Merge tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Slightly delayed due to the issue with printk() calling
  probe_kernel_read() interacting with our new user access prevention
  stuff, but all fixed now.

  The only out-of-area changes are the addition of a cpuhp_state, small
  additions to Documentation and MAINTAINERS updates.

  Highlights:

   - Support for Kernel Userspace Access/Execution Prevention (like
     SMAP/SMEP/PAN/PXN) on some 64-bit and 32-bit CPUs. This prevents
     the kernel from accidentally accessing userspace outside
     copy_to/from_user(), or ever executing userspace.

   - KASAN support on 32-bit.

   - Rework of where we map the kernel, vmalloc, etc. on 64-bit hash to
     use the same address ranges we use with the Radix MMU.

   - A rewrite into C of large parts of our idle handling code for
     64-bit Book3S (ie. power8 & power9).

   - A fast path entry for syscalls on 32-bit CPUs, for a 12-17% speedup
     in the null_syscall benchmark.

   - On 64-bit bare metal we have support for recovering from errors
     with the time base (our clocksource), however if that fails
     currently we hang in __delay() and never crash. We now have support
     for detecting that case and short circuiting __delay() so we at
     least panic() and reboot.

   - Add support for optionally enabling the DAWR on Power9, which had
     to be disabled by default due to a hardware erratum. This has the
     effect of enabling hardware breakpoints for GDB, the downside is a
     badly behaved program could crash the machine by pointing the DAWR
     at cache inhibited memory. This is opt-in obviously.

   - xmon, our crash handler, gets support for a read only mode where
     operations that could change memory or otherwise disturb the system
     are disabled.

  Plus many clean-ups, reworks and minor fixes etc.

  Thanks to: Christophe Leroy, Akshay Adiga, Alastair D'Silva, Alexey
  Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar,
  Anton Blanchard, Ben Hutchings, Bo YU, Breno Leitao, Cédric Le Goater,
  Christopher M. Riedl, Christoph Hellwig, Colin Ian King, David Gibson,
  Ganesh Goudar, Gautham R. Shenoy, George Spelvin, Greg Kroah-Hartman,
  Greg Kurz, Horia Geantă, Jagadeesh Pagadala, Joel Stanley, Joe
  Perches, Julia Lawall, Laurentiu Tudor, Laurent Vivier, Lukas Bulwahn,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael
  Neuling, Mukesh Ojha, Nathan Fontenot, Nathan Lynch, Nicholas Piggin,
  Nick Desaulniers, Oliver O'Halloran, Peng Hao, Qian Cai, Ravi
  Bangoria, Rick Lindsley, Russell Currey, Sachin Sant, Stewart Smith,
  Sukadev Bhattiprolu, Thomas Huth, Tobin C. Harding, Tyrel Datwyler,
  Valentin Schneider, Wei Yongjun, Wen Yang, YueHaibing"

* tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (205 commits)
  powerpc/64s: Use early_mmu_has_feature() in set_kuap()
  powerpc/book3s/64: check for NULL pointer in pgd_alloc()
  powerpc/mm: Fix hugetlb page initialization
  ocxl: Fix return value check in afu_ioctl()
  powerpc/mm: fix section mismatch for setup_kup()
  powerpc/mm: fix redundant inclusion of pgtable-frag.o in Makefile
  powerpc/mm: Fix makefile for KASAN
  powerpc/kasan: add missing/lost Makefile
  selftests/powerpc: Add a signal fuzzer selftest
  powerpc/booke64: set RI in default MSR
  ocxl: Provide global MMIO accessors for external drivers
  ocxl: move event_fd handling to frontend
  ocxl: afu_irq only deals with IRQ IDs, not offsets
  ocxl: Allow external drivers to use OpenCAPI contexts
  ocxl: Create a clear delineation between ocxl backend & frontend
  ocxl: Don't pass pci_dev around
  ocxl: Split pci.c
  ocxl: Remove some unused exported symbols
  ocxl: Remove superfluous 'extern' from headers
  ocxl: read_pasid never returns an error, so make it void
  ...

