[PATCH v2 00/17] arm64: Self-hosted trace related errata workarounds

@@ -363,7 +363,7 @@ static unsigned long __trbe_normal_offset(struct perf_output_handle *handle)
 
 static unsigned long trbe_normal_offset(struct perf_output_handle *handle)
 {
-	struct trbe_buf *buf = perf_get_aux(handle);
+	struct trbe_buf *buf = etm_perf_sink_config(handle);
 	u64 limit = __trbe_normal_offset(handle);
 	u64 head = PERF_IDX2OFF(handle->head, buf);
 

@@ -16,6 +16,8 @@
 #define pr_fmt(fmt) DRVNAME ": " fmt
 
 #include <asm/barrier.h>
+#include <asm/cputype.h>
+
 #include "coresight-self-hosted-trace.h"
 #include "coresight-trbe.h"
 

@@ -65,6 +67,35 @@ struct trbe_buf {
 	struct trbe_cpudata *cpudata;
 };
 
+/*
+ * TRBE erratum list
+ *
+ * We rely on the corresponding cpucaps to be defined for a given
+ * TRBE erratum. We map the given cpucap into a TRBE internal number
+ * to make the tracking of the errata lean.
+ *
+ * This helps in :
+ *   - Not duplicating the detection logic
+ *   - Streamlined detection of erratum across the system
+ *
+ * Since the erratum work arounds could be applied individually
+ * per TRBE instance, we keep track of the list of errata that
+ * affects the given instance of the TRBE.
+ */
+#define TRBE_ERRATA_MAX			0
+
+static unsigned long trbe_errata_cpucaps[TRBE_ERRATA_MAX] = {
+};
+
+/*
+ * struct trbe_cpudata: TRBE instance specific data
+ * @trbe_flag		- TRBE dirty/access flag support
+ * @tbre_align		- Actual TRBE alignment required for TRBPTR_EL1.
+ * @cpu			- CPU this TRBE belongs to.
+ * @mode		- Mode of current operation. (perf/disabled)
+ * @drvdata		- TRBE specific drvdata
+ * @errata		- Bit map for the errata on this TRBE.
+ */
 struct trbe_cpudata {
 	bool trbe_flag;
 	u64 trbe_align;

@@ -72,6 +103,7 @@ struct trbe_cpudata {
 	enum cs_mode mode;
 	struct trbe_buf *buf;
 	struct trbe_drvdata *drvdata;
+	DECLARE_BITMAP(errata, TRBE_ERRATA_MAX);
 };
 
 struct trbe_drvdata {

@@ -84,6 +116,21 @@ struct trbe_drvdata {
 	struct platform_device *pdev;
 };
 
+static void trbe_check_errata(struct trbe_cpudata *cpudata)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(trbe_errata_cpucaps); i++) {
+		if (this_cpu_has_cap(trbe_errata_cpucaps[i]))
+			set_bit(i, cpudata->errata);
+	}
+}
+
+static inline bool trbe_has_erratum(struct trbe_cpudata *cpudata, int i)
+{
+	return (i < TRBE_ERRATA_MAX) && test_bit(i, cpudata->errata);
+}
+
 static int trbe_alloc_node(struct perf_event *event)
 {
 	if (event->cpu == -1)

@@ -926,6 +973,8 @@ static void arm_trbe_probe_cpu(void *info)
 		pr_err("Unsupported alignment on cpu %d\n", cpu);
 		goto cpu_clear;
 	}
+
+	trbe_check_errata(cpudata);
 	cpudata->trbe_flag = get_trbe_flag_update(trbidr);
 	cpudata->cpu = cpu;
 	cpudata->drvdata = drvdata;

@@ -527,6 +527,30 @@ static enum trbe_fault_action trbe_get_fault_act(u64 trbsr)
 	return TRBE_FAULT_ACT_SPURIOUS;
 }
 
+static unsigned long trbe_get_trace_size(struct perf_output_handle *handle,
+					 struct trbe_buf *buf,
+					 bool wrap)
+{
+	u64 write;
+	u64 start_off, end_off;
+
+	/*
+	 * If the TRBE has wrapped around the write pointer has
+	 * wrapped and should be treated as limit.
+	 */
+	if (wrap)
+		write = get_trbe_limit_pointer();
+	else
+		write = get_trbe_write_pointer();
+
+	end_off = write - buf->trbe_base;
+	start_off = PERF_IDX2OFF(handle->head, buf);
+
+	if (WARN_ON_ONCE(end_off < start_off))
+		return 0;
+	return (end_off - start_off);
+}
+
 static void *arm_trbe_alloc_buffer(struct coresight_device *csdev,
 				   struct perf_event *event, void **pages,
 				   int nr_pages, bool snapshot)

