Merge tag 'perf-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events updates from Ingo Molnar:

 - Platform PMU driver updates:

     - x86 Intel uncore driver updates for Skylake (SNR) and Icelake (ICX) servers
     - Fix RDPMC support
     - Fix [extended-]PEBS-via-PT support
     - Fix Sapphire Rapids event constraints
     - Fix :ppp support on Sapphire Rapids
     - Fix fixed counter sanity check on Alder Lake & X86_FEATURE_HYBRID_CPU
     - Other heterogenous-PMU fixes

 - Kprobes:

     - Remove the unused and misguided kprobe::fault_handler callbacks.
     - Warn about kprobes taking a page fault.
     - Fix the 'nmissed' stat counter.

 - Misc cleanups and fixes.

* tag 'perf-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Fix task context PMU for Hetero
  perf/x86/intel: Fix instructions:ppp support in Sapphire Rapids
  perf/x86/intel: Add more events requires FRONTEND MSR on Sapphire Rapids
  perf/x86/intel: Fix fixed counter check warning for some Alder Lake
  perf/x86/intel: Fix PEBS-via-PT reload base value for Extended PEBS
  perf/x86: Reset the dirty counter to prevent the leak for an RDPMC task
  kprobes: Do not increment probe miss count in the fault handler
  x86,kprobes: WARN if kprobes tries to handle a fault
  kprobes: Remove kprobe::fault_handler
  uprobes: Update uprobe_write_opcode() kernel-doc comment
  perf/hw_breakpoint: Fix DocBook warnings in perf hw_breakpoint
  perf/core: Fix DocBook warnings
  perf/core: Make local function perf_pmu_snapshot_aux() static
  perf/x86/intel/uncore: Enable I/O stacks to IIO PMON mapping on ICX
  perf/x86/intel/uncore: Enable I/O stacks to IIO PMON mapping on SNR
  perf/x86/intel/uncore: Generalize I/O stacks to PMON mapping procedure
  perf/x86/intel/uncore: Drop unnecessary NULL checks after container_of()

Documentation/trace/kprobes.rst

@@ -362,14 +362,11 @@ register_kprobe
 	#include <linux/kprobes.h>
 	int register_kprobe(struct kprobe *kp);
 
-Sets a breakpoint at the address kp->addr.  When the breakpoint is
-hit, Kprobes calls kp->pre_handler.  After the probed instruction
-is single-stepped, Kprobe calls kp->post_handler.  If a fault
-occurs during execution of kp->pre_handler or kp->post_handler,
-or during single-stepping of the probed instruction, Kprobes calls
-kp->fault_handler.  Any or all handlers can be NULL. If kp->flags
-is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled,
-so, its handlers aren't hit until calling enable_kprobe(kp).
+Sets a breakpoint at the address kp->addr.  When the breakpoint is hit, Kprobes
+calls kp->pre_handler.  After the probed instruction is single-stepped, Kprobe
+calls kp->post_handler.  Any or all handlers can be NULL. If kp->flags is set
+KPROBE_FLAG_DISABLED, that kp will be registered but disabled, so, its handlers
+aren't hit until calling enable_kprobe(kp).
 
 .. note::
 
@@ -415,17 +412,6 @@ User's post-handler (kp->post_handler)::
 p and regs are as described for the pre_handler.  flags always seems
 to be zero.
 
-User's fault-handler (kp->fault_handler)::
-
-	#include <linux/kprobes.h>
-	#include <linux/ptrace.h>
-	int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
-
-p and regs are as described for the pre_handler.  trapnr is the
-architecture-specific trap number associated with the fault (e.g.,
-on i386, 13 for a general protection fault or 14 for a page fault).
-Returns 1 if it successfully handled the exception.
-
 register_kretprobe
 ------------------
 

arch/arc/kernel/kprobes.c

@@ -317,22 +317,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned long trapnr)
 		 * caused the fault.
 		 */
 
-		/* We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned zero,
 		 * try to fix up.

