Merge tag 'perf-core-2024-09-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events updates from Ingo Molnar:

 - Implement per-PMU context rescheduling to significantly improve
   single-PMU performance, and related cleanups/fixes (Peter Zijlstra
   and Namhyung Kim)

 - Fix ancient bug resulting in a lot of events being dropped
   erroneously at higher sampling frequencies (Luo Gengkun)

 - uprobes enhancements:

     - Implement RCU-protected hot path optimizations for better
       performance:

         "For baseline vs SRCU, peak througput increased from 3.7 M/s
          (million uprobe triggerings per second) up to about 8 M/s. For
          uretprobes it's a bit more modest with bump from 2.4 M/s to
          5 M/s.

          For SRCU vs RCU Tasks Trace, peak throughput for uprobes
          increases further from 8 M/s to 10.3 M/s (+28%!), and for
          uretprobes from 5.3 M/s to 5.8 M/s (+11%), as we have more
          work to do on uretprobes side.

          Even single-thread (no contention) performance is slightly
          better: 3.276 M/s to 3.396 M/s (+3.5%) for uprobes, and 2.055
          M/s to 2.174 M/s (+5.8%) for uretprobes."

          (Andrii Nakryiko et al)

     - Document mmap_lock, don't abuse get_user_pages_remote() (Oleg
       Nesterov)

     - Cleanups & fixes to prepare for future work:
        - Remove uprobe_register_refctr()
	- Simplify error handling for alloc_uprobe()
        - Make uprobe_register() return struct uprobe *
        - Fold __uprobe_unregister() into uprobe_unregister()
        - Shift put_uprobe() from delete_uprobe() to uprobe_unregister()
        - BPF: Fix use-after-free in bpf_uprobe_multi_link_attach()
          (Oleg Nesterov)

 - New feature & ABI extension: allow events to use PERF_SAMPLE READ
   with inheritance, enabling sample based profiling of a group of
   counters over a hierarchy of processes or threads (Ben Gainey)

 - Intel uncore & power events updates:

      - Add Arrow Lake and Lunar Lake support
      - Add PERF_EV_CAP_READ_SCOPE
      - Clean up and enhance cpumask and hotplug support
        (Kan Liang)

      - Add LNL uncore iMC freerunning support
      - Use D0:F0 as a default device
        (Zhenyu Wang)

 - Intel PT: fix AUX snapshot handling race (Adrian Hunter)

 - Misc fixes and cleanups (James Clark, Jiri Olsa, Oleg Nesterov and
   Peter Zijlstra)

* tag 'perf-core-2024-09-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  dmaengine: idxd: Clean up cpumask and hotplug for perfmon
  iommu/vt-d: Clean up cpumask and hotplug for perfmon
  perf/x86/intel/cstate: Clean up cpumask and hotplug
  perf: Add PERF_EV_CAP_READ_SCOPE
  perf: Generic hotplug support for a PMU with a scope
  uprobes: perform lockless SRCU-protected uprobes_tree lookup
  rbtree: provide rb_find_rcu() / rb_find_add_rcu()
  perf/uprobe: split uprobe_unregister()
  uprobes: travers uprobe's consumer list locklessly under SRCU protection
  uprobes: get rid of enum uprobe_filter_ctx in uprobe filter callbacks
  uprobes: protected uprobe lifetime with SRCU
  uprobes: revamp uprobe refcounting and lifetime management
  bpf: Fix use-after-free in bpf_uprobe_multi_link_attach()
  perf/core: Fix small negative period being ignored
  perf: Really fix event_function_call() locking
  perf: Optimize __pmu_ctx_sched_out()
  perf: Add context time freeze
  perf: Fix event_function_call() locking
  perf: Extract a few helpers
  perf: Optimize context reschedule for single PMU cases
  ...

arch/x86/events/core.c

@@ -41,6 +41,8 @@
 #include <asm/desc.h>
 #include <asm/ldt.h>
 #include <asm/unwind.h>
+#include <asm/uprobes.h>
+#include <asm/ibt.h>
 
 #include "perf_event.h"
 
@@ -2816,6 +2818,46 @@ static unsigned long get_segment_base(unsigned int segment)
 	return get_desc_base(desc);
 }
 
+#ifdef CONFIG_UPROBES
+/*
+ * Heuristic-based check if uprobe is installed at the function entry.
+ *
+ * Under assumption of user code being compiled with frame pointers,
+ * `push %rbp/%ebp` is a good indicator that we indeed are.
+ *
+ * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern.
+ * If we get this wrong, captured stack trace might have one extra bogus
+ * entry, but the rest of stack trace will still be meaningful.
+ */
+static bool is_uprobe_at_func_entry(struct pt_regs *regs)
+{
+	struct arch_uprobe *auprobe;
+
+	if (!current->utask)
+		return false;
+
+	auprobe = current->utask->auprobe;
+	if (!auprobe)
+		return false;
+
+	/* push %rbp/%ebp */
+	if (auprobe->insn[0] == 0x55)
+		return true;
+
+	/* endbr64 (64-bit only) */
+	if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn))
+		return true;
+
+	return false;
+}
+
+#else
+static bool is_uprobe_at_func_entry(struct pt_regs *regs)
+{
+	return false;
+}
+#endif /* CONFIG_UPROBES */
+
 #ifdef CONFIG_IA32_EMULATION
 
 #include <linux/compat.h>
@@ -2827,6 +2869,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 	unsigned long ss_base, cs_base;
 	struct stack_frame_ia32 frame;
 	const struct stack_frame_ia32 __user *fp;
+	u32 ret_addr;
 
 	if (user_64bit_mode(regs))
 		return 0;
@@ -2836,6 +2879,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 
 	fp = compat_ptr(ss_base + regs->bp);
 	pagefault_disable();
+
+	/* see perf_callchain_user() below for why we do this */
+	if (is_uprobe_at_func_entry(regs) &&
+	    !get_user(ret_addr, (const u32 __user *)regs->sp))
+		perf_callchain_store(entry, ret_addr);
+
 	while (entry->nr < entry->max_stack) {
 		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
@@ -2864,6 +2913,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 {
 	struct stack_frame frame;
 	const struct stack_frame __user *fp;
+	unsigned long ret_addr;
 
 	if (perf_guest_state()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2887,6 +2937,19 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 		return;
 
 	pagefault_disable();
+
+	/*
+	 * If we are called from uprobe handler, and we are indeed at the very
+	 * entry to user function (which is normally a `push %rbp` instruction,
+	 * under assumption of application being compiled with frame pointers),
+	 * we should read return address from *regs->sp before proceeding
+	 * to follow frame pointers, otherwise we'll skip immediate caller
+	 * as %rbp is not yet setup.
+	 */
+	if (is_uprobe_at_func_entry(regs) &&
+	    !get_user(ret_addr, (const unsigned long __user *)regs->sp))
+		perf_callchain_store(entry, ret_addr);
+
 	while (entry->nr < entry->max_stack) {
 		if (!valid_user_frame(fp, sizeof(frame)))
 			break;

arch/x86/events/intel/bts.c

@@ -557,9 +557,6 @@ static int bts_event_init(struct perf_event *event)
 	 * disabled, so disallow intel_bts driver for unprivileged
 	 * users on paranoid systems since it provides trace data
 	 * to the user in a zero-copy fashion.
-	 *
-	 * Note that the default paranoia setting permits unprivileged
-	 * users to profile the kernel.
 	 */
 	if (event->attr.exclude_kernel) {
 		ret = perf_allow_kernel(&event->attr);

arch/x86/events/intel/cstate.c

@@ -128,10 +128,6 @@ static ssize_t __cstate_##_var##_show(struct device *dev,	\
 static struct device_attribute format_attr_##_var =		\
 	__ATTR(_name, 0444, __cstate_##_var##_show, NULL)
 