@@ -588,9 +612,9 @@ static unsigned long arm_trbe_update_buffer(struct coresight_device *csdev,
 	struct trbe_cpudata *cpudata = dev_get_drvdata(&csdev->dev);
 	struct trbe_buf *buf = config;
 	enum trbe_fault_action act;
-	unsigned long size, offset;
-	unsigned long write, base, status;
+	unsigned long size, status;
 	unsigned long flags;
+	bool wrap = false;
 
 	WARN_ON(buf->cpudata != cpudata);
 	WARN_ON(cpudata->cpu != smp_processor_id());

@@ -630,8 +654,6 @@ static unsigned long arm_trbe_update_buffer(struct coresight_device *csdev,
 	 * handle gets freed in etm_event_stop().
 	 */
 	trbe_drain_and_disable_local();
-	write = get_trbe_write_pointer();
-	base = get_trbe_base_pointer();
 
 	/* Check if there is a pending interrupt and handle it here */
 	status = read_sysreg_s(SYS_TRBSR_EL1);

@@ -655,20 +677,11 @@ static unsigned long arm_trbe_update_buffer(struct coresight_device *csdev,
 			goto done;
 		}
 
-		/*
-		 * Otherwise, the buffer is full and the write pointer
-		 * has reached base. Adjust this back to the Limit pointer
-		 * for correct size. Also, mark the buffer truncated.
-		 */
-		write = get_trbe_limit_pointer();
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION);
+		wrap = true;
 	}
 
-	offset = write - base;
-	if (WARN_ON_ONCE(offset < PERF_IDX2OFF(handle->head, buf)))
-		size = 0;
-	else
-		size = offset - PERF_IDX2OFF(handle->head, buf);
+	size = trbe_get_trace_size(handle, buf, wrap);
 
 done:
 	local_irq_restore(flags);

@@ -749,11 +762,10 @@ static int trbe_handle_overflow(struct perf_output_handle *handle)
 {
 	struct perf_event *event = handle->event;
 	struct trbe_buf *buf = etm_perf_sink_config(handle);
-	unsigned long offset, size;
+	unsigned long size;
 	struct etm_event_data *event_data;
 
-	offset = get_trbe_limit_pointer() - get_trbe_base_pointer();
-	size = offset - PERF_IDX2OFF(handle->head, buf);
+	size = trbe_get_trace_size(handle, buf, true);
 	if (buf->snapshot)
 		handle->head += size;
 

@@ -227,12 +227,18 @@ static void trbe_stop_and_truncate_event(struct perf_output_handle *handle)
  * consumed from the user space. The enabled TRBE buffer area is a moving subset of
  * the allocated perf auxiliary buffer.
  */
+
+static void __trbe_pad_buf(struct trbe_buf *buf, u64 offset, int len)
+{
+	memset((void *)buf->trbe_base + offset, ETE_IGNORE_PACKET, len);
+}
+
 static void trbe_pad_buf(struct perf_output_handle *handle, int len)
 {
 	struct trbe_buf *buf = etm_perf_sink_config(handle);
 	u64 head = PERF_IDX2OFF(handle->head, buf);
 
-	memset((void *)buf->trbe_base + head, ETE_IGNORE_PACKET, len);
+	__trbe_pad_buf(buf, head, len);
 	if (!buf->snapshot)
 		perf_aux_output_skip(handle, len);
 }

@@ -59,6 +59,8 @@ struct trbe_buf {
 	 * trbe_limit sibling pointers.
 	 */
 	unsigned long trbe_base;
+	/* The base programmed into the TRBE */
+	unsigned long trbe_hw_base;
 	unsigned long trbe_limit;
 	unsigned long trbe_write;
 	int nr_pages;

@@ -498,12 +500,13 @@ static void set_trbe_limit_pointer_enabled(unsigned long addr)
 
 static void trbe_enable_hw(struct trbe_buf *buf)
 {
-	WARN_ON(buf->trbe_write < buf->trbe_base);
+	WARN_ON(buf->trbe_hw_base < buf->trbe_base);
+	WARN_ON(buf->trbe_write < buf->trbe_hw_base);
 	WARN_ON(buf->trbe_write >= buf->trbe_limit);
 	set_trbe_disabled();
 	isb();
 	clr_trbe_status();
-	set_trbe_base_pointer(buf->trbe_base);
+	set_trbe_base_pointer(buf->trbe_hw_base);
 	set_trbe_write_pointer(buf->trbe_write);
 
