Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "The highlights this time are support for dynamically enabling and
  disabling Clang's Shadow Call Stack at boot and a long-awaited
  optimisation to the way in which we handle the SVE register state on
  system call entry to avoid taking unnecessary traps from userspace.

  Summary:

  ACPI:
   - Enable FPDT support for boot-time profiling
   - Fix CPU PMU probing to work better with PREEMPT_RT
   - Update SMMUv3 MSI DeviceID parsing to latest IORT spec
   - APMT support for probing Arm CoreSight PMU devices

  CPU features:
   - Advertise new SVE instructions (v2.1)
   - Advertise range prefetch instruction
   - Advertise CSSC ("Common Short Sequence Compression") scalar
     instructions, adding things like min, max, abs, popcount
   - Enable DIT (Data Independent Timing) when running in the kernel
   - More conversion of system register fields over to the generated
     header

  CPU misfeatures:
   - Workaround for Cortex-A715 erratum #2645198

  Dynamic SCS:
   - Support for dynamic shadow call stacks to allow switching at
     runtime between Clang's SCS implementation and the CPU's pointer
     authentication feature when it is supported (complete with scary
     DWARF parser!)

  Tracing and debug:
   - Remove static ftrace in favour of, err, dynamic ftrace!
   - Seperate 'struct ftrace_regs' from 'struct pt_regs' in core ftrace
     and existing arch code
   - Introduce and implement FTRACE_WITH_ARGS on arm64 to replace the
     old FTRACE_WITH_REGS
   - Extend 'crashkernel=' parameter with default value and fallback to
     placement above 4G physical if initial (low) allocation fails

  SVE:
   - Optimisation to avoid disabling SVE unconditionally on syscall
     entry and just zeroing the non-shared state on return instead

  Exceptions:
   - Rework of undefined instruction handling to avoid serialisation on
     global lock (this includes emulation of user accesses to the ID
     registers)

  Perf and PMU:
   - Support for TLP filters in Hisilicon's PCIe PMU device
   - Support for the DDR PMU present in Amlogic Meson G12 SoCs
   - Support for the terribly-named "CoreSight PMU" architecture from
     Arm (and Nvidia's implementation of said architecture)

  Misc:
   - Tighten up our boot protocol for systems with memory above 52 bits
     physical
   - Const-ify static keys to satisty jump label asm constraints
   - Trivial FFA driver cleanups in preparation for v1.1 support
   - Export the kernel_neon_* APIs as GPL symbols
   - Harden our instruction generation routines against instrumentation
   - A bunch of robustness improvements to our arch-specific selftests
   - Minor cleanups and fixes all over (kbuild, kprobes, kfence, PMU, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (151 commits)
  arm64: kprobes: Return DBG_HOOK_ERROR if kprobes can not handle a BRK
  arm64: kprobes: Let arch do_page_fault() fix up page fault in user handler
  arm64: Prohibit instrumentation on arch_stack_walk()
  arm64:uprobe fix the uprobe SWBP_INSN in big-endian
  arm64: alternatives: add __init/__initconst to some functions/variables
  arm_pmu: Drop redundant armpmu->map_event() in armpmu_event_init()
  kselftest/arm64: Allow epoll_wait() to return more than one result
  kselftest/arm64: Don't drain output while spawning children
  kselftest/arm64: Hold fp-stress children until they're all spawned
  arm64/sysreg: Remove duplicate definitions from asm/sysreg.h
  arm64/sysreg: Convert ID_DFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_DFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_AFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_MMFR5_EL1 to automatic generation
  arm64/sysreg: Convert MVFR2_EL1 to automatic generation
  arm64/sysreg: Convert MVFR1_EL1 to automatic generation
  arm64/sysreg: Convert MVFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR2_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR0_EL1 to automatic generation
  ...

6 files changed, 197 insertions, 5 deletions

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 473241b5193f..1cc11d2a2a88 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -90,7 +90,7 @@ config ACPI_SPCR_TABLE
 
 config ACPI_FPDT
 	bool "ACPI Firmware Performance Data Table (FPDT) support"
-	depends on X86_64
+	depends on X86_64 || ARM64
 	help
 	  Enable support for the Firmware Performance Data Table (FPDT).
 	  This table provides information on the timing of the system
diff --git a/drivers/acpi/arm64/Kconfig b/drivers/acpi/arm64/Kconfig
index d4a72835f328..b3ed6212244c 100644
--- a/drivers/acpi/arm64/Kconfig
+++ b/drivers/acpi/arm64/Kconfig
@@ -18,3 +18,6 @@ config ACPI_AGDI
 	  reset command.
 