-static ssize_t cstate_get_attr_cpumask(struct device *dev,
-				       struct device_attribute *attr,
-				       char *buf);
-
 /* Model -> events mapping */
 struct cstate_model {
 	unsigned long		core_events;
@@ -206,22 +202,9 @@ static struct attribute_group cstate_format_attr_group = {
 	.attrs = cstate_format_attrs,
 };
 
-static cpumask_t cstate_core_cpu_mask;
-static DEVICE_ATTR(cpumask, S_IRUGO, cstate_get_attr_cpumask, NULL);
-
-static struct attribute *cstate_cpumask_attrs[] = {
-	&dev_attr_cpumask.attr,
-	NULL,
-};
-
-static struct attribute_group cpumask_attr_group = {
-	.attrs = cstate_cpumask_attrs,
-};
-
 static const struct attribute_group *cstate_attr_groups[] = {
 	&cstate_events_attr_group,
 	&cstate_format_attr_group,
-	&cpumask_attr_group,
 	NULL,
 };
 
@@ -269,8 +252,6 @@ static struct perf_msr pkg_msr[] = {
 	[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY,	&group_cstate_pkg_c10,	test_msr },
 };
 
-static cpumask_t cstate_pkg_cpu_mask;
-
 /* cstate_module PMU */
 static struct pmu cstate_module_pmu;
 static bool has_cstate_module;
@@ -291,28 +272,9 @@ static struct perf_msr module_msr[] = {
 	[PERF_CSTATE_MODULE_C6_RES]  = { MSR_MODULE_C6_RES_MS,	&group_cstate_module_c6,	test_msr },
 };
 
-static cpumask_t cstate_module_cpu_mask;
-
-static ssize_t cstate_get_attr_cpumask(struct device *dev,
-				       struct device_attribute *attr,
-				       char *buf)
-{
-	struct pmu *pmu = dev_get_drvdata(dev);
-
-	if (pmu == &cstate_core_pmu)
-		return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask);
-	else if (pmu == &cstate_pkg_pmu)
-		return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask);
-	else if (pmu == &cstate_module_pmu)
-		return cpumap_print_to_pagebuf(true, buf, &cstate_module_cpu_mask);
-	else
-		return 0;
-}
-
 static int cstate_pmu_event_init(struct perf_event *event)
 {
 	u64 cfg = event->attr.config;
-	int cpu;
 
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
@@ -331,20 +293,13 @@ static int cstate_pmu_event_init(struct perf_event *event)
 		if (!(core_msr_mask & (1 << cfg)))
 			return -EINVAL;
 		event->hw.event_base = core_msr[cfg].msr;
-		cpu = cpumask_any_and(&cstate_core_cpu_mask,
-				      topology_sibling_cpumask(event->cpu));
 	} else if (event->pmu == &cstate_pkg_pmu) {
 		if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
 			return -EINVAL;
 		cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
 		if (!(pkg_msr_mask & (1 << cfg)))
 			return -EINVAL;
-
-		event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
-
 		event->hw.event_base = pkg_msr[cfg].msr;
-		cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
-				      topology_die_cpumask(event->cpu));
 	} else if (event->pmu == &cstate_module_pmu) {
 		if (cfg >= PERF_CSTATE_MODULE_EVENT_MAX)
 			return -EINVAL;
@@ -352,16 +307,10 @@ static int cstate_pmu_event_init(struct perf_event *event)
 		if (!(module_msr_mask & (1 << cfg)))
 			return -EINVAL;
 		event->hw.event_base = module_msr[cfg].msr;
-		cpu = cpumask_any_and(&cstate_module_cpu_mask,
-				      topology_cluster_cpumask(event->cpu));
 	} else {
 		return -ENOENT;
 	}
 
-	if (cpu >= nr_cpu_ids)
-		return -ENODEV;
-
-	event->cpu = cpu;
 	event->hw.config = cfg;
 	event->hw.idx = -1;
 	return 0;
@@ -412,84 +361,6 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode)
 	return 0;
 }
 
-/*
- * Check if exiting cpu is the designated reader. If so migrate the
- * events when there is a valid target available
- */
-static int cstate_cpu_exit(unsigned int cpu)
-{
-	unsigned int target;
-
-	if (has_cstate_core &&
-	    cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) {
-
-		target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
-		/* Migrate events if there is a valid target */
-		if (target < nr_cpu_ids) {
-			cpumask_set_cpu(target, &cstate_core_cpu_mask);
-			perf_pmu_migrate_context(&cstate_core_pmu, cpu, target);
-		}
-	}
-
-	if (has_cstate_pkg &&
-	    cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {
-
-		target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
-		/* Migrate events if there is a valid target */
-		if (target < nr_cpu_ids) {
-			cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
-			perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
-		}
-	}
-
-	if (has_cstate_module &&
-	    cpumask_test_and_clear_cpu(cpu, &cstate_module_cpu_mask)) {
-
-		target = cpumask_any_but(topology_cluster_cpumask(cpu), cpu);
-		/* Migrate events if there is a valid target */
-		if (target < nr_cpu_ids) {
-			cpumask_set_cpu(target, &cstate_module_cpu_mask);
-			perf_pmu_migrate_context(&cstate_module_pmu, cpu, target);
-		}
-	}
-	return 0;
-}
-
-static int cstate_cpu_init(unsigned int cpu)
-{
-	unsigned int target;
-
-	/*
-	 * If this is the first online thread of that core, set it in
-	 * the core cpu mask as the designated reader.
-	 */
-	target = cpumask_any_and(&cstate_core_cpu_mask,
-				 topology_sibling_cpumask(cpu));
-
-	if (has_cstate_core && target >= nr_cpu_ids)
-		cpumask_set_cpu(cpu, &cstate_core_cpu_mask);
-
-	/*
-	 * If this is the first online thread of that package, set it
-	 * in the package cpu mask as the designated reader.
-	 */
-	target = cpumask_any_and(&cstate_pkg_cpu_mask,
-				 topology_die_cpumask(cpu));
-	if (has_cstate_pkg && target >= nr_cpu_ids)
-		cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
-
-	/*
-	 * If this is the first online thread of that cluster, set it
-	 * in the cluster cpu mask as the designated reader.
-	 */
-	target = cpumask_any_and(&cstate_module_cpu_mask,
-				 topology_cluster_cpumask(cpu));
-	if (has_cstate_module && target >= nr_cpu_ids)
-		cpumask_set_cpu(cpu, &cstate_module_cpu_mask);
-
-	return 0;
-}
-
 static const struct attribute_group *core_attr_update[] = {
 	&group_cstate_core_c1,
 	&group_cstate_core_c3,
@@ -526,6 +397,7 @@ static struct pmu cstate_core_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+	.scope		= PERF_PMU_SCOPE_CORE,
 	.module		= THIS_MODULE,
 };
 
@@ -541,6 +413,7 @@ static struct pmu cstate_pkg_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+	.scope		= PERF_PMU_SCOPE_PKG,
 	.module		= THIS_MODULE,
 };
 
@@ -556,6 +429,7 @@ static struct pmu cstate_module_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+	.scope		= PERF_PMU_SCOPE_CLUSTER,
 	.module		= THIS_MODULE,
 };
 
@@ -810,9 +684,6 @@ static int __init cstate_probe(const struct cstate_model *cm)
 
 static inline void cstate_cleanup(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING);
-
 	if (has_cstate_core)
 		perf_pmu_unregister(&cstate_core_pmu);
 
@@ -827,11 +698,6 @@ static int __init cstate_init(void)
 {
 	int err;
 