 	/*

@@ -707,6 +710,8 @@ static int __arm_trbe_enable(struct trbe_buf *buf,
 		trbe_stop_and_truncate_event(handle);
 		return -ENOSPC;
 	}
+	/* Set the base of the TRBE to the buffer base */
+	buf->trbe_hw_base = buf->trbe_base;
 	*this_cpu_ptr(buf->cpudata->drvdata->handle) = handle;
 	trbe_enable_hw(buf);
 	return 0;

@@ -804,7 +809,7 @@ static bool is_perf_trbe(struct perf_output_handle *handle)
 	struct trbe_drvdata *drvdata = cpudata->drvdata;
 	int cpu = smp_processor_id();
 
-	WARN_ON(buf->trbe_base != get_trbe_base_pointer());
+	WARN_ON(buf->trbe_hw_base != get_trbe_base_pointer());
 	WARN_ON(buf->trbe_limit != get_trbe_limit_pointer());
 
 	if (cpudata->mode != CS_MODE_PERF)

@@ -92,7 +92,8 @@ static unsigned long trbe_errata_cpucaps[TRBE_ERRATA_MAX] = {
 /*
  * struct trbe_cpudata: TRBE instance specific data
  * @trbe_flag		- TRBE dirty/access flag support
- * @tbre_align		- Actual TRBE alignment required for TRBPTR_EL1.
+ * @trbe_hw_align	- Actual TRBE alignment required for TRBPTR_EL1.
+ * @trbe_align		- Software alignment used for the TRBPTR_EL1,
  * @cpu			- CPU this TRBE belongs to.
  * @mode		- Mode of current operation. (perf/disabled)
  * @drvdata		- TRBE specific drvdata

@@ -100,6 +101,7 @@ static unsigned long trbe_errata_cpucaps[TRBE_ERRATA_MAX] = {
  */
 struct trbe_cpudata {
 	bool trbe_flag;
+	u64 trbe_hw_align;
 	u64 trbe_align;
 	int cpu;
 	enum cs_mode mode;

@@ -903,7 +905,7 @@ static ssize_t align_show(struct device *dev, struct device_attribute *attr, cha
 {
 	struct trbe_cpudata *cpudata = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%llx\n", cpudata->trbe_align);
+	return sprintf(buf, "%llx\n", cpudata->trbe_hw_align);
 }
 static DEVICE_ATTR_RO(align);
 

@@ -991,13 +993,14 @@ static void arm_trbe_probe_cpu(void *info)
 		goto cpu_clear;
 	}
 
-	cpudata->trbe_align = 1ULL << get_trbe_address_align(trbidr);
-	if (cpudata->trbe_align > SZ_2K) {
+	cpudata->trbe_hw_align = 1ULL << get_trbe_address_align(trbidr);
+	if (cpudata->trbe_hw_align > SZ_2K) {
 		pr_err("Unsupported alignment on cpu %d\n", cpu);
 		goto cpu_clear;
 	}
 
 	trbe_check_errata(cpudata);
+	cpudata->trbe_align = cpudata->trbe_hw_align;
 	cpudata->trbe_flag = get_trbe_flag_update(trbidr);
 	cpudata->cpu = cpu;
 	cpudata->drvdata = drvdata;

@@ -73,6 +73,8 @@
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
 #define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_CORTEX_A710	0xD47
+#define ARM_CPU_PART_NEOVERSE_N2	0xD49
 
 #define APM_CPU_PART_POTENZA		0x000
 

@@ -113,6 +115,8 @@
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
 #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
+#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

@@ -340,6 +340,18 @@ static const struct midr_range erratum_1463225[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
+#ifdef CONFIG_ARM64_ERRATUM_2139208
+	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_2119858
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+#endif
+	{},
+};
+#endif	/* CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE */
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{

@@ -533,6 +545,19 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP,
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
 	},
+#endif
+#ifdef CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+	{
+		/*
+		 * The erratum work around is handled within the TRBE
+		 * driver and can be applied per-cpu. So, we can allow
+		 * a late CPU to come online with this erratum.
+		 */
+		.desc = "ARM erratum 2119858 or 2139208",
+		.capability = ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		CAP_MIDR_RANGE_LIST(trbe_overwrite_fill_mode_cpus),
+	},
 #endif
 	{
 	}

@@ -53,6 +53,7 @@ WORKAROUND_1418040
 WORKAROUND_1463225
 WORKAROUND_1508412
 WORKAROUND_1542419
+WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_CAVIUM_23154
 WORKAROUND_CAVIUM_27456
 WORKAROUND_CAVIUM_30115

