arm64 updates for 5.12

- 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.
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAmAmwZcQHHdpbGxAa2Vy
 bmVsLm9yZwAKCRC3rHDchMFjNLA1B/0XMwWUhmJ4ZPK4sr28YWHNGLuCFHDgkMKU
 dEmS806OF9d0J7fTczGsKdS4IKtXWko67Z0UGiPIStwfm0itSW2Zgbo9KZeDPqPI
 fH0s23nQKxUMyNW7b9p4cTV3YuGVMZSBoMug2jU2DEDpSqeGBk09NPi6inERBCz/
 qZxcqXTKxXbtOY56eJmq09UlFZiwfONubzuCrrUH7LU8ZBSInM/6Q4us/oVm4zYI
 Pnv996mtL4UxRqq/KoU9+cQ1zsI01kt9/coHwfCYvSpZEVAnTWtfECsJ690tr3mF
 TSKQLvOzxbDtU+HcbkNVKW0A38EIO1xXr8yXW9SJx6BJBkyb24xo
 =IwMb
 -----END PGP SIGNATURE-----

Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/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
@@ -953,6 +953,7 @@ choice
 
 config CPU_BIG_ENDIAN
 	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.
 
@@ -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
+	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso \
-	$(if $(CONFIG_COMPAT_VDSO),$(Q)$(MAKE) \
+	include/generated/vdso-offsets.h arch/arm64/kernel/vdso/vdso.so
-		$(build)=arch/arm64/kernel/vdso32  \
+ifdef CONFIG_COMPAT_VDSO
-		include/generated/vdso32-offsets.h)
+	$(Q)$(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))
+	if (cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndr(v))
+		return true;
+
 	return false;
-
-	return __arm64_rndr(v);
 }
 
-
 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);
 
+	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 ok;
+			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())
+	if (smccc_trng_available) {
-		return false;
+		struct arm_smccc_res res;
 
-	return __arm64_rndr(v);
+		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 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);
 

arch/arm64/include/asm/el2_setup.h

@@ -32,46 +32,39 @@
  * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in
  * EL2.
  */
-.macro __init_el2_timers mode
+.macro __init_el2_timers
-.ifeqs "\mode", "nvhe"
 	mrs	x0, cnthctl_el2
 	orr	x0, x0, #3			// Enable EL1 physical timers
 	msr	cnthctl_el2, x0
-.endif
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 .endm
 
-.macro __init_el2_debug mode
+.macro __init_el2_debug
 	mrs	x1, id_aa64dfr0_el1
 	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	x0, #1
-	b.lt	1f				// Skip if no PMU present
+	b.lt	.Lskip_pmu_\@			// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-1:
+.Lskip_pmu_\@:
 	csel	x2, xzr, x0, lt			// all PMU counters from EL1
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
-	cbz	x0, 3f				// Skip if SPE not present
+	cbz	x0, .Lskip_spe_\@		// Skip if SPE not present
 
-.ifeqs "\mode", "nvhe"
 	mrs_s	x0, SYS_PMBIDR_EL1              // If SPE available at EL2,
 	and	x0, x0, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
-	cbnz	x0, 2f				// then permit sampling of physical
+	cbnz	x0, .Lskip_spe_el2_\@		// then permit sampling of physical
 	mov	x0, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
 		      1 << SYS_PMSCR_EL2_PA_SHIFT)
 	msr_s	SYS_PMSCR_EL2, x0		// addresses and physical counter
-2:
+.Lskip_spe_el2_\@:
 	mov	x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
 	orr	x2, x2, x0			// If we don't have VHE, then
 						// use EL1&0 translation.
-.else
-	orr	x2, x2, #MDCR_EL2_TPMS		// For VHE, use EL2 translation
-						// and disable access from EL1
-.endif
 
-3:
+.Lskip_spe_\@:
 	msr	mdcr_el2, x2			// Configure debug traps
 .endm
 
@@ -79,9 +72,9 @@
 .macro __init_el2_lor
 	mrs	x1, id_aa64mmfr1_el1
 	ubfx	x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4
-	cbz	x0, 1f
+	cbz	x0, .Lskip_lor_\@
 	msr_s	SYS_LORC_EL1, xzr
-1:
+.Lskip_lor_\@:
 .endm
 
 /* Stage-2 translation */
@@ -93,7 +86,7 @@
 .macro __init_el2_gicv3
 	mrs	x0, id_aa64pfr0_el1
 	ubfx	x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
-	cbz	x0, 1f
+	cbz	x0, .Lskip_gicv3_\@
 
 	mrs_s	x0, SYS_ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
@@ -103,7 +96,7 @@
 	mrs_s	x0, SYS_ICC_SRE_EL2		// Read SRE back,
 	tbz	x0, #0, 1f			// and check that it sticks
 	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
-1:
+.Lskip_gicv3_\@:
 .endm
 
 .macro __init_el2_hstr
@@ -128,14 +121,14 @@
 .macro __init_el2_nvhe_sve
 	mrs	x1, id_aa64pfr0_el1
 	ubfx	x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4
-	cbz	x1, 1f
+	cbz	x1, .Lskip_sve_\@
 
 	bic	x0, x0, #CPTR_EL2_TZ		// Also disable SVE traps
 	msr	cptr_el2, x0			// Disable copro. traps to EL2
 	isb
 	mov	x1, #ZCR_ELx_LEN_MASK		// SVE: Enable full vector
 	msr_s	SYS_ZCR_EL2, x1			// length for EL1.
-1:
+.Lskip_sve_\@:
 .endm
 
 .macro __init_el2_nvhe_prepare_eret
@@ -145,37 +138,24 @@
 
 /**
  * Initialize EL2 registers to sane values. This should be called early on all
- * cores that were booted in EL2.
+ * cores that were booted in EL2. Note that everything gets initialised as
+ * if VHE was not evailable. The kernel context will be upgraded to VHE
+ * if possible later on in the boot process
  *
  * Regs: x0, x1 and x2 are clobbered.
  */
-.macro init_el2_state mode
+.macro init_el2_state
-.ifnes "\mode", "vhe"
-.ifnes "\mode", "nvhe"
-.error "Invalid 'mode' argument"
-.endif
-.endif
-
 	__init_el2_sctlr
-	__init_el2_timers \mode
+	__init_el2_timers
-	__init_el2_debug \mode
+	__init_el2_debug
 	__init_el2_lor
 	__init_el2_stage2
 	__init_el2_gicv3
 	__init_el2_hstr
-
-	/*
-	 * When VHE is not in use, early init of EL2 needs to be done here.
-	 * When VHE _is_ in use, EL1 will not be used in the host and
-	 * requires no configuration, and all non-hyp-specific EL2 setup
-	 * will be done via the _EL1 system register aliases in __cpu_setup.
-	 */
-.ifeqs "\mode", "nvhe"
 	__init_el2_nvhe_idregs
 	__init_el2_nvhe_cptr
 	__init_el2_nvhe_sve
 	__init_el2_nvhe_prepare_eret
-.endif
 .endm
 
 #endif /* __ARM_KVM_INIT_H__ */

arch/arm64/include/asm/kexec.h

@@ -90,18 +90,19 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
-#ifdef CONFIG_KEXEC_FILE
 #define ARCH_HAS_KIMAGE_ARCH
 
 struct kimage_arch {
 	void *dtb;
-	unsigned long dtb_mem;
+	phys_addr_t dtb_mem;
+	phys_addr_t kern_reloc;
 	/* Core ELF header buffer */
 	void *elf_headers;
 	unsigned long elf_headers_mem;
 	unsigned long elf_headers_sz;
 };
 
