Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle were:

  Kernel side changes:

   - Kprobes and uprobes changes:
      - Make their trampolines read-only while they are used
      - Make UPROBES_EVENTS default-y which is the distro practice
      - Apply misc fixes and robustization to probe point insertion.

   - add support for AMD IOMMU events

   - extend hw events on Intel Goldmont CPUs

   - ... plus misc fixes and updates.

  Tooling side changes:

   - support s390 jump instructions in perf annotate (Christian
     Borntraeger)

   - vendor hardware events updates (Andi Kleen)

   - add argument support for SDT events in powerpc (Ravi Bangoria)

   - beautify the statx syscall arguments in 'perf trace' (Arnaldo
     Carvalho de Melo)

   - handle inline functions in callchains (Jin Yao)

   - enable sorting by srcline as key (Milian Wolff)

   - add 'brstackinsn' field in 'perf script' to reuse the x86
     instruction decoder used in the Intel PT code to study hot paths to
     samples (Andi Kleen)

   - add PERF_RECORD_NAMESPACES so that the kernel can record
     information required to associate samples to namespaces, helping in
     container problem characterization. (Hari Bathini)

   - allow sorting by symbol_size in 'perf report' and 'perf top'
     (Charles Baylis)

   - in perf stat, make system wide (-a) the default option if no target
     was specified and one of following conditions is met:
      - no workload specified (current behaviour)
      - a workload is specified but all requested events are system wide
        ones, like uncore ones. (Jiri Olsa)

   - ... plus lots of other updates, enhancements, cleanups and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (235 commits)
  perf tools: Fix the code to strip command name
  tools arch x86: Sync cpufeatures.h
  tools arch: Sync arch/x86/lib/memcpy_64.S with the kernel
  tools: Update asm-generic/mman-common.h copy from the kernel
  perf tools: Use just forward declarations for struct thread where possible
  perf tools: Add the right header to obtain PERF_ALIGN()
  perf tools: Remove poll.h and wait.h from util.h
  perf tools: Remove string.h, unistd.h and sys/stat.h from util.h
  perf tools: Remove stale prototypes from builtin.h
  perf tools: Remove string.h from util.h
  perf tools: Remove sys/ioctl.h from util.h
  perf tools: Remove a few more needless includes from util.h
  perf tools: Include sys/param.h where needed
  perf callchain: Move callchain specific routines from util.[ch]
  perf tools: Add compress.h for the *_decompress_to_file() headers
  perf mem: Fix display of data source snoop indication
  perf debug: Move dump_stack() and sighandler_dump_stack() to debug.h
  perf kvm: Make function only used by 'perf kvm' static
  perf tools: Move timestamp routines from util.h to time-utils.h
  perf tools: Move units conversion/formatting routines to separate object
  ...

8 files changed, 76 insertions, 69 deletions

diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index d7325c6534ad..979ea6ec7902 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -321,7 +321,7 @@ static int etb_set_buffer(struct coresight_device *csdev,
 
 static unsigned long etb_reset_buffer(struct coresight_device *csdev,
 				      struct perf_output_handle *handle,
-				      void *sink_config, bool *lost)
+				      void *sink_config)
 {
 	unsigned long size = 0;
 	struct cs_buffers *buf = sink_config;
@@ -343,7 +343,6 @@ static unsigned long etb_reset_buffer(struct coresight_device *csdev,
 		 * resetting parameters here and squaring off with the ring
 		 * buffer API in the tracer PMU is fine.
 		 */
-		*lost = !!local_xchg(&buf->lost, 0);
 		size = local_xchg(&buf->data_size, 0);
 	}
 
@@ -385,7 +384,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 			(unsigned long)write_ptr);
 
 		write_ptr &= ~(ETB_FRAME_SIZE_WORDS - 1);
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	}
 
 	/*
@@ -396,7 +395,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 	 */
 	status = readl_relaxed(drvdata->base + ETB_STATUS_REG);
 	if (status & ETB_STATUS_RAM_FULL) {
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 		to_read = capacity;
 		read_ptr = write_ptr;
 	} else {
@@ -429,7 +428,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 		if (read_ptr > (drvdata->buffer_depth - 1))
 			read_ptr -= drvdata->buffer_depth;
 		/* let the decoder know we've skipped ahead */
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	}
 
 	/* finally tell HW where we want to start reading from */
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 26cfac3e6de7..288a423c1b27 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -302,7 +302,8 @@ out:
 	return;
 
 fail_end_stop:
-	perf_aux_output_end(handle, 0, true);
+	perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+	perf_aux_output_end(handle, 0);
 fail:
 	event->hw.state = PERF_HES_STOPPED;
 	goto out;
@@ -310,7 +311,6 @@ fail:
 
 static void etm_event_stop(struct perf_event *event, int mode)
 {
-	bool lost;
 	int cpu = smp_processor_id();
 	unsigned long size;
 	struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu);
@@ -348,10 +348,9 @@ static void etm_event_stop(struct perf_event *event, int mode)
 			return;
 
 		size = sink_ops(sink)->reset_buffer(sink, handle,
-						    event_data->snk_config,
-						    &lost);
+						    event_data->snk_config);
 