13 files changed, 617 insertions, 35 deletions

diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index ab26df5bacb9..c155dcbb8691 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -5,7 +5,8 @@ obj-$(CONFIG_PERF_EVENTS)	+= callchain.o perf_regs.o
 obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o \
-				   isa207-common.o power8-pmu.o power9-pmu.o
+				   isa207-common.o power8-pmu.o power9-pmu.o \
+				   generic-compat-pmu.o
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_PPC_POWERNV)	+= imc-pmu.o
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index b0723002a396..a66fb9c01c9e 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -22,6 +22,10 @@
 #include <asm/ptrace.h>
 #include <asm/code-patching.h>
 
+#ifdef CONFIG_PPC64
+#include "internal.h"
+#endif
+
 #define BHRB_MAX_ENTRIES	32
 #define BHRB_TARGET		0x0000000000000002
 #define BHRB_PREDICTION		0x0000000000000001
@@ -2294,3 +2298,27 @@ int register_power_pmu(struct power_pmu *pmu)
 			  power_pmu_prepare_cpu, NULL);
 	return 0;
 }
+
+#ifdef CONFIG_PPC64
+static int __init init_ppc64_pmu(void)
+{
+	/* run through all the pmu drivers one at a time */
+	if (!init_power5_pmu())
+		return 0;
+	else if (!init_power5p_pmu())
+		return 0;
+	else if (!init_power6_pmu())
+		return 0;
+	else if (!init_power7_pmu())
+		return 0;
+	else if (!init_power8_pmu())
+		return 0;
+	else if (!init_power9_pmu())
+		return 0;
+	else if (!init_ppc970_pmu())
+		return 0;
+	else
+		return init_generic_compat_pmu();
+}
+early_initcall(init_ppc64_pmu);
+#endif
diff --git a/arch/powerpc/perf/generic-compat-pmu.c b/arch/powerpc/perf/generic-compat-pmu.c
new file mode 100644
index 000000000000..5e5a54d5588e
--- /dev/null
+++ b/arch/powerpc/perf/generic-compat-pmu.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2019 Madhavan Srinivasan, IBM Corporation.
+
+#define pr_fmt(fmt)	"generic-compat-pmu: " fmt
+
+#include "isa207-common.h"
+
+/*
+ * Raw event encoding:
+ *
+ *        60        56        52        48        44        40        36        32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *
+ *        28        24        20        16        12         8         4         0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *                                 [ pmc ]   [unit ]   [ ]   m   [    pmcxsel    ]
+ *                                                     |     |
+ *                                                     |     *- mark
+ *                                                     |
+ *                                                     |
+ *                                                     *- combine
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit    (PMCxUNIT)
+ * MMCR1[24]   = pmc1combine[0]
+ * MMCR1[25]   = pmc1combine[1]