+#ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops kexec_image_ops;
 
 struct kimage;

arch/arm64/include/asm/kvm_asm.h

@@ -199,12 +199,6 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
-#if defined(GCC_VERSION) && GCC_VERSION < 50000
-#define SYM_CONSTRAINT	"i"
-#else
-#define SYM_CONSTRAINT	"S"
-#endif
-
 /*
  * Obtain the PC-relative address of a kernel symbol
  * s: symbol
@@ -221,7 +215,7 @@ extern u32 __kvm_get_mdcr_el2(void);
 		typeof(s) *addr;					\
 		asm("adrp	%0, %1\n"				\
 		    "add	%0, %0, :lo12:%1\n"			\
-		    : "=r" (addr) : SYM_CONSTRAINT (&s));		\
+		    : "=r" (addr) : "S" (&s));				\
 		addr;							\
 	})
 

arch/arm64/include/asm/memory.h

@@ -159,6 +159,18 @@
 #define IOREMAP_MAX_ORDER	(PMD_SHIFT)
 #endif
 
+/*
+ *  Open-coded (swapper_pg_dir - reserved_pg_dir) as this cannot be calculated
+ *  until link time.
+ */
+#define RESERVED_SWAPPER_OFFSET	(PAGE_SIZE)
+
+/*
+ *  Open-coded (swapper_pg_dir - tramp_pg_dir) as this cannot be calculated
+ *  until link time.
+ */
+#define TRAMP_SWAPPER_OFFSET	(2 * PAGE_SIZE)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/bitops.h>

arch/arm64/include/asm/mmu_context.h

@@ -81,16 +81,15 @@ static inline bool __cpu_uses_extended_idmap_level(void)
 }
 
 /*
- * Set TCR.T0SZ to its default value (based on VA_BITS)
+ * Ensure TCR.T0SZ is set to the provided value.
  */
 static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
 {
-	unsigned long tcr;
+	unsigned long tcr = read_sysreg(tcr_el1);
 
-	if (!__cpu_uses_extended_idmap())
+	if ((tcr & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET == t0sz)
 		return;
 
-	tcr = read_sysreg(tcr_el1);
 	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= t0sz << TCR_T0SZ_OFFSET;
 	write_sysreg(tcr, tcr_el1);

arch/arm64/include/asm/pgtable.h

@@ -982,6 +982,16 @@ static inline bool arch_faults_on_old_pte(void)
 }
 #define arch_faults_on_old_pte		arch_faults_on_old_pte
 
+/*
+ * Experimentally, it's cheap to set the access flag in hardware and we
+ * benefit from prefaulting mappings as 'old' to start with.
+ */
+static inline bool arch_wants_old_prefaulted_pte(void)
+{
+	return !arch_faults_on_old_pte();
+}
+#define arch_wants_old_prefaulted_pte	arch_wants_old_prefaulted_pte
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */

arch/arm64/include/asm/pointer_auth.h

@@ -76,6 +76,15 @@ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 	return ptrauth_clear_pac(ptr);
 }
 
+static __always_inline void ptrauth_enable(void)
+{
+	if (!system_supports_address_auth())
+		return;
+	sysreg_clear_set(sctlr_el1, 0, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB |
+					SCTLR_ELx_ENDA | SCTLR_ELx_ENDB));
+	isb();
+}
+
 #define ptrauth_thread_init_user(tsk)					\
 	ptrauth_keys_init_user(&(tsk)->thread.keys_user)
 #define ptrauth_thread_init_kernel(tsk)					\
@@ -84,6 +93,7 @@ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 	ptrauth_keys_switch_kernel(&(tsk)->thread.keys_kernel)
 
 #else /* CONFIG_ARM64_PTR_AUTH */
+#define ptrauth_enable()
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
 #define ptrauth_strip_insn_pac(lr)	(lr)
 #define ptrauth_thread_init_user(tsk)

arch/arm64/include/asm/setup.h

@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef __ARM64_ASM_SETUP_H
+#define __ARM64_ASM_SETUP_H
+
+#include <uapi/asm/setup.h>
+
+void *get_early_fdt_ptr(void);
+void early_fdt_map(u64 dt_phys);
+
+#endif

arch/arm64/include/asm/sparsemem.h

@@ -7,7 +7,26 @@
 
 #ifdef CONFIG_SPARSEMEM
 #define MAX_PHYSMEM_BITS	CONFIG_ARM64_PA_BITS
-#define SECTION_SIZE_BITS	30
+
-#endif
+/*
+ * Section size must be at least 512MB for 64K base
+ * page size config. Otherwise it will be less than
+ * (MAX_ORDER - 1) and the build process will fail.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define SECTION_SIZE_BITS 29
+
+#else
+
+/*
+ * Section size must be at least 128MB for 4K base
+ * page size config. Otherwise PMD based huge page
+ * entries could not be created for vmemmap mappings.
+ * 16K follows 4K for simplicity.
+ */
+#define SECTION_SIZE_BITS 27
+#endif /* CONFIG_ARM64_64K_PAGES */
+
+#endif /* CONFIG_SPARSEMEM*/
 
 #endif

arch/arm64/include/asm/stackprotector.h

@@ -41,6 +41,7 @@ static __always_inline void boot_init_stack_canary(void)
 #endif
 	ptrauth_thread_init_kernel(current);
 	ptrauth_thread_switch_kernel(current);
+	ptrauth_enable();
 }
 
 #endif	/* _ASM_STACKPROTECTOR_H */

arch/arm64/include/asm/sysreg.h

@@ -291,7 +291,11 @@
 #define SYS_PMSFCR_EL1_ST_SHIFT		18
 
 #define SYS_PMSEVFR_EL1			sys_reg(3, 0, 9, 9, 5)
-#define SYS_PMSEVFR_EL1_RES0		0x0000ffff00ff0f55UL
+#define SYS_PMSEVFR_EL1_RES0_8_2	\
+	(GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\
+	 BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0))
+#define SYS_PMSEVFR_EL1_RES0_8_3	\
+	(SYS_PMSEVFR_EL1_RES0_8_2 & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11)))
 
 #define SYS_PMSLATFR_EL1		sys_reg(3, 0, 9, 9, 6)
 #define SYS_PMSLATFR_EL1_MINLAT_SHIFT	0
@@ -844,6 +848,9 @@
 #define ID_AA64DFR0_PMUVER_8_5		0x6
 #define ID_AA64DFR0_PMUVER_IMP_DEF	0xf
 
+#define ID_AA64DFR0_PMSVER_8_2		0x1
+#define ID_AA64DFR0_PMSVER_8_3		0x2
+
 #define ID_DFR0_PERFMON_SHIFT		24
 
 #define ID_DFR0_PERFMON_8_1		0x4

arch/arm64/include/asm/trans_pgd.h

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2020, Microsoft Corporation.
+ * Pavel Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#ifndef _ASM_TRANS_TABLE_H
+#define _ASM_TRANS_TABLE_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+#include <asm/pgtable-types.h>
+
+/*
+ * trans_alloc_page
+ *	- Allocator that should return exactly one zeroed page, if this
+ *	  allocator fails, trans_pgd_create_copy() and trans_pgd_map_page()
+ *	  return -ENOMEM error.
+ *
+ * trans_alloc_arg
+ *	- Passed to trans_alloc_page as an argument
+ */
+
+struct trans_pgd_info {
+	void * (*trans_alloc_page)(void *arg);
+	void *trans_alloc_arg;
+};
+
+int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **trans_pgd,
+			  unsigned long start, unsigned long end);
+
+int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
+		       void *page, unsigned long dst_addr, pgprot_t pgprot);
+
+int trans_pgd_idmap_page(struct trans_pgd_info *info, phys_addr_t *trans_ttbr0,
+			 unsigned long *t0sz, void *page);
+
+#endif /* _ASM_TRANS_TABLE_H */

arch/arm64/include/asm/uaccess.h

@@ -87,7 +87,7 @@ static inline void __uaccess_ttbr0_disable(void)
 	ttbr = read_sysreg(ttbr1_el1);
 	ttbr &= ~TTBR_ASID_MASK;
 	/* reserved_pg_dir placed before swapper_pg_dir */
-	write_sysreg(ttbr - PAGE_SIZE, ttbr0_el1);
+	write_sysreg(ttbr - RESERVED_SWAPPER_OFFSET, ttbr0_el1);
 	isb();
 	/* Set reserved ASID */
 	write_sysreg(ttbr, ttbr1_el1);

arch/arm64/include/asm/virt.h

@@ -35,8 +35,13 @@
  */
 #define HVC_RESET_VECTORS 2
 
+/*
+ * HVC_VHE_RESTART - Upgrade the CPU from EL1 to EL2, if possible
+ */
+#define HVC_VHE_RESTART	3
+
 /* Max number of HYP stub hypercalls */
-#define HVC_STUB_HCALL_NR 3
+#define HVC_STUB_HCALL_NR 4
 