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING,
-			  "perf/x86/cstate:starting", cstate_cpu_init, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE,
-			  "perf/x86/cstate:online", NULL, cstate_cpu_exit);
-
 	if (has_cstate_core) {
 		err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
 		if (err) {
@@ -844,6 +710,8 @@ static int __init cstate_init(void)
 
 	if (has_cstate_pkg) {
 		if (topology_max_dies_per_package() > 1) {
+			/* CLX-AP is multi-die and the cstate is die-scope */
+			cstate_pkg_pmu.scope = PERF_PMU_SCOPE_DIE;
 			err = perf_pmu_register(&cstate_pkg_pmu,
 						"cstate_die", -1);
 		} else {

arch/x86/events/intel/pt.c

@@ -416,7 +416,7 @@ static bool pt_event_valid(struct perf_event *event)
 static void pt_config_start(struct perf_event *event)
 {
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
-	u64 ctl = event->hw.config;
+	u64 ctl = event->hw.aux_config;
 
 	ctl |= RTIT_CTL_TRACEEN;
 	if (READ_ONCE(pt->vmx_on))
@@ -424,7 +424,7 @@ static void pt_config_start(struct perf_event *event)
 	else
 		wrmsrl(MSR_IA32_RTIT_CTL, ctl);
 
-	WRITE_ONCE(event->hw.config, ctl);
+	WRITE_ONCE(event->hw.aux_config, ctl);
 }
 
 /* Address ranges and their corresponding msr configuration registers */
@@ -503,7 +503,7 @@ static void pt_config(struct perf_event *event)
 	u64 reg;
 
 	/* First round: clear STATUS, in particular the PSB byte counter. */
-	if (!event->hw.config) {
+	if (!event->hw.aux_config) {
 		perf_event_itrace_started(event);
 		wrmsrl(MSR_IA32_RTIT_STATUS, 0);
 	}
@@ -533,14 +533,14 @@ static void pt_config(struct perf_event *event)
 
 	reg |= (event->attr.config & PT_CONFIG_MASK);
 
-	event->hw.config = reg;
+	event->hw.aux_config = reg;
 	pt_config_start(event);
 }
 
 static void pt_config_stop(struct perf_event *event)
 {
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
-	u64 ctl = READ_ONCE(event->hw.config);
+	u64 ctl = READ_ONCE(event->hw.aux_config);
 
 	/* may be already stopped by a PMI */
 	if (!(ctl & RTIT_CTL_TRACEEN))
@@ -550,7 +550,7 @@ static void pt_config_stop(struct perf_event *event)
 	if (!READ_ONCE(pt->vmx_on))
 		wrmsrl(MSR_IA32_RTIT_CTL, ctl);
 
-	WRITE_ONCE(event->hw.config, ctl);
+	WRITE_ONCE(event->hw.aux_config, ctl);
 
 	/*
 	 * A wrmsr that disables trace generation serializes other PT
@@ -1557,7 +1557,7 @@ void intel_pt_handle_vmx(int on)
 
 	/* Turn PTs back on */
 	if (!on && event)
-		wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config);
+		wrmsrl(MSR_IA32_RTIT_CTL, event->hw.aux_config);
 
 	local_irq_restore(flags);
 }
@@ -1606,6 +1606,7 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	 * see comment in intel_pt_interrupt().
 	 */
 	WRITE_ONCE(pt->handle_nmi, 0);
+	barrier();
 
 	pt_config_stop(event);
 
@@ -1657,11 +1658,10 @@ static long pt_event_snapshot_aux(struct perf_event *event,
 		return 0;
 
 	/*
-	 * Here, handle_nmi tells us if the tracing is on
+	 * There is no PT interrupt in this mode, so stop the trace and it will
+	 * remain stopped while the buffer is copied.
 	 */
-	if (READ_ONCE(pt->handle_nmi))
-		pt_config_stop(event);
-
+	pt_config_stop(event);
 	pt_read_offset(buf);
 	pt_update_head(pt);
 
@@ -1673,11 +1673,10 @@ static long pt_event_snapshot_aux(struct perf_event *event,
 	ret = perf_output_copy_aux(&pt->handle, handle, from, to);
 
 	/*
-	 * If the tracing was on when we turned up, restart it.
-	 * Compiler barrier not needed as we couldn't have been
-	 * preempted by anything that touches pt->handle_nmi.
+	 * Here, handle_nmi tells us if the tracing was on.
+	 * If the tracing was on, restart it.
 	 */
-	if (pt->handle_nmi)
+	if (READ_ONCE(pt->handle_nmi))
 		pt_config_start(event);
 
 	return ret;

arch/x86/events/intel/uncore.c

@@ -1816,6 +1816,11 @@ static const struct intel_uncore_init_fun mtl_uncore_init __initconst = {
 	.mmio_init = adl_uncore_mmio_init,
 };
 
+static const struct intel_uncore_init_fun lnl_uncore_init __initconst = {
+	.cpu_init = lnl_uncore_cpu_init,
+	.mmio_init = lnl_uncore_mmio_init,
+};
+
 static const struct intel_uncore_init_fun icx_uncore_init __initconst = {
 	.cpu_init = icx_uncore_cpu_init,
 	.pci_init = icx_uncore_pci_init,
@@ -1893,6 +1898,10 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,	&adl_uncore_init),
 	X86_MATCH_VFM(INTEL_METEORLAKE,		&mtl_uncore_init),
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&mtl_uncore_init),
+	X86_MATCH_VFM(INTEL_ARROWLAKE,		&mtl_uncore_init),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&mtl_uncore_init),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&mtl_uncore_init),
+	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&lnl_uncore_init),
 	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_VFM(INTEL_GRANITERAPIDS_X,	&gnr_uncore_init),

arch/x86/events/intel/uncore.h

@@ -611,10 +611,12 @@ void skl_uncore_cpu_init(void);
 void icl_uncore_cpu_init(void);
 void tgl_uncore_cpu_init(void);
 void adl_uncore_cpu_init(void);
+void lnl_uncore_cpu_init(void);
 void mtl_uncore_cpu_init(void);
 void tgl_uncore_mmio_init(void);
 void tgl_l_uncore_mmio_init(void);
 void adl_uncore_mmio_init(void);
+void lnl_uncore_mmio_init(void);
 int snb_pci2phy_map_init(int devid);
 
 /* uncore_snbep.c */

arch/x86/events/intel/uncore_snb.c

@@ -252,6 +252,7 @@ DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
 DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
 DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
 DEFINE_UNCORE_FORMAT_ATTR(threshold, threshold, "config:24-29");
+DEFINE_UNCORE_FORMAT_ATTR(threshold2, threshold, "config:24-31");
 
 /* Sandy Bridge uncore support */
 static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -746,6 +747,34 @@ void mtl_uncore_cpu_init(void)
 	uncore_msr_uncores = mtl_msr_uncores;
 }
 
+static struct intel_uncore_type *lnl_msr_uncores[] = {
+	&mtl_uncore_cbox,
+	&mtl_uncore_arb,
+	NULL
+};
+
+#define LNL_UNC_MSR_GLOBAL_CTL			0x240e
+
+static void lnl_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0)
+		wrmsrl(LNL_UNC_MSR_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+}
+
+static struct intel_uncore_ops lnl_uncore_msr_ops = {
+	.init_box	= lnl_uncore_msr_init_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= snb_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+void lnl_uncore_cpu_init(void)
+{
+	mtl_uncore_cbox.num_boxes = 4;
+	mtl_uncore_cbox.ops = &lnl_uncore_msr_ops;
+	uncore_msr_uncores = lnl_msr_uncores;
+}
+
 enum {
 	SNB_PCI_UNCORE_IMC,
 };
@@ -1475,39 +1504,45 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void)
 		ids++;
 	}
 
