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

…el/git/arm64/linux

Pull arm64 updates from Will Deacon:

 - vDSO build improvements including support for building with BSD.

 - Cleanup to the AMU support code and initialisation rework to support
   cpufreq drivers built as modules.

 - Removal of synthetic frame record from exception stack when entering
   the kernel from EL0.

 - Add support for the TRNG firmware call introduced by Arm spec
   DEN0098.

 - Cleanup and refactoring across the board.

 - Avoid calling arch_get_random_seed_long() from
   add_interrupt_randomness()

 - Perf and PMU updates including support for Cortex-A78 and the v8.3
   SPE extensions.

 - Significant steps along the road to leaving the MMU enabled during
   kexec relocation.

 - Faultaround changes to initialise prefaulted PTEs as 'old' when
   hardware access-flag updates are supported, which drastically
   improves vmscan performance.

 - CPU errata updates for Cortex-A76 (#1463225) and Cortex-A55
   (#1024718)

 - Preparatory work for yielding the vector unit at a finer granularity
   in the crypto code, which in turn will one day allow us to defer
   softirq processing when it is in use.

 - Support for overriding CPU ID register fields on the command-line.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (85 commits)
  drivers/perf: Replace spin_lock_irqsave to spin_lock
  mm: filemap: Fix microblaze build failure with 'mmu_defconfig'
  arm64: Make CPU_BIG_ENDIAN depend on ld.bfd or ld.lld 13.0.0+
  arm64: cpufeatures: Allow disabling of Pointer Auth from the command-line
  arm64: Defer enabling pointer authentication on boot core
  arm64: cpufeatures: Allow disabling of BTI from the command-line
  arm64: Move "nokaslr" over to the early cpufeature infrastructure
  KVM: arm64: Document HVC_VHE_RESTART stub hypercall
  arm64: Make kvm-arm.mode={nvhe, protected} an alias of id_aa64mmfr1.vh=0
  arm64: Add an aliasing facility for the idreg override
  arm64: Honor VHE being disabled from the command-line
  arm64: Allow ID_AA64MMFR1_EL1.VH to be overridden from the command line
  arm64: cpufeature: Add an early command-line cpufeature override facility
  arm64: Extract early FDT mapping from kaslr_early_init()
  arm64: cpufeature: Use IDreg override in __read_sysreg_by_encoding()
  arm64: cpufeature: Add global feature override facility
  arm64: Move SCTLR_EL1 initialisation to EL-agnostic code
  arm64: Simplify init_el2_state to be non-VHE only
  arm64: Move VHE-specific SPE setup to mutate_to_vhe()
  arm64: Drop early setting of MDSCR_EL2.TPMS
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -373,6 +373,12 @@
 	arcrimi=	[HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
 			Format: <io>,<irq>,<nodeID>
 
+	arm64.nobti	[ARM64] Unconditionally disable Branch Target
+			Identification support
+
+	arm64.nopauth	[ARM64] Unconditionally disable Pointer Authentication
+			support
+
 	ataflop=	[HW,M68k]
 
 	atarimouse=	[HW,MOUSE] Atari Mouse
@@ -2252,6 +2258,9 @@
 	kvm-arm.mode=
 			[KVM,ARM] Select one of KVM/arm64's modes of operation.
 
+			nvhe: Standard nVHE-based mode, without support for
+			      protected guests.
+
 			protected: nVHE-based mode with support for guests whose
 				   state is kept private from the host.
 				   Not valid if the kernel is running in EL2.

Documentation/admin-guide/perf/arm-cmn.rst

@@ -17,7 +17,7 @@ PMU events
 ----------
 
 The PMU driver registers a single PMU device for the whole interconnect,
-see /sys/bus/event_source/devices/arm_cmn. Multi-chip systems may link
+see /sys/bus/event_source/devices/arm_cmn_0. Multi-chip systems may link
 more than one CMN together via external CCIX links - in this situation,
 each mesh counts its own events entirely independently, and additional
 PMU devices will be named arm_cmn_{1..n}.

Documentation/devicetree/bindings/arm/pmu.yaml

@@ -43,6 +43,7 @@ properties:
           - arm,cortex-a75-pmu
           - arm,cortex-a76-pmu
           - arm,cortex-a77-pmu
+          - arm,cortex-a78-pmu
           - arm,neoverse-e1-pmu
           - arm,neoverse-n1-pmu
           - brcm,vulcan-pmu

Documentation/virt/kvm/arm/hyp-abi.rst

@@ -58,6 +58,15 @@ these functions (see arch/arm{,64}/include/asm/virt.h):
   into place (arm64 only), and jump to the restart address while at HYP/EL2.
   This hypercall is not expected to return to its caller.
 