 /* Error returned when an invalid stub number is passed into x0 */
 #define HVC_STUB_ERR	0xbadca11

arch/arm64/kernel/Makefile

@@ -17,7 +17,7 @@ obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
-			   syscall.o proton-pack.o
+			   syscall.o proton-pack.o idreg-override.o
 
 targets			+= efi-entry.o
 
@@ -59,9 +59,10 @@ obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
 obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
 obj-$(CONFIG_ARM64_MTE)			+= mte.o
+obj-y					+= vdso-wrap.o
+obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o
 
-obj-y					+= vdso/ probes/
+obj-y					+= probes/
-obj-$(CONFIG_COMPAT_VDSO)		+= vdso32/
 head-y					:= head.o
 extra-y					+= $(head-y) vmlinux.lds
 

arch/arm64/kernel/alternative.c

@@ -17,7 +17,7 @@
 #include <asm/sections.h>
 #include <linux/stop_machine.h>
 
-#define __ALT_PTR(a,f)		((void *)&(a)->f + (a)->f)
+#define __ALT_PTR(a, f)		((void *)&(a)->f + (a)->f)
 #define ALT_ORIG_PTR(a)		__ALT_PTR(a, orig_offset)
 #define ALT_REPL_PTR(a)		__ALT_PTR(a, alt_offset)
 

arch/arm64/kernel/asm-offsets.c

@@ -99,6 +99,9 @@ int main(void)
   DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
   BLANK();
+  DEFINE(FTR_OVR_VAL_OFFSET,	offsetof(struct arm64_ftr_override, val));
+  DEFINE(FTR_OVR_MASK_OFFSET,	offsetof(struct arm64_ftr_override, mask));
+  BLANK();
 #ifdef CONFIG_KVM
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));

arch/arm64/kernel/cpu_errata.c

@@ -107,8 +107,6 @@ cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 }
 
 #ifdef CONFIG_ARM64_ERRATUM_1463225
-DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
-
 static bool
 has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry,
 			       int scope)

arch/arm64/kernel/cpufeature.c

@@ -352,9 +352,12 @@ static const struct arm64_ftr_bits ftr_ctr[] = {
 	ARM64_FTR_END,
 };
 
+static struct arm64_ftr_override __ro_after_init no_override = { };
+
 struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
 	.name		= "SYS_CTR_EL0",
-	.ftr_bits	= ftr_ctr
+	.ftr_bits	= ftr_ctr,
+	.override	= &no_override,
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
@@ -544,13 +547,20 @@ static const struct arm64_ftr_bits ftr_raz[] = {
 	ARM64_FTR_END,
 };
 
-#define ARM64_FTR_REG(id, table) {		\
+#define ARM64_FTR_REG_OVERRIDE(id, table, ovr) {		\
 		.sys_id = id,					\
 		.reg = 	&(struct arm64_ftr_reg){		\
 			.name = #id,				\
+			.override = (ovr),			\
 			.ftr_bits = &((table)[0]),		\
 	}}
 
+#define ARM64_FTR_REG(id, table) ARM64_FTR_REG_OVERRIDE(id, table, &no_override)
+
+struct arm64_ftr_override __ro_after_init id_aa64mmfr1_override;
+struct arm64_ftr_override __ro_after_init id_aa64pfr1_override;
+struct arm64_ftr_override __ro_after_init id_aa64isar1_override;
+
 static const struct __ftr_reg_entry {
 	u32			sys_id;
 	struct arm64_ftr_reg 	*reg;
@@ -585,7 +595,8 @@ static const struct __ftr_reg_entry {
 
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
-	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
+	ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1,
+			       &id_aa64pfr1_override),
 	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
@@ -594,11 +605,13 @@ static const struct __ftr_reg_entry {
 
 	/* Op1 = 0, CRn = 0, CRm = 6 */
 	ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0),
-	ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1),
+	ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1,
+			       &id_aa64isar1_override),
 
 	/* Op1 = 0, CRn = 0, CRm = 7 */
 	ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0),
-	ARM64_FTR_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1),
+	ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1,
+			       &id_aa64mmfr1_override),
 	ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
 
 	/* Op1 = 0, CRn = 1, CRm = 2 */
@@ -770,6 +783,33 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
 	for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
 		u64 ftr_mask = arm64_ftr_mask(ftrp);
 		s64 ftr_new = arm64_ftr_value(ftrp, new);
+		s64 ftr_ovr = arm64_ftr_value(ftrp, reg->override->val);
+
+		if ((ftr_mask & reg->override->mask) == ftr_mask) {
+			s64 tmp = arm64_ftr_safe_value(ftrp, ftr_ovr, ftr_new);
+			char *str = NULL;
+
+			if (ftr_ovr != tmp) {
+				/* Unsafe, remove the override */
+				reg->override->mask &= ~ftr_mask;
+				reg->override->val &= ~ftr_mask;
+				tmp = ftr_ovr;
+				str = "ignoring override";
+			} else if (ftr_new != tmp) {
+				/* Override was valid */
+				ftr_new = tmp;
+				str = "forced";
+			} else if (ftr_ovr == tmp) {
+				/* Override was the safe value */
+				str = "already set";
+			}
+
+			if (str)
+				pr_warn("%s[%d:%d]: %s to %llx\n",
+					reg->name,
+					ftrp->shift + ftrp->width - 1,
+					ftrp->shift, str, tmp);
+		}
 
 		val = arm64_ftr_set_value(ftrp, val, ftr_new);
 
@@ -1115,14 +1155,17 @@ u64 read_sanitised_ftr_reg(u32 id)
 EXPORT_SYMBOL_GPL(read_sanitised_ftr_reg);
 
 #define read_sysreg_case(r)	\
-	case r:		return read_sysreg_s(r)
+	case r:		val = read_sysreg_s(r); break;
 
 /*
  * __read_sysreg_by_encoding() - Used by a STARTING cpu before cpuinfo is populated.
  * Read the system register on the current CPU
  */
-static u64 __read_sysreg_by_encoding(u32 sys_id)
+u64 __read_sysreg_by_encoding(u32 sys_id)
 {
+	struct arm64_ftr_reg *regp;
+	u64 val;
+
 	switch (sys_id) {
 	read_sysreg_case(SYS_ID_PFR0_EL1);
 	read_sysreg_case(SYS_ID_PFR1_EL1);
@@ -1165,6 +1208,14 @@ static u64 __read_sysreg_by_encoding(u32 sys_id)
 		BUG();
 		return 0;
 	}
+
+	regp  = get_arm64_ftr_reg(sys_id);
+	if (regp) {
+		val &= ~regp->override->mask;
+		val |= (regp->override->val & regp->override->mask);
+	}
+
+	return val;
 }
 
 #include <linux/irqchip/arm-gic-v3.h>
@@ -1455,7 +1506,7 @@ static bool cpu_has_broken_dbm(void)
 	/* List of CPUs which have broken DBM support. */
 	static const struct midr_range cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1024718
-		MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 1, 0),  // A55 r0p0 -r1p0
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 		/* Kryo4xx Silver (rdpe => r1p0) */
 		MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe),
 #endif

arch/arm64/kernel/entry-common.c

@@ -109,6 +109,55 @@ asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
 		exit_to_kernel_mode(regs);
 }
 