+	/* Just try to grab 00:00.0 device */
+	if (!mc_dev)
+		mc_dev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
+
 	return mc_dev;
 }
 
 #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET		0x10000
 #define TGL_UNCORE_PCI_IMC_MAP_SIZE		0xe000
 
-static void __uncore_imc_init_box(struct intel_uncore_box *box,
-				  unsigned int base_offset)
+static void
+uncore_get_box_mmio_addr(struct intel_uncore_box *box,
+			 unsigned int base_offset,
+			 int bar_offset, int step)
 {
 	struct pci_dev *pdev = tgl_uncore_get_mc_dev();
 	struct intel_uncore_pmu *pmu = box->pmu;
 	struct intel_uncore_type *type = pmu->type;
 	resource_size_t addr;
-	u32 mch_bar;
+	u32 bar;
 
 	if (!pdev) {
 		pr_warn("perf uncore: Cannot find matched IMC device.\n");
 		return;
 	}
 
-	pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &mch_bar);
-	/* MCHBAR is disabled */
-	if (!(mch_bar & BIT(0))) {
-		pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n");
+	pci_read_config_dword(pdev, bar_offset, &bar);
+	if (!(bar & BIT(0))) {
+		pr_warn("perf uncore: BAR 0x%x is disabled. Failed to map %s counters.\n",
+			bar_offset, type->name);
 		pci_dev_put(pdev);
 		return;
 	}
-	mch_bar &= ~BIT(0);
-	addr = (resource_size_t)(mch_bar + TGL_UNCORE_MMIO_IMC_MEM_OFFSET * pmu->pmu_idx);
+	bar &= ~BIT(0);
+	addr = (resource_size_t)(bar + step * pmu->pmu_idx);
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET + 4, &mch_bar);
-	addr |= ((resource_size_t)mch_bar << 32);
+	pci_read_config_dword(pdev, bar_offset + 4, &bar);
+	addr |= ((resource_size_t)bar << 32);
 #endif
 
 	addr += base_offset;
@@ -1518,6 +1553,14 @@ static void __uncore_imc_init_box(struct intel_uncore_box *box,
 	pci_dev_put(pdev);
 }
 
+static void __uncore_imc_init_box(struct intel_uncore_box *box,
+				  unsigned int base_offset)
+{
+	uncore_get_box_mmio_addr(box, base_offset,
+				 SNB_UNCORE_PCI_IMC_BAR_OFFSET,
+				 TGL_UNCORE_MMIO_IMC_MEM_OFFSET);
+}
+
 static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
 {
 	__uncore_imc_init_box(box, 0);
@@ -1612,14 +1655,17 @@ static void adl_uncore_mmio_enable_box(struct intel_uncore_box *box)
 	writel(0, box->io_addr + uncore_mmio_box_ctl(box));
 }
 
+#define MMIO_UNCORE_COMMON_OPS()				\
+	.exit_box	= uncore_mmio_exit_box,		\
+	.disable_box	= adl_uncore_mmio_disable_box,	\
+	.enable_box	= adl_uncore_mmio_enable_box,	\
+	.disable_event	= intel_generic_uncore_mmio_disable_event,	\
+	.enable_event	= intel_generic_uncore_mmio_enable_event,	\
+	.read_counter	= uncore_mmio_read_counter,
+
 static struct intel_uncore_ops adl_uncore_mmio_ops = {
 	.init_box	= adl_uncore_imc_init_box,
-	.exit_box	= uncore_mmio_exit_box,
-	.disable_box	= adl_uncore_mmio_disable_box,
-	.enable_box	= adl_uncore_mmio_enable_box,
-	.disable_event	= intel_generic_uncore_mmio_disable_event,
-	.enable_event	= intel_generic_uncore_mmio_enable_event,
-	.read_counter	= uncore_mmio_read_counter,
+	MMIO_UNCORE_COMMON_OPS()
 };
 
 #define ADL_UNC_CTL_CHMASK_MASK			0x00000f00
@@ -1703,3 +1749,108 @@ void adl_uncore_mmio_init(void)
 }
 
 /* end of Alder Lake MMIO uncore support */
+
+/* Lunar Lake MMIO uncore support */
+#define LNL_UNCORE_PCI_SAFBAR_OFFSET		0x68
+#define LNL_UNCORE_MAP_SIZE			0x1000
+#define LNL_UNCORE_SNCU_BASE			0xE4B000
+#define LNL_UNCORE_SNCU_CTR			0x390
+#define LNL_UNCORE_SNCU_CTRL			0x398
+#define LNL_UNCORE_SNCU_BOX_CTL			0x380
+#define LNL_UNCORE_GLOBAL_CTL			0x700
+#define LNL_UNCORE_HBO_BASE			0xE54000
+#define LNL_UNCORE_HBO_OFFSET			-4096
+#define LNL_UNCORE_HBO_CTR			0x570
+#define LNL_UNCORE_HBO_CTRL			0x550
+#define LNL_UNCORE_HBO_BOX_CTL			0x548
+
+#define LNL_UNC_CTL_THRESHOLD			0xff000000
+#define LNL_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
+						 SNB_UNC_CTL_UMASK_MASK | \
+						 SNB_UNC_CTL_EDGE_DET | \
+						 SNB_UNC_CTL_INVERT | \
+						 LNL_UNC_CTL_THRESHOLD)
+
+static struct attribute *lnl_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_threshold2.attr,
+	NULL
+};
+
+static const struct attribute_group lnl_uncore_format_group = {
+	.name		= "format",
+	.attrs		= lnl_uncore_formats_attr,
+};
+
+static void lnl_uncore_hbo_init_box(struct intel_uncore_box *box)
+{
+	uncore_get_box_mmio_addr(box, LNL_UNCORE_HBO_BASE,
+				 LNL_UNCORE_PCI_SAFBAR_OFFSET,
+				 LNL_UNCORE_HBO_OFFSET);
+}
+
+static struct intel_uncore_ops lnl_uncore_hbo_ops = {
+	.init_box	= lnl_uncore_hbo_init_box,
+	MMIO_UNCORE_COMMON_OPS()
+};
+
+static struct intel_uncore_type lnl_uncore_hbo = {
+	.name		= "hbo",
+	.num_counters   = 4,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 64,
+	.perf_ctr	= LNL_UNCORE_HBO_CTR,
+	.event_ctl	= LNL_UNCORE_HBO_CTRL,
+	.event_mask	= LNL_UNC_RAW_EVENT_MASK,
+	.box_ctl	= LNL_UNCORE_HBO_BOX_CTL,
+	.mmio_map_size	= LNL_UNCORE_MAP_SIZE,
+	.ops		= &lnl_uncore_hbo_ops,
+	.format_group	= &lnl_uncore_format_group,
+};
+
+static void lnl_uncore_sncu_init_box(struct intel_uncore_box *box)
+{
+	uncore_get_box_mmio_addr(box, LNL_UNCORE_SNCU_BASE,
+				 LNL_UNCORE_PCI_SAFBAR_OFFSET,
+				 0);
+
+	if (box->io_addr)
+		writel(ADL_UNCORE_IMC_CTL_INT, box->io_addr + LNL_UNCORE_GLOBAL_CTL);
+}
+
+static struct intel_uncore_ops lnl_uncore_sncu_ops = {
+	.init_box	= lnl_uncore_sncu_init_box,
+	MMIO_UNCORE_COMMON_OPS()
+};
+
+static struct intel_uncore_type lnl_uncore_sncu = {
+	.name		= "sncu",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 64,
+	.perf_ctr	= LNL_UNCORE_SNCU_CTR,
+	.event_ctl	= LNL_UNCORE_SNCU_CTRL,
+	.event_mask	= LNL_UNC_RAW_EVENT_MASK,
+	.box_ctl	= LNL_UNCORE_SNCU_BOX_CTL,
+	.mmio_map_size	= LNL_UNCORE_MAP_SIZE,
+	.ops		= &lnl_uncore_sncu_ops,
+	.format_group	= &lnl_uncore_format_group,
+};
+
+static struct intel_uncore_type *lnl_mmio_uncores[] = {
+	&adl_uncore_imc,
+	&lnl_uncore_hbo,
+	&lnl_uncore_sncu,
+	&adl_uncore_imc_free_running,
+	NULL
+};
+
+void lnl_uncore_mmio_init(void)
+{
+	uncore_mmio_uncores = lnl_mmio_uncores;
+}
+
+/* end of Lunar Lake MMIO uncore support */

