RISC-V Fixes for 6.10-rc7

* A fix for the CMODX example in therecently added icache flushing
   prctl().
 * A fix to the perf driver to avoid corrupting event data on counter
   overflows when external overflow handlers are in use.
 * A fix to clear all hardware performance monitor events on boot, to
   avoid dangling events firmware or previously booted kernels from
   triggering spuriously.
 * A fix to the perf event probing logic to avoid erroneously reporting
   the presence of unimplemented counters.  This also prevents some
   implemented counters from being reported.
 * A build fix for the vector sigreturn selftest on clang.
 * A fix to ftrace, which now requires the previously optional index
   argument to ftrace_graph_ret_addr().
 * A fix to avoid deadlocking if kexec crash handling triggers in an
   interrupt context.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmaIJBATHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYiYk6D/981DUAWJ5JPsqve7PihWnhFXh7T/fm
 KZL7cNQN7/9QmqzJMD756oQCHZT2TeDTxwji4WUQo27uoS1SamsAxRWCPdW8GqDt
 GwBJeviyWDwjNMgrejWwgH3d9so+WZ4kNKfiUrY+j1vgQ8TkE4h5wMzUtOBTSgDI
 5EhHT5B5yjiRcadPshXivZAyimc6mxKJKph5v8W3BGgtLQRHs5tYop4ZkP5Utmv3
 yBie7orfMRx5fNxE6fgn0c/3r49i+KGTSCzkK+0689qPlQNt7MTj4kqDVp7xu2ll
 jl5GJNZrWSZR0cST9AG3VByqfeN2f9sbGYq5fAozkZy3idEYovtvGIU2xJVZRuIU
 ZhY+VTk0fwO8HlilTLMbyk7t99EJ4a7bXcUuD6ub3BthlKfc41PArhZgasL/dFPd
 VOSjy5hfGpJgmifSTpPXElf8jgBq6N4Kw9N+rBNkNiruEiwtWfsyqOckYAfNbULe
 Z8Nikl+3pfWlwzQrAb30X78s4ZyJyOX+XxP118lvx+UAbZofxg5qJJGo7U0Ru54r
 JPBCW8swlco6AXwvAj3yKcaL3qtKlc6f068QvcSaRELUvS2qfuJ7w4fjKdl/IT93
 QggGUyuEVG3UC1Dj961plrACXmqISTAlW8HqkdPvUgLY9rSPuTLuCR54b3fGI+n/
 3wJF6gl5leEPMw==
 =/Gsf
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-6.10-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Palmer Dabbelt:

 - A fix for the CMODX example in the recently added icache flushing
   prctl()

 - A fix to the perf driver to avoid corrupting event data on counter
   overflows when external overflow handlers are in use

 - A fix to clear all hardware performance monitor events on boot, to
   avoid dangling events firmware or previously booted kernels from
   triggering spuriously

 - A fix to the perf event probing logic to avoid erroneously reporting
   the presence of unimplemented counters. This also prevents some
   implemented counters from being reported

 - A build fix for the vector sigreturn selftest on clang

 - A fix to ftrace, which now requires the previously optional index
   argument to ftrace_graph_ret_addr()

 - A fix to avoid deadlocking if kexec crash handling triggers in an
   interrupt context

* tag 'riscv-for-linus-6.10-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: kexec: Avoid deadlock in kexec crash path
  riscv: stacktrace: fix usage of ftrace_graph_ret_addr()
  riscv: selftests: Fix vsetivli args for clang
  perf: RISC-V: Check standard event availability
  drivers/perf: riscv: Reset the counter to hpmevent mapping while starting cpus
  drivers/perf: riscv: Do not update the event data if uptodate
  documentation: Fix riscv cmodx example

Documentation/arch/riscv/cmodx.rst

@@ -62,10 +62,10 @@ cmodx.c::
 		printf("Value before cmodx: %d\n", value);
 
 		// Call prctl before first fence.i is called inside modify_instruction
-		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX_ON, PR_RISCV_CTX_SW_FENCEI, PR_RISCV_SCOPE_PER_PROCESS);
+		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX, PR_RISCV_CTX_SW_FENCEI_ON, PR_RISCV_SCOPE_PER_PROCESS);
 		modify_instruction();
 		// Call prctl after final fence.i is called in process
-		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX_OFF, PR_RISCV_CTX_SW_FENCEI, PR_RISCV_SCOPE_PER_PROCESS);
+		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX, PR_RISCV_CTX_SW_FENCEI_OFF, PR_RISCV_SCOPE_PER_PROCESS);
 
 		value = get_value();
 		printf("Value after cmodx: %d\n", value);

arch/riscv/kernel/machine_kexec.c

@@ -121,20 +121,12 @@ static void machine_kexec_mask_interrupts(void)
 
 	for_each_irq_desc(i, desc) {
 		struct irq_chip *chip;
-		int ret;
 
 		chip = irq_desc_get_chip(desc);
 		if (!chip)
 			continue;
 
