sparc: Fix single-pcr perf event counter management.

From: "David S. Miller" <[email protected]>

[ Upstream commit cfdc3170d214046b9509183fe9b9544dc644d40b ]

It is important to clear the hw->state value for non-stopped events when they are added into the PMU. Otherwise when the event is scheduled out, we won't read the counter because HES_UPTODATE is still set. This breaks 'perf stat' and similar use cases, causing all the events to show zero.

This worked for multi-pcr because we make explicit sparc_pmu_start() calls in calculate_multiple_pcrs(). calculate_single_pcr() doesn't do this because the idea there is to accumulate all of the counter settings into the single pcr value. So we have to add explicit hw->state handling there.

Like x86, we use the PERF_HES_ARCH bit to track truly stopped events so that we don't accidently start them on a reload.

Related to all of this, sparc_pmu_start() is missing a userpage update so add it.

---
 arch/sparc/kernel/perf_event.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

index 6596f66ce112..a5d0c2f08110 100644
@@ -926,6 +926,8 @@ static void read_in_all_counters(struct cpu_hw_events *cpuc)
 			sparc_perf_event_update(cp, &cp->hw,
 						cpuc->current_idx[i]);
 			cpuc->current_idx[i] = PIC_NO_INDEX;
+			if (cp->hw.state & PERF_HES_STOPPED)
+				cp->hw.state |= PERF_HES_ARCH;
 		}
 	}
 }

@@ -958,10 +960,12 @@ static void calculate_single_pcr(struct cpu_hw_events *cpuc)
 
 		enc = perf_event_get_enc(cpuc->events[i]);
 		cpuc->pcr[0] &= ~mask_for_index(idx);
-		if (hwc->state & PERF_HES_STOPPED)
+		if (hwc->state & PERF_HES_ARCH) {
 			cpuc->pcr[0] |= nop_for_index(idx);
-		else
+		} else {
 			cpuc->pcr[0] |= event_encoding(enc, idx);
+			hwc->state = 0;
+		}
 	}
 out:
 	cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;

@@ -987,6 +991,9 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 
 		cpuc->current_idx[i] = idx;
 
+		if (cp->hw.state & PERF_HES_ARCH)
+			continue;
+
 		sparc_pmu_start(cp, PERF_EF_RELOAD);
 	}
 out:

@@ -1078,6 +1085,8 @@ static void sparc_pmu_start(struct perf_event *event, int flags)
 	event->hw.state = 0;
 
 	sparc_pmu_enable_event(cpuc, &event->hw, idx);
+
+	perf_event_update_userpage(event);
 }
 
 static void sparc_pmu_stop(struct perf_event *event, int flags)

@@ -1370,9 +1379,9 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 	cpuc->events[n0] = event->hw.event_base;
 	cpuc->current_idx[n0] = PIC_NO_INDEX;
 
-	event->hw.state = PERF_HES_UPTODATE;
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 	if (!(ef_flags & PERF_EF_START))
-		event->hw.state |= PERF_HES_STOPPED;
+		event->hw.state |= PERF_HES_ARCH;
 
 	/*
 	 * If group events scheduling transaction was started,

2.17.1

From: "David S. Miller" <[email protected]>

[ Upstream commit 455adb3174d2c8518cef1a61140c211f6ac224d2 ]

Like x86 and arm, call perf_sample_event_took() in perf event NMI interrupt handler.

---
 arch/sparc/kernel/perf_event.c | 9 +++++++++
 1 file changed, 9 insertions(+)

index a5d0c2f08110..dd02219bcc35 100644
@@ -23,6 +23,7 @@
 #include <asm/cpudata.h>
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
+#include <linux/sched/clock.h>
 #include <asm/nmi.h>
 #include <asm/pcr.h>
 #include <asm/cacheflush.h>

@@ -1611,6 +1612,8 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
 	struct pt_regs *regs;
+	u64 finish_clock;
+	u64 start_clock;
 	int i;
 
 	if (!atomic_read(&active_events))

@@ -1624,6 +1627,8 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 		return NOTIFY_DONE;
 	}
 
+	start_clock = sched_clock();
+
 	regs = args->regs;
 
 	cpuc = this_cpu_ptr(&cpu_hw_events);

@@ -1662,6 +1667,10 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 			sparc_pmu_stop(event, 0);
 	}
 
+	finish_clock = sched_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+
 	return NOTIFY_STOP;
 }
 

2.17.1

From: Sebastian Andrzej Siewior <[email protected]>

[ Upstream commit 6aa676761d4c1acfa31320e55fa1f83f3fcbbc7a ]

Commit:

c5bedc6847c3b ("x86/fpu: Get rid of PF_USED_MATH usage, convert it to fpu->fpstate_active")

introduced the 'fpu' variable at top of __restore_xstate_sig(), which now shadows the other definition:

arch/x86/kernel/fpu/signal.c:318:28: warning: symbol 'fpu' shadows an earlier one arch/x86/kernel/fpu/signal.c:271:20: originally declared here

Remove the shadowed definition of 'fpu', as the two definitions are the same.

---
 arch/x86/kernel/fpu/signal.c | 1 -
 1 file changed, 1 deletion(-)

index 9be3e79eb629..31fad2cbd734 100644
@@ -294,7 +294,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		 * thread's fpu state, reconstruct fxstate from the fsave
 		 * header. Sanitize the copied state etc.
 		 */
-		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 

2.17.1

From: Nathan Chancellor <[email protected]>

[ Upstream commit 8c3bf9b62b667456a57aefcf1689e826df146159 ]

Clang currently warns:

drivers/net/ethernet/qlogic/qla3xxx.c:384:24: warning: signed shift result (0xF00000000) requires 37 bits to represent, but 'int' only has 32 bits [-Wshift-overflow]

                    ((ISP_NVRAM_MASK << 16) | qdev->eeprom_cmd_data));
                      ~~~~~~~~~~~~~~ ^  ~~

1 warning generated.