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+static DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
+
+static void cortex_a76_erratum_1463225_svc_handler(void)
+{
+	u32 reg, val;
+
+	if (!unlikely(test_thread_flag(TIF_SINGLESTEP)))
+		return;
+
+	if (!unlikely(this_cpu_has_cap(ARM64_WORKAROUND_1463225)))
+		return;
+
+	__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 1);
+	reg = read_sysreg(mdscr_el1);
+	val = reg | DBG_MDSCR_SS | DBG_MDSCR_KDE;
+	write_sysreg(val, mdscr_el1);
+	asm volatile("msr daifclr, #8");
+	isb();
+
+	/* We will have taken a single-step exception by this point */
+
+	write_sysreg(reg, mdscr_el1);
+	__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0);
+}
+
+static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+{
+	if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa))
+		return false;
+
+	/*
+	 * We've taken a dummy step exception from the kernel to ensure
+	 * that interrupts are re-enabled on the syscall path. Return back
+	 * to cortex_a76_erratum_1463225_svc_handler() with debug exceptions
+	 * masked so that we can safely restore the mdscr and get on with
+	 * handling the syscall.
+	 */
+	regs->pstate |= PSR_D_BIT;
+	return true;
+}
+#else /* CONFIG_ARM64_ERRATUM_1463225 */
+static void cortex_a76_erratum_1463225_svc_handler(void) { }
+static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+{
+	return false;
+}
+#endif /* CONFIG_ARM64_ERRATUM_1463225 */
+
 static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr)
 {
 	unsigned long far = read_sysreg(far_el1);
@@ -186,6 +235,7 @@ static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr)
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 
 	arm64_enter_el1_dbg(regs);
+	if (!cortex_a76_erratum_1463225_debug_handler(regs))
 		do_debug_exception(far, esr, regs);
 	arm64_exit_el1_dbg(regs);
 }
@@ -362,6 +412,7 @@ static void noinstr el0_svc(struct pt_regs *regs)
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 
 	enter_from_user_mode();
+	cortex_a76_erratum_1463225_svc_handler();
 	do_el0_svc(regs);
 }
 
@@ -439,6 +490,7 @@ static void noinstr el0_svc_compat(struct pt_regs *regs)
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 
 	enter_from_user_mode();
+	cortex_a76_erratum_1463225_svc_handler();
 	do_el0_svc_compat(regs);
 }
 

arch/arm64/kernel/entry.S

@@ -261,16 +261,16 @@ alternative_else_nop_endif
 	stp	lr, x21, [sp, #S_LR]
 
 	/*
-	 * In order to be able to dump the contents of struct pt_regs at the
+	 * For exceptions from EL0, terminate the callchain here.
-	 * time the exception was taken (in case we attempt to walk the call
+	 * For exceptions from EL1, create a synthetic frame record so the
-	 * stack later), chain it together with the stack frames.
+	 * interrupted code shows up in the backtrace.
 	 */
 	.if \el == 0
-	stp	xzr, xzr, [sp, #S_STACKFRAME]
+	mov	x29, xzr
 	.else
 	stp	x29, x22, [sp, #S_STACKFRAME]
-	.endif
 	add	x29, sp, #S_STACKFRAME
+	.endif
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 alternative_if_not ARM64_HAS_PAN
@@ -805,7 +805,7 @@ SYM_CODE_END(ret_to_user)
 	// Move from tramp_pg_dir to swapper_pg_dir
 	.macro tramp_map_kernel, tmp
 	mrs	\tmp, ttbr1_el1
-	add	\tmp, \tmp, #(2 * PAGE_SIZE)
+	add	\tmp, \tmp, #TRAMP_SWAPPER_OFFSET
 	bic	\tmp, \tmp, #USER_ASID_FLAG
 	msr	ttbr1_el1, \tmp
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
@@ -825,7 +825,7 @@ alternative_else_nop_endif
 	// Move from swapper_pg_dir to tramp_pg_dir
 	.macro tramp_unmap_kernel, tmp
 	mrs	\tmp, ttbr1_el1
-	sub	\tmp, \tmp, #(2 * PAGE_SIZE)
+	sub	\tmp, \tmp, #TRAMP_SWAPPER_OFFSET
 	orr	\tmp, \tmp, #USER_ASID_FLAG
 	msr	ttbr1_el1, \tmp
 	/*

arch/arm64/kernel/head.S

@@ -404,10 +404,6 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	adr_l	x5, init_task
 	msr	sp_el0, x5			// Save thread_info
 
-#ifdef CONFIG_ARM64_PTR_AUTH
-	__ptrauth_keys_init_cpu	x5, x6, x7, x8
-#endif
-
 	adr_l	x8, vectors			// load VBAR_EL1 with virtual
 	msr	vbar_el1, x8			// vector table address
 	isb
@@ -436,10 +432,12 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	bl	kasan_early_init
 #endif
+	mov	x0, x21				// pass FDT address in x0
+	bl	early_fdt_map			// Try mapping the FDT early
+	bl	init_feature_override		// Parse cpu feature overrides
 #ifdef CONFIG_RANDOMIZE_BASE
 	tst	x23, ~(MIN_KIMG_ALIGN - 1)	// already running randomized?
 	b.ne	0f
-	mov	x0, x21				// pass FDT address in x0
 	bl	kaslr_early_init		// parse FDT for KASLR options
 	cbz	x0, 0f				// KASLR disabled? just proceed
 	orr	x23, x23, x0			// record KASLR offset
@@ -447,6 +445,7 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	ret					// to __primary_switch()
 0:
 #endif
+	bl	switch_to_vhe			// Prefer VHE if possible
 	add	sp, sp, #16
 	mov	x29, #0
 	mov	x30, #0
@@ -478,13 +477,14 @@ EXPORT_SYMBOL(kimage_vaddr)
  * booted in EL1 or EL2 respectively.
  */
 SYM_FUNC_START(init_kernel_el)
+	mov_q	x0, INIT_SCTLR_EL1_MMU_OFF
+	msr	sctlr_el1, x0
+
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
 	b.eq	init_el2
 
 SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
-	mov_q	x0, INIT_SCTLR_EL1_MMU_OFF
-	msr	sctlr_el1, x0
 	isb
 	mov_q	x0, INIT_PSTATE_EL1
 	msr	spsr_el1, x0
@@ -493,50 +493,11 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
 	eret
 
 SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
-#ifdef CONFIG_ARM64_VHE
-	/*
-	 * Check for VHE being present. x2 being non-zero indicates that we
-	 * do have VHE, and that the kernel is intended to run at EL2.
-	 */
-	mrs	x2, id_aa64mmfr1_el1
-	ubfx	x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4
-#else
-	mov	x2, xzr
-#endif
-	cbz	x2, init_el2_nvhe
-
-	/*
-	 * When VHE _is_ in use, EL1 will not be used in the host and
-	 * requires no configuration, and all non-hyp-specific EL2 setup
-	 * will be done via the _EL1 system register aliases in __cpu_setup.
-	 */
-	mov_q	x0, HCR_HOST_VHE_FLAGS
-	msr	hcr_el2, x0
-	isb
-
-	init_el2_state vhe
-
-	isb
-
-	mov_q	x0, INIT_PSTATE_EL2
-	msr	spsr_el2, x0
-	msr	elr_el2, lr
-	mov	w0, #BOOT_CPU_MODE_EL2
-	eret
-
-SYM_INNER_LABEL(init_el2_nvhe, SYM_L_LOCAL)
-	/*
-	 * When VHE is not in use, early init of EL2 and EL1 needs to be
-	 * done here.
-	 */
-	mov_q	x0, INIT_SCTLR_EL1_MMU_OFF
-	msr	sctlr_el1, x0
-
 	mov_q	x0, HCR_HOST_NVHE_FLAGS
 	msr	hcr_el2, x0
 	isb
 