arch/arm/probes/kprobes/core.c

@@ -348,29 +348,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 			reset_current_kprobe();
 		}
 		break;
-
-	case KPROBE_HIT_ACTIVE:
-	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
-			return 1;
-		break;
-
-	default:
-		break;
 	}
 
 	return 0;

arch/arm64/kernel/probes/kprobes.c

@@ -276,23 +276,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/csky/kernel/probes/kprobes.c

@@ -294,23 +294,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/ia64/kernel/kprobes.c

@@ -843,22 +843,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/mips/kernel/kprobes.c

@@ -403,9 +403,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
-	if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-		return 1;
-
 	if (kcb->kprobe_status & KPROBE_HIT_SS) {
 		resume_execution(cur, regs, kcb);
 		regs->cp0_status |= kcb->kprobe_old_SR;

arch/powerpc/kernel/kprobes.c

@@ -501,23 +501,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/riscv/kernel/probes/kprobes.c

@@ -278,23 +278,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/s390/kernel/kprobes.c

@@ -445,23 +445,6 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(p);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (p->fault_handler && p->fault_handler(p, regs, trapnr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/sh/kernel/kprobes.c

@@ -382,23 +382,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/sparc/kernel/kprobes.c

@@ -345,23 +345,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		break;
 	case KPROBE_HIT_ACTIVE:
 	case KPROBE_HIT_SSDONE:
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
-
 		/*
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.

arch/x86/events/core.c

@@ -1626,6 +1626,8 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
 		goto do_del;
 
+	__set_bit(event->hw.idx, cpuc->dirty);
+
 	/*
 	 * Not a TXN, therefore cleanup properly.
 	 */
@@ -2474,6 +2476,31 @@ static int x86_pmu_event_init(struct perf_event *event)
 	return err;
 }
 
+void perf_clear_dirty_counters(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int i;
+
+	 /* Don't need to clear the assigned counter. */
+	for (i = 0; i < cpuc->n_events; i++)
+		__clear_bit(cpuc->assign[i], cpuc->dirty);
+
+	if (bitmap_empty(cpuc->dirty, X86_PMC_IDX_MAX))
+		return;
+
+	for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
+		/* Metrics and fake events don't have corresponding HW counters. */
+		if (is_metric_idx(i) || (i == INTEL_PMC_IDX_FIXED_VLBR))
+			continue;
+		else if (i >= INTEL_PMC_IDX_FIXED)
+			wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
+		else
+			wrmsrl(x86_pmu_event_addr(i), 0);
+	}
+
+	bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX);
+}
+
 static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 {
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
@@ -2497,7 +2524,6 @@ static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 
 static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
 {
-
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
 

arch/x86/events/intel/core.c

@@ -280,6 +280,8 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+	INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE),
+	INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE),
 	EVENT_EXTRA_END
 };
 
@@ -4030,8 +4032,10 @@ spr_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	 * The :ppp indicates the Precise Distribution (PDist) facility, which
 	 * is only supported on the GP counter 0. If a :ppp event which is not
 	 * available on the GP counter 0, error out.
+	 * Exception: Instruction PDIR is only available on the fixed counter 0.
 	 */
-	if (event->attr.precise_ip == 3) {
+	if ((event->attr.precise_ip == 3) &&
+	    !constraint_match(&fixed0_constraint, event->hw.config)) {
 		if (c->idxmsk64 & BIT_ULL(0))
 			return &counter0_constraint;
 
@@ -6163,8 +6167,13 @@ __init int intel_pmu_init(void)
 		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
 		pmu->name = "cpu_core";
 		pmu->cpu_type = hybrid_big;
-		pmu->num_counters = x86_pmu.num_counters + 2;
-		pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
+		if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
+			pmu->num_counters = x86_pmu.num_counters + 2;
+			pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
+		} else {
+			pmu->num_counters = x86_pmu.num_counters;
+			pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+		}
 		pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
 		pmu->unconstrained = (struct event_constraint)
 					__EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,

arch/x86/events/intel/ds.c

@@ -1187,6 +1187,9 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
+	u64 value = ds->pebs_event_reset[hwc->idx];
+	u32 base = MSR_RELOAD_PMC0;
+	unsigned int idx = hwc->idx;
 
 	if (!is_pebs_pt(event))
 		return;
@@ -1196,7 +1199,12 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 
 	cpuc->pebs_enabled |= PEBS_OUTPUT_PT;
 
