control registers setup in C code
  s390/kasan: support memcpy_real with TRACE_IRQFLAGS
  s390/crypto: Fix unsigned variable compared with zero
  s390/pkey: use memdup_user() to simplify code
  s390/pkey: fix memory leak within _copy_apqns_from_user()
  s390/disassembler: don't hide instruction addresses
  s390/cpum_sf: Assign error value to err variable
  s390/cpum_sf: Replace function name in debug statements
  s390/cpum_sf: Use consistant debug print format for sampling
  s390/unwind: drop unnecessary code around calling ftrace_graph_ret_addr()
  s390: add error handling to perf_callchain_kernel
  s390: always inline current_stack_pointer()
  s390/mm: add mm_pxd_folded() checks to pxd_free()
  s390/mm: properly clear _PAGE_NOEXEC bit when it is not supported
  s390/mm: simplify page table helpers for large entries
  s390/mm: make pmd/pud_bad() report large entries as bad
  ...

10 files changed, 129 insertions, 73 deletions

diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile
index f6a8db04177c..23eae4188876 100644
--- a/drivers/s390/cio/Makefile
+++ b/drivers/s390/cio/Makefile
@@ -5,7 +5,7 @@
 
 # The following is required for define_trace.h to find ./trace.h
 CFLAGS_trace.o := -I$(src)
-CFLAGS_vfio_ccw_fsm.o := -I$(src)
+CFLAGS_vfio_ccw_trace.o := -I$(src)
 
 obj-y += airq.o blacklist.o chsc.o cio.o css.o chp.o idset.o isc.o \
 	fcx.o itcw.o crw.o ccwreq.o trace.o ioasm.o
@@ -21,5 +21,5 @@ qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o
 obj-$(CONFIG_QDIO) += qdio.o
 
 vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \
-	vfio_ccw_async.o
+	vfio_ccw_async.o vfio_ccw_trace.o
 obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index a58b45df95d7..64cc14e47e35 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -252,9 +252,6 @@ struct qdio_q {
 	/* input or output queue */
 	int is_input_q;
 
-	/* list of thinint input queues */
-	struct list_head entry;
-
 	/* upper-layer program handler */
 	qdio_handler_t (*handler);
 
@@ -272,6 +269,7 @@ struct qdio_irq {
 	struct qib qib;
 	u32 *dsci;		/* address of device state change indicator */
 	struct ccw_device *cdev;
+	struct list_head entry;		/* list of thinint devices */
 	struct dentry *debugfs_dev;
 	struct dentry *debugfs_perf;
 
@@ -317,13 +315,15 @@ struct qdio_irq {
 
 #define qperf(__qdev, __attr)	((__qdev)->perf_stat.(__attr))
 
-#define qperf_inc(__q, __attr)						\
+#define QDIO_PERF_STAT_INC(__irq, __attr)				\
 ({									\
-	struct qdio_irq *qdev = (__q)->irq_ptr;				\
+	struct qdio_irq *qdev = __irq;					\
 	if (qdev->perf_stat_enabled)					\
 		(qdev->perf_stat.__attr)++;				\
 })
 
+#define qperf_inc(__q, __attr)	QDIO_PERF_STAT_INC((__q)->irq_ptr, __attr)
+
 static inline void account_sbals_error(struct qdio_q *q, int count)
 {
 	q->q_stats.nr_sbal_error += count;
@@ -355,14 +355,10 @@ static inline int multicast_outbound(struct qdio_q *q)
 	for (i = 0; i < irq_ptr->nr_output_qs &&	\
 		({ q = irq_ptr->output_qs[i]; 1; }); i++)
 
-#define prev_buf(bufnr)	\
-	((bufnr + QDIO_MAX_BUFFERS_MASK) & QDIO_MAX_BUFFERS_MASK)
-#define next_buf(bufnr)	\
-	((bufnr + 1) & QDIO_MAX_BUFFERS_MASK)
-#define add_buf(bufnr, inc) \
-	((bufnr + inc) & QDIO_MAX_BUFFERS_MASK)
-#define sub_buf(bufnr, dec) \
-	((bufnr - dec) & QDIO_MAX_BUFFERS_MASK)
+#define add_buf(bufnr, inc)	QDIO_BUFNR((bufnr) + (inc))
+#define next_buf(bufnr)		add_buf(bufnr, 1)
+#define sub_buf(bufnr, dec)	QDIO_BUFNR((bufnr) - (dec))
+#define prev_buf(bufnr)		sub_buf(bufnr, 1)
 