-		perf_aux_output_end(handle, size, lost);
+		perf_aux_output_end(handle, size);
 	}
 
 	/* Disabling the path make its elements available to other sessions */
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index ef9d8e93e3b2..5f662d82052c 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -76,7 +76,6 @@ enum cs_mode {
  * @nr_pages:	max number of pages granted to us
  * @offset:	offset within the current buffer
  * @data_size:	how much we collected in this run
- * @lost:	other than zero if we had a HW buffer wrap around
  * @snapshot:	is this run in snapshot mode
  * @data_pages:	a handle the ring buffer
  */
@@ -85,7 +84,6 @@ struct cs_buffers {
 	unsigned int		nr_pages;
 	unsigned long		offset;
 	local_t			data_size;
-	local_t			lost;
 	bool			snapshot;
 	void			**data_pages;
 };
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 1549436e2492..aec61a6d5c63 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -329,7 +329,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev,
 
 static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
 					  struct perf_output_handle *handle,
-					  void *sink_config, bool *lost)
+					  void *sink_config)
 {
 	long size = 0;
 	struct cs_buffers *buf = sink_config;
@@ -350,7 +350,6 @@ static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
 		 * resetting parameters here and squaring off with the ring
 		 * buffer API in the tracer PMU is fine.
 		 */
-		*lost = !!local_xchg(&buf->lost, 0);
 		size = local_xchg(&buf->data_size, 0);
 	}
 
@@ -389,7 +388,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 	 */
 	status = readl_relaxed(drvdata->base + TMC_STS);
 	if (status & TMC_STS_FULL) {
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 		to_read = drvdata->size;
 	} else {
 		to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size);
@@ -434,7 +433,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 			read_ptr -= drvdata->size;
 		/* Tell the HW */
 		writel_relaxed(read_ptr, drvdata->base + TMC_RRP);
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	}
 
 	cur = buf->cur;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index b17536d6e69b..63cacf5d6cf2 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1234,7 +1234,7 @@ static void __domain_flush_pages(struct protection_domain *domain,
 
 	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
 
-	for (i = 0; i < amd_iommus_present; ++i) {
+	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
 			continue;
 
@@ -1278,7 +1278,7 @@ static void domain_flush_complete(struct protection_domain *domain)
 {
 	int i;
 
-	for (i = 0; i < amd_iommus_present; ++i) {
+	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (domain && !domain->dev_iommu[i])
 			continue;
 
@@ -3363,7 +3363,7 @@ static int __flush_pasid(struct protection_domain *domain, int pasid,
 	 * IOMMU TLB needs to be flushed before Device TLB to
 	 * prevent device TLB refill from IOMMU TLB
 	 */
-	for (i = 0; i < amd_iommus_present; ++i) {
+	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (domain->dev_iommu[i] == 0)
 			continue;
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6130278c5d71..5a11328f4d98 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -167,7 +167,9 @@ LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
 
 /* Array to assign indices to IOMMUs*/
 struct amd_iommu *amd_iommus[MAX_IOMMUS];
-int amd_iommus_present;
+
+/* Number of IOMMUs present in the system */
+static int amd_iommus_present;
 
 /* IOMMUs have a non-present cache? */
 bool amd_iommu_np_cache __read_mostly;
@@ -254,10 +256,6 @@ static int amd_iommu_enable_interrupts(void);
 static int __init iommu_go_to_state(enum iommu_init_state state);
 static void init_device_table_dma(void);
 
-static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
-				    u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write);
-
 static inline void update_last_devid(u16 devid)
 {
 	if (devid > amd_iommu_last_bdf)
@@ -272,6 +270,11 @@ static inline unsigned long tbl_size(int entry_size)
 	return 1UL << shift;
 }
 
+int amd_iommu_get_num_iommus(void)
+{
+	return amd_iommus_present;
+}
+
 /* Access to l1 and l2 indexed register spaces */
 
 static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address)
@@ -1336,7 +1339,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);
-	iommu->index             = amd_iommus_present++;
+	iommu->index = amd_iommus_present++;
 
 	if (unlikely(iommu->index >= MAX_IOMMUS)) {
 		WARN(1, "AMD-Vi: System has more IOMMUs than supported by this driver\n");
@@ -1477,6 +1480,8 @@ static int __init init_iommu_all(struct acpi_table_header *table)
 	return 0;
 }
 
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value, bool is_write);
 
 static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 {
@@ -1488,8 +1493,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 	amd_iommu_pc_present = true;
 
 	/* Check if the performance counters can be written to */
-	if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) ||
-	    (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) ||
+	if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) ||
+	    (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) ||
 	    (val != val2)) {
 		pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n");
 		amd_iommu_pc_present = false;
@@ -2711,6 +2716,18 @@ bool amd_iommu_v2_supported(void)
 }
 EXPORT_SYMBOL(amd_iommu_v2_supported);
 