-	wrmsrl(MSR_RELOAD_PMC0 + hwc->idx, ds->pebs_event_reset[hwc->idx]);
+	if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
+		base = MSR_RELOAD_FIXED_CTR0;
+		idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+		value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx];
+	}
+	wrmsrl(base + idx, value);
 }
 
 void intel_pmu_pebs_enable(struct perf_event *event)
@@ -1204,6 +1212,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
+	unsigned int idx = hwc->idx;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
@@ -1222,19 +1231,18 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 		}
 	}
 
+	if (idx >= INTEL_PMC_IDX_FIXED)
+		idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+
 	/*
 	 * Use auto-reload if possible to save a MSR write in the PMI.
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		unsigned int idx = hwc->idx;
-
-		if (idx >= INTEL_PMC_IDX_FIXED)
-			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
 		ds->pebs_event_reset[idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	} else {
-		ds->pebs_event_reset[hwc->idx] = 0;
+		ds->pebs_event_reset[idx] = 0;
 	}
 
 	intel_pmu_pebs_via_pt_enable(event);

arch/x86/events/intel/uncore.c

@@ -801,8 +801,6 @@ static void uncore_pmu_enable(struct pmu *pmu)
 	struct intel_uncore_box *box;
 
 	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
-	if (!uncore_pmu)
-		return;
 
 	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
 	if (!box)
@@ -818,8 +816,6 @@ static void uncore_pmu_disable(struct pmu *pmu)
 	struct intel_uncore_box *box;
 
 	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
-	if (!uncore_pmu)
-		return;
 
 	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
 	if (!box)

arch/x86/events/intel/uncore.h

@@ -92,6 +92,7 @@ struct intel_uncore_type {
 	/*
 	 * Optional callbacks for managing mapping of Uncore units to PMONs
 	 */
+	int (*get_topology)(struct intel_uncore_type *type);
 	int (*set_mapping)(struct intel_uncore_type *type);
 	void (*cleanup_mapping)(struct intel_uncore_type *type);
 };

arch/x86/events/intel/uncore_snbep.c

@@ -348,6 +348,13 @@
 #define SKX_M2M_PCI_PMON_CTR0		0x200
 #define SKX_M2M_PCI_PMON_BOX_CTL	0x258
 
+/* Memory Map registers device ID */
+#define SNR_ICX_MESH2IIO_MMAP_DID		0x9a2
+#define SNR_ICX_SAD_CONTROL_CFG		0x3f4
+
+/* Getting I/O stack id in SAD_COTROL_CFG notation */
+#define SAD_CONTROL_STACK_ID(data)		(((data) >> 4) & 0x7)
+
 /* SNR Ubox */
 #define SNR_U_MSR_PMON_CTR0			0x1f98
 #define SNR_U_MSR_PMON_CTL0			0x1f91
@@ -3682,12 +3689,19 @@ static inline u8 skx_iio_stack(struct intel_uncore_pmu *pmu, int die)
 }
 
 static umode_t
-skx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die)
+pmu_iio_mapping_visible(struct kobject *kobj, struct attribute *attr,
+			 int die, int zero_bus_pmu)
 {
 	struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(kobj_to_dev(kobj));
 
-	/* Root bus 0x00 is valid only for die 0 AND pmu_idx = 0. */
-	return (!skx_iio_stack(pmu, die) && pmu->pmu_idx) ? 0 : attr->mode;
+	return (!skx_iio_stack(pmu, die) && pmu->pmu_idx != zero_bus_pmu) ? 0 : attr->mode;
+}
+
+static umode_t
+skx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die)
+{
+	/* Root bus 0x00 is valid only for pmu_idx = 0. */
+	return pmu_iio_mapping_visible(kobj, attr, die, 0);
 }
 
 static ssize_t skx_iio_mapping_show(struct device *dev,
@@ -3772,7 +3786,8 @@ static const struct attribute_group *skx_iio_attr_update[] = {
 	NULL,
 };
 
