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

Pull arm64 updates from Catalin Marinas:
 "Nothing major this time around.

  Apart from the usual perf/PMU updates, some page table cleanups, the
  notable features are average CPU frequency based on the AMUv1
  counters, CONFIG_HOTPLUG_SMT and MOPS instructions (memcpy/memset) in
  the uaccess routines.

  Perf and PMUs:

   - Support for the 'Rainier' CPU PMU from Arm

   - Preparatory driver changes and cleanups that pave the way for BRBE
     support

   - Support for partial virtualisation of the Apple-M1 PMU

   - Support for the second event filter in Arm CSPMU designs

   - Minor fixes and cleanups (CMN and DWC PMUs)

   - Enable EL2 requirements for FEAT_PMUv3p9

  Power, CPU topology:

   - Support for AMUv1-based average CPU frequency

   - Run-time SMT control wired up for arm64 (CONFIG_HOTPLUG_SMT). It
     adds a generic topology_is_primary_thread() function overridden by
     x86 and powerpc

  New(ish) features:

   - MOPS (memcpy/memset) support for the uaccess routines

  Security/confidential compute:

   - Fix the DMA address for devices used in Realms with Arm CCA. The
     CCA architecture uses the address bit to differentiate between
     shared and private addresses

   - Spectre-BHB: assume CPUs Linux doesn't know about vulnerable by
     default

  Memory management clean-ups:

   - Drop the P*D_TABLE_BIT definition in preparation for 128-bit PTEs

   - Some minor page table accessor clean-ups

   - PIE/POE (permission indirection/overlay) helpers clean-up

  Kselftests:

   - MTE: skip hugetlb tests if MTE is not supported on such mappings
     and user correct naming for sync/async tag checking modes

  Miscellaneous:

   - Add a PKEY_UNRESTRICTED definition as 0 to uapi (toolchain people
     request)

   - Sysreg updates for new register fields

   - CPU type info for some Qualcomm Kryo cores"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits)
  arm64: mm: Don't use %pK through printk
  perf/arm_cspmu: Fix missing io.h include
  arm64: errata: Add newer ARM cores to the spectre_bhb_loop_affected() lists
  arm64: cputype: Add MIDR_CORTEX_A76AE
  arm64: errata: Add KRYO 2XX/3XX/4XX silver cores to Spectre BHB safe list
  arm64: errata: Assume that unknown CPUs _are_ vulnerable to Spectre BHB
  arm64: errata: Add QCOM_KRYO_4XX_GOLD to the spectre_bhb_k24_list
  arm64/sysreg: Enforce whole word match for open/close tokens
  arm64/sysreg: Fix unbalanced closing block
  arm64: Kconfig: Enable HOTPLUG_SMT
  arm64: topology: Support SMT control on ACPI based system
  arch_topology: Support SMT control for OF based system
  cpu/SMT: Provide a default topology_is_primary_thread()
  arm64/mm: Define PTDESC_ORDER
  perf/arm_cspmu: Add PMEVFILT2R support
  perf/arm_cspmu: Generalise event filtering
  perf/arm_cspmu: Move register definitons to header
  arm64/kernel: Always use level 2 or higher for early mappings
  arm64/mm: Drop PXD_TABLE_BIT
  arm64/mm: Check pmd_table() in pmd_trans_huge()
  ...

5 files changed, 63 insertions, 11 deletions

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 7fe0981a7e46..02fd4746231d 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1184,7 +1184,7 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_
 }
 #endif
 
-extern unsigned int arch_freq_get_on_cpu(int cpu);
+extern int arch_freq_get_on_cpu(int cpu);
 
 #ifndef arch_set_freq_scale
 static __always_inline
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index d7e30d4f7503..f3bc0bcd7098 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -78,14 +78,18 @@ static inline dma_addr_t dma_range_map_max(const struct bus_dma_region *map)
 #define phys_to_dma_unencrypted		phys_to_dma
 #endif
 #else
-static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
-		phys_addr_t paddr)
+static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	if (dev->dma_range_map)
 		return translate_phys_to_dma(dev, paddr);
 	return paddr;
 }
 