 #define queue_irqs_enabled(q)			\
 	(test_bit(QDIO_QUEUE_IRQS_DISABLED, &q->u.in.queue_irq_state) == 0)
@@ -375,8 +371,8 @@ extern u64 last_ai_time;
 void qdio_setup_thinint(struct qdio_irq *irq_ptr);
 int qdio_establish_thinint(struct qdio_irq *irq_ptr);
 void qdio_shutdown_thinint(struct qdio_irq *irq_ptr);
-void tiqdio_add_input_queues(struct qdio_irq *irq_ptr);
-void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr);
+void tiqdio_add_device(struct qdio_irq *irq_ptr);
+void tiqdio_remove_device(struct qdio_irq *irq_ptr);
 void tiqdio_inbound_processing(unsigned long q);
 int tiqdio_allocate_memory(void);
 void tiqdio_free_memory(void);
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 5b63c505a2f7..2b797cbb9d57 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -131,7 +131,7 @@ again:
 	case 96:
 		/* not all buffers processed */
 		qperf_inc(q, eqbs_partial);
-		DBF_DEV_EVENT(DBF_WARN, q->irq_ptr, "EQBS part:%02x",
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "EQBS part:%02x",
 			tmp_count);
 		return count - tmp_count;
 	case 97:
@@ -423,9 +423,6 @@ static inline void account_sbals(struct qdio_q *q, unsigned int count)
 static void process_buffer_error(struct qdio_q *q, unsigned int start,
 				 int count)
 {
-	unsigned char state = (q->is_input_q) ? SLSB_P_INPUT_NOT_INIT :
-					SLSB_P_OUTPUT_NOT_INIT;
-
 	q->qdio_error = QDIO_ERROR_SLSB_STATE;
 
 	/* special handling for no target buffer empty */
@@ -433,7 +430,7 @@ static void process_buffer_error(struct qdio_q *q, unsigned int start,
 	    q->sbal[start]->element[15].sflags == 0x10) {
 		qperf_inc(q, target_full);
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x", start);
-		goto set;
+		return;
 	}
 
 	DBF_ERROR("%4x BUF ERROR", SCH_NO(q));
@@ -442,13 +439,6 @@ static void process_buffer_error(struct qdio_q *q, unsigned int start,
 	DBF_ERROR("F14:%2x F15:%2x",
 		  q->sbal[start]->element[14].sflags,
 		  q->sbal[start]->element[15].sflags);
-
-set:
-	/*
-	 * Interrupts may be avoided as long as the error is present
-	 * so change the buffer state immediately to avoid starvation.
-	 */
-	set_buf_states(q, start, state, count);
 }
 
 static inline void inbound_primed(struct qdio_q *q, unsigned int start,
@@ -530,6 +520,11 @@ static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 		return count;
 	case SLSB_P_INPUT_ERROR:
 		process_buffer_error(q, start, count);
+		/*
+		 * Interrupts may be avoided as long as the error is present
+		 * so change the buffer state immediately to avoid starvation.
+		 */
+		set_buf_states(q, start, SLSB_P_INPUT_NOT_INIT, count);
 		if (atomic_sub_return(count, &q->nr_buf_used) == 0)
 			qperf_inc(q, inbound_queue_full);
 		if (q->irq_ptr->perf_stat_enabled)
@@ -963,7 +958,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr)
 			/* skip if polling is enabled or already in work */
 			if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED,
 				     &q->u.in.queue_irq_state)) {
-				qperf_inc(q, int_discarded);
+				QDIO_PERF_STAT_INC(irq_ptr, int_discarded);
 				continue;
 			}
 			q->u.in.queue_start_poll(q->irq_ptr->cdev, q->nr,
@@ -1162,7 +1157,7 @@ int qdio_shutdown(struct ccw_device *cdev, int how)
 	 */
 	qdio_set_state(irq_ptr, QDIO_IRQ_STATE_STOPPED);
 
-	tiqdio_remove_input_queues(irq_ptr);
+	tiqdio_remove_device(irq_ptr);
 	qdio_shutdown_queues(cdev);
 	qdio_shutdown_debug_entries(irq_ptr);
 
@@ -1284,6 +1279,7 @@ int qdio_allocate(struct qdio_initialize *init_data)
 			     init_data->no_output_qs))
 		goto out_rel;
 
+	INIT_LIST_HEAD(&irq_ptr->entry);
 	init_data->cdev->private->qdio_data = irq_ptr;
 	qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE);
 	return 0;
@@ -1428,7 +1424,7 @@ int qdio_activate(struct ccw_device *cdev)
 	}
 
 	if (is_thinint_irq(irq_ptr))
-		tiqdio_add_input_queues(irq_ptr);
+		tiqdio_add_device(irq_ptr);
 