-static int skx_iio_set_mapping(struct intel_uncore_type *type)
+static int
+pmu_iio_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag)
 {
 	char buf[64];
 	int ret;
@@ -3780,7 +3795,7 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type)
 	struct attribute **attrs = NULL;
 	struct dev_ext_attribute *eas = NULL;
 
-	ret = skx_iio_get_topology(type);
+	ret = type->get_topology(type);
 	if (ret < 0)
 		goto clear_attr_update;
 
@@ -3807,7 +3822,7 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type)
 		eas[die].var = (void *)die;
 		attrs[die] = &eas[die].attr.attr;
 	}
-	skx_iio_mapping_group.attrs = attrs;
+	ag->attrs = attrs;
 
 	return 0;
 err:
@@ -3821,6 +3836,11 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type)
 	return ret;
 }
 
+static int skx_iio_set_mapping(struct intel_uncore_type *type)
+{
+	return pmu_iio_set_mapping(type, &skx_iio_mapping_group);
+}
+
 static void skx_iio_cleanup_mapping(struct intel_uncore_type *type)
 {
 	struct attribute **attr = skx_iio_mapping_group.attrs;
@@ -3851,6 +3871,7 @@ static struct intel_uncore_type skx_uncore_iio = {
 	.ops			= &skx_uncore_iio_ops,
 	.format_group		= &skx_uncore_iio_format_group,
 	.attr_update		= skx_iio_attr_update,
+	.get_topology		= skx_iio_get_topology,
 	.set_mapping		= skx_iio_set_mapping,
 	.cleanup_mapping	= skx_iio_cleanup_mapping,
 };
@@ -4393,6 +4414,91 @@ static const struct attribute_group snr_uncore_iio_format_group = {
 	.attrs = snr_uncore_iio_formats_attr,
 };
 
+static umode_t
+snr_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die)
+{
+	/* Root bus 0x00 is valid only for pmu_idx = 1. */
+	return pmu_iio_mapping_visible(kobj, attr, die, 1);
+}
+
+static struct attribute_group snr_iio_mapping_group = {
+	.is_visible	= snr_iio_mapping_visible,
+};
+
+static const struct attribute_group *snr_iio_attr_update[] = {
+	&snr_iio_mapping_group,
+	NULL,
+};
+
+static int sad_cfg_iio_topology(struct intel_uncore_type *type, u8 *sad_pmon_mapping)
+{
+	u32 sad_cfg;
+	int die, stack_id, ret = -EPERM;
+	struct pci_dev *dev = NULL;
+
+	type->topology = kcalloc(uncore_max_dies(), sizeof(*type->topology),
+				 GFP_KERNEL);
+	if (!type->topology)
+		return -ENOMEM;
+
+	while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, SNR_ICX_MESH2IIO_MMAP_DID, dev))) {
+		ret = pci_read_config_dword(dev, SNR_ICX_SAD_CONTROL_CFG, &sad_cfg);
+		if (ret) {
+			ret = pcibios_err_to_errno(ret);
+			break;
+		}
+
+		die = uncore_pcibus_to_dieid(dev->bus);
+		stack_id = SAD_CONTROL_STACK_ID(sad_cfg);
+		if (die < 0 || stack_id >= type->num_boxes) {
+			ret = -EPERM;
+			break;
+		}
+
+		/* Convert stack id from SAD_CONTROL to PMON notation. */
+		stack_id = sad_pmon_mapping[stack_id];
+
+		((u8 *)&(type->topology[die].configuration))[stack_id] = dev->bus->number;
+		type->topology[die].segment = pci_domain_nr(dev->bus);
+	}
+
+	if (ret) {
+		kfree(type->topology);
+		type->topology = NULL;
+	}
+
+	return ret;
+}
+
+/*
+ * SNR has a static mapping of stack IDs from SAD_CONTROL_CFG notation to PMON
+ */
+enum {
+	SNR_QAT_PMON_ID,
+	SNR_CBDMA_DMI_PMON_ID,
+	SNR_NIS_PMON_ID,
+	SNR_DLB_PMON_ID,
+	SNR_PCIE_GEN3_PMON_ID
+};
+
+static u8 snr_sad_pmon_mapping[] = {
+	SNR_CBDMA_DMI_PMON_ID,
+	SNR_PCIE_GEN3_PMON_ID,
+	SNR_DLB_PMON_ID,
+	SNR_NIS_PMON_ID,
+	SNR_QAT_PMON_ID
+};
+
+static int snr_iio_get_topology(struct intel_uncore_type *type)
+{
+	return sad_cfg_iio_topology(type, snr_sad_pmon_mapping);
+}
+
+static int snr_iio_set_mapping(struct intel_uncore_type *type)
+{
+	return pmu_iio_set_mapping(type, &snr_iio_mapping_group);
+}
+
 static struct intel_uncore_type snr_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
@@ -4406,6 +4512,10 @@ static struct intel_uncore_type snr_uncore_iio = {
 	.msr_offset		= SNR_IIO_MSR_OFFSET,
 	.ops			= &ivbep_uncore_msr_ops,
 	.format_group		= &snr_uncore_iio_format_group,
+	.attr_update		= snr_iio_attr_update,
+	.get_topology		= snr_iio_get_topology,
+	.set_mapping		= snr_iio_set_mapping,
+	.cleanup_mapping	= skx_iio_cleanup_mapping,
 };
 