+static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
+						phys_addr_t paddr)
+{
+	return dma_addr_unencrypted(__phys_to_dma(dev, paddr));
+}
 /*
  * If memory encryption is supported, phys_to_dma will set the memory encryption
  * bit in the DMA address, and dma_to_phys will clear it.
@@ -94,19 +98,20 @@ static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
  */
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
+	return dma_addr_encrypted(__phys_to_dma(dev, paddr));
 }
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	phys_addr_t paddr;
 
+	dma_addr = dma_addr_canonical(dma_addr);
 	if (dev->dma_range_map)
 		paddr = translate_dma_to_phys(dev, dma_addr);
 	else
 		paddr = dma_addr;
 
-	return __sme_clr(paddr);
+	return paddr;
 }
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h
index ae4526389261..07584c5e36fb 100644
--- a/include/linux/mem_encrypt.h
+++ b/include/linux/mem_encrypt.h
@@ -26,11 +26,34 @@
  */
 #define __sme_set(x)		((x) | sme_me_mask)
 #define __sme_clr(x)		((x) & ~sme_me_mask)
+
+#define dma_addr_encrypted(x)	__sme_set(x)
+#define dma_addr_canonical(x)	__sme_clr(x)
+
 #else
 #define __sme_set(x)		(x)
 #define __sme_clr(x)		(x)
 #endif
 
+/*
+ * dma_addr_encrypted() and dma_addr_unencrypted() are for converting a given DMA
+ * address to the respective type of addressing.
+ *
+ * dma_addr_canonical() is used to reverse any conversions for encrypted/decrypted
+ * back to the canonical address.
+ */
+#ifndef dma_addr_encrypted
+#define dma_addr_encrypted(x)		(x)
+#endif
+
+#ifndef dma_addr_unencrypted
+#define dma_addr_unencrypted(x)		(x)
+#endif
+
+#ifndef dma_addr_canonical
+#define dma_addr_canonical(x)		(x)
+#endif
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __MEM_ENCRYPT_H__ */
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 4b5b83677e3f..c70d528594f2 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -84,7 +84,6 @@ struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	supported_cpus;
 	char		*name;
-	int		pmuver;
 	irqreturn_t	(*handle_irq)(struct arm_pmu *pmu);
 	void		(*enable)(struct perf_event *event);
 	void		(*disable)(struct perf_event *event);
@@ -102,18 +101,20 @@ struct arm_pmu {
 	int		(*map_event)(struct perf_event *event);
 	DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS);
 	bool		secure_access; /* 32-bit ARM only */
-#define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40
-	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
-#define ARMV8_PMUV3_EXT_COMMON_EVENT_BASE	0x4000
-	DECLARE_BITMAP(pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 	struct platform_device	*plat_device;
 	struct pmu_hw_events	__percpu *hw_events;
 	struct hlist_node	node;
 	struct notifier_block	cpu_pm_nb;
 	/* the attr_groups array must be NULL-terminated */
 	const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1];
-	/* store the PMMIR_EL1 to expose slots */
+
+	/* PMUv3 only */
+	int		pmuver;
 	u64		reg_pmmir;
+#define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40
+	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+#define ARMV8_PMUV3_EXT_COMMON_EVENT_BASE	0x4000
+	DECLARE_BITMAP(pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 
 	/* Only to be used by ACPI probing code */
 	unsigned long acpi_cpuid;
diff --git a/include/linux/topology.h b/include/linux/topology.h
index a1815f4395ab..24e715f0f6d2 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -240,6 +240,29 @@ static inline const struct cpumask *cpu_smt_mask(int cpu)
 }
 #endif
 
+#ifndef topology_is_primary_thread
+
+static inline bool topology_is_primary_thread(unsigned int cpu)
+{
+	/*
+	 * When disabling SMT, the primary thread of the SMT will remain
+	 * enabled/active. Architectures that have a special primary thread
+	 * (e.g. x86) need to override this function. Otherwise the first
+	 * thread in the SMT can be made the primary thread.
+	 *
+	 * The sibling cpumask of an offline CPU always contains the CPU
+	 * itself on architectures using the implementation of
+	 * CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology.
+	 * Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for
+	 * building their topology have to check whether to use this default
+	 * implementation or to override it.
+	 */
+	return cpu == cpumask_first(topology_sibling_cpumask(cpu));
+}
+#define topology_is_primary_thread topology_is_primary_thread
+
+#endif
+
 static inline const struct cpumask *cpu_cpu_mask(int cpu)
 {
 	return cpumask_of_node(cpu_to_node(cpu));