 	/* wait for subchannel to become active */
 	msleep(5);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index cd164886132f..dc430bd86ade 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -150,7 +150,6 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues)
 			return -ENOMEM;
 		}
 		irq_ptr_qs[i] = q;
-		INIT_LIST_HEAD(&q->entry);
 	}
 	return 0;
 }
@@ -179,7 +178,6 @@ static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr,
 	q->mask = 1 << (31 - i);
 	q->nr = i;
 	q->handler = handler;
-	INIT_LIST_HEAD(&q->entry);
 }
 
 static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 93ee067c10ca..7c4e4ec08a12 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -39,14 +39,6 @@ struct indicator_t {
 static LIST_HEAD(tiq_list);
 static DEFINE_MUTEX(tiq_list_lock);
 
-/* Adapter interrupt definitions */
-static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating);
-
-static struct airq_struct tiqdio_airq = {
-	.handler = tiqdio_thinint_handler,
-	.isc = QDIO_AIRQ_ISC,
-};
-
 static struct indicator_t *q_indicators;
 
 u64 last_ai_time;
@@ -74,26 +66,20 @@ static void put_indicator(u32 *addr)
 	atomic_dec(&ind->count);
 }
 
-void tiqdio_add_input_queues(struct qdio_irq *irq_ptr)
+void tiqdio_add_device(struct qdio_irq *irq_ptr)
 {
 	mutex_lock(&tiq_list_lock);
-	list_add_rcu(&irq_ptr->input_qs[0]->entry, &tiq_list);
+	list_add_rcu(&irq_ptr->entry, &tiq_list);
 	mutex_unlock(&tiq_list_lock);
 }
 
-void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
+void tiqdio_remove_device(struct qdio_irq *irq_ptr)
 {
-	struct qdio_q *q;
-
-	q = irq_ptr->input_qs[0];
-	if (!q)
-		return;
-
 	mutex_lock(&tiq_list_lock);
-	list_del_rcu(&q->entry);
+	list_del_rcu(&irq_ptr->entry);
 	mutex_unlock(&tiq_list_lock);
 	synchronize_rcu();
-	INIT_LIST_HEAD(&q->entry);
+	INIT_LIST_HEAD(&irq_ptr->entry);
 }
 
 static inline int has_multiple_inq_on_dsci(struct qdio_irq *irq_ptr)
@@ -154,7 +140,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
 			/* skip if polling is enabled or already in work */
 			if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED,
 					     &q->u.in.queue_irq_state)) {
-				qperf_inc(q, int_discarded);
+				QDIO_PERF_STAT_INC(irq, int_discarded);
 				continue;
 			}
 
@@ -182,7 +168,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
 static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 {
 	u32 si_used = clear_shared_ind();
-	struct qdio_q *q;
+	struct qdio_irq *irq;
 
 	last_ai_time = S390_lowcore.int_clock;
 	inc_irq_stat(IRQIO_QAI);
@@ -190,12 +176,8 @@ static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 	/* protect tiq_list entries, only changed in activate or shutdown */
 	rcu_read_lock();
 
-	/* check for work on all inbound thinint queues */
-	list_for_each_entry_rcu(q, &tiq_list, entry) {
-		struct qdio_irq *irq;
-
+	list_for_each_entry_rcu(irq, &tiq_list, entry) {
 		/* only process queues from changed sets */
-		irq = q->irq_ptr;
 		if (unlikely(references_shared_dsci(irq))) {
 			if (!si_used)
 				continue;
@@ -204,11 +186,16 @@ static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 
 		tiqdio_call_inq_handlers(irq);
 
-		qperf_inc(q, adapter_int);
+		QDIO_PERF_STAT_INC(irq, adapter_int);
 	}
 	rcu_read_unlock();
 }
 
+static struct airq_struct tiqdio_airq = {
+	.handler = tiqdio_thinint_handler,
+	.isc = QDIO_AIRQ_ISC,
+};
+
 static int set_subchannel_ind(struct qdio_irq *irq_ptr, int reset)
 {
 	struct chsc_scssc_area *scssc = (void *)irq_ptr->chsc_page;
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index 7cdc38049033..ba31240ce965 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -15,6 +15,7 @@
 #include <asm/scsw.h>
 
 #include "orb.h"
+#include "vfio_ccw_trace.h"
 
 /*
  * Max length for ccw chain.
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 4a1e727c62d9..23e61aa638e4 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -15,9 +15,6 @@
 #include "ioasm.h"
 #include "vfio_ccw_private.h"
 
-#define CREATE_TRACE_POINTS
-#include "vfio_ccw_trace.h"
-
 static int fsm_io_helper(struct vfio_ccw_private *private)
 {
 	struct subchannel *sch;
@@ -321,8 +318,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	}
 
 err_out:
-	trace_vfio_ccw_io_fctl(scsw->cmd.fctl, schid,
-			       io_region->ret_code, errstr);
+	trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid,
+				      io_region->ret_code, errstr);
 }
 