@@ -16,6 +16,7 @@
 #define pr_fmt(fmt) DRVNAME ": " fmt
 
 #include <asm/barrier.h>
+#include <asm/cpufeature.h>
 #include <asm/cputype.h>
 
 #include "coresight-self-hosted-trace.h"

@@ -84,9 +85,17 @@ struct trbe_buf {
  * per TRBE instance, we keep track of the list of errata that
  * affects the given instance of the TRBE.
  */
-#define TRBE_ERRATA_MAX			0
+#define TRBE_WORKAROUND_OVERWRITE_FILL_MODE	0
+#define TRBE_ERRATA_MAX				1
+
+/*
+ * Safe limit for the number of bytes that may be overwritten
+ * when the erratum is triggered.
+ */
+#define TRBE_WORKAROUND_OVERWRITE_FILL_MODE_SKIP_BYTES	256
 
 static unsigned long trbe_errata_cpucaps[TRBE_ERRATA_MAX] = {
+	[TRBE_WORKAROUND_OVERWRITE_FILL_MODE] = ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE,
 };
 
 /*

@@ -519,10 +528,13 @@ static void trbe_enable_hw(struct trbe_buf *buf)
 	set_trbe_limit_pointer_enabled(buf->trbe_limit);
 }
 
-static enum trbe_fault_action trbe_get_fault_act(u64 trbsr)
+static enum trbe_fault_action trbe_get_fault_act(struct perf_output_handle *handle,
+						 u64 trbsr)
 {
 	int ec = get_trbe_ec(trbsr);
 	int bsc = get_trbe_bsc(trbsr);
+	struct trbe_buf *buf = etm_perf_sink_config(handle);
+	struct trbe_cpudata *cpudata = buf->cpudata;
 
 	WARN_ON(is_trbe_running(trbsr));
 	if (is_trbe_trg(trbsr) || is_trbe_abort(trbsr))

@@ -531,10 +543,16 @@ static enum trbe_fault_action trbe_get_fault_act(u64 trbsr)
 	if ((ec == TRBE_EC_STAGE1_ABORT) || (ec == TRBE_EC_STAGE2_ABORT))
 		return TRBE_FAULT_ACT_FATAL;
 
-	if (is_trbe_wrap(trbsr) && (ec == TRBE_EC_OTHERS) && (bsc == TRBE_BSC_FILLED)) {
-		if (get_trbe_write_pointer() == get_trbe_base_pointer())
-			return TRBE_FAULT_ACT_WRAP;
-	}
+	/*
+	 * If the trbe is affected by TRBE_WORKAROUND_OVERWRITE_FILL_MODE,
+	 * it might write data after a WRAP event in the fill mode.
+	 * Thus the check TRBPTR == TRBBASER will not be honored.
+	 */
+	if ((is_trbe_wrap(trbsr) && (ec == TRBE_EC_OTHERS) && (bsc == TRBE_BSC_FILLED)) &&
+	    (trbe_has_erratum(cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE) ||
+	     get_trbe_write_pointer() == get_trbe_base_pointer()))
+		return TRBE_FAULT_ACT_WRAP;
+
 	return TRBE_FAULT_ACT_SPURIOUS;
 }
 

@@ -544,6 +562,8 @@ static unsigned long trbe_get_trace_size(struct perf_output_handle *handle,
 {
 	u64 write;
 	u64 start_off, end_off;
+	u64 size;
+	u64 overwrite_skip = TRBE_WORKAROUND_OVERWRITE_FILL_MODE_SKIP_BYTES;
 
 	/*
 	 * If the TRBE has wrapped around the write pointer has

@@ -559,7 +579,18 @@ static unsigned long trbe_get_trace_size(struct perf_output_handle *handle,
 
 	if (WARN_ON_ONCE(end_off < start_off))
 		return 0;
-	return (end_off - start_off);
+
+	size = end_off - start_off;
+	/*
+	 * If the TRBE is affected by the following erratum, we must fill
+	 * the space we skipped with IGNORE packets. And we are always
+	 * guaranteed to have at least a PAGE_SIZE space in the buffer.
+	 */
+	if (trbe_has_erratum(buf->cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE) &&
+	    !WARN_ON(size < overwrite_skip))
+		__trbe_pad_buf(buf, start_off, overwrite_skip);
+
+	return size;
 }
 
 static void *arm_trbe_alloc_buffer(struct coresight_device *csdev,

@@ -678,7 +709,7 @@ static unsigned long arm_trbe_update_buffer(struct coresight_device *csdev,
 		clr_trbe_irq();
 		isb();
 
-		act = trbe_get_fault_act(status);
+		act = trbe_get_fault_act(handle, status);
 		/*
 		 * If this was not due to a WRAP event, we have some
 		 * errors and as such buffer is empty.