+struct amd_iommu *get_amd_iommu(unsigned int idx)
+{
+	unsigned int i = 0;
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		if (i++ == idx)
+			return iommu;
+	return NULL;
+}
+EXPORT_SYMBOL(get_amd_iommu);
+
 /****************************************************************************
  *
  * IOMMU EFR Performance Counter support functionality. This code allows
@@ -2718,17 +2735,14 @@ EXPORT_SYMBOL(amd_iommu_v2_supported);
  *
  ****************************************************************************/
 
-u8 amd_iommu_pc_get_max_banks(u16 devid)
+u8 amd_iommu_pc_get_max_banks(unsigned int idx)
 {
-	struct amd_iommu *iommu;
-	u8 ret = 0;
+	struct amd_iommu *iommu = get_amd_iommu(idx);
 
-	/* locate the iommu governing the devid */
-	iommu = amd_iommu_rlookup_table[devid];
 	if (iommu)
-		ret = iommu->max_banks;
+		return iommu->max_banks;
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_max_banks);
 
@@ -2738,62 +2752,69 @@ bool amd_iommu_pc_supported(void)
 }
 EXPORT_SYMBOL(amd_iommu_pc_supported);
 
-u8 amd_iommu_pc_get_max_counters(u16 devid)
+u8 amd_iommu_pc_get_max_counters(unsigned int idx)
 {
-	struct amd_iommu *iommu;
-	u8 ret = 0;
+	struct amd_iommu *iommu = get_amd_iommu(idx);
 
-	/* locate the iommu governing the devid */
-	iommu = amd_iommu_rlookup_table[devid];
 	if (iommu)
-		ret = iommu->max_counters;
+		return iommu->max_counters;
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
 
-static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
-				    u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write)
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value, bool is_write)
 {
 	u32 offset;
 	u32 max_offset_lim;
 
+	/* Make sure the IOMMU PC resource is available */
+	if (!amd_iommu_pc_present)
+		return -ENODEV;
+
 	/* Check for valid iommu and pc register indexing */
-	if (WARN_ON((fxn > 0x28) || (fxn & 7)))
+	if (WARN_ON(!iommu || (fxn > 0x28) || (fxn & 7)))
 		return -ENODEV;
 
-	offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn);
+	offset = (u32)(((0x40 | bank) << 12) | (cntr << 8) | fxn);
 
 	/* Limit the offset to the hw defined mmio region aperture */
-	max_offset_lim = (u32)(((0x40|iommu->max_banks) << 12) |
+	max_offset_lim = (u32)(((0x40 | iommu->max_banks) << 12) |
 				(iommu->max_counters << 8) | 0x28);
 	if ((offset < MMIO_CNTR_REG_OFFSET) ||
 	    (offset > max_offset_lim))
 		return -EINVAL;
 
 	if (is_write) {
-		writel((u32)*value, iommu->mmio_base + offset);
-		writel((*value >> 32), iommu->mmio_base + offset + 4);
+		u64 val = *value & GENMASK_ULL(47, 0);
+
+		writel((u32)val, iommu->mmio_base + offset);
+		writel((val >> 32), iommu->mmio_base + offset + 4);
 	} else {
 		*value = readl(iommu->mmio_base + offset + 4);
 		*value <<= 32;
-		*value = readl(iommu->mmio_base + offset);
+		*value |= readl(iommu->mmio_base + offset);
+		*value &= GENMASK_ULL(47, 0);
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val);
 
-int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write)
+int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
 {
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+	if (!iommu)
+		return -EINVAL;
 
-	/* Make sure the IOMMU PC resource is available */
-	if (!amd_iommu_pc_present || iommu == NULL)
-		return -ENODEV;
+	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, false);
+}
+EXPORT_SYMBOL(amd_iommu_pc_get_reg);
+
+int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
+{
+	if (!iommu)
+		return -EINVAL;
 
-	return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn,
-					value, is_write);
+	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true);
 }
+EXPORT_SYMBOL(amd_iommu_pc_set_reg);
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 7eb60c15c582..466260f8a1df 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -21,6 +21,7 @@
 
 #include "amd_iommu_types.h"
 
+extern int amd_iommu_get_num_iommus(void);
 extern int amd_iommu_init_dma_ops(void);
 extern int amd_iommu_init_passthrough(void);
 extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
@@ -56,13 +57,6 @@ extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
 extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
 extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
 
-/* IOMMU Performance Counter functions */
-extern bool amd_iommu_pc_supported(void);
-extern u8 amd_iommu_pc_get_max_banks(u16 devid);
-extern u8 amd_iommu_pc_get_max_counters(u16 devid);
-extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write);
-
 #ifdef CONFIG_IRQ_REMAP
 extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
 #else
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 003f3ceb2661..4de8f4160bb8 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -611,9 +611,6 @@ extern struct list_head amd_iommu_list;
  */
 extern struct amd_iommu *amd_iommus[MAX_IOMMUS];
 
-/* Number of IOMMUs present in the system */
-extern int amd_iommus_present;
-
 /*
  * Declarations for the global list of all protection domains
  */