+ * MMCR1[26]   = pmc2combine[0]
+ * MMCR1[27]   = pmc2combine[1]
+ * MMCR1[28]   = pmc3combine[0]
+ * MMCR1[29]   = pmc3combine[1]
+ * MMCR1[30]   = pmc4combine[0]
+ * MMCR1[31]   = pmc4combine[1]
+ *
+ */
+
+/*
+ * Some power9 event codes.
+ */
+#define EVENT(_name, _code)	_name = _code,
+
+enum {
+EVENT(PM_CYC,					0x0001e)
+EVENT(PM_INST_CMPL,				0x00002)
+};
+
+#undef EVENT
+
+GENERIC_EVENT_ATTR(cpu-cycles,			PM_CYC);
+GENERIC_EVENT_ATTR(instructions,		PM_INST_CMPL);
+
+static struct attribute *generic_compat_events_attr[] = {
+	GENERIC_EVENT_PTR(PM_CYC),
+	GENERIC_EVENT_PTR(PM_INST_CMPL),
+	NULL
+};
+
+static struct attribute_group generic_compat_pmu_events_group = {
+	.name = "events",
+	.attrs = generic_compat_events_attr,
+};
+
+PMU_FORMAT_ATTR(event,		"config:0-19");
+PMU_FORMAT_ATTR(pmcxsel,	"config:0-7");
+PMU_FORMAT_ATTR(mark,		"config:8");
+PMU_FORMAT_ATTR(combine,	"config:10-11");
+PMU_FORMAT_ATTR(unit,		"config:12-15");
+PMU_FORMAT_ATTR(pmc,		"config:16-19");
+
+static struct attribute *generic_compat_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_pmcxsel.attr,
+	&format_attr_mark.attr,
+	&format_attr_combine.attr,
+	&format_attr_unit.attr,
+	&format_attr_pmc.attr,
+	NULL,
+};
+
+static struct attribute_group generic_compat_pmu_format_group = {
+	.name = "format",
+	.attrs = generic_compat_pmu_format_attr,
+};
+
+static const struct attribute_group *generic_compat_pmu_attr_groups[] = {
+	&generic_compat_pmu_format_group,
+	&generic_compat_pmu_events_group,
+	NULL,
+};
+
+static int compat_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] =			PM_CYC,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
+static struct power_pmu generic_compat_pmu = {
+	.name			= "GENERIC_COMPAT",
+	.n_counter		= MAX_PMU_COUNTERS,
+	.add_fields		= ISA207_ADD_FIELDS,
+	.test_adder		= ISA207_TEST_ADDER,
+	.compute_mmcr		= isa207_compute_mmcr,
+	.get_constraint		= isa207_get_constraint,
+	.disable_pmc		= isa207_disable_pmc,
+	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
+	.n_generic		= ARRAY_SIZE(compat_generic_events),
+	.generic_events		= compat_generic_events,
+	.cache_events		= &generic_compat_cache_events,
+	.attr_groups		= generic_compat_pmu_attr_groups,
+};
+
+int init_generic_compat_pmu(void)
+{
+	int rc = 0;
+
+	rc = register_power_pmu(&generic_compat_pmu);
+	if (rc)
+		return rc;
+
+	/* Tell userspace that EBB is supported */
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+
+	return 0;
+}
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index b1c37cc3fa98..31fa753e2eb2 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -43,12 +43,17 @@ static DEFINE_PER_CPU(u64 *, thread_imc_mem);
 static struct imc_pmu *thread_imc_pmu;
 static int thread_imc_mem_size;
 