@@ -702,21 +733,95 @@ static unsigned long arm_trbe_update_buffer(struct coresight_device *csdev,
 	return size;
 }
 
+
+static int trbe_apply_work_around_before_enable(struct trbe_buf *buf)
+{
+	/*
+	 * TRBE_WORKAROUND_OVERWRITE_FILL_MODE causes the TRBE to overwrite a few cache
+	 * line size from the "TRBBASER_EL1" in the event of a "FILL".
+	 * Thus, we could loose some amount of the trace at the base.
+	 *
+	 * Before Fix:
+	 *
+	 *  normal-BASE     head  normal-PTR              tail normal-LIMIT
+	 *  |                   \/                       /
+	 *   -------------------------------------------------------------
+	 *  |         |          |xyzdefghij..|...  tuvw|                |
+	 *   -------------------------------------------------------------
+	 *                      /    |                   \
+	 * After Fix->  TRBBASER     TRBPTR              TRBLIMITR.LIMIT
+	 *
+	 * In the normal course of action, we would set the TRBBASER to the
+	 * beginning of the ring-buffer (normal-BASE). But with the erratum,
+	 * the TRBE could overwrite the contents at the "normal-BASE", after
+	 * hitting the "normal-LIMIT", since it doesn't stop as expected. And
+	 * this is wrong. So we must always make sure that the TRBBASER is
+	 * within the region [head, head+size].
+	 *
+	 * Also, we would set the TRBPTR to head (after adjusting for
+	 * alignment) at normal-PTR. This would mean that the last few bytes
+	 * of the trace (say, "xyz") might overwrite the first few bytes of
+	 * trace written ("abc"). More importantly they will appear in what\
+	 * userspace sees as the beginning of the trace, which is wrong. We may
+	 * not always have space to move the latest trace "xyz" to the correct
+	 * order as it must appear beyond the LIMIT. (i.e, [head..head+size].
+	 * Thus it is easier to ignore those bytes than to complicate the
+	 * driver to move it, assuming that the erratum was triggered and doing
+	 * additional checks to see if there is indeed allowed space at
+	 * TRBLIMITR.LIMIT.
+	 *
+	 * To summarize, with the work around:
+	 *
+	 *  - We always align the offset for the next session to PAGE_SIZE
+	 *    (This is to ensure we can program the TRBBASER to this offset
+	 *    within the region [head...head+size]).
+	 *
+	 *  - At TRBE enable:
+	 *     - Set the TRBBASER to the page aligned offset of the current
+	 *       proposed write offset. (which is guaranteed to be aligned
+	 *       as above)
+	 *     - Move the TRBPTR to skip first 256bytes (that might be
+	 *       overwritten with the erratum). This ensures that the trace
+	 *       generated in the session is not re-written.
+	 *
+	 *  - At trace collection:
+	 *     - Pad the 256bytes skipped above again with IGNORE packets.
+	 */
+	if (trbe_has_erratum(buf->cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE)) {
+		if (WARN_ON(!IS_ALIGNED(buf->trbe_write, PAGE_SIZE)))
+			return -EINVAL;
+		buf->trbe_hw_base = buf->trbe_write;
+		buf->trbe_write += TRBE_WORKAROUND_OVERWRITE_FILL_MODE_SKIP_BYTES;
+	}
+
+	return 0;
+}
+
 static int __arm_trbe_enable(struct trbe_buf *buf,
 			     struct perf_output_handle *handle)
 {
+	int ret = 0;
+
 	perf_aux_output_flag(handle, PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW);
 	buf->trbe_limit = compute_trbe_buffer_limit(handle);
 	buf->trbe_write = buf->trbe_base + PERF_IDX2OFF(handle->head, buf);
 	if (buf->trbe_limit == buf->trbe_base) {
-		trbe_stop_and_truncate_event(handle);
-		return -ENOSPC;
+		ret = -ENOSPC;
+		goto err;
 	}
 	/* Set the base of the TRBE to the buffer base */
 	buf->trbe_hw_base = buf->trbe_base;
+
+	ret = trbe_apply_work_around_before_enable(buf);
+	if (ret)
+		goto err;
+
 	*this_cpu_ptr(buf->cpudata->drvdata->handle) = handle;
 	trbe_enable_hw(buf);
 	return 0;
+err:
+	trbe_stop_and_truncate_event(handle);
+	return ret;
 }
 
 static int arm_trbe_enable(struct coresight_device *csdev, u32 mode, void *data)