 static struct intel_uncore_type snr_uncore_irp = {
@@ -4933,6 +5043,53 @@ static struct event_constraint icx_uncore_iio_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+static umode_t
+icx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die)
+{
+	/* Root bus 0x00 is valid only for pmu_idx = 5. */
+	return pmu_iio_mapping_visible(kobj, attr, die, 5);
+}
+
+static struct attribute_group icx_iio_mapping_group = {
+	.is_visible	= icx_iio_mapping_visible,
+};
+
+static const struct attribute_group *icx_iio_attr_update[] = {
+	&icx_iio_mapping_group,
+	NULL,
+};
+
+/*
+ * ICX has a static mapping of stack IDs from SAD_CONTROL_CFG notation to PMON
+ */
+enum {
+	ICX_PCIE1_PMON_ID,
+	ICX_PCIE2_PMON_ID,
+	ICX_PCIE3_PMON_ID,
+	ICX_PCIE4_PMON_ID,
+	ICX_PCIE5_PMON_ID,
+	ICX_CBDMA_DMI_PMON_ID
+};
+
+static u8 icx_sad_pmon_mapping[] = {
+	ICX_CBDMA_DMI_PMON_ID,
+	ICX_PCIE1_PMON_ID,
+	ICX_PCIE2_PMON_ID,
+	ICX_PCIE3_PMON_ID,
+	ICX_PCIE4_PMON_ID,
+	ICX_PCIE5_PMON_ID,
+};
+
+static int icx_iio_get_topology(struct intel_uncore_type *type)
+{
+	return sad_cfg_iio_topology(type, icx_sad_pmon_mapping);
+}
+
+static int icx_iio_set_mapping(struct intel_uncore_type *type)
+{
+	return pmu_iio_set_mapping(type, &icx_iio_mapping_group);
+}
+
 static struct intel_uncore_type icx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
@@ -4947,6 +5104,10 @@ static struct intel_uncore_type icx_uncore_iio = {
 	.constraints		= icx_uncore_iio_constraints,
 	.ops			= &skx_uncore_iio_ops,
 	.format_group		= &snr_uncore_iio_format_group,
+	.attr_update		= icx_iio_attr_update,
+	.get_topology		= icx_iio_get_topology,
+	.set_mapping		= icx_iio_set_mapping,
+	.cleanup_mapping	= skx_iio_cleanup_mapping,
 };
 
 static struct intel_uncore_type icx_uncore_irp = {

arch/x86/events/perf_event.h

@@ -229,6 +229,7 @@ struct cpu_hw_events {
 	 */
 	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long		dirty[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	int			enabled;
 
 	int			n_events; /* the # of events in the below arrays */

arch/x86/include/asm/perf_event.h

@@ -478,6 +478,7 @@ struct x86_pmu_lbr {
 
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
+extern void perf_clear_dirty_counters(void);
 extern int x86_perf_rdpmc_index(struct perf_event *event);
 #else
 static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)