+/* Trace IMC data structures */
+static DEFINE_PER_CPU(u64 *, trace_imc_mem);
+static struct imc_pmu_ref *trace_imc_refc;
+static int trace_imc_mem_size;
+
 static struct imc_pmu *imc_event_to_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct imc_pmu, pmu);
 }
 
-PMU_FORMAT_ATTR(event, "config:0-40");
+PMU_FORMAT_ATTR(event, "config:0-61");
 PMU_FORMAT_ATTR(offset, "config:0-31");
 PMU_FORMAT_ATTR(rvalue, "config:32");
 PMU_FORMAT_ATTR(mode, "config:33-40");
@@ -65,6 +70,25 @@ static struct attribute_group imc_format_group = {
 	.attrs = imc_format_attrs,
 };
 
+/* Format attribute for imc trace-mode */
+PMU_FORMAT_ATTR(cpmc_reserved, "config:0-19");
+PMU_FORMAT_ATTR(cpmc_event, "config:20-27");
+PMU_FORMAT_ATTR(cpmc_samplesel, "config:28-29");
+PMU_FORMAT_ATTR(cpmc_load, "config:30-61");
+static struct attribute *trace_imc_format_attrs[] = {
+	&format_attr_event.attr,
+	&format_attr_cpmc_reserved.attr,
+	&format_attr_cpmc_event.attr,
+	&format_attr_cpmc_samplesel.attr,
+	&format_attr_cpmc_load.attr,
+	NULL,
+};
+
+static struct attribute_group trace_imc_format_group = {
+.name = "format",
+.attrs = trace_imc_format_attrs,
+};
+
 /* Get the cpumask printed to a buffer "buf" */
 static ssize_t imc_pmu_cpumask_get_attr(struct device *dev,
 					struct device_attribute *attr,
@@ -487,6 +511,11 @@ static int nest_imc_event_init(struct perf_event *event)
 	 * Get the base memory addresss for this cpu.
 	 */
 	chip_id = cpu_to_chip_id(event->cpu);
+
+	/* Return, if chip_id is not valid */
+	if (chip_id < 0)
+		return -ENODEV;
+
 	pcni = pmu->mem_info;
 	do {
 		if (pcni->id == chip_id) {
@@ -494,7 +523,7 @@ static int nest_imc_event_init(struct perf_event *event)
 			break;
 		}
 		pcni++;
-	} while (pcni);
+	} while (pcni->vbase != 0);
 
 	if (!flag)
 		return -ENODEV;
@@ -788,8 +817,11 @@ static int core_imc_event_init(struct perf_event *event)
 }
 
 /*
- * Allocates a page of memory for each of the online cpus, and write the
- * physical base address of that page to the LDBAR for that cpu.
+ * Allocates a page of memory for each of the online cpus, and load
+ * LDBAR with 0.
+ * The physical base address of the page allocated for a cpu will be
+ * written to the LDBAR for that cpu, when the thread-imc event
+ * is added.
  *
  * LDBAR Register Layout:
  *
@@ -807,7 +839,7 @@ static int core_imc_event_init(struct perf_event *event)
  */
 static int thread_imc_mem_alloc(int cpu_id, int size)
 {
-	u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, cpu_id);
+	u64 *local_mem = per_cpu(thread_imc_mem, cpu_id);
 	int nid = cpu_to_node(cpu_id);
 
 	if (!local_mem) {
@@ -824,9 +856,7 @@ static int thread_imc_mem_alloc(int cpu_id, int size)
 		per_cpu(thread_imc_mem, cpu_id) = local_mem;
 	}
 
-	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | THREAD_IMC_ENABLE;
-
-	mtspr(SPRN_LDBAR, ldbar_value);
+	mtspr(SPRN_LDBAR, 0);
 	return 0;
 }
 
@@ -858,6 +888,9 @@ static int thread_imc_event_init(struct perf_event *event)
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	/* Sampling not supported */
 	if (event->hw.sample_period)
 		return -EINVAL;
@@ -977,6 +1010,7 @@ static int thread_imc_event_add(struct perf_event *event, int flags)
 {
 	int core_id;
 	struct imc_pmu_ref *ref;
+	u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, smp_processor_id());
 
 	if (flags & PERF_EF_START)
 		imc_event_start(event, flags);
@@ -985,6 +1019,9 @@ static int thread_imc_event_add(struct perf_event *event, int flags)
 		return -EINVAL;
 
 	core_id = smp_processor_id() / threads_per_core;
+	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | THREAD_IMC_ENABLE;
+	mtspr(SPRN_LDBAR, ldbar_value);
+
 	/*
 	 * imc pmus are enabled only when it is used.
 	 * See if this is triggered for the first time.
@@ -1016,11 +1053,7 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 	int core_id;
 	struct imc_pmu_ref *ref;
 