drivers/dma/idxd/idxd.h

@@ -124,7 +124,6 @@ struct idxd_pmu {
 
 	struct pmu pmu;
 	char name[IDXD_NAME_SIZE];
-	int cpu;
 
 	int n_counters;
 	int counter_width;
@@ -135,8 +134,6 @@ struct idxd_pmu {
 
 	unsigned long supported_filters;
 	int n_filters;
-
-	struct hlist_node cpuhp_node;
 };
 
 #define IDXD_MAX_PRIORITY	0xf
@@ -803,14 +800,10 @@ void idxd_user_counter_increment(struct idxd_wq *wq, u32 pasid, int index);
 int perfmon_pmu_init(struct idxd_device *idxd);
 void perfmon_pmu_remove(struct idxd_device *idxd);
 void perfmon_counter_overflow(struct idxd_device *idxd);
-void perfmon_init(void);
-void perfmon_exit(void);
 #else
 static inline int perfmon_pmu_init(struct idxd_device *idxd) { return 0; }
 static inline void perfmon_pmu_remove(struct idxd_device *idxd) {}
 static inline void perfmon_counter_overflow(struct idxd_device *idxd) {}
-static inline void perfmon_init(void) {}
-static inline void perfmon_exit(void) {}
 #endif
 
 /* debugfs */

drivers/dma/idxd/init.c

@@ -878,8 +878,6 @@ static int __init idxd_init_module(void)
 	else
 		support_enqcmd = true;
 
-	perfmon_init();
-
 	err = idxd_driver_register(&idxd_drv);
 	if (err < 0)
 		goto err_idxd_driver_register;
@@ -928,7 +926,6 @@ static void __exit idxd_exit_module(void)
 	idxd_driver_unregister(&idxd_drv);
 	pci_unregister_driver(&idxd_pci_driver);
 	idxd_cdev_remove();
-	perfmon_exit();
 	idxd_remove_debugfs();
 }
 module_exit(idxd_exit_module);

drivers/dma/idxd/perfmon.c

@@ -6,29 +6,6 @@
 #include "idxd.h"
 #include "perfmon.h"
 
-static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
-			    char *buf);
-
-static cpumask_t		perfmon_dsa_cpu_mask;
-static bool			cpuhp_set_up;
-static enum cpuhp_state		cpuhp_slot;
-
-/*
- * perf userspace reads this attribute to determine which cpus to open
- * counters on.  It's connected to perfmon_dsa_cpu_mask, which is
- * maintained by the cpu hotplug handlers.
- */
-static DEVICE_ATTR_RO(cpumask);
-
-static struct attribute *perfmon_cpumask_attrs[] = {
-	&dev_attr_cpumask.attr,
-	NULL,
-};
-
-static struct attribute_group cpumask_attr_group = {
-	.attrs = perfmon_cpumask_attrs,
-};
-
 /*
  * These attributes specify the bits in the config word that the perf
  * syscall uses to pass the event ids and categories to perfmon.
@@ -67,16 +44,9 @@ static struct attribute_group perfmon_format_attr_group = {
 
 static const struct attribute_group *perfmon_attr_groups[] = {
 	&perfmon_format_attr_group,
-	&cpumask_attr_group,
 	NULL,
 };
 
-static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
-			    char *buf)
-{
-	return cpumap_print_to_pagebuf(true, buf, &perfmon_dsa_cpu_mask);
-}
-
 static bool is_idxd_event(struct idxd_pmu *idxd_pmu, struct perf_event *event)
 {
 	return &idxd_pmu->pmu == event->pmu;
@@ -217,7 +187,6 @@ static int perfmon_pmu_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	event->hw.event_base = ioread64(PERFMON_TABLE_OFFSET(idxd));
-	event->cpu = idxd->idxd_pmu->cpu;
 	event->hw.config = event->attr.config;
 
 	if (event->group_leader != event)
@@ -488,6 +457,7 @@ static void idxd_pmu_init(struct idxd_pmu *idxd_pmu)
 	idxd_pmu->pmu.stop		= perfmon_pmu_event_stop;
 	idxd_pmu->pmu.read		= perfmon_pmu_event_update;
 	idxd_pmu->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
+	idxd_pmu->pmu.scope		= PERF_PMU_SCOPE_SYS_WIDE;
 	idxd_pmu->pmu.module		= THIS_MODULE;
 }
 
@@ -496,59 +466,17 @@ void perfmon_pmu_remove(struct idxd_device *idxd)
 	if (!idxd->idxd_pmu)
 		return;
 
-	cpuhp_state_remove_instance(cpuhp_slot, &idxd->idxd_pmu->cpuhp_node);
 	perf_pmu_unregister(&idxd->idxd_pmu->pmu);
 	kfree(idxd->idxd_pmu);
 	idxd->idxd_pmu = NULL;
 }
 
-static int perf_event_cpu_online(unsigned int cpu, struct hlist_node *node)
-{
-	struct idxd_pmu *idxd_pmu;
-
-	idxd_pmu = hlist_entry_safe(node, typeof(*idxd_pmu), cpuhp_node);
-
-	/* select the first online CPU as the designated reader */
-	if (cpumask_empty(&perfmon_dsa_cpu_mask)) {
-		cpumask_set_cpu(cpu, &perfmon_dsa_cpu_mask);
-		idxd_pmu->cpu = cpu;
-	}
-
-	return 0;
-}
-
-static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node)
-{
-	struct idxd_pmu *idxd_pmu;
-	unsigned int target;
-
-	idxd_pmu = hlist_entry_safe(node, typeof(*idxd_pmu), cpuhp_node);
-
-	if (!cpumask_test_and_clear_cpu(cpu, &perfmon_dsa_cpu_mask))
-		return 0;
-
-	target = cpumask_any_but(cpu_online_mask, cpu);
-	/* migrate events if there is a valid target */
-	if (target < nr_cpu_ids) {
-		cpumask_set_cpu(target, &perfmon_dsa_cpu_mask);
-		perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target);
-	}
-
-	return 0;
-}
-
 int perfmon_pmu_init(struct idxd_device *idxd)
 {
 	union idxd_perfcap perfcap;
 	struct idxd_pmu *idxd_pmu;
 	int rc = -ENODEV;
 
-	/*
-	 * perfmon module initialization failed, nothing to do
-	 */
-	if (!cpuhp_set_up)
-		return -ENODEV;
-
 	/*
 	 * If perfmon_offset or num_counters is 0, it means perfmon is
 	 * not supported on this hardware.
@@ -624,11 +552,6 @@ int perfmon_pmu_init(struct idxd_device *idxd)
 	if (rc)
 		goto free;
 