arch/x86/kernel/kprobes/core.c

@@ -1102,24 +1102,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 			restore_previous_kprobe(kcb);
 		else
 			reset_current_kprobe();
-	} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
-		   kcb->kprobe_status == KPROBE_HIT_SSDONE) {
-		/*
-		 * We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
-		 * these specific fault cases.
-		 */
-		kprobes_inc_nmissed_count(cur);
-
-		/*
-		 * We come here because instructions in the pre/post
-		 * handler caused the page_fault, this could happen
-		 * if handler tries to access user space by
-		 * copy_from_user(), get_user() etc. Let the
-		 * user-specified handler try to fix it first.
-		 */
-		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-			return 1;
 	}
 
 	return 0;

arch/x86/mm/fault.c

@@ -1186,7 +1186,7 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 		return;
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (kprobe_page_fault(regs, X86_TRAP_PF))
+	if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF)))
 		return;
 
 	/*
@@ -1239,7 +1239,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	}
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (unlikely(kprobe_page_fault(regs, X86_TRAP_PF)))
+	if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF)))
 		return;
 
 	/*

arch/x86/mm/tlb.c

@@ -14,6 +14,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/cache.h>
 #include <asm/apic.h>
+#include <asm/perf_event.h>
 
 #include "mm_internal.h"
 
@@ -404,9 +405,14 @@ static inline void cr4_update_pce_mm(struct mm_struct *mm)
 {
 	if (static_branch_unlikely(&rdpmc_always_available_key) ||
 	    (!static_branch_unlikely(&rdpmc_never_available_key) &&
-	     atomic_read(&mm->context.perf_rdpmc_allowed)))
+	     atomic_read(&mm->context.perf_rdpmc_allowed))) {
+		/*
+		 * Clear the existing dirty counters to
+		 * prevent the leak for an RDPMC task.
+		 */
+		perf_clear_dirty_counters();
 		cr4_set_bits_irqsoff(X86_CR4_PCE);
-	else
+	} else
 		cr4_clear_bits_irqsoff(X86_CR4_PCE);
 }
 

include/linux/kprobes.h

@@ -54,8 +54,6 @@ struct kretprobe_instance;
 typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *);
 typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *,
 				       unsigned long flags);
-typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *,
-				       int trapnr);
 typedef int (*kretprobe_handler_t) (struct kretprobe_instance *,
 				    struct pt_regs *);
 
@@ -83,12 +81,6 @@ struct kprobe {
 	/* Called after addr is executed, unless... */
 	kprobe_post_handler_t post_handler;
 
-	/*
-	 * ... called if executing addr causes a fault (eg. page fault).
-	 * Return 1 if it handled fault, otherwise kernel will see it.
-	 */
-	kprobe_fault_handler_t fault_handler;
-
 	/* Saved opcode (which has been replaced with breakpoint) */
 	kprobe_opcode_t opcode;
 

kernel/events/core.c

@@ -132,6 +132,7 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 
 /**
  * cpu_function_call - call a function on the cpu
+ * @cpu:	target cpu to queue this function
  * @func:	the function to be called
  * @info:	the function call argument
  *
@@ -3821,9 +3822,16 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 					struct task_struct *task)
 {
 	struct perf_cpu_context *cpuctx;
-	struct pmu *pmu = ctx->pmu;
+	struct pmu *pmu;
 
 	cpuctx = __get_cpu_context(ctx);
+
+	/*
+	 * HACK: for HETEROGENEOUS the task context might have switched to a
+	 * different PMU, force (re)set the context,
+	 */
+	pmu = ctx->pmu = cpuctx->ctx.pmu;
+
 	if (cpuctx->task_ctx == ctx) {
 		if (cpuctx->sched_cb_usage)
 			__perf_pmu_sched_task(cpuctx, true);
@@ -6669,10 +6677,10 @@ static unsigned long perf_prepare_sample_aux(struct perf_event *event,
 	return data->aux_size;
 }
 