-	/*
-	 * Take a snapshot and calculate the delta and update
-	 * the event counter values.
-	 */
-	imc_event_update(event);
+	mtspr(SPRN_LDBAR, 0);
 
 	core_id = smp_processor_id() / threads_per_core;
 	ref = &core_imc_refc[core_id];
@@ -1039,6 +1072,240 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+	/*
+	 * Take a snapshot and calculate the delta and update
+	 * the event counter values.
+	 */
+	imc_event_update(event);
+}
+
+/*
+ * Allocate a page of memory for each cpu, and load LDBAR with 0.
+ */
+static int trace_imc_mem_alloc(int cpu_id, int size)
+{
+	u64 *local_mem = per_cpu(trace_imc_mem, cpu_id);
+	int phys_id = cpu_to_node(cpu_id), rc = 0;
+	int core_id = (cpu_id / threads_per_core);
+
+	if (!local_mem) {
+		local_mem = page_address(alloc_pages_node(phys_id,
+					GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+					__GFP_NOWARN, get_order(size)));
+		if (!local_mem)
+			return -ENOMEM;
+		per_cpu(trace_imc_mem, cpu_id) = local_mem;
+
+		/* Initialise the counters for trace mode */
+		rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_TRACE, __pa((void *)local_mem),
+					    get_hard_smp_processor_id(cpu_id));
+		if (rc) {
+			pr_info("IMC:opal init failed for trace imc\n");
+			return rc;
+		}
+	}
+
+	/* Init the mutex, if not already */
+	trace_imc_refc[core_id].id = core_id;
+	mutex_init(&trace_imc_refc[core_id].lock);
+
+	mtspr(SPRN_LDBAR, 0);
+	return 0;
+}
+
+static int ppc_trace_imc_cpu_online(unsigned int cpu)
+{
+	return trace_imc_mem_alloc(cpu, trace_imc_mem_size);
+}
+
+static int ppc_trace_imc_cpu_offline(unsigned int cpu)
+{
+	mtspr(SPRN_LDBAR, 0);
+	return 0;
+}
+
+static int trace_imc_cpu_init(void)
+{
+	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE,
+			  "perf/powerpc/imc_trace:online",
+			  ppc_trace_imc_cpu_online,
+			  ppc_trace_imc_cpu_offline);
+}
+
+static u64 get_trace_imc_event_base_addr(void)
+{
+	return (u64)per_cpu(trace_imc_mem, smp_processor_id());
+}
+
+/*
+ * Function to parse trace-imc data obtained
+ * and to prepare the perf sample.
+ */
+static int trace_imc_prepare_sample(struct trace_imc_data *mem,
+				    struct perf_sample_data *data,
+				    u64 *prev_tb,
+				    struct perf_event_header *header,
+				    struct perf_event *event)
+{
+	/* Sanity checks for a valid record */
+	if (be64_to_cpu(READ_ONCE(mem->tb1)) > *prev_tb)
+		*prev_tb = be64_to_cpu(READ_ONCE(mem->tb1));
+	else
+		return -EINVAL;
+
+	if ((be64_to_cpu(READ_ONCE(mem->tb1)) & IMC_TRACE_RECORD_TB1_MASK) !=
+			 be64_to_cpu(READ_ONCE(mem->tb2)))
+		return -EINVAL;
+
+	/* Prepare perf sample */
+	data->ip =  be64_to_cpu(READ_ONCE(mem->ip));
+	data->period = event->hw.last_period;
+
+	header->type = PERF_RECORD_SAMPLE;
+	header->size = sizeof(*header) + event->header_size;
+	header->misc = 0;
+
+	if (is_kernel_addr(data->ip))
+		header->misc |= PERF_RECORD_MISC_KERNEL;
+	else
+		header->misc |= PERF_RECORD_MISC_USER;
+
+	perf_event_header__init_id(header, data, event);
+
+	return 0;
+}
+
+static void dump_trace_imc_data(struct perf_event *event)
+{
+	struct trace_imc_data *mem;
+	int i, ret;
+	u64 prev_tb = 0;
+
+	mem = (struct trace_imc_data *)get_trace_imc_event_base_addr();