@@ -860,7 +965,7 @@ static irqreturn_t arm_trbe_irq_handler(int irq, void *dev)
 	if (!is_perf_trbe(handle))
 		return IRQ_NONE;
 
-	act = trbe_get_fault_act(status);
+	act = trbe_get_fault_act(handle, status);
 	switch (act) {
 	case TRBE_FAULT_ACT_WRAP:
 		truncated = !!trbe_handle_overflow(handle);

@@ -1000,7 +1105,22 @@ static void arm_trbe_probe_cpu(void *info)
 	}
 
 	trbe_check_errata(cpudata);
-	cpudata->trbe_align = cpudata->trbe_hw_align;
+	/*
+	 * If the TRBE is affected by erratum TRBE_WORKAROUND_OVERWRITE_FILL_MODE,
+	 * we must always program the TBRPTR_EL1, 256bytes from a page
+	 * boundary, with TRBBASER_EL1 set to the page, to prevent
+	 * TRBE over-writing 256bytes at TRBBASER_EL1 on FILL event.
+	 *
+	 * Thus make sure we always align our write pointer to a PAGE_SIZE,
+	 * which also guarantees that we have at least a PAGE_SIZE space in
+	 * the buffer (TRBLIMITR is PAGE aligned) and thus we can skip
+	 * the required bytes at the base.
+	 */
+	if (trbe_has_erratum(cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE))
+		cpudata->trbe_align = PAGE_SIZE;
+	else
+		cpudata->trbe_align = cpudata->trbe_hw_align;
+
 	cpudata->trbe_flag = get_trbe_flag_update(trbidr);
 	cpudata->cpu = cpu;
 	cpudata->drvdata = drvdata;

@@ -92,12 +92,16 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A77      | #1508412        | ARM64_ERRATUM_1508412       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A710     | #2119858        | ARM64_ERRATUM_2119858       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N2     | #2139208        | ARM64_ERRATUM_2139208       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

@@ -666,6 +666,45 @@ config ARM64_ERRATUM_1508412
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+	bool
+
+config ARM64_ERRATUM_2119858
+	bool "Cortex-A710: 2119858: workaround TRBE overwriting trace data in FILL mode"
+	default y
+	depends on CORESIGHT_TRBE
+	select ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+	help
+	  This option adds the workaround for ARM Cortex-A710 erratum 2119858.
+
+	  Affected Cortex-A710 cores could overwrite upto 3 cache lines of trace
+	  data at the base of the buffer (ponited by TRBASER_EL1) in FILL mode in
+	  the event of a WRAP event.
+
+	  Work around the issue by always making sure we move the TRBPTR_EL1 by
+	  256bytes before enabling the buffer and filling the first 256bytes of
+	  the buffer with ETM ignore packets upon disabling.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_2139208
+	bool "Neoverse-N2: 2139208: workaround TRBE overwriting trace data in FILL mode"
+	default y
+	depends on CORESIGHT_TRBE
+	select ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+	help
+	  This option adds the workaround for ARM Neoverse-N2 erratum 2139208.
+
+	  Affected Neoverse-N2 cores could overwrite upto 3 cache lines of trace
+	  data at the base of the buffer (ponited by TRBASER_EL1) in FILL mode in
+	  the event of a WRAP event.
+
+	  Work around the issue by always making sure we move the TRBPTR_EL1 by
+	  256bytes before enabling the buffer and filling the first 256bytes of
+	  the buffer with ETM ignore packets upon disabling.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

@@ -94,6 +94,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A710     | #2054223        | ARM64_ERRATUM_2054223       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |

@@ -102,6 +104,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N2     | #2139208        | ARM64_ERRATUM_2139208       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N2     | #2067961        | ARM64_ERRATUM_2067961       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

@@ -705,6 +705,37 @@ config ARM64_ERRATUM_2139208
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	bool
+
+config ARM64_ERRATUM_2054223
+	bool "Cortex-A710: 2054223: workaround TSB instruction failing to flush trace"
+	default y
+	help
+	  Enable workaround for ARM Cortex-A710 erratum 2054223
+
+	  Affected cores may fail to flush the trace data on a TSB instruction, when
+	  the PE is in trace prohibited state. This will cause losing a few bytes
+	  of the trace cached.
+
+	  Workaround is to issue two TSB consecutively on affected cores.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_2067961
+	bool "Neoverse-N2: 2067961: workaround TSB instruction failing to flush trace"
+	default y
+	help
+	  Enable workaround for ARM Neoverse-N2 erratum 2067961
+
+	  Affected cores may fail to flush the trace data on a TSB instruction, when
+	  the PE is in trace prohibited state. This will cause losing a few bytes
+	  of the trace cached.
+
+	  Workaround is to issue two TSB consecutively on affected cores.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