+* ::
+
+    x0 = HVC_VHE_RESTART (arm64 only)
+
+  Attempt to upgrade the kernel's exception level from EL1 to EL2 by enabling
+  the VHE mode. This is conditioned by the CPU supporting VHE, the EL2 MMU
+  being off, and VHE not being disabled by any other means (command line
+  option, for example).
+
 Any other value of r0/x0 triggers a hypervisor-specific handling,
 which is not documented here.
 

arch/arm/include/asm/archrandom.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARCHRANDOM_H
+#define _ASM_ARCHRANDOM_H
+
+static inline bool __init smccc_probe_trng(void)
+{
+	return false;
+}
+
+#endif /* _ASM_ARCHRANDOM_H */

arch/arm64/Kconfig

@@ -522,7 +522,7 @@ config ARM64_ERRATUM_1024718
 	help
 	  This option adds a workaround for ARM Cortex-A55 Erratum 1024718.
 
-	  Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect
+	  Affected Cortex-A55 cores (all revisions) could cause incorrect
 	  update of the hardware dirty bit when the DBM/AP bits are updated
 	  without a break-before-make. The workaround is to disable the usage
 	  of hardware DBM locally on the affected cores. CPUs not affected by
@@ -952,8 +952,9 @@ choice
 	  that is selected here.
 
 config CPU_BIG_ENDIAN
-       bool "Build big-endian kernel"
-       help
+	bool "Build big-endian kernel"
+	depends on !LD_IS_LLD || LLD_VERSION >= 130000
+	help
 	  Say Y if you plan on running a kernel with a big-endian userspace.
 
 config CPU_LITTLE_ENDIAN
@@ -1132,6 +1133,10 @@ config CRASH_DUMP
 
 	  For more details see Documentation/admin-guide/kdump/kdump.rst
 
+config TRANS_TABLE
+	def_bool y
+	depends on HIBERNATION
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN

arch/arm64/Makefile

@@ -188,10 +188,12 @@ ifeq ($(KBUILD_EXTMOD),)
 # this hack.
 prepare: vdso_prepare
 vdso_prepare: prepare0
-	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h
-	$(if $(CONFIG_COMPAT_VDSO),$(Q)$(MAKE) \
-		$(build)=arch/arm64/kernel/vdso32  \
-		include/generated/vdso32-offsets.h)
+	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso \
+	include/generated/vdso-offsets.h arch/arm64/kernel/vdso/vdso.so
+ifdef CONFIG_COMPAT_VDSO
+	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 \
+	include/generated/vdso32-offsets.h arch/arm64/kernel/vdso32/vdso.so
+endif
 endif
 
 define archhelp

arch/arm64/include/asm/archrandom.h

@@ -4,10 +4,26 @@
 
 #ifdef CONFIG_ARCH_RANDOM
 
+#include <linux/arm-smccc.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
 #include <asm/cpufeature.h>
 
+#define ARM_SMCCC_TRNG_MIN_VERSION	0x10000UL
+
+extern bool smccc_trng_available;
+
+static inline bool __init smccc_probe_trng(void)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_VERSION, &res);
+	if ((s32)res.a0 < 0)
+		return false;
+
+	return res.a0 >= ARM_SMCCC_TRNG_MIN_VERSION;
+}
+
 static inline bool __arm64_rndr(unsigned long *v)
 {
 	bool ok;
@@ -38,26 +54,55 @@ static inline bool __must_check arch_get_random_int(unsigned int *v)
 
 static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
+	struct arm_smccc_res res;
+
+	/*
+	 * We prefer the SMCCC call, since its semantics (return actual
+	 * hardware backed entropy) is closer to the idea behind this
+	 * function here than what even the RNDRSS register provides
+	 * (the output of a pseudo RNG freshly seeded by a TRNG).
+	 */
+	if (smccc_trng_available) {
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 64, &res);
+		if ((int)res.a0 >= 0) {
+			*v = res.a3;
+			return true;
+		}
+	}
+
 	/*
 	 * Only support the generic interface after we have detected
 	 * the system wide capability, avoiding complexity with the
 	 * cpufeature code and with potential scheduling between CPUs
 	 * with and without the feature.
 	 */
-	if (!cpus_have_const_cap(ARM64_HAS_RNG))
-		return false;
+	if (cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndr(v))
+		return true;
 
-	return __arm64_rndr(v);
+	return false;
 }
 
-
 static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
+	struct arm_smccc_res res;
 	unsigned long val;
-	bool ok = arch_get_random_seed_long(&val);
 
-	*v = val;
-	return ok;
+	if (smccc_trng_available) {
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 32, &res);
+		if ((int)res.a0 >= 0) {
+			*v = res.a3 & GENMASK(31, 0);
+			return true;
+		}
+	}
+
+	if (cpus_have_const_cap(ARM64_HAS_RNG)) {
+		if (__arm64_rndr(&val)) {
+			*v = val;
+			return true;
+		}
+	}
+
+	return false;
 }
 
 static inline bool __init __early_cpu_has_rndr(void)
@@ -72,12 +117,29 @@ arch_get_random_seed_long_early(unsigned long *v)
 {
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (!__early_cpu_has_rndr())
-		return false;
+	if (smccc_trng_available) {
+		struct arm_smccc_res res;
+
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 64, &res);
+		if ((int)res.a0 >= 0) {
+			*v = res.a3;
+			return true;
+		}
+	}
+
+	if (__early_cpu_has_rndr() && __arm64_rndr(v))
+		return true;
 