-	rc = cpuhp_state_add_instance(cpuhp_slot, &idxd_pmu->cpuhp_node);
-	if (rc) {
-		perf_pmu_unregister(&idxd->idxd_pmu->pmu);
-		goto free;
-	}
 out:
 	return rc;
 free:
@@ -637,22 +560,3 @@ int perfmon_pmu_init(struct idxd_device *idxd)
 
 	goto out;
 }
-
-void __init perfmon_init(void)
-{
-	int rc = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
-					 "driver/dma/idxd/perf:online",
-					 perf_event_cpu_online,
-					 perf_event_cpu_offline);
-	if (WARN_ON(rc < 0))
-		return;
-
-	cpuhp_slot = rc;
-	cpuhp_set_up = true;
-}
-
-void __exit perfmon_exit(void)
-{
-	if (cpuhp_set_up)
-		cpuhp_remove_multi_state(cpuhp_slot);
-}

drivers/iommu/intel/iommu.h

@@ -700,8 +700,6 @@ struct iommu_pmu {
 	DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX);
 	struct perf_event	*event_list[IOMMU_PMU_IDX_MAX];
 	unsigned char		irq_name[16];
-	struct hlist_node	cpuhp_node;
-	int			cpu;
 };
 
 #define IOMMU_IRQ_ID_OFFSET_PRQ		(DMAR_UNITS_SUPPORTED)

drivers/iommu/intel/perfmon.c

@@ -34,28 +34,9 @@ static struct attribute_group iommu_pmu_events_attr_group = {
 	.attrs = attrs_empty,
 };
 
-static cpumask_t iommu_pmu_cpu_mask;
-
-static ssize_t
-cpumask_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	return cpumap_print_to_pagebuf(true, buf, &iommu_pmu_cpu_mask);
-}
-static DEVICE_ATTR_RO(cpumask);
-
-static struct attribute *iommu_pmu_cpumask_attrs[] = {
-	&dev_attr_cpumask.attr,
-	NULL
-};
-
-static struct attribute_group iommu_pmu_cpumask_attr_group = {
-	.attrs = iommu_pmu_cpumask_attrs,
-};
-
 static const struct attribute_group *iommu_pmu_attr_groups[] = {
 	&iommu_pmu_format_attr_group,
 	&iommu_pmu_events_attr_group,
-	&iommu_pmu_cpumask_attr_group,
 	NULL
 };
 
@@ -565,6 +546,7 @@ static int __iommu_pmu_register(struct intel_iommu *iommu)
 	iommu_pmu->pmu.attr_groups	= iommu_pmu_attr_groups;
 	iommu_pmu->pmu.attr_update	= iommu_pmu_attr_update;
 	iommu_pmu->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
+	iommu_pmu->pmu.scope		= PERF_PMU_SCOPE_SYS_WIDE;
 	iommu_pmu->pmu.module		= THIS_MODULE;
 
 	return perf_pmu_register(&iommu_pmu->pmu, iommu_pmu->pmu.name, -1);
@@ -773,89 +755,6 @@ static void iommu_pmu_unset_interrupt(struct intel_iommu *iommu)
 	iommu->perf_irq = 0;
 }
 
-static int iommu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
-{
-	struct iommu_pmu *iommu_pmu = hlist_entry_safe(node, typeof(*iommu_pmu), cpuhp_node);
-
-	if (cpumask_empty(&iommu_pmu_cpu_mask))
-		cpumask_set_cpu(cpu, &iommu_pmu_cpu_mask);
-
-	if (cpumask_test_cpu(cpu, &iommu_pmu_cpu_mask))
-		iommu_pmu->cpu = cpu;
-
-	return 0;
-}
-
-static int iommu_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
-{
-	struct iommu_pmu *iommu_pmu = hlist_entry_safe(node, typeof(*iommu_pmu), cpuhp_node);
-	int target = cpumask_first(&iommu_pmu_cpu_mask);
-
-	/*
-	 * The iommu_pmu_cpu_mask has been updated when offline the CPU
-	 * for the first iommu_pmu. Migrate the other iommu_pmu to the
-	 * new target.
-	 */
-	if (target < nr_cpu_ids && target != iommu_pmu->cpu) {
-		perf_pmu_migrate_context(&iommu_pmu->pmu, cpu, target);
-		iommu_pmu->cpu = target;
-		return 0;
-	}
-
-	if (!cpumask_test_and_clear_cpu(cpu, &iommu_pmu_cpu_mask))
-		return 0;
-
-	target = cpumask_any_but(cpu_online_mask, cpu);
-
-	if (target < nr_cpu_ids)
-		cpumask_set_cpu(target, &iommu_pmu_cpu_mask);
-	else
-		return 0;
-
-	perf_pmu_migrate_context(&iommu_pmu->pmu, cpu, target);
-	iommu_pmu->cpu = target;
-
-	return 0;
-}
-
-static int nr_iommu_pmu;
-static enum cpuhp_state iommu_cpuhp_slot;
-
-static int iommu_pmu_cpuhp_setup(struct iommu_pmu *iommu_pmu)
-{
-	int ret;
-
-	if (!nr_iommu_pmu) {
-		ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
-					      "driver/iommu/intel/perfmon:online",
-					      iommu_pmu_cpu_online,
-					      iommu_pmu_cpu_offline);
-		if (ret < 0)
-			return ret;
-		iommu_cpuhp_slot = ret;
-	}
-
-	ret = cpuhp_state_add_instance(iommu_cpuhp_slot, &iommu_pmu->cpuhp_node);
-	if (ret) {
-		if (!nr_iommu_pmu)
-			cpuhp_remove_multi_state(iommu_cpuhp_slot);
-		return ret;
-	}
-	nr_iommu_pmu++;
-
-	return 0;
-}
-
-static void iommu_pmu_cpuhp_free(struct iommu_pmu *iommu_pmu)
-{
-	cpuhp_state_remove_instance(iommu_cpuhp_slot, &iommu_pmu->cpuhp_node);
-
-	if (--nr_iommu_pmu)
-		return;
-
-	cpuhp_remove_multi_state(iommu_cpuhp_slot);
-}
-
 void iommu_pmu_register(struct intel_iommu *iommu)
 {
 	struct iommu_pmu *iommu_pmu = iommu->pmu;
@@ -866,17 +765,12 @@ void iommu_pmu_register(struct intel_iommu *iommu)
 	if (__iommu_pmu_register(iommu))
 		goto err;
 
-	if (iommu_pmu_cpuhp_setup(iommu_pmu))
-		goto unregister;
-
 	/* Set interrupt for overflow */
 	if (iommu_pmu_set_interrupt(iommu))
-		goto cpuhp_free;
+		goto unregister;
 
 	return;
 
-cpuhp_free:
-	iommu_pmu_cpuhp_free(iommu_pmu);
 unregister:
 	perf_pmu_unregister(&iommu_pmu->pmu);
 err:
@@ -892,6 +786,5 @@ void iommu_pmu_unregister(struct intel_iommu *iommu)
 		return;
 
 	iommu_pmu_unset_interrupt(iommu);
-	iommu_pmu_cpuhp_free(iommu_pmu);
 	perf_pmu_unregister(&iommu_pmu->pmu);
 }

include/linux/cpuhotplug.h

@@ -153,7 +153,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-	CPUHP_AP_PERF_X86_CSTATE_STARTING,
 	CPUHP_AP_PERF_XTENSA_STARTING,
 	CPUHP_AP_ARM_VFP_STARTING,
 	CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
@@ -210,7 +209,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
 	CPUHP_AP_PERF_X86_RAPL_ONLINE,
-	CPUHP_AP_PERF_X86_CSTATE_ONLINE,
 	CPUHP_AP_PERF_S390_CF_ONLINE,
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,

include/linux/perf_event.h

@@ -168,6 +168,9 @@ struct hw_perf_event {
 			struct hw_perf_event_extra extra_reg;
 			struct hw_perf_event_extra branch_reg;
 		};
+		struct { /* aux / Intel-PT */
+			u64		aux_config;
+		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
 		};
@@ -292,6 +295,19 @@ struct perf_event_pmu_context;
 #define PERF_PMU_CAP_AUX_OUTPUT			0x0080
 #define PERF_PMU_CAP_EXTENDED_HW_TYPE		0x0100
 