 	  If set, the kernel parses AGDI table and listens for the command.
+
+config ACPI_APMT
+	bool
diff --git a/drivers/acpi/arm64/Makefile b/drivers/acpi/arm64/Makefile
index 7b9e4045659d..e21a9e84e394 100644
--- a/drivers/acpi/arm64/Makefile
+++ b/drivers/acpi/arm64/Makefile
@@ -2,4 +2,5 @@
 obj-$(CONFIG_ACPI_AGDI) 	+= agdi.o
 obj-$(CONFIG_ACPI_IORT) 	+= iort.o
 obj-$(CONFIG_ACPI_GTDT) 	+= gtdt.o
+obj-$(CONFIG_ACPI_APMT) 	+= apmt.o
 obj-y				+= dma.o
diff --git a/drivers/acpi/arm64/apmt.c b/drivers/acpi/arm64/apmt.c
new file mode 100644
index 000000000000..8cab69fa5d59
--- /dev/null
+++ b/drivers/acpi/arm64/apmt.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM APMT table support.
+ * Design document number: ARM DEN0117.
+ *
+ * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES.
+ *
+ */
+
+#define pr_fmt(fmt)	"ACPI: APMT: " fmt
+
+#include <linux/acpi.h>
+#include <linux/acpi_apmt.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+#define DEV_NAME "arm-cs-arch-pmu"
+
+/* There can be up to 3 resources: page 0 and 1 address, and interrupt. */
+#define DEV_MAX_RESOURCE_COUNT 3
+
+/* Root pointer to the mapped APMT table */
+static struct acpi_table_header *apmt_table;
+
+static int __init apmt_init_resources(struct resource *res,
+				      struct acpi_apmt_node *node)
+{
+	int irq, trigger;
+	int num_res = 0;
+
+	res[num_res].start = node->base_address0;
+	res[num_res].end = node->base_address0 + SZ_4K - 1;
+	res[num_res].flags = IORESOURCE_MEM;
+
+	num_res++;
+
+	res[num_res].start = node->base_address1;
+	res[num_res].end = node->base_address1 + SZ_4K - 1;
+	res[num_res].flags = IORESOURCE_MEM;
+
+	num_res++;
+
+	if (node->ovflw_irq != 0) {
+		trigger = (node->ovflw_irq_flags & ACPI_APMT_OVFLW_IRQ_FLAGS_MODE);
+		trigger = (trigger == ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_LEVEL) ?
+			ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+		irq = acpi_register_gsi(NULL, node->ovflw_irq, trigger,
+						ACPI_ACTIVE_HIGH);
+
+		if (irq <= 0) {
+			pr_warn("APMT could not register gsi hwirq %d\n", irq);
+			return num_res;
+		}
+
+		res[num_res].start = irq;
+		res[num_res].end = irq;
+		res[num_res].flags = IORESOURCE_IRQ;
+
+		num_res++;
+	}
+
+	return num_res;
+}
+
+/**
+ * apmt_add_platform_device() - Allocate a platform device for APMT node
+ * @node: Pointer to device ACPI APMT node
+ * @fwnode: fwnode associated with the APMT node
+ *
+ * Returns: 0 on success, <0 failure
+ */
+static int __init apmt_add_platform_device(struct acpi_apmt_node *node,
+					   struct fwnode_handle *fwnode)
+{
+	struct platform_device *pdev;
+	int ret, count;
+	struct resource res[DEV_MAX_RESOURCE_COUNT];
+
+	pdev = platform_device_alloc(DEV_NAME, PLATFORM_DEVID_AUTO);
+	if (!pdev)
+		return -ENOMEM;
+
+	memset(res, 0, sizeof(res));
+
+	count = apmt_init_resources(res, node);
+
+	ret = platform_device_add_resources(pdev, res, count);
+	if (ret)
+		goto dev_put;
+
+	/*
+	 * Add a copy of APMT node pointer to platform_data to be used to
+	 * retrieve APMT data information.
+	 */
+	ret = platform_device_add_data(pdev, &node, sizeof(node));
+	if (ret)
+		goto dev_put;
+
+	pdev->dev.fwnode = fwnode;
+
+	ret = platform_device_add(pdev);
+
+	if (ret)
+		goto dev_put;
+
+	return 0;
+
+dev_put:
+	platform_device_put(pdev);
+
+	return ret;
+}
+
+static int __init apmt_init_platform_devices(void)
+{
+	struct acpi_apmt_node *apmt_node;
+	struct acpi_table_apmt *apmt;
+	struct fwnode_handle *fwnode;
+	u64 offset, end;
+	int ret;
+
+	/*
+	 * apmt_table and apmt both point to the start of APMT table, but
+	 * have different struct types
+	 */
+	apmt = (struct acpi_table_apmt *)apmt_table;
+	offset = sizeof(*apmt);
+	end = apmt->header.length;
+
+	while (offset < end) {
+		apmt_node = ACPI_ADD_PTR(struct acpi_apmt_node, apmt,
+				 offset);
+
+		fwnode = acpi_alloc_fwnode_static();
+		if (!fwnode)
+			return -ENOMEM;
+
+		ret = apmt_add_platform_device(apmt_node, fwnode);
+		if (ret) {
+			acpi_free_fwnode_static(fwnode);
+			return ret;
+		}
+
+		offset += apmt_node->length;
+	}
+
+	return 0;
+}
+
+void __init acpi_apmt_init(void)
+{
+	acpi_status status;
+	int ret;
+
+	/**
+	 * APMT table nodes will be used at runtime after the apmt init,
+	 * so we don't need to call acpi_put_table() to release
+	 * the APMT table mapping.
+	 */
+	status = acpi_get_table(ACPI_SIG_APMT, 0, &apmt_table);
+
+	if (ACPI_FAILURE(status)) {
+		if (status != AE_NOT_FOUND) {
+			const char *msg = acpi_format_exception(status);
+
+			pr_err("Failed to get APMT table, %s\n", msg);
+		}
+
+		return;
+	}
+
+	ret = apmt_init_platform_devices();
+	if (ret) {
+		pr_err("Failed to initialize APMT platform devices, ret: %d\n", ret);
+		acpi_put_table(apmt_table);
+	}
+}
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 8059baf4ef27..38fb84974f35 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -402,6 +402,10 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 	return NULL;
 }
 