-	return __arm64_rndr(v);
+	return false;
 }
 #define arch_get_random_seed_long_early arch_get_random_seed_long_early
 
+#else /* !CONFIG_ARCH_RANDOM */
+
+static inline bool __init smccc_probe_trng(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_ARCH_RANDOM */
 #endif /* _ASM_ARCHRANDOM_H */

arch/arm64/include/asm/asm-uaccess.h

@@ -15,10 +15,10 @@
 	.macro	__uaccess_ttbr0_disable, tmp1
 	mrs	\tmp1, ttbr1_el1			// swapper_pg_dir
 	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
-	sub	\tmp1, \tmp1, #PAGE_SIZE		// reserved_pg_dir just before swapper_pg_dir
+	sub	\tmp1, \tmp1, #RESERVED_SWAPPER_OFFSET	// reserved_pg_dir
 	msr	ttbr0_el1, \tmp1			// set reserved TTBR0_EL1
 	isb
-	add	\tmp1, \tmp1, #PAGE_SIZE
+	add	\tmp1, \tmp1, #RESERVED_SWAPPER_OFFSET
 	msr	ttbr1_el1, \tmp1		// set reserved ASID
 	isb
 	.endm

arch/arm64/include/asm/assembler.h

@@ -675,6 +675,23 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	.endif
 	.endm
 
+/*
+ * Set SCTLR_EL1 to the passed value, and invalidate the local icache
+ * in the process. This is called when setting the MMU on.
+ */
+.macro set_sctlr_el1, reg
+	msr	sctlr_el1, \reg
+	isb
+	/*
+	 * Invalidate the local I-cache so that any instructions fetched
+	 * speculatively from the PoC are discarded, since they may have
+	 * been dynamically patched at the PoU.
+	 */
+	ic	iallu
+	dsb	nsh
+	isb
+.endm
+
 /*
  * Check whether to yield to another runnable task from kernel mode NEON code
  * (which runs with preemption disabled).
@@ -745,6 +762,22 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 .Lyield_out_\@ :
 	.endm
 
+	/*
+	 * Check whether preempt-disabled code should yield as soon as it
+	 * is able. This is the case if re-enabling preemption a single
+	 * time results in a preempt count of zero, and the TIF_NEED_RESCHED
+	 * flag is set. (Note that the latter is stored negated in the
+	 * top word of the thread_info::preempt_count field)
+	 */
+	.macro		cond_yield, lbl:req, tmp:req
+#ifdef CONFIG_PREEMPTION
+	get_current_task \tmp
+	ldr		\tmp, [\tmp, #TSK_TI_PREEMPT]
+	sub		\tmp, \tmp, #PREEMPT_DISABLE_OFFSET
+	cbz		\tmp, \lbl
+#endif
+	.endm
+
 /*
  * This macro emits a program property note section identifying
  * architecture features which require special handling, mainly for

arch/arm64/include/asm/cacheflush.h

@@ -30,11 +30,6 @@
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
  *	VIPT I-cache.
  *
- *	flush_cache_mm(mm)
- *
- *		Clean and invalidate all user space cache entries
- *		before a change of page tables.
- *
  *	flush_icache_range(start, end)
  *
  *		Ensure coherency between the I-cache and the D-cache in the

arch/arm64/include/asm/cpufeature.h

@@ -63,6 +63,11 @@ struct arm64_ftr_bits {
 	s64		safe_val; /* safe value for FTR_EXACT features */
 };
 
+struct arm64_ftr_override {
+	u64		val;
+	u64		mask;
+};
+
 /*
  * @arm64_ftr_reg - Feature register
  * @strict_mask		Bits which should match across all CPUs for sanity.
@@ -74,6 +79,7 @@ struct arm64_ftr_reg {
 	u64				user_mask;
 	u64				sys_val;
 	u64				user_val;
+	struct arm64_ftr_override	*override;
 	const struct arm64_ftr_bits	*ftr_bits;
 };
 
@@ -600,6 +606,7 @@ void __init setup_cpu_features(void);
 void check_local_cpu_capabilities(void);
 
 u64 read_sanitised_ftr_reg(u32 id);
+u64 __read_sysreg_by_encoding(u32 sys_id);
 
 static inline bool cpu_supports_mixed_endian_el0(void)
 {
@@ -811,6 +818,10 @@ static inline unsigned int get_vmid_bits(u64 mmfr1)
 	return 8;
 }
 
+extern struct arm64_ftr_override id_aa64mmfr1_override;
+extern struct arm64_ftr_override id_aa64pfr1_override;
+extern struct arm64_ftr_override id_aa64isar1_override;
+
 u32 get_kvm_ipa_limit(void);
 void dump_cpu_features(void);