-long perf_pmu_snapshot_aux(struct perf_buffer *rb,
-			   struct perf_event *event,
-			   struct perf_output_handle *handle,
-			   unsigned long size)
+static long perf_pmu_snapshot_aux(struct perf_buffer *rb,
+                                 struct perf_event *event,
+                                 struct perf_output_handle *handle,
+                                 unsigned long size)
 {
 	unsigned long flags;
 	long ret;
@@ -11919,6 +11927,7 @@ __perf_event_ctx_lock_double(struct perf_event *group_leader,
  * @pid:		target pid
  * @cpu:		target cpu
  * @group_fd:		group leader event fd
+ * @flags:		perf event open flags
  */
 SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_attr __user *, attr_uptr,
@@ -12375,6 +12384,8 @@ SYSCALL_DEFINE5(perf_event_open,
  * @attr: attributes of the counter to create
  * @cpu: cpu in which the counter is bound
  * @task: task to profile (NULL for percpu)
+ * @overflow_handler: callback to trigger when we hit the event
+ * @context: context data could be used in overflow_handler callback
  */
 struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,

kernel/events/hw_breakpoint.c

@@ -451,6 +451,7 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
  * register_user_hw_breakpoint - register a hardware breakpoint for user space
  * @attr: breakpoint attributes
  * @triggered: callback to trigger when we hit the breakpoint
+ * @context: context data could be used in the triggered callback
  * @tsk: pointer to 'task_struct' of the process to which the address belongs
  */
 struct perf_event *
@@ -550,6 +551,7 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
  * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
  * @attr: breakpoint attributes
  * @triggered: callback to trigger when we hit the breakpoint
+ * @context: context data could be used in the triggered callback
  *
  * @return a set of per_cpu pointers to perf events
  */

kernel/events/uprobes.c

@@ -453,6 +453,7 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
  * that have fixed length instructions.
  *
  * uprobe_write_opcode - write the opcode at a given virtual address.
+ * @auprobe: arch specific probepoint information.
  * @mm: the probed process address space.
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.

kernel/kprobes.c

@@ -1183,23 +1183,6 @@ static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
 }
 NOKPROBE_SYMBOL(aggr_post_handler);
 
-static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
-			      int trapnr)
-{
-	struct kprobe *cur = __this_cpu_read(kprobe_instance);
-
-	/*
-	 * if we faulted "during" the execution of a user specified
-	 * probe handler, invoke just that probe's fault handler
-	 */
-	if (cur && cur->fault_handler) {
-		if (cur->fault_handler(cur, regs, trapnr))
-			return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(aggr_fault_handler);
-
 /* Walks the list and increments nmissed count for multiprobe case */
 void kprobes_inc_nmissed_count(struct kprobe *p)
 {
@@ -1330,7 +1313,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 	ap->addr = p->addr;
 	ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED;
 	ap->pre_handler = aggr_pre_handler;
-	ap->fault_handler = aggr_fault_handler;
 	/* We don't care the kprobe which has gone. */
 	if (p->post_handler && !kprobe_gone(p))
 		ap->post_handler = aggr_post_handler;
@@ -2014,7 +1996,6 @@ int register_kretprobe(struct kretprobe *rp)
 
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
-	rp->kp.fault_handler = NULL;
 
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {

samples/kprobes/kprobe_example.c

@@ -94,26 +94,11 @@ static void __kprobes handler_post(struct kprobe *p, struct pt_regs *regs,
 #endif
 }
 
-/*
- * fault_handler: this is called if an exception is generated for any
- * instruction within the pre- or post-handler, or when Kprobes
- * single-steps the probed instruction.
- */
-static int handler_fault(struct kprobe *p, struct pt_regs *regs, int trapnr)
-{
-	pr_info("fault_handler: p->addr = 0x%p, trap #%dn", p->addr, trapnr);
-	/* Return 0 because we don't handle the fault. */
-	return 0;
-}
-/* NOKPROBE_SYMBOL() is also available */
-NOKPROBE_SYMBOL(handler_fault);
-
 static int __init kprobe_init(void)
 {
 	int ret;
 	kp.pre_handler = handler_pre;
 	kp.post_handler = handler_post;
-	kp.fault_handler = handler_fault;
 
 	ret = register_kprobe(&kp);
 	if (ret < 0) {