-	init_el2_state nvhe
+	init_el2_state
 
 	/* Hypervisor stub */
 	adr_l	x0, __hyp_stub_vectors
@@ -623,6 +584,7 @@ SYM_FUNC_START_LOCAL(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
 	 */
+	bl	switch_to_vhe
 	bl	__cpu_secondary_check52bitva
 	bl	__cpu_setup			// initialise processor
 	adrp	x1, swapper_pg_dir
@@ -703,16 +665,9 @@ SYM_FUNC_START(__enable_mmu)
 	offset_ttbr1 x1, x3
 	msr	ttbr1_el1, x1			// load TTBR1
 	isb
-	msr	sctlr_el1, x0
+
-	isb
+	set_sctlr_el1	x0
-	/*
+
-	 * 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
 	ret
 SYM_FUNC_END(__enable_mmu)
 
@@ -883,11 +838,7 @@ SYM_FUNC_START_LOCAL(__primary_switch)
 	tlbi	vmalle1				// Remove any stale TLB entries
 	dsb	nsh
 
-	msr	sctlr_el1, x19			// re-enable the MMU
+	set_sctlr_el1	x19			// re-enable the MMU
-	isb
-	ic	iallu				// flush instructions fetched
-	dsb	nsh				// via old mapping
-	isb
 
 	bl	__relocate_kernel
 #endif

arch/arm64/kernel/hibernate.c

@@ -16,7 +16,6 @@
 #define pr_fmt(x) "hibernate: " x
 #include <linux/cpu.h>
 #include <linux/kvm_host.h>
-#include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/sched.h>
 #include <linux/suspend.h>
@@ -31,13 +30,12 @@
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
 #include <asm/smp.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/sysreg.h>
+#include <asm/trans_pgd.h>
 #include <asm/virt.h>
 
 /*
@@ -178,52 +176,9 @@ int arch_hibernation_header_restore(void *addr)
 }
 EXPORT_SYMBOL(arch_hibernation_header_restore);
 
-static int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
+static void *hibernate_page_alloc(void *arg)
-		       unsigned long dst_addr,
-		       pgprot_t pgprot)
 {
-	pgd_t *pgdp;
+	return (void *)get_safe_page((__force gfp_t)(unsigned long)arg);
-	p4d_t *p4dp;
-	pud_t *pudp;
-	pmd_t *pmdp;
-	pte_t *ptep;
-
-	pgdp = pgd_offset_pgd(trans_pgd, dst_addr);
-	if (pgd_none(READ_ONCE(*pgdp))) {
-		pudp = (void *)get_safe_page(GFP_ATOMIC);
-		if (!pudp)
-			return -ENOMEM;
-		pgd_populate(&init_mm, pgdp, pudp);
-	}
-
-	p4dp = p4d_offset(pgdp, dst_addr);
-	if (p4d_none(READ_ONCE(*p4dp))) {
-		pudp = (void *)get_safe_page(GFP_ATOMIC);
-		if (!pudp)
-			return -ENOMEM;
-		p4d_populate(&init_mm, p4dp, pudp);
-	}
-
-	pudp = pud_offset(p4dp, dst_addr);
-	if (pud_none(READ_ONCE(*pudp))) {
-		pmdp = (void *)get_safe_page(GFP_ATOMIC);
-		if (!pmdp)
-			return -ENOMEM;
-		pud_populate(&init_mm, pudp, pmdp);
-	}
-
-	pmdp = pmd_offset(pudp, dst_addr);
-	if (pmd_none(READ_ONCE(*pmdp))) {
-		ptep = (void *)get_safe_page(GFP_ATOMIC);
-		if (!ptep)
-			return -ENOMEM;
-		pmd_populate_kernel(&init_mm, pmdp, ptep);
-	}
-
-	ptep = pte_offset_kernel(pmdp, dst_addr);
-	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
-
-	return 0;
 }
 
 /*
@@ -239,11 +194,16 @@ static int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
  * page system.
  */
 static int create_safe_exec_page(void *src_start, size_t length,
-				 unsigned long dst_addr,
 				 phys_addr_t *phys_dst_addr)
 {
+	struct trans_pgd_info trans_info = {
+		.trans_alloc_page	= hibernate_page_alloc,
+		.trans_alloc_arg	= (__force void *)GFP_ATOMIC,
+	};
+
 	void *page = (void *)get_safe_page(GFP_ATOMIC);
-	pgd_t *trans_pgd;
+	phys_addr_t trans_ttbr0;
+	unsigned long t0sz;
 	int rc;
 
 	if (!page)
@@ -251,13 +211,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 
 	memcpy(page, src_start, length);
 	__flush_icache_range((unsigned long)page, (unsigned long)page + length);
-
+	rc = trans_pgd_idmap_page(&trans_info, &trans_ttbr0, &t0sz, page);
-	trans_pgd = (void *)get_safe_page(GFP_ATOMIC);
-	if (!trans_pgd)
-		return -ENOMEM;
-
-	rc = trans_pgd_map_page(trans_pgd, page, dst_addr,
-				PAGE_KERNEL_EXEC);
 	if (rc)
 		return rc;
 
@@ -270,12 +224,15 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	 * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI
 	 * runtime services), while for a userspace-driven test_resume cycle it
 	 * points to userspace page tables (and we must point it at a zero page
-	 * ourselves). Elsewhere we only (un)install the idmap with preemption
+	 * ourselves).
-	 * disabled, so T0SZ should be as required regardless.
+	 *
+	 * We change T0SZ as part of installing the idmap. This is undone by
+	 * cpu_uninstall_idmap() in __cpu_suspend_exit().
 	 */
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	write_sysreg(phys_to_ttbr(virt_to_phys(trans_pgd)), ttbr0_el1);
+	__cpu_set_tcr_t0sz(t0sz);
+	write_sysreg(trans_ttbr0, ttbr0_el1);
 	isb();
 
 	*phys_dst_addr = virt_to_phys(page);
@@ -462,182 +419,6 @@ int swsusp_arch_suspend(void)
 	return ret;
 }
 
