Merge tag 'coresight-next-v5.16.v3' of gitolite.kernel.org:pub/scm/linux/kernel/git/coresight/linux into char-misc-next

Mathieu writes:

Coresight changes for v5.16

- A new option to make coresight cpu-debug capabilities available as early
as possible in the kernel boot process.

- Make trace sessions more enduring by coping with scenarios where events
are scheduled on CPUs that can't reach the selected sink.

- A set of improvement to make the TMC-ETR driver more efficient.

- Enhancements to the TRBE driver to correct several errata.

- An enhancement to make the AXI burts size configurable for TMC devices
that can't work with the default value.

- A fix in the CTI module to use the correct device when calling
pm_runtime_put()

- The addition of the Kryo-5xx device to the list of support ETMs.

Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>

* tag 'coresight-next-v5.16.v3' of gitolite.kernel.org:pub/scm/linux/kernel/git/coresight/linux: (39 commits)
  arm64: errata: Enable TRBE workaround for write to out-of-range address
  arm64: errata: Enable workaround for TRBE overwrite in FILL mode
  coresight: trbe: Work around write to out of range
  coresight: trbe: Make sure we have enough space
  coresight: trbe: Add a helper to determine the minimum buffer size
  coresight: trbe: Workaround TRBE errata overwrite in FILL mode
  coresight: trbe: Add infrastructure for Errata handling
  coresight: trbe: Allow driver to choose a different alignment
  coresight: trbe: Decouple buffer base from the hardware base
  coresight: trbe: Add a helper to pad a given buffer area
  coresight: trbe: Add a helper to calculate the trace generated
  coresight: trbe: Defer the probe on offline CPUs
  coresight: trbe: Fix incorrect access of the sink specific data
  coresight: etm4x: Add ETM PID for Kryo-5XX
  coresight: trbe: Prohibit trace before disabling TRBE
  coresight: trbe: End the AUX handle on truncation
  coresight: trbe: Do not truncate buffer on IRQ
  coresight: trbe: Fix handling of spurious interrupts
  coresight: trbe: irq handler: Do not disable TRBE if no action is needed
  coresight: trbe: Unify the enabling sequence
  ...

5 files changed, 197 insertions, 1 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fee914c716aa..ebb77b894630 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -666,6 +666,117 @@ 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 up to 3 cache lines of trace
+	  data at the base of the buffer (pointed to 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
+	  256 bytes before enabling the buffer and filling the first 256 bytes 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 up to 3 cache lines of trace
+	  data at the base of the buffer (pointed to 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
+	  256 bytes before enabling the buffer and filling the first 256 bytes of
+	  the buffer with ETM ignore packets upon disabling.
+
+	  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
+	select ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	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
+	select ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	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 ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
+	bool
+
+config ARM64_ERRATUM_2253138
+	bool "Neoverse-N2: 2253138: workaround TRBE writing to address out-of-range"
+	depends on CORESIGHT_TRBE
+	default y
+	select ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
+	help
+	  This option adds the workaround for ARM Neoverse-N2 erratum 2253138.
+
+	  Affected Neoverse-N2 cores might write to an out-of-range address, not reserved
+	  for TRBE. Under some conditions, the TRBE might generate a write to the next
+	  virtually addressed page following the last page of the TRBE address space
+	  (i.e., the TRBLIMITR_EL1.LIMIT), instead of wrapping around to the base.
+
+	  Work around this in the driver by always making sure that there is a
+	  page beyond the TRBLIMITR_EL1.LIMIT, within the space allowed for the TRBE.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_2224489
+	bool "Cortex-A710: 2224489: workaround TRBE writing to address out-of-range"
+	depends on CORESIGHT_TRBE
+	default y
+	select ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
+	help
+	  This option adds the workaround for ARM Cortex-A710 erratum 2224489.
+
+	  Affected Cortex-A710 cores might write to an out-of-range address, not reserved
+	  for TRBE. Under some conditions, the TRBE might generate a write to the next
+	  virtually addressed page following the last page of the TRBE address space
+	  (i.e., the TRBLIMITR_EL1.LIMIT), instead of wrapping around to the base.
+
+	  Work around this in the driver by always making sure that there is a
+	  page beyond the TRBLIMITR_EL1.LIMIT, within the space allowed for the TRBE.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 451e11e5fd23..1c5a00598458 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -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.
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 6231e1f0abe7..19b8441aa8f2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -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)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index e2c20c036442..9e1c1aef9ebd 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -340,6 +340,42 @@ 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 */
+
+#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 */
+
+#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
 	{
@@ -534,6 +570,34 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		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
+#ifdef CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	{
+		.desc = "ARM erratum 2067961 or 2054223",
+		.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
 	{
 	}
 };
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 49305c2e6dfd..90628638e0f9 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -53,6 +53,9 @@ WORKAROUND_1418040
 WORKAROUND_1463225
 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