@@ -23,7 +23,7 @@
 #define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
 #define psb_csync()	asm volatile("hint #17" : : : "memory")
-#define tsb_csync()	asm volatile("hint #18" : : : "memory")
+#define __tsb_csync()	asm volatile("hint #18" : : : "memory")
 #define csdb()		asm volatile("hint #20" : : : "memory")
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI

@@ -46,6 +46,20 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
+
+#define tsb_csync()								\
+	do {									\
+		/*								\
+		 * CPUs affected by Arm Erratum 2054223 or 2067961 needs	\
+		 * another TSB to ensure the trace is flushed. The barriers	\
+		 * don't have to be strictly back to back, as long as the	\
+		 * CPU is in trace prohibited state.				\
+		 */								\
+		if (cpus_have_final_cap(ARM64_WORKAROUND_TSB_FLUSH_FAILURE))	\
+			__tsb_csync();						\
+		__tsb_csync();							\
+	} while (0)
+
 /*
  * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
  * and 0 otherwise.

@@ -352,6 +352,18 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 };
 #endif	/* CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE */
 
+#ifdef CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+static const struct midr_range tsb_flush_fail_cpus[] = {
+#ifdef CONFIG_ARM64_ERRATUM_2067961
+	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_2054223
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+#endif
+	{},
+};
+#endif	/* CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE */
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{

@@ -558,6 +570,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
 		CAP_MIDR_RANGE_LIST(trbe_overwrite_fill_mode_cpus),
 	},
+#endif
+#ifdef CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILRE
+	{
+		.desc = "ARM erratum 2067961 or 2054223",
+		.capability = ARM64_WORKAROUND_TSB_FLUSH_FAILURE,
+		ERRATA_MIDR_RANGE_LIST(tsb_flush_fail_cpus),
+	},
 #endif
 	{
 	}

@@ -54,6 +54,7 @@ WORKAROUND_1463225
 WORKAROUND_1508412
 WORKAROUND_1542419
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+WORKAROUND_TSB_FLUSH_FAILURE
 WORKAROUND_CAVIUM_23154
 WORKAROUND_CAVIUM_27456
 WORKAROUND_CAVIUM_30115

@@ -268,6 +268,15 @@ static unsigned long trbe_snapshot_offset(struct perf_output_handle *handle)
 	return buf->nr_pages * PAGE_SIZE;
 }
 
+static inline struct trbe_cpudata *
+trbe_handle_to_cpudata(struct perf_output_handle *handle)
+{
+	struct trbe_buf *buf = etm_perf_sink_config(handle);
+
+	BUG_ON(!buf || !buf->cpudata);
+	return buf->cpudata;
+}
+
 /*
  * TRBE Limit Calculation
  *

@@ -533,8 +542,7 @@ static enum trbe_fault_action trbe_get_fault_act(struct perf_output_handle *hand
 {
 	int ec = get_trbe_ec(trbsr);
 	int bsc = get_trbe_bsc(trbsr);
-	struct trbe_buf *buf = etm_perf_sink_config(handle);
-	struct trbe_cpudata *cpudata = buf->cpudata;
+	struct trbe_cpudata *cpudata = trbe_handle_to_cpudata(handle);
 
 	WARN_ON(is_trbe_running(trbsr));
 	if (is_trbe_trg(trbsr) || is_trbe_abort(trbsr))

@@ -277,6 +277,11 @@ trbe_handle_to_cpudata(struct perf_output_handle *handle)
 	return buf->cpudata;
 }
 
+static u64 trbe_min_trace_buf_size(struct perf_output_handle *handle)
+{
+	return TRBE_TRACE_MIN_BUF_SIZE;
+}
+
 /*
  * TRBE Limit Calculation
  *

@@ -447,7 +452,7 @@ static unsigned long trbe_normal_offset(struct perf_output_handle *handle)
 	 * have space for a meaningful run, we rather pad it
 	 * and start fresh.
 	 */
-	if (limit && (limit - head < TRBE_TRACE_MIN_BUF_SIZE)) {
+	if (limit && ((limit - head) < trbe_min_trace_buf_size(handle))) {
 		trbe_pad_buf(handle, limit - head);
 		limit = __trbe_normal_offset(handle);
 	}