The warning is certainly accurate since ISP_NVRAM_MASK is defined as (0x000F << 16) which is then shifted by 16, resulting in 64424509440, well above UINT_MAX.

Given that this is the only location in this driver where ISP_NVRAM_MASK is shifted again, it seems likely that ISP_NVRAM_MASK was originally defined without a shift and during the move of the shift to the definition, this statement wasn't properly removed (since ISP_NVRAM_MASK is used in the statenent right above this). Only the maintainers can confirm this since this statment has been here since the driver was first added to the kernel.

---
 drivers/net/ethernet/qlogic/qla3xxx.c | 2 --
 1 file changed, 2 deletions(-)

index b09a6b80d107..355c5fb802cd 100644
@@ -380,8 +380,6 @@ static void fm93c56a_select(struct ql3_adapter *qdev)
 
 	qdev->eeprom_cmd_data = AUBURN_EEPROM_CS_1;
 	ql_write_nvram_reg(qdev, spir, ISP_NVRAM_MASK | qdev->eeprom_cmd_data);
-	ql_write_nvram_reg(qdev, spir,
-			   ((ISP_NVRAM_MASK << 16) | qdev->eeprom_cmd_data));
 }
 
 /*

2.17.1

From: Heiner Kallweit <[email protected]>

[ Upstream commit 6b839b6cf9eada30b086effb51e5d6076bafc761 ]

rtl_rx() and rtl_tx() are called only if the respective bits are set in the interrupt status register. Under high load NAPI may not be able to process all data (work_done == budget) and it will schedule subsequent calls to the poll callback.
rtl_ack_events() however resets the bits in the interrupt status register, therefore subsequent calls to rtl8169_poll() won't call rtl_rx() and rtl_tx() - chip interrupts are still disabled.

Fix this by calling rtl_rx() and rtl_tx() independent of the bits set in the interrupt status register. Both functions will detect if there's nothing to do for them.

---
 drivers/net/ethernet/realtek/r8169.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

index c6782ebd35e1..93543e176829 100644
@@ -7540,17 +7540,15 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 	struct rtl8169_private *tp = container_of(napi, struct rtl8169_private, napi);
 	struct net_device *dev = tp->dev;
 	u16 enable_mask = RTL_EVENT_NAPI | tp->event_slow;
-	int work_done= 0;
+	int work_done;
 	u16 status;
 
 	status = rtl_get_events(tp);
 	rtl_ack_events(tp, status & ~tp->event_slow);
 
-	if (status & RTL_EVENT_NAPI_RX)
-		work_done = rtl_rx(dev, tp, (u32) budget);
+	work_done = rtl_rx(dev, tp, (u32) budget);
 
-	if (status & RTL_EVENT_NAPI_TX)
-		rtl_tx(dev, tp);
+	rtl_tx(dev, tp);
 
 	if (status & tp->event_slow) {
 		enable_mask &= ~tp->event_slow;

2.17.1

From: Masami Hiramatsu <[email protected]>

[ Upstream commit ba0e41ca81b935b958006c7120466e2217357827 ]

Add a testcase to check the syntax and field types for synthetic_events interface.

---
 .../trigger-synthetic-event-syntax.tc         | 80 +++++++++++++++++++
 1 file changed, 80 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc

new file mode 100644
index 000000000000..88e6c3f43006
@@ -0,0 +1,80 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: event trigger - test synthetic_events syntax parser
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo "Test synthetic_events syntax parser"
+
+echo > synthetic_events
+
+# synthetic event must have a field
+! echo "myevent" >> synthetic_events
+echo "myevent u64 var1" >> synthetic_events
+
+# synthetic event must be found in synthetic_events
+grep "myevent[[:space:]]u64 var1" synthetic_events
+
+# it is not possible to add same name event
+! echo "myevent u64 var2" >> synthetic_events
+
+# Non-append open will cleanup all events and add new one
+echo "myevent u64 var2" > synthetic_events
+
+# multiple fields with different spaces
+echo "myevent u64 var1; u64 var2;" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+echo "myevent u64 var1 ; u64 var2 ;" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+echo "myevent u64 var1 ;u64 var2" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+
+# test field types
+echo "myevent u32 var" > synthetic_events
+echo "myevent u16 var" > synthetic_events
+echo "myevent u8 var" > synthetic_events
+echo "myevent s64 var" > synthetic_events
+echo "myevent s32 var" > synthetic_events
+echo "myevent s16 var" > synthetic_events
+echo "myevent s8 var" > synthetic_events
+
+echo "myevent char var" > synthetic_events
+echo "myevent int var" > synthetic_events
+echo "myevent long var" > synthetic_events
+echo "myevent pid_t var" > synthetic_events
+
+echo "myevent unsigned char var" > synthetic_events
+echo "myevent unsigned int var" > synthetic_events
+echo "myevent unsigned long var" > synthetic_events
+grep "myevent[[:space:]]unsigned long var" synthetic_events
+
+# test string type
+echo "myevent char var[10]" > synthetic_events
+grep "myevent[[:space:]]char\[10\] var" synthetic_events
+
+do_reset
+
+exit 0

2.17.1