-static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
-{
-	pte_t pte = READ_ONCE(*src_ptep);
-
-	if (pte_valid(pte)) {
-		/*
-		 * Resume will overwrite areas that may be marked
-		 * read only (code, rodata). Clear the RDONLY bit from
-		 * the temporary mappings we use during restore.
-		 */
-		set_pte(dst_ptep, pte_mkwrite(pte));
-	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
-		/*
-		 * debug_pagealloc will removed the PTE_VALID bit if
-		 * the page isn't in use by the resume kernel. It may have
-		 * been in use by the original kernel, in which case we need
-		 * to put it back in our copy to do the restore.
-		 *
-		 * Before marking this entry valid, check the pfn should
-		 * be mapped.
-		 */
-		BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
-	}
-}
-
-static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
-		    unsigned long end)
-{
-	pte_t *src_ptep;
-	pte_t *dst_ptep;
-	unsigned long addr = start;
-
-	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
-	if (!dst_ptep)
-		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
-	dst_ptep = pte_offset_kernel(dst_pmdp, start);
-
-	src_ptep = pte_offset_kernel(src_pmdp, start);
-	do {
-		_copy_pte(dst_ptep, src_ptep, addr);
-	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 0;
-}
-
-static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
-		    unsigned long end)
-{
-	pmd_t *src_pmdp;
-	pmd_t *dst_pmdp;
-	unsigned long next;
-	unsigned long addr = start;
-
-	if (pud_none(READ_ONCE(*dst_pudp))) {
-		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pmdp)
-			return -ENOMEM;
-		pud_populate(&init_mm, dst_pudp, dst_pmdp);
-	}
-	dst_pmdp = pmd_offset(dst_pudp, start);
-
-	src_pmdp = pmd_offset(src_pudp, start);
-	do {
-		pmd_t pmd = READ_ONCE(*src_pmdp);
-
-		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
-			continue;
-		if (pmd_table(pmd)) {
-			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
-				return -ENOMEM;
-		} else {
-			set_pmd(dst_pmdp,
-				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
-		}
-	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
-
-	return 0;
-}
-
-static int copy_pud(p4d_t *dst_p4dp, p4d_t *src_p4dp, unsigned long start,
-		    unsigned long end)
-{
-	pud_t *dst_pudp;
-	pud_t *src_pudp;
-	unsigned long next;
-	unsigned long addr = start;
-
-	if (p4d_none(READ_ONCE(*dst_p4dp))) {
-		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pudp)
-			return -ENOMEM;
-		p4d_populate(&init_mm, dst_p4dp, dst_pudp);
-	}
-	dst_pudp = pud_offset(dst_p4dp, start);
-
-	src_pudp = pud_offset(src_p4dp, start);
-	do {
-		pud_t pud = READ_ONCE(*src_pudp);
-
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			continue;
-		if (pud_table(pud)) {
-			if (copy_pmd(dst_pudp, src_pudp, addr, next))
-				return -ENOMEM;
-		} else {
-			set_pud(dst_pudp,
-				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
-		}
-	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
-
-	return 0;
-}
-
-static int copy_p4d(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
-		    unsigned long end)
-{
-	p4d_t *dst_p4dp;
-	p4d_t *src_p4dp;
-	unsigned long next;
-	unsigned long addr = start;
-
-	dst_p4dp = p4d_offset(dst_pgdp, start);
-	src_p4dp = p4d_offset(src_pgdp, start);
-	do {
-		next = p4d_addr_end(addr, end);
-		if (p4d_none(READ_ONCE(*src_p4dp)))
-			continue;
-		if (copy_pud(dst_p4dp, src_p4dp, addr, next))
-			return -ENOMEM;
-	} while (dst_p4dp++, src_p4dp++, addr = next, addr != end);
-
-	return 0;
-}
-
-static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
-			    unsigned long end)
-{
-	unsigned long next;
-	unsigned long addr = start;
-	pgd_t *src_pgdp = pgd_offset_k(start);
-
-	dst_pgdp = pgd_offset_pgd(dst_pgdp, start);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(READ_ONCE(*src_pgdp)))
-			continue;
-		if (copy_p4d(dst_pgdp, src_pgdp, addr, next))
-			return -ENOMEM;
-	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
-
-	return 0;
-}
-
-static int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
-			  unsigned long end)
-{
-	int rc;
-	pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
-
-	if (!trans_pgd) {
-		pr_err("Failed to allocate memory for temporary page tables.\n");
-		return -ENOMEM;
-	}
-
-	rc = copy_page_tables(trans_pgd, start, end);
-	if (!rc)
-		*dst_pgdp = trans_pgd;
-
-	return rc;
-}
-
 /*
  * Setup then Resume from the hibernate image using swsusp_arch_suspend_exit().
  *
@@ -650,16 +431,20 @@ int swsusp_arch_resume(void)
 	void *zero_page;
 	size_t exit_size;
 	pgd_t *tmp_pg_dir;
-	phys_addr_t phys_hibernate_exit;
 	void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *,
 					  void *, phys_addr_t, phys_addr_t);
+	struct trans_pgd_info trans_info = {
+		.trans_alloc_page	= hibernate_page_alloc,
+		.trans_alloc_arg	= (void *)GFP_ATOMIC,
+	};
 
 	/*
 	 * Restoring the memory image will overwrite the ttbr1 page tables.
 	 * Create a second copy of just the linear map, and use this when
 	 * restoring.
 	 */
-	rc = trans_pgd_create_copy(&tmp_pg_dir, PAGE_OFFSET, PAGE_END);
+	rc = trans_pgd_create_copy(&trans_info, &tmp_pg_dir, PAGE_OFFSET,
+				   PAGE_END);
 	if (rc)
 		return rc;
 
@@ -673,19 +458,13 @@ int swsusp_arch_resume(void)
 		return -ENOMEM;
 	}
 
-	/*
-	 * Locate the exit code in the bottom-but-one page, so that *NULL
-	 * still has disastrous affects.
-	 */
-	hibernate_exit = (void *)PAGE_SIZE;
 	exit_size = __hibernate_exit_text_end - __hibernate_exit_text_start;
 	/*
 	 * Copy swsusp_arch_suspend_exit() to a safe page. This will generate
 	 * a new set of ttbr0 page tables and load them.
 	 */
 	rc = create_safe_exec_page(__hibernate_exit_text_start, exit_size,
-				   (unsigned long)hibernate_exit,
+				   (phys_addr_t *)&hibernate_exit);
-				   &phys_hibernate_exit);
 	if (rc) {
 		pr_err("Failed to create safe executable page for hibernate_exit code.\n");
 		return rc;
@@ -704,7 +483,7 @@ int swsusp_arch_resume(void)
 	 * We can skip this step if we booted at EL1, or are running with VHE.
 	 */
 	if (el2_reset_needed()) {
-		phys_addr_t el2_vectors = phys_hibernate_exit;  /* base */
+		phys_addr_t el2_vectors = (phys_addr_t)hibernate_exit;
 		el2_vectors += hibernate_el2_vectors -
 			       __hibernate_exit_text_start;     /* offset */
 

arch/arm64/kernel/hyp-stub.S

@@ -8,9 +8,9 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
-#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
+#include <asm/el2_setup.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/ptrace.h>
@@ -47,10 +47,13 @@ SYM_CODE_END(__hyp_stub_vectors)
 
 SYM_CODE_START_LOCAL(el1_sync)
 	cmp	x0, #HVC_SET_VECTORS
-	b.ne	2f
+	b.ne	1f
 	msr	vbar_el2, x1
 	b	9f
 
+1:	cmp	x0, #HVC_VHE_RESTART
+	b.eq	mutate_to_vhe
+
 2:	cmp	x0, #HVC_SOFT_RESTART
 	b.ne	3f
 	mov	x0, x2
@@ -70,6 +73,88 @@ SYM_CODE_START_LOCAL(el1_sync)
 	eret
 SYM_CODE_END(el1_sync)
 