+	for (i = 0; i < (trace_imc_mem_size / sizeof(struct trace_imc_data));
+		i++, mem++) {
+		struct perf_sample_data data;
+		struct perf_event_header header;
+
+		ret = trace_imc_prepare_sample(mem, &data, &prev_tb, &header, event);
+		if (ret) /* Exit, if not a valid record */
+			break;
+		else {
+			/* If this is a valid record, create the sample */
+			struct perf_output_handle handle;
+
+			if (perf_output_begin(&handle, event, header.size))
+				return;
+
+			perf_output_sample(&handle, &header, &data, event);
+			perf_output_end(&handle);
+		}
+	}
+}
+
+static int trace_imc_event_add(struct perf_event *event, int flags)
+{
+	int core_id = smp_processor_id() / threads_per_core;
+	struct imc_pmu_ref *ref = NULL;
+	u64 local_mem, ldbar_value;
+
+	/* Set trace-imc bit in ldbar and load ldbar with per-thread memory address */
+	local_mem = get_trace_imc_event_base_addr();
+	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE;
+
+	if (core_imc_refc)
+		ref = &core_imc_refc[core_id];
+	if (!ref) {
+		/* If core-imc is not enabled, use trace-imc reference count */
+		if (trace_imc_refc)
+			ref = &trace_imc_refc[core_id];
+		if (!ref)
+			return -EINVAL;
+	}
+	mtspr(SPRN_LDBAR, ldbar_value);
+	mutex_lock(&ref->lock);
+	if (ref->refc == 0) {
+		if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE,
+				get_hard_smp_processor_id(smp_processor_id()))) {
+			mutex_unlock(&ref->lock);
+			pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
+			mtspr(SPRN_LDBAR, 0);
+			return -EINVAL;
+		}
+	}
+	++ref->refc;
+	mutex_unlock(&ref->lock);
+
+	return 0;
+}
+
+static void trace_imc_event_read(struct perf_event *event)
+{
+	return;
+}
+
+static void trace_imc_event_stop(struct perf_event *event, int flags)
+{
+	u64 local_mem = get_trace_imc_event_base_addr();
+	dump_trace_imc_data(event);
+	memset((void *)local_mem, 0, sizeof(u64));
+}
+
+static void trace_imc_event_start(struct perf_event *event, int flags)
+{
+	return;
+}
+
+static void trace_imc_event_del(struct perf_event *event, int flags)
+{
+	int core_id = smp_processor_id() / threads_per_core;
+	struct imc_pmu_ref *ref = NULL;
+
+	if (core_imc_refc)
+		ref = &core_imc_refc[core_id];
+	if (!ref) {
+		/* If core-imc is not enabled, use trace-imc reference count */
+		if (trace_imc_refc)
+			ref = &trace_imc_refc[core_id];
+		if (!ref)
+			return;
+	}
+	mtspr(SPRN_LDBAR, 0);
+	mutex_lock(&ref->lock);
+	ref->refc--;
+	if (ref->refc == 0) {
+		if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE,
+				get_hard_smp_processor_id(smp_processor_id()))) {
+			mutex_unlock(&ref->lock);
+			pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id);
+			return;
+		}
+	} else if (ref->refc < 0) {
+		ref->refc = 0;
+	}
+	mutex_unlock(&ref->lock);
+	trace_imc_event_stop(event, flags);
+}
+
+static int trace_imc_event_init(struct perf_event *event)
+{
+	struct task_struct *target;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	/* Return if this is a couting event */
+	if (event->attr.sample_period == 0)
+		return -ENOENT;
+
+	event->hw.idx = -1;
+	target = event->hw.target;
+
+	event->pmu->task_ctx_nr = perf_hw_context;
+	return 0;
 }
 