@@ -451,10 +451,14 @@ static unsigned long trbe_normal_offset(struct perf_output_handle *handle)
 	 * If the head is too close to the limit and we don't
 	 * have space for a meaningful run, we rather pad it
 	 * and start fresh.
+	 *
+	 * We might have to do this more than once to make sure
+	 * we have enough required space.
 	 */
-	if (limit && ((limit - head) < trbe_min_trace_buf_size(handle))) {
+	while (limit && ((limit - head) < trbe_min_trace_buf_size(handle))) {
 		trbe_pad_buf(handle, limit - head);
 		limit = __trbe_normal_offset(handle);
+		head = PERF_IDX2OFF(handle->head, buf);
 	}
 	return limit;
 }

@@ -364,6 +364,18 @@ static const struct midr_range tsb_flush_fail_cpus[] = {
 };
 #endif	/* CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE */
 
+#ifdef CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
+static struct midr_range trbe_write_out_of_range_cpus[] = {
+#ifdef CONFIG_ARM64_ERRATUM_2253138
+	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_2224489
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+#endif
+	{},
+};
+#endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{

@@ -577,6 +589,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_WORKAROUND_TSB_FLUSH_FAILURE,
 		ERRATA_MIDR_RANGE_LIST(tsb_flush_fail_cpus),
 	},
+#endif
+#ifdef CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
+	{
+		.desc = "ARM erratum 2253138 or 2224489",
+		.capability = ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
+	},
 #endif
 	{
 	}

@@ -55,6 +55,7 @@ WORKAROUND_1508412
 WORKAROUND_1542419
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
+WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
 WORKAROUND_CAVIUM_23154
 WORKAROUND_CAVIUM_27456
 WORKAROUND_CAVIUM_30115

@@ -86,7 +86,8 @@ struct trbe_buf {
  * affects the given instance of the TRBE.
  */
 #define TRBE_WORKAROUND_OVERWRITE_FILL_MODE	0
-#define TRBE_ERRATA_MAX				1
+#define TRBE_WORKAROUND_WRITE_OUT_OF_RANGE	1
+#define TRBE_ERRATA_MAX				2
 
 /*
  * Safe limit for the number of bytes that may be overwritten

@@ -96,6 +97,7 @@ struct trbe_buf {
 
 static unsigned long trbe_errata_cpucaps[TRBE_ERRATA_MAX] = {
 	[TRBE_WORKAROUND_OVERWRITE_FILL_MODE] = ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE,
+	[TRBE_WORKAROUND_WRITE_OUT_OF_RANGE] = ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE,
 };
 
 /*

@@ -279,7 +281,20 @@ trbe_handle_to_cpudata(struct perf_output_handle *handle)
 
 static u64 trbe_min_trace_buf_size(struct perf_output_handle *handle)
 {
-	return TRBE_TRACE_MIN_BUF_SIZE;
+	u64 size = TRBE_TRACE_MIN_BUF_SIZE;
+	struct trbe_cpudata *cpudata = trbe_handle_to_cpudata(handle);
+
+	/*
+	 * When the TRBE is affected by an erratum that could make it
+	 * write to the next "virtually addressed" page beyond the LIMIT.
+	 * We need to make sure there is always a PAGE after the LIMIT,
+	 * within the buffer. Thus we ensure there is at least an extra
+	 * page than normal. With this we could then adjust the LIMIT
+	 * pointer down by a PAGE later.
+	 */
+	if (trbe_has_erratum(cpudata, TRBE_WORKAROUND_WRITE_OUT_OF_RANGE))
+		size += PAGE_SIZE;
+	return size;
 }
 
 /*

@@ -585,6 +600,17 @@ static unsigned long trbe_get_trace_size(struct perf_output_handle *handle,
 	/*
 	 * If the TRBE has wrapped around the write pointer has
 	 * wrapped and should be treated as limit.
+	 *
+	 * When the TRBE is affected by TRBE_WORKAROUND_WRITE_OUT_OF_RANGE,
+	 * it may write upto 64bytes beyond the "LIMIT". The driver already
+	 * keeps a valid page next to the LIMIT and we could potentially
+	 * consume the trace data that may have been collected there. But we
+	 * cannot be really sure it is available, and the TRBPTR may not
+	 * indicate the same. Also, affected cores are also affected by another
+	 * erratum which forces the PAGE_SIZE alignment on the TRBPTR, and thus
+	 * could potentially pad an entire PAGE_SIZE - 64bytes, to get those
+	 * 64bytes. Thus we ignore the potential triggering of the erratum
+	 * on WRAP and limit the data to LIMIT.
 	 */
 	if (wrap)
 		write = get_trbe_limit_pointer();