+#ifndef ACPI_IORT_SMMU_V3_DEVICEID_VALID
+#define ACPI_IORT_SMMU_V3_DEVICEID_VALID (1 << 4)
+#endif
+
 static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
@@ -418,12 +422,16 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 
 		smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 		/*
-		 * ID mapping index is only ignored if all interrupts are
-		 * GSIV based
+		 * Until IORT E.e (node rev. 5), the ID mapping index was
+		 * defined to be valid unless all interrupts are GSIV-based.
 		 */
-		if (smmu->event_gsiv && smmu->pri_gsiv && smmu->gerr_gsiv
-		    && smmu->sync_gsiv)
+		if (node->revision < 5) {
+			if (smmu->event_gsiv && smmu->pri_gsiv &&
+			    smmu->gerr_gsiv && smmu->sync_gsiv)
+				return -EINVAL;
+		} else if (!(smmu->flags & ACPI_IORT_SMMU_V3_DEVICEID_VALID)) {
 			return -EINVAL;
+		}
 
 		if (smmu->id_mapping_index >= node->mapping_count) {
 			pr_err(FW_BUG "[node %p type %d] ID mapping index overflows valid mappings\n",
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index d466c8195314..351208eda9be 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -27,6 +27,7 @@
 #include <linux/dmi.h>
 #endif
 #include <linux/acpi_agdi.h>
+#include <linux/acpi_apmt.h>
 #include <linux/acpi_iort.h>
 #include <linux/acpi_viot.h>
 #include <linux/pci.h>
@@ -1423,6 +1424,7 @@ static int __init acpi_init(void)
 	acpi_setup_sb_notify_handler();
 	acpi_viot_init();
 	acpi_agdi_init();
+	acpi_apmt_init();
 	return 0;
 }