+// nVHE? No way! Give me the real thing!
+SYM_CODE_START_LOCAL(mutate_to_vhe)
+	// Be prepared to fail
+	mov_q	x0, HVC_STUB_ERR
+
+	// Sanity check: MMU *must* be off
+	mrs	x1, sctlr_el2
+	tbnz	x1, #0, 1f
+
+	// Needs to be VHE capable, obviously
+	mrs	x1, id_aa64mmfr1_el1
+	ubfx	x1, x1, #ID_AA64MMFR1_VHE_SHIFT, #4
+	cbz	x1, 1f
+
+	// Check whether VHE is disabled from the command line
+	adr_l	x1, id_aa64mmfr1_override
+	ldr	x2, [x1, FTR_OVR_VAL_OFFSET]
+	ldr	x1, [x1, FTR_OVR_MASK_OFFSET]
+	ubfx	x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4
+	ubfx	x1, x1, #ID_AA64MMFR1_VHE_SHIFT, #4
+	cmp	x1, xzr
+	and	x2, x2, x1
+	csinv	x2, x2, xzr, ne
+	cbz	x2, 1f
+
+	// Engage the VHE magic!
+	mov_q	x0, HCR_HOST_VHE_FLAGS
+	msr	hcr_el2, x0
+	isb
+
+	// Use the EL1 allocated stack, per-cpu offset
+	mrs	x0, sp_el1
+	mov	sp, x0
+	mrs	x0, tpidr_el1
+	msr	tpidr_el2, x0
+
+	// FP configuration, vectors
+	mrs_s	x0, SYS_CPACR_EL12
+	msr	cpacr_el1, x0
+	mrs_s	x0, SYS_VBAR_EL12
+	msr	vbar_el1, x0
+
+	// Use EL2 translations for SPE and disable access from EL1
+	mrs	x0, mdcr_el2
+	bic	x0, x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
+	msr	mdcr_el2, x0
+
+	// Transfer the MM state from EL1 to EL2
+	mrs_s	x0, SYS_TCR_EL12
+	msr	tcr_el1, x0
+	mrs_s	x0, SYS_TTBR0_EL12
+	msr	ttbr0_el1, x0
+	mrs_s	x0, SYS_TTBR1_EL12
+	msr	ttbr1_el1, x0
+	mrs_s	x0, SYS_MAIR_EL12
+	msr	mair_el1, x0
+	isb
+
+	// Invalidate TLBs before enabling the MMU
+	tlbi	vmalle1
+	dsb	nsh
+
+	// Enable the EL2 S1 MMU, as set up from EL1
+	mrs_s	x0, SYS_SCTLR_EL12
+	set_sctlr_el1	x0
+
+	// Disable the EL1 S1 MMU for a good measure
+	mov_q	x0, INIT_SCTLR_EL1_MMU_OFF
+	msr_s	SYS_SCTLR_EL12, x0
+
+	// Hack the exception return to stay at EL2
+	mrs	x0, spsr_el1
+	and	x0, x0, #~PSR_MODE_MASK
+	mov	x1, #PSR_MODE_EL2h
+	orr	x0, x0, x1
+	msr	spsr_el1, x0
+
+	mov	x0, xzr
+
+1:	eret
+SYM_CODE_END(mutate_to_vhe)
+
 .macro invalid_vector	label
 SYM_CODE_START_LOCAL(\label)
 	b \label
@@ -85,6 +170,8 @@ SYM_CODE_END(\label)
 	invalid_vector	el1_fiq_invalid
 	invalid_vector	el1_error_invalid
 
+	.popsection
+
 /*
  * __hyp_set_vectors: Call this after boot to set the initial hypervisor
  * vectors as part of hypervisor installation.  On an SMP system, this should
@@ -118,3 +205,27 @@ SYM_FUNC_START(__hyp_reset_vectors)
 	hvc	#0
 	ret
 SYM_FUNC_END(__hyp_reset_vectors)
+
+/*
+ * Entry point to switch to VHE if deemed capable
+ */
+SYM_FUNC_START(switch_to_vhe)
+#ifdef CONFIG_ARM64_VHE
+	// Need to have booted at EL2
+	adr_l	x1, __boot_cpu_mode
+	ldr	w0, [x1]
+	cmp	w0, #BOOT_CPU_MODE_EL2
+	b.ne	1f
+
+	// and still be at EL1
+	mrs	x0, CurrentEL
+	cmp	x0, #CurrentEL_EL1
+	b.ne	1f
+
+	// Turn the world upside down
+	mov	x0, #HVC_VHE_RESTART
+	hvc	#0
+1:
+#endif
+	ret
+SYM_FUNC_END(switch_to_vhe)

arch/arm64/kernel/idreg-override.c

@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Early cpufeature override framework
+ *
+ * Copyright (C) 2020 Google LLC
+ * Author: Marc Zyngier <maz@kernel.org>
+ */
+
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/libfdt.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/setup.h>
+
+#define FTR_DESC_NAME_LEN	20
+#define FTR_DESC_FIELD_LEN	10
+#define FTR_ALIAS_NAME_LEN	30
+#define FTR_ALIAS_OPTION_LEN	80
+
+struct ftr_set_desc {
+	char 				name[FTR_DESC_NAME_LEN];
+	struct arm64_ftr_override	*override;
+	struct {
+		char			name[FTR_DESC_FIELD_LEN];
+		u8			shift;
+	} 				fields[];
+};
+
+static const struct ftr_set_desc mmfr1 __initconst = {
+	.name		= "id_aa64mmfr1",
+	.override	= &id_aa64mmfr1_override,
+	.fields		= {
+	        { "vh", ID_AA64MMFR1_VHE_SHIFT },
+		{}
+	},
+};
+
+static const struct ftr_set_desc pfr1 __initconst = {
+	.name		= "id_aa64pfr1",
+	.override	= &id_aa64pfr1_override,
+	.fields		= {
+	        { "bt", ID_AA64PFR1_BT_SHIFT },
+		{}
+	},
+};
+
+static const struct ftr_set_desc isar1 __initconst = {
+	.name		= "id_aa64isar1",
+	.override	= &id_aa64isar1_override,
+	.fields		= {
+	        { "gpi", ID_AA64ISAR1_GPI_SHIFT },
+	        { "gpa", ID_AA64ISAR1_GPA_SHIFT },
+	        { "api", ID_AA64ISAR1_API_SHIFT },
+	        { "apa", ID_AA64ISAR1_APA_SHIFT },
+		{}
+	},
+};
+
+extern struct arm64_ftr_override kaslr_feature_override;
+
+static const struct ftr_set_desc kaslr __initconst = {
+	.name		= "kaslr",
+#ifdef CONFIG_RANDOMIZE_BASE
+	.override	= &kaslr_feature_override,
+#endif
+	.fields		= {
+		{ "disabled", 0 },
+		{}
+	},
+};
+
+static const struct ftr_set_desc * const regs[] __initconst = {
+	&mmfr1,
+	&pfr1,
+	&isar1,
+	&kaslr,
+};
+
+static const struct {
+	char	alias[FTR_ALIAS_NAME_LEN];
+	char	feature[FTR_ALIAS_OPTION_LEN];
+} aliases[] __initconst = {
+	{ "kvm-arm.mode=nvhe",		"id_aa64mmfr1.vh=0" },
+	{ "kvm-arm.mode=protected",	"id_aa64mmfr1.vh=0" },
+	{ "arm64.nobti",		"id_aa64pfr1.bt=0" },
+	{ "arm64.nopauth",
+	  "id_aa64isar1.gpi=0 id_aa64isar1.gpa=0 "
+	  "id_aa64isar1.api=0 id_aa64isar1.apa=0"	   },
+	{ "nokaslr",			"kaslr.disabled=1" },
+};
+
+static int __init find_field(const char *cmdline,
+			     const struct ftr_set_desc *reg, int f, u64 *v)
+{
+	char opt[FTR_DESC_NAME_LEN + FTR_DESC_FIELD_LEN + 2];
+	int len;
+
+	len = snprintf(opt, ARRAY_SIZE(opt), "%s.%s=",
+		       reg->name, reg->fields[f].name);
+
+	if (!parameqn(cmdline, opt, len))
+		return -1;
+
+	return kstrtou64(cmdline + len, 0, v);
+}
+
+static void __init match_options(const char *cmdline)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(regs); i++) {
+		int f;
+
+		if (!regs[i]->override)
+			continue;
+
+		for (f = 0; strlen(regs[i]->fields[f].name); f++) {
+			u64 shift = regs[i]->fields[f].shift;
+			u64 mask = 0xfUL << shift;
+			u64 v;
+
+			if (find_field(cmdline, regs[i], f, &v))
+				continue;
+
+			regs[i]->override->val  &= ~mask;
+			regs[i]->override->val  |= (v << shift) & mask;
+			regs[i]->override->mask |= mask;
+
+			return;
+		}
+	}
+}
+
+static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
+{
+	do {
+		char buf[256];
+		size_t len;
+		int i;
+
+		cmdline = skip_spaces(cmdline);
+
+		for (len = 0; cmdline[len] && !isspace(cmdline[len]); len++);
+		if (!len)
+			return;
+
+		len = min(len, ARRAY_SIZE(buf) - 1);
+		strncpy(buf, cmdline, len);
+		buf[len] = 0;
+
+		if (strcmp(buf, "--") == 0)
+			return;
+
+		cmdline += len;
+
+		match_options(buf);
+
+		for (i = 0; parse_aliases && i < ARRAY_SIZE(aliases); i++)
+			if (parameq(buf, aliases[i].alias))
+				__parse_cmdline(aliases[i].feature, false);
+	} while (1);
+}
+
+static __init void parse_cmdline(void)
+{
+	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) {
+		const u8 *prop;
+		void *fdt;
+		int node;
+
+		fdt = get_early_fdt_ptr();
+		if (!fdt)
+			goto out;
+
+		node = fdt_path_offset(fdt, "/chosen");
+		if (node < 0)
+			goto out;
+
+		prop = fdt_getprop(fdt, node, "bootargs", NULL);
+		if (!prop)
+			goto out;
+
+		__parse_cmdline(prop, true);
+
+		if (!IS_ENABLED(CONFIG_CMDLINE_EXTEND))
+			return;
+	}
+
+out:
+	__parse_cmdline(CONFIG_CMDLINE, true);
+}
+
+/* Keep checkers quiet */
+void init_feature_override(void);
+
+asmlinkage void __init init_feature_override(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(regs); i++) {
+		if (regs[i]->override) {
+			regs[i]->override->val  = 0;
+			regs[i]->override->mask = 0;
+		}
+	}
+
+	parse_cmdline();
+
+	for (i = 0; i < ARRAY_SIZE(regs); i++) {
+		if (regs[i]->override)
+			__flush_dcache_area(regs[i]->override,
+					    sizeof(*regs[i]->override));
+	}
+}

