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

Pull arm64 updates from Will Deacon:
 "The changes are a real mixed bag this time around.

  The only scary looking one from the diffstat is the uapi change to
  asm-generic/mman-common.h, but this has been acked by Arnd and is
  actually just adding a pair of comments in an attempt to prevent
  allocation of some PROT values which tend to get used for
  arch-specific purposes. We'll be using them for Branch Target
  Identification (a CFI-like hardening feature), which is currently
  under review on the mailing list.

  New architecture features:

   - Support for Armv8.5 E0PD, which benefits KASLR in the same way as
     KPTI but without the overhead. This allows KPTI to be disabled on
     CPUs that are not affected by Meltdown, even is KASLR is enabled.

   - Initial support for the Armv8.5 RNG instructions, which claim to
     provide access to a high bandwidth, cryptographically secure
     hardware random number generator. As well as exposing these to
     userspace, we also use them as part of the KASLR seed and to seed
     the crng once all CPUs have come online.

   - Advertise a bunch of new instructions to userspace, including
     support for Data Gathering Hint, Matrix Multiply and 16-bit
     floating point.

  Kexec:

   - Cleanups in preparation for relocating with the MMU enabled

   - Support for loading crash dump kernels with kexec_file_load()

  Perf and PMU drivers:

   - Cleanups and non-critical fixes for a couple of system PMU drivers

  FPU-less (aka broken) CPU support:

   - Considerable fixes to support CPUs without the FP/SIMD extensions,
     including their presence in heterogeneous systems. Good luck
     finding a 64-bit userspace that handles this.

  Modern assembly function annotations:

   - Start migrating our use of ENTRY() and ENDPROC() over to the
     new-fangled SYM_{CODE,FUNC}_{START,END} macros, which are intended
     to aid debuggers

  Kbuild:

   - Cleanup detection of LSE support in the assembler by introducing
     'as-instr'

   - Remove compressed Image files when building clean targets

  IP checksumming:

   - Implement optimised IPv4 checksumming routine when hardware offload
     is not in use. An IPv6 version is in the works, pending testing.

  Hardware errata:

   - Work around Cortex-A55 erratum #1530923

  Shadow call stack:

   - Work around some issues with Clang's integrated assembler not
     liking our perfectly reasonable assembly code

   - Avoid allocating the X18 register, so that it can be used to hold
     the shadow call stack pointer in future

  ACPI:

   - Fix ID count checking in IORT code. This may regress broken
     firmware that happened to work with the old implementation, in
     which case we'll have to revert it and try something else

   - Fix DAIF corruption on return from GHES handler with pseudo-NMIs

  Miscellaneous:

   - Whitelist some CPUs that are unaffected by Spectre-v2

   - Reduce frequency of ASID rollover when KPTI is compiled in but
     inactive

   - Reserve a couple of arch-specific PROT flags that are already used
     by Sparc and PowerPC and are planned for later use with BTI on
     arm64

   - Preparatory cleanup of our entry assembly code in preparation for
     moving more of it into C later on

   - Refactoring and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (73 commits)
  arm64: acpi: fix DAIF manipulation with pNMI
  arm64: kconfig: Fix alignment of E0PD help text
  arm64: Use v8.5-RNG entropy for KASLR seed
  arm64: Implement archrandom.h for ARMv8.5-RNG
  arm64: kbuild: remove compressed images on 'make ARCH=arm64 (dist)clean'
  arm64: entry: Avoid empty alternatives entries
  arm64: Kconfig: select HAVE_FUTEX_CMPXCHG
  arm64: csum: Fix pathological zero-length calls
  arm64: entry: cleanup sp_el0 manipulation
  arm64: entry: cleanup el0 svc handler naming
  arm64: entry: mark all entry code as notrace
  arm64: assembler: remove smp_dmb macro
  arm64: assembler: remove inherit_daif macro
  ACPI/IORT: Fix 'Number of IDs' handling in iort_id_map()
  mm: Reserve asm-generic prot flags 0x10 and 0x20 for arch use
  arm64: Use macros instead of hard-coded constants for MAIR_EL1
  arm64: Add KRYO{3,4}XX CPU cores to spectre-v2 safe list
  arm64: kernel: avoid x18 in __cpu_soft_restart
  arm64: kvm: stop treating register x18 as caller save
  arm64/lib: copy_page: avoid x18 register in assembler code
  ...

3 files changed, 98 insertions, 33 deletions

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 33f71983e001..6078064684c6 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -298,6 +298,59 @@ out:
 	return status;
 }
 
+struct iort_workaround_oem_info {
+	char oem_id[ACPI_OEM_ID_SIZE + 1];
+	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
+	u32 oem_revision;
+};
+
+static bool apply_id_count_workaround;
+
+static struct iort_workaround_oem_info wa_info[] __initdata = {
+	{
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP07   ",
+		.oem_revision	= 0,
+	}, {
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP08   ",
+		.oem_revision	= 0,
+	}
+};
+
+static void __init
+iort_check_id_count_workaround(struct acpi_table_header *tbl)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(wa_info); i++) {
+		if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) &&
+		    !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
+		    wa_info[i].oem_revision == tbl->oem_revision) {
+			apply_id_count_workaround = true;
+			pr_warn(FW_BUG "ID count for ID mapping entry is wrong, applying workaround\n");
+			break;
+		}
+	}
+}
+
+static inline u32 iort_get_map_max(struct acpi_iort_id_mapping *map)
+{
+	u32 map_max = map->input_base + map->id_count;
+
+	/*
+	 * The IORT specification revision D (Section 3, table 4, page 9) says
+	 * Number of IDs = The number of IDs in the range minus one, but the
+	 * IORT code ignored the "minus one", and some firmware did that too,
+	 * so apply a workaround here to keep compatible with both the spec
+	 * compliant and non-spec compliant firmwares.
+	 */
+	if (apply_id_count_workaround)
+		map_max--;
+
+	return map_max;
+}
+
 static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 		       u32 *rid_out)
 {
@@ -314,8 +367,7 @@ static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 		return -ENXIO;
 	}
 