-		/*
-		 * First try to remove the active state. If this
-		 * fails, try to EOI the interrupt.
-		 */
-		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
-
-		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
-		    chip->irq_eoi)
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
 			chip->irq_eoi(&desc->irq_data);
 
 		if (chip->irq_mask)

arch/riscv/kernel/stacktrace.c

@@ -32,6 +32,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 			     bool (*fn)(void *, unsigned long), void *arg)
 {
 	unsigned long fp, sp, pc;
+	int graph_idx = 0;
 	int level = 0;
 
 	if (regs) {
@@ -68,7 +69,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 			pc = regs->ra;
 		} else {
 			fp = frame->fp;
-			pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+			pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra,
 						   &frame->ra);
 			if (pc == (unsigned long)ret_from_exception) {
 				if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc)))

arch/riscv/kvm/vcpu_pmu.c

@@ -327,7 +327,7 @@ static long kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_att
 
 	event = perf_event_create_kernel_counter(attr, -1, current, kvm_riscv_pmu_overflow, pmc);
 	if (IS_ERR(event)) {
-		pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event));
+		pr_debug("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event));
 		return PTR_ERR(event);
 	}
 

drivers/perf/riscv_pmu.c

@@ -167,7 +167,7 @@ u64 riscv_pmu_event_update(struct perf_event *event)
 	unsigned long cmask;
 	u64 oldval, delta;
 
-	if (!rvpmu->ctr_read)
+	if (!rvpmu->ctr_read || (hwc->state & PERF_HES_UPTODATE))
 		return 0;
 
 	cmask = riscv_pmu_ctr_get_width_mask(event);

drivers/perf/riscv_pmu_sbi.c

@@ -20,6 +20,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/sched/clock.h>
 #include <linux/soc/andes/irq.h>
+#include <linux/workqueue.h>
 
 #include <asm/errata_list.h>
 #include <asm/sbi.h>
@@ -114,7 +115,7 @@ struct sbi_pmu_event_data {
 	};
 };
 
-static const struct sbi_pmu_event_data pmu_hw_event_map[] = {
+static struct sbi_pmu_event_data pmu_hw_event_map[] = {
 	[PERF_COUNT_HW_CPU_CYCLES]		= {.hw_gen_event = {
 							SBI_PMU_HW_CPU_CYCLES,
 							SBI_PMU_EVENT_TYPE_HW, 0}},
@@ -148,7 +149,7 @@ static const struct sbi_pmu_event_data pmu_hw_event_map[] = {
 };
 
 #define C(x) PERF_COUNT_HW_CACHE_##x
-static const struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
+static struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
 [PERF_COUNT_HW_CACHE_OP_MAX]
 [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
 	[C(L1D)] = {
@@ -293,6 +294,34 @@ static const struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_M
 	},
 };
 
+static void pmu_sbi_check_event(struct sbi_pmu_event_data *edata)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH,
+			0, cmask, 0, edata->event_idx, 0, 0);
+	if (!ret.error) {
+		sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
+			  ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
+	} else if (ret.error == SBI_ERR_NOT_SUPPORTED) {
+		/* This event cannot be monitored by any counter */
+		edata->event_idx = -EINVAL;
+	}
+}
+
+static void pmu_sbi_check_std_events(struct work_struct *work)
+{
+	for (int i = 0; i < ARRAY_SIZE(pmu_hw_event_map); i++)
+		pmu_sbi_check_event(&pmu_hw_event_map[i]);
+
+	for (int i = 0; i < ARRAY_SIZE(pmu_cache_event_map); i++)
+		for (int j = 0; j < ARRAY_SIZE(pmu_cache_event_map[i]); j++)
+			for (int k = 0; k < ARRAY_SIZE(pmu_cache_event_map[i][j]); k++)
+				pmu_sbi_check_event(&pmu_cache_event_map[i][j][k]);
+}
+
+static DECLARE_WORK(check_std_events_work, pmu_sbi_check_std_events);
+
 static int pmu_sbi_ctr_get_width(int idx)
 {
 	return pmu_ctr_list[idx].width;
@@ -478,6 +507,12 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig)
 	u64 raw_config_val;
 	int ret;
 
+	/*
+	 * Ensure we are finished checking standard hardware events for
+	 * validity before allowing userspace to configure any events.
+	 */
+	flush_work(&check_std_events_work);
+
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
 		if (config >= PERF_COUNT_HW_MAX)
@@ -762,7 +797,7 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu)
 	 * which may include counters that are not enabled yet.
 	 */
 	sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
-		  0, pmu->cmask, 0, 0, 0, 0);
+		  0, pmu->cmask, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
 }
 
 static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu)
@@ -1359,6 +1394,9 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_unregister;
 
+	/* Asynchronously check which standard events are available */
+	schedule_work(&check_std_events_work);
+
 	return 0;
 
 out_unregister:

tools/testing/selftests/riscv/sigreturn/sigreturn.c

@@ -51,7 +51,7 @@ static int vector_sigreturn(int data, void (*handler)(int, siginfo_t *, void *))
 
 	asm(".option push				\n\
 		.option		arch, +v		\n\
-		vsetivli	x0, 1, e32, ta, ma	\n\
+		vsetivli	x0, 1, e32, m1, ta, ma	\n\
 		vmv.s.x		v0, %1			\n\
 		# Generate SIGSEGV			\n\
 		lw		a0, 0(x0)		\n\