+/**
+ * pmu::scope
+ */
+enum perf_pmu_scope {
+	PERF_PMU_SCOPE_NONE	= 0,
+	PERF_PMU_SCOPE_CORE,
+	PERF_PMU_SCOPE_DIE,
+	PERF_PMU_SCOPE_CLUSTER,
+	PERF_PMU_SCOPE_PKG,
+	PERF_PMU_SCOPE_SYS_WIDE,
+	PERF_PMU_MAX_SCOPE,
+};
+
 struct perf_output_handle;
 
 #define PMU_NULL_DEV	((void *)(~0UL))
@@ -315,6 +331,11 @@ struct pmu {
 	 */
 	int				capabilities;
 
+	/*
+	 * PMU scope
+	 */
+	unsigned int			scope;
+
 	int __percpu			*pmu_disable_count;
 	struct perf_cpu_pmu_context __percpu *cpu_pmu_context;
 	atomic_t			exclusive_cnt; /* < 0: cpu; > 0: tsk */
@@ -615,10 +636,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
  * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and
  * cannot be a group leader. If an event with this flag is detached from the
  * group it is scheduled out and moved into an unrecoverable ERROR state.
+ * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the
+ * PMU scope where it is active.
  */
 #define PERF_EV_CAP_SOFTWARE		BIT(0)
 #define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
 #define PERF_EV_CAP_SIBLING		BIT(2)
+#define PERF_EV_CAP_READ_SCOPE		BIT(3)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
@@ -963,12 +987,16 @@ struct perf_event_context {
 	struct rcu_head			rcu_head;
 
 	/*
-	 * Sum (event->pending_work + event->pending_work)
+	 * The count of events for which using the switch-out fast path
+	 * should be avoided.
+	 *
+	 * Sum (event->pending_work + events with
+	 *    (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ)))
 	 *
 	 * The SIGTRAP is targeted at ctx->task, as such it won't do changing
 	 * that until the signal is delivered.
 	 */
-	local_t				nr_pending;
+	local_t				nr_no_switch_fast;
 };
 
 struct perf_cpu_pmu_context {

include/linux/rbtree.h

@@ -244,6 +244,42 @@ rb_find_add(struct rb_node *node, struct rb_root *tree,
 	return NULL;
 }
 
+/**
+ * rb_find_add_rcu() - find equivalent @node in @tree, or add @node
+ * @node: node to look-for / insert
+ * @tree: tree to search / modify
+ * @cmp: operator defining the node order
+ *
+ * Adds a Store-Release for link_node.
+ *
+ * Returns the rb_node matching @node, or NULL when no match is found and @node
+ * is inserted.
+ */
+static __always_inline struct rb_node *
+rb_find_add_rcu(struct rb_node *node, struct rb_root *tree,
+		int (*cmp)(struct rb_node *, const struct rb_node *))
+{
+	struct rb_node **link = &tree->rb_node;
+	struct rb_node *parent = NULL;
+	int c;
+
+	while (*link) {
+		parent = *link;
+		c = cmp(node, parent);
+
+		if (c < 0)
+			link = &parent->rb_left;
+		else if (c > 0)
+			link = &parent->rb_right;
+		else
+			return parent;
+	}
+
+	rb_link_node_rcu(node, parent, link);
+	rb_insert_color(node, tree);
+	return NULL;
+}
+
 /**
  * rb_find() - find @key in tree @tree
  * @key: key to match
@@ -272,6 +308,37 @@ rb_find(const void *key, const struct rb_root *tree,
 	return NULL;
 }
 
+/**
+ * rb_find_rcu() - find @key in tree @tree
+ * @key: key to match
+ * @tree: tree to search
+ * @cmp: operator defining the node order
+ *
+ * Notably, tree descent vs concurrent tree rotations is unsound and can result
+ * in false-negatives.
+ *
+ * Returns the rb_node matching @key or NULL.
+ */
+static __always_inline struct rb_node *
+rb_find_rcu(const void *key, const struct rb_root *tree,
+	    int (*cmp)(const void *key, const struct rb_node *))
+{
+	struct rb_node *node = tree->rb_node;
+
+	while (node) {
+		int c = cmp(key, node);
+
+		if (c < 0)
+			node = rcu_dereference_raw(node->rb_left);
+		else if (c > 0)
+			node = rcu_dereference_raw(node->rb_right);
+		else
+			return node;
+	}
+
+	return NULL;
+}
+
 /**
  * rb_find_first() - find the first @key in @tree
  * @key: key to match

include/linux/uprobes.h

@@ -16,6 +16,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 
+struct uprobe;
 struct vm_area_struct;
 struct mm_struct;
 struct inode;
@@ -27,22 +28,22 @@ struct page;
 
 #define MAX_URETPROBE_DEPTH		64
 
-enum uprobe_filter_ctx {
-	UPROBE_FILTER_REGISTER,
-	UPROBE_FILTER_UNREGISTER,
-	UPROBE_FILTER_MMAP,
-};
-
 struct uprobe_consumer {
+	/*
+	 * handler() can return UPROBE_HANDLER_REMOVE to signal the need to
+	 * unregister uprobe for current process. If UPROBE_HANDLER_REMOVE is
+	 * returned, filter() callback has to be implemented as well and it
+	 * should return false to "confirm" the decision to uninstall uprobe
+	 * for the current process. If filter() is omitted or returns true,
+	 * UPROBE_HANDLER_REMOVE is effectively ignored.
+	 */
 	int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs);
 	int (*ret_handler)(struct uprobe_consumer *self,
 				unsigned long func,
 				struct pt_regs *regs);
-	bool (*filter)(struct uprobe_consumer *self,
-				enum uprobe_filter_ctx ctx,
-				struct mm_struct *mm);
+	bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm);
 
-	struct uprobe_consumer *next;
+	struct list_head cons_node;
 };
 
 #ifdef CONFIG_UPROBES
@@ -76,6 +77,8 @@ struct uprobe_task {
 	struct uprobe			*active_uprobe;
 	unsigned long			xol_vaddr;
 
+	struct arch_uprobe              *auprobe;
+
 	struct return_instance		*return_instances;
 	unsigned int			depth;
 };
@@ -110,10 +113,10 @@ extern bool is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
 extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
-extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
-extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
-extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
-extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
+extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
+extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
+extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
+extern void uprobe_unregister_sync(void);
 extern int uprobe_mmap(struct vm_area_struct *vma);
 extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void uprobe_start_dup_mmap(void);
@@ -151,22 +154,21 @@ static inline void uprobes_init(void)
 
 #define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
 
-static inline int
-uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
-{
-	return -ENOSYS;
-}
-static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc)
+static inline struct uprobe *
+uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc)
 {
-	return -ENOSYS;
+	return ERR_PTR(-ENOSYS);
 }
 static inline int
-uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add)
+uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add)
 {
 	return -ENOSYS;
 }
 static inline void
-uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
+uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc)
+{
+}
+static inline void uprobe_unregister_sync(void)
 {
 }
 static inline int uprobe_mmap(struct vm_area_struct *vma)

kernel/trace/bpf_trace.c

@@ -3160,6 +3160,7 @@ struct bpf_uprobe {
 	loff_t offset;
 	unsigned long ref_ctr_offset;
 	u64 cookie;
+	struct uprobe *uprobe;
 	struct uprobe_consumer consumer;
 };
 