-	if (rid_in < map->input_base ||
-	    (rid_in >= map->input_base + map->id_count))
+	if (rid_in < map->input_base || rid_in > iort_get_map_max(map))
 		return -ENXIO;
 
 	*rid_out = map->output_base + (rid_in - map->input_base);
@@ -1631,5 +1683,6 @@ void __init acpi_iort_init(void)
 		return;
 	}
 
+	iort_check_id_count_workaround(iort_table);
 	iort_init_platform_devices();
 }
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 55083c67b2bb..95dca2cb5265 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -633,13 +633,17 @@ static int ddr_perf_probe(struct platform_device *pdev)
 
 	if (ret < 0) {
 		dev_err(&pdev->dev, "cpuhp_setup_state_multi failed\n");
-		goto ddr_perf_err;
+		goto cpuhp_state_err;
 	}
 
 	pmu->cpuhp_state = ret;
 
 	/* Register the pmu instance for cpu hotplug */
-	cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+	ret = cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+		goto cpuhp_instance_err;
+	}
 
 	/* Request irq */
 	irq = of_irq_get(np, 0);
@@ -673,9 +677,10 @@ static int ddr_perf_probe(struct platform_device *pdev)
 	return 0;
 
 ddr_perf_err:
-	if (pmu->cpuhp_state)
-		cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
-
+	cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+cpuhp_instance_err:
+	cpuhp_remove_multi_state(pmu->cpuhp_state);
+cpuhp_state_err:
 	ida_simple_remove(&ddr_ida, pmu->id);
 	dev_warn(&pdev->dev, "i.MX8 DDR Perf PMU failed (%d), disabled\n", ret);
 	return ret;
@@ -686,6 +691,7 @@ static int ddr_perf_remove(struct platform_device *pdev)
 	struct ddr_pmu *pmu = platform_get_drvdata(pdev);
 
 	cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+	cpuhp_remove_multi_state(pmu->cpuhp_state);
 	irq_set_affinity_hint(pmu->irq, NULL);
 
 	perf_pmu_unregister(&pmu->pmu);
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 96183e31b96a..584de8f807cc 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -337,38 +337,44 @@ void hisi_uncore_pmu_disable(struct pmu *pmu)
 	hisi_pmu->ops->stop_counters(hisi_pmu);
 }
 
+
 /*
- * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1.
- * If multi-threading is supported, On Huawei Kunpeng 920 SoC whose cpu
- * core is tsv110, CCL_ID is the low 3-bits in MPIDR[Aff2] and SCCL_ID
- * is the upper 5-bits of Aff2 field; while for other cpu types, SCCL_ID
- * is in MPIDR[Aff3] and CCL_ID is in MPIDR[Aff2], if not, SCCL_ID
- * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1].
+ * The Super CPU Cluster (SCCL) and CPU Cluster (CCL) IDs can be
+ * determined from the MPIDR_EL1, but the encoding varies by CPU:
+ *
+ * - For MT variants of TSV110:
+ *   SCCL is Aff2[7:3], CCL is Aff2[2:0]
+ *
+ * - For other MT parts:
+ *   SCCL is Aff3[7:0], CCL is Aff2[7:0]
+ *
+ * - For non-MT parts:
+ *   SCCL is Aff2[7:0], CCL is Aff1[7:0]
  */
-static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
+static void hisi_read_sccl_and_ccl_id(int *scclp, int *cclp)
 {
 	u64 mpidr = read_cpuid_mpidr();
-
-	if (mpidr & MPIDR_MT_BITMASK) {
-		if (read_cpuid_part_number() == HISI_CPU_PART_TSV110) {
-			int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-
-			if (sccl_id)
-				*sccl_id = aff2 >> 3;
-			if (ccl_id)
-				*ccl_id = aff2 & 0x7;
-		} else {
-			if (sccl_id)
-				*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3);
-			if (ccl_id)
-				*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-		}
+	int aff3 = MPIDR_AFFINITY_LEVEL(mpidr, 3);
+	int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+	int aff1 = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	bool mt = mpidr & MPIDR_MT_BITMASK;
+	int sccl, ccl;
+
+	if (mt && read_cpuid_part_number() == HISI_CPU_PART_TSV110) {
+		sccl = aff2 >> 3;
+		ccl = aff2 & 0x7;
+	} else if (mt) {
+		sccl = aff3;
+		ccl = aff2;
 	} else {
-		if (sccl_id)
-			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-		if (ccl_id)
-			*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+		sccl = aff2;
+		ccl = aff1;
 	}
+
+	if (scclp)
+		*scclp = sccl;
+	if (cclp)
+		*cclp = ccl;
 }
 
 /*