 /* update_pmu_ops : Populate the appropriate operations for "pmu" */
@@ -1071,6 +1338,14 @@ static int update_pmu_ops(struct imc_pmu *pmu)
 		pmu->pmu.cancel_txn = thread_imc_pmu_cancel_txn;
 		pmu->pmu.commit_txn = thread_imc_pmu_commit_txn;
 		break;
+	case IMC_DOMAIN_TRACE:
+		pmu->pmu.event_init = trace_imc_event_init;
+		pmu->pmu.add = trace_imc_event_add;
+		pmu->pmu.del = trace_imc_event_del;
+		pmu->pmu.start = trace_imc_event_start;
+		pmu->pmu.stop = trace_imc_event_stop;
+		pmu->pmu.read = trace_imc_event_read;
+		pmu->attr_groups[IMC_FORMAT_ATTR] = &trace_imc_format_group;
 	default:
 		break;
 	}
@@ -1163,6 +1438,18 @@ static void cleanup_all_thread_imc_memory(void)
 	}
 }
 
+static void cleanup_all_trace_imc_memory(void)
+{
+	int i, order = get_order(trace_imc_mem_size);
+
+	for_each_online_cpu(i) {
+		if (per_cpu(trace_imc_mem, i))
+			free_pages((u64)per_cpu(trace_imc_mem, i), order);
+
+	}
+	kfree(trace_imc_refc);
+}
+
 /* Function to free the attr_groups which are dynamically allocated */
 static void imc_common_mem_free(struct imc_pmu *pmu_ptr)
 {
@@ -1204,6 +1491,11 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE);
 		cleanup_all_thread_imc_memory();
 	}
+
+	if (pmu_ptr->domain == IMC_DOMAIN_TRACE) {
+		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE);
+		cleanup_all_trace_imc_memory();
+	}
 }
 
 /*
@@ -1286,6 +1578,27 @@ static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent,
 
 		thread_imc_pmu = pmu_ptr;
 		break;
+	case IMC_DOMAIN_TRACE:
+		/* Update the pmu name */
+		pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s", s, "_imc");
+		if (!pmu_ptr->pmu.name)
+			return -ENOMEM;
+
+		nr_cores = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
+		trace_imc_refc = kcalloc(nr_cores, sizeof(struct imc_pmu_ref),
+								GFP_KERNEL);
+		if (!trace_imc_refc)
+			return -ENOMEM;
+
+		trace_imc_mem_size = pmu_ptr->counter_mem_size;
+		for_each_online_cpu(cpu) {
+			res = trace_imc_mem_alloc(cpu, trace_imc_mem_size);
+			if (res) {
+				cleanup_all_trace_imc_memory();
+				goto err;
+			}
+		}
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1359,6 +1672,14 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 		}
 
 		break;
+	case IMC_DOMAIN_TRACE:
+		ret = trace_imc_cpu_init();
+		if (ret) {
+			cleanup_all_trace_imc_memory();
+			goto err_free_mem;
+		}
+
+		break;
 	default:
 		return  -EINVAL;	/* Unknown domain */
 	}
diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h
new file mode 100644
index 000000000000..f755c64da137
--- /dev/null
+++ b/arch/powerpc/perf/internal.h
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2019 Madhavan Srinivasan, IBM Corporation.
+
+extern int init_ppc970_pmu(void);
+extern int init_power5_pmu(void);
+extern int init_power5p_pmu(void);
+extern int init_power6_pmu(void);
+extern int init_power7_pmu(void);
+extern int init_power8_pmu(void);
+extern int init_power9_pmu(void);
+extern int init_generic_compat_pmu(void);
diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index 0526dac66007..9aa803504cb2 100644
--- a/arch/powerpc/perf/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
@@ -677,7 +677,7 @@ static struct power_pmu power5p_pmu = {
 	.cache_events		= &power5p_cache_events,
 };
 