@@ -3178,15 +3179,15 @@ struct bpf_uprobe_multi_run_ctx {
 	struct bpf_uprobe *uprobe;
 };
 
-static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes,
-				  u32 cnt)
+static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt)
 {
 	u32 i;
 
-	for (i = 0; i < cnt; i++) {
-		uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset,
-				  &uprobes[i].consumer);
-	}
+	for (i = 0; i < cnt; i++)
+		uprobe_unregister_nosync(uprobes[i].uprobe, &uprobes[i].consumer);
+
+	if (cnt)
+		uprobe_unregister_sync();
 }
 
 static void bpf_uprobe_multi_link_release(struct bpf_link *link)
@@ -3194,7 +3195,7 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link)
 	struct bpf_uprobe_multi_link *umulti_link;
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
-	bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+	bpf_uprobe_unregister(umulti_link->uprobes, umulti_link->cnt);
 	if (umulti_link->task)
 		put_task_struct(umulti_link->task);
 	path_put(&umulti_link->path);
@@ -3322,8 +3323,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 }
 
 static bool
-uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx,
-			 struct mm_struct *mm)
+uprobe_multi_link_filter(struct uprobe_consumer *con, struct mm_struct *mm)
 {
 	struct bpf_uprobe *uprobe;
 
@@ -3480,22 +3480,26 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		      &bpf_uprobe_multi_link_lops, prog);
 
 	for (i = 0; i < cnt; i++) {
-		err = uprobe_register_refctr(d_real_inode(link->path.dentry),
-					     uprobes[i].offset,
-					     uprobes[i].ref_ctr_offset,
-					     &uprobes[i].consumer);
-		if (err) {
-			bpf_uprobe_unregister(&path, uprobes, i);
-			goto error_free;
+		uprobes[i].uprobe = uprobe_register(d_real_inode(link->path.dentry),
+						    uprobes[i].offset,
+						    uprobes[i].ref_ctr_offset,
+						    &uprobes[i].consumer);
+		if (IS_ERR(uprobes[i].uprobe)) {
+			err = PTR_ERR(uprobes[i].uprobe);
+			link->cnt = i;
+			goto error_unregister;
 		}
 	}
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err)
-		goto error_free;
+		goto error_unregister;
 
 	return bpf_link_settle(&link_primer);
 
+error_unregister:
+	bpf_uprobe_unregister(uprobes, link->cnt);
+
 error_free:
 	kvfree(uprobes);
 	kfree(link);

kernel/trace/trace_uprobe.c

@@ -58,8 +58,8 @@ struct trace_uprobe {
 	struct dyn_event		devent;
 	struct uprobe_consumer		consumer;
 	struct path			path;
-	struct inode			*inode;
 	char				*filename;
+	struct uprobe			*uprobe;
 	unsigned long			offset;
 	unsigned long			ref_ctr_offset;
 	unsigned long			nhit;
@@ -1078,43 +1078,40 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
 	return trace_handle_return(s);
 }
 
-typedef bool (*filter_func_t)(struct uprobe_consumer *self,
-				enum uprobe_filter_ctx ctx,
-				struct mm_struct *mm);
+typedef bool (*filter_func_t)(struct uprobe_consumer *self, struct mm_struct *mm);
 
 static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter)
 {
-	int ret;
+	struct inode *inode = d_real_inode(tu->path.dentry);
+	struct uprobe *uprobe;
 
 	tu->consumer.filter = filter;
-	tu->inode = d_real_inode(tu->path.dentry);
-
-	if (tu->ref_ctr_offset)
-		ret = uprobe_register_refctr(tu->inode, tu->offset,
-				tu->ref_ctr_offset, &tu->consumer);
-	else
-		ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+	uprobe = uprobe_register(inode, tu->offset, tu->ref_ctr_offset, &tu->consumer);
+	if (IS_ERR(uprobe))
+		return PTR_ERR(uprobe);
 
-	if (ret)
-		tu->inode = NULL;
-
-	return ret;
+	tu->uprobe = uprobe;
+	return 0;
 }
 
 static void __probe_event_disable(struct trace_probe *tp)
 {
 	struct trace_uprobe *tu;
+	bool sync = false;
 
 	tu = container_of(tp, struct trace_uprobe, tp);
 	WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		if (!tu->inode)
+		if (!tu->uprobe)
 			continue;
 
-		uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
-		tu->inode = NULL;
+		uprobe_unregister_nosync(tu->uprobe, &tu->consumer);
+		sync = true;
+		tu->uprobe = NULL;
 	}
+	if (sync)
+		uprobe_unregister_sync();
 }
 
 static int probe_event_enable(struct trace_event_call *call,
@@ -1310,7 +1307,7 @@ static int uprobe_perf_close(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
+		ret = uprobe_apply(tu->uprobe, &tu->consumer, false);
 		if (ret)
 			break;
 	}
@@ -1334,7 +1331,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		err = uprobe_apply(tu->uprobe, &tu->consumer, true);
 		if (err) {
 			uprobe_perf_close(call, event);
 			break;
@@ -1344,8 +1341,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 	return err;
 }
 
-static bool uprobe_perf_filter(struct uprobe_consumer *uc,
-				enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+static bool uprobe_perf_filter(struct uprobe_consumer *uc, struct mm_struct *mm)
 {
 	struct trace_uprobe_filter *filter;
 	struct trace_uprobe *tu;
@@ -1431,7 +1427,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs,
 			    struct uprobe_cpu_buffer **ucbp)
 {
-	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
+	if (!uprobe_perf_filter(&tu->consumer, current->mm))
 		return UPROBE_HANDLER_REMOVE;
 
 	if (!is_ret_probe(tu))

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c

@@ -434,7 +434,7 @@ uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func,
 
 struct testmod_uprobe {
 	struct path path;
-	loff_t offset;
+	struct uprobe *uprobe;
 	struct uprobe_consumer consumer;
 };
 
@@ -448,25 +448,25 @@ static int testmod_register_uprobe(loff_t offset)
 {
 	int err = -EBUSY;
 
-	if (uprobe.offset)
+	if (uprobe.uprobe)
 		return -EBUSY;
 
 	mutex_lock(&testmod_uprobe_mutex);
 
-	if (uprobe.offset)
+	if (uprobe.uprobe)
 		goto out;
 
 	err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path);
 	if (err)
 		goto out;
 
-	err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry),
-				     offset, 0, &uprobe.consumer);
-	if (err)
+	uprobe.uprobe = uprobe_register(d_real_inode(uprobe.path.dentry),
+					offset, 0, &uprobe.consumer);
+	if (IS_ERR(uprobe.uprobe)) {
+		err = PTR_ERR(uprobe.uprobe);
 		path_put(&uprobe.path);
-	else
-		uprobe.offset = offset;
-
+		uprobe.uprobe = NULL;
+	}
 out:
 	mutex_unlock(&testmod_uprobe_mutex);
 	return err;
@@ -476,10 +476,11 @@ static void testmod_unregister_uprobe(void)
 {
 	mutex_lock(&testmod_uprobe_mutex);
 
-	if (uprobe.offset) {
-		uprobe_unregister(d_real_inode(uprobe.path.dentry),
-				  uprobe.offset, &uprobe.consumer);
-		uprobe.offset = 0;
+	if (uprobe.uprobe) {
+		uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer);
+		uprobe_unregister_sync();
+		path_put(&uprobe.path);
+		uprobe.uprobe = NULL;
 	}
 
 	mutex_unlock(&testmod_uprobe_mutex);