 /*
@@ -344,6 +341,10 @@ static void fsm_async_request(struct vfio_ccw_private *private,
 		/* should not happen? */
 		cmd_region->ret_code = -EINVAL;
 	}
+
+	trace_vfio_ccw_fsm_async_request(get_schid(private),
+					 cmd_region->command,
+					 cmd_region->ret_code);
 }
 
 /*
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index bbe9babf767b..9b9bb4982972 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -135,6 +135,7 @@ extern fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS];
 static inline void vfio_ccw_fsm_event(struct vfio_ccw_private *private,
 				     int event)
 {
+	trace_vfio_ccw_fsm_event(private->sch->schid, private->state, event);
 	vfio_ccw_jumptable[private->state][event](private, event);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_trace.c b/drivers/s390/cio/vfio_ccw_trace.c
new file mode 100644
index 000000000000..8c671d2519f6
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_trace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Tracepoint definitions for vfio_ccw
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Eric Farman <farman@linux.ibm.com>
+ */
+
+#define CREATE_TRACE_POINTS
+#include "vfio_ccw_trace.h"
+
+EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_async_request);
+EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_event);
+EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_io_request);
diff --git a/drivers/s390/cio/vfio_ccw_trace.h b/drivers/s390/cio/vfio_ccw_trace.h
index b1da53ddec1f..30162a318a8a 100644
--- a/drivers/s390/cio/vfio_ccw_trace.h
+++ b/drivers/s390/cio/vfio_ccw_trace.h
@@ -7,6 +7,8 @@
  *            Halil Pasic <pasic@linux.vnet.ibm.com>
  */
 
+#include "cio.h"
+
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM vfio_ccw
 
@@ -15,28 +17,88 @@
 
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(vfio_ccw_io_fctl,
+TRACE_EVENT(vfio_ccw_fsm_async_request,
+	TP_PROTO(struct subchannel_id schid,
+		 int command,
+		 int errno),
+	TP_ARGS(schid, command, errno),
+
+	TP_STRUCT__entry(
+		__field(u8, cssid)
+		__field(u8, ssid)
+		__field(u16, sch_no)
+		__field(int, command)
+		__field(int, errno)
+	),
+
+	TP_fast_assign(
+		__entry->cssid = schid.cssid;
+		__entry->ssid = schid.ssid;
+		__entry->sch_no = schid.sch_no;
+		__entry->command = command;
+		__entry->errno = errno;
+	),
+
+	TP_printk("schid=%x.%x.%04x command=0x%x errno=%d",
+		  __entry->cssid,
+		  __entry->ssid,
+		  __entry->sch_no,
+		  __entry->command,
+		  __entry->errno)
+);
+
+TRACE_EVENT(vfio_ccw_fsm_event,
+	TP_PROTO(struct subchannel_id schid, int state, int event),
+	TP_ARGS(schid, state, event),
+
+	TP_STRUCT__entry(
+		__field(u8, cssid)
+		__field(u8, ssid)
+		__field(u16, schno)
+		__field(int, state)
+		__field(int, event)
+	),
+
+	TP_fast_assign(
+		__entry->cssid = schid.cssid;
+		__entry->ssid = schid.ssid;
+		__entry->schno = schid.sch_no;
+		__entry->state = state;
+		__entry->event = event;
+	),
+
+	TP_printk("schid=%x.%x.%04x state=%d event=%d",
+		__entry->cssid, __entry->ssid, __entry->schno,
+		__entry->state,
+		__entry->event)
+);
+
+TRACE_EVENT(vfio_ccw_fsm_io_request,
 	TP_PROTO(int fctl, struct subchannel_id schid, int errno, char *errstr),
 	TP_ARGS(fctl, schid, errno, errstr),
 
 	TP_STRUCT__entry(
+		__field(u8, cssid)
+		__field(u8, ssid)
+		__field(u16, sch_no)
 		__field(int, fctl)
-		__field_struct(struct subchannel_id, schid)
 		__field(int, errno)
 		__field(char*, errstr)
 	),
 
 	TP_fast_assign(
+		__entry->cssid = schid.cssid;
+		__entry->ssid = schid.ssid;
+		__entry->sch_no = schid.sch_no;
 		__entry->fctl = fctl;
-		__entry->schid = schid;
 		__entry->errno = errno;
 		__entry->errstr = errstr;
 	),
 
-	TP_printk("schid=%x.%x.%04x fctl=%x errno=%d info=%s",
-		  __entry->schid.cssid,
-		  __entry->schid.ssid,
-		  __entry->schid.sch_no,
+	TP_printk("schid=%x.%x.%04x fctl=0x%x errno=%d info=%s",
+		  __entry->cssid,
+		  __entry->ssid,
+		  __entry->sch_no,
 		  __entry->fctl,
 		  __entry->errno,
 		  __entry->errstr)