-static int __init init_power5p_pmu(void)
+int init_power5p_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+")
@@ -686,5 +686,3 @@ static int __init init_power5p_pmu(void)
 
 	return register_power_pmu(&power5p_pmu);
 }
-
-early_initcall(init_power5p_pmu);
diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index 4dc99f9f7962..30cb13d081a9 100644
--- a/arch/powerpc/perf/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
@@ -618,7 +618,7 @@ static struct power_pmu power5_pmu = {
 	.flags			= PPMU_HAS_SSLOT,
 };
 
-static int __init init_power5_pmu(void)
+int init_power5_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5"))
@@ -626,5 +626,3 @@ static int __init init_power5_pmu(void)
 
 	return register_power_pmu(&power5_pmu);
 }
-
-early_initcall(init_power5_pmu);
diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 9c9d646b68a1..80ec48632cfe 100644
--- a/arch/powerpc/perf/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -540,7 +540,7 @@ static struct power_pmu power6_pmu = {
 	.cache_events		= &power6_cache_events,
 };
 
-static int __init init_power6_pmu(void)
+int init_power6_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6"))
@@ -548,5 +548,3 @@ static int __init init_power6_pmu(void)
 
 	return register_power_pmu(&power6_pmu);
 }
-
-early_initcall(init_power6_pmu);
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 6dbae9884ec4..bb6efd5d2530 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -445,7 +445,7 @@ static struct power_pmu power7_pmu = {
 	.cache_events		= &power7_cache_events,
 };
 
-static int __init init_power7_pmu(void)
+int init_power7_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7"))
@@ -456,5 +456,3 @@ static int __init init_power7_pmu(void)
 
 	return register_power_pmu(&power7_pmu);
 }
-
-early_initcall(init_power7_pmu);
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index d12a2db26353..bcc3409a06de 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -379,7 +379,7 @@ static struct power_pmu power8_pmu = {
 	.bhrb_nr		= 32,
 };
 
-static int __init init_power8_pmu(void)
+int init_power8_pmu(void)
 {
 	int rc;
 
@@ -399,4 +399,3 @@ static int __init init_power8_pmu(void)
 
 	return 0;
 }
-early_initcall(init_power8_pmu);
diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h
index 063c9d9f2516..6b1dc9a83ede 100644
--- a/arch/powerpc/perf/power9-events-list.h
+++ b/arch/powerpc/perf/power9-events-list.h
@@ -63,8 +63,6 @@ EVENT(PM_RUN_CYC_ALT,				0x200f4)
 /* Instruction Dispatched */
 EVENT(PM_INST_DISP,				0x200f2)
 EVENT(PM_INST_DISP_ALT,				0x300f2)
-/* Alternate Branch event code */
-EVENT(PM_BR_CMPL_ALT,				0x10012)
 /* Branch event that are not strongly biased */
 EVENT(PM_BR_2PATH,				0x20036)
 /* ALternate branch event that are not strongly biased */
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 030544e35959..3a31ac6f4805 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -437,7 +437,7 @@ static struct power_pmu power9_pmu = {
 	.bhrb_nr		= 32,
 };
 
-static int __init init_power9_pmu(void)
+int init_power9_pmu(void)
 {
 	int rc = 0;
 	unsigned int pvr = mfspr(SPRN_PVR);
@@ -467,4 +467,3 @@ static int __init init_power9_pmu(void)
 
 	return 0;
 }
-early_initcall(init_power9_pmu);
diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index 8b6a8a36fa38..1d3370914022 100644
--- a/arch/powerpc/perf/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -490,7 +490,7 @@ static struct power_pmu ppc970_pmu = {
 	.flags			= PPMU_NO_SIPR | PPMU_NO_CONT_SAMPLING,
 };
 
-static int __init init_ppc970_pmu(void)
+int init_ppc970_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970")
@@ -499,5 +499,3 @@ static int __init init_ppc970_pmu(void)
 
 	return register_power_pmu(&ppc970_pmu);
 }
-
-early_initcall(init_ppc970_pmu);