arch/arm64/kernel/kaslr.c

@@ -19,6 +19,7 @@
 #include <asm/memory.h>
 #include <asm/mmu.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 
 enum kaslr_status {
 	KASLR_ENABLED,
@@ -50,39 +51,7 @@ static __init u64 get_kaslr_seed(void *fdt)
 	return ret;
 }
 
-static __init bool cmdline_contains_nokaslr(const u8 *cmdline)
+struct arm64_ftr_override kaslr_feature_override __initdata;
-{
-	const u8 *str;
-
-	str = strstr(cmdline, "nokaslr");
-	return str == cmdline || (str > cmdline && *(str - 1) == ' ');
-}
-
-static __init bool is_kaslr_disabled_cmdline(void *fdt)
-{
-	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) {
-		int node;
-		const u8 *prop;
-
-		node = fdt_path_offset(fdt, "/chosen");
-		if (node < 0)
-			goto out;
-
-		prop = fdt_getprop(fdt, node, "bootargs", NULL);
-		if (!prop)
-			goto out;
-
-		if (cmdline_contains_nokaslr(prop))
-			return true;
-
-		if (IS_ENABLED(CONFIG_CMDLINE_EXTEND))
-			goto out;
-
-		return false;
-	}
-out:
-	return cmdline_contains_nokaslr(CONFIG_CMDLINE);
-}
 
 /*
  * This routine will be executed with the kernel mapped at its default virtual
@@ -92,12 +61,11 @@ static __init bool is_kaslr_disabled_cmdline(void *fdt)
  * containing function pointers) to be reinitialized, and zero-initialized
  * .bss variables will be reset to 0.
  */
-u64 __init kaslr_early_init(u64 dt_phys)
+u64 __init kaslr_early_init(void)
 {
 	void *fdt;
 	u64 seed, offset, mask, module_range;
 	unsigned long raw;
-	int size;
 
 	/*
 	 * Set a reasonable default for module_alloc_base in case
@@ -111,8 +79,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * and proceed with KASLR disabled. We will make another
 	 * attempt at mapping the FDT in setup_machine()
 	 */
-	early_fixmap_init();
+	fdt = get_early_fdt_ptr();
-	fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
 	if (!fdt) {
 		kaslr_status = KASLR_DISABLED_FDT_REMAP;
 		return 0;
@@ -127,7 +94,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * Check if 'nokaslr' appears on the command line, and
 	 * return 0 if that is the case.
 	 */
-	if (is_kaslr_disabled_cmdline(fdt)) {
+	if (kaslr_feature_override.val & kaslr_feature_override.mask & 0xf) {
 		kaslr_status = KASLR_DISABLED_CMDLINE;
 		return 0;
 	}

arch/arm64/kernel/machine_kexec.c

@@ -42,6 +42,7 @@ static void _kexec_image_info(const char *func, int line,
 	pr_debug("    start:       %lx\n", kimage->start);
 	pr_debug("    head:        %lx\n", kimage->head);
 	pr_debug("    nr_segments: %lu\n", kimage->nr_segments);
+	pr_debug("    kern_reloc: %pa\n", &kimage->arch.kern_reloc);
 
 	for (i = 0; i < kimage->nr_segments; i++) {
 		pr_debug("      segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
@@ -58,6 +59,23 @@ void machine_kexec_cleanup(struct kimage *kimage)
 	/* Empty routine needed to avoid build errors. */
 }
 
+int machine_kexec_post_load(struct kimage *kimage)
+{
+	void *reloc_code = page_to_virt(kimage->control_code_page);
+
+	memcpy(reloc_code, arm64_relocate_new_kernel,
+	       arm64_relocate_new_kernel_size);
+	kimage->arch.kern_reloc = __pa(reloc_code);
+	kexec_image_info(kimage);
+
+	/* Flush the reloc_code in preparation for its execution. */
+	__flush_dcache_area(reloc_code, arm64_relocate_new_kernel_size);
+	flush_icache_range((uintptr_t)reloc_code, (uintptr_t)reloc_code +
+			   arm64_relocate_new_kernel_size);
+
+	return 0;
+}
+
 /**
  * machine_kexec_prepare - Prepare for a kexec reboot.
  *
@@ -67,8 +85,6 @@ void machine_kexec_cleanup(struct kimage *kimage)
  */
 int machine_kexec_prepare(struct kimage *kimage)
 {
-	kexec_image_info(kimage);
-
 	if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) {
 		pr_err("Can't kexec: CPUs are stuck in the kernel.\n");
 		return -EBUSY;
@@ -143,8 +159,6 @@ static void kexec_segment_flush(const struct kimage *kimage)
  */
 void machine_kexec(struct kimage *kimage)
 {
-	phys_addr_t reboot_code_buffer_phys;
-	void *reboot_code_buffer;
 	bool in_kexec_crash = (kimage == kexec_crash_image);
 	bool stuck_cpus = cpus_are_stuck_in_kernel();
 
@@ -155,31 +169,6 @@ void machine_kexec(struct kimage *kimage)
 	WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()),
 		"Some CPUs may be stale, kdump will be unreliable.\n");
 
-	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
-	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
-
-	kexec_image_info(kimage);
-
-	/*
-	 * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use
-	 * after the kernel is shut down.
-	 */
-	memcpy(reboot_code_buffer, arm64_relocate_new_kernel,
-		arm64_relocate_new_kernel_size);
-
-	/* Flush the reboot_code_buffer in preparation for its execution. */
-	__flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);
-
-	/*
-	 * Although we've killed off the secondary CPUs, we don't update
-	 * the online mask if we're handling a crash kernel and consequently
-	 * need to avoid flush_icache_range(), which will attempt to IPI
-	 * the offline CPUs. Therefore, we must use the __* variant here.
-	 */
-	__flush_icache_range((uintptr_t)reboot_code_buffer,
-			     (uintptr_t)reboot_code_buffer +
-			     arm64_relocate_new_kernel_size);
-
 	/* Flush the kimage list and its buffers. */
 	kexec_list_flush(kimage);
 
@@ -193,7 +182,7 @@ void machine_kexec(struct kimage *kimage)
 
 	/*
 	 * cpu_soft_restart will shutdown the MMU, disable data caches, then
-	 * transfer control to the reboot_code_buffer which contains a copy of
+	 * transfer control to the kern_reloc which contains a copy of
 	 * the arm64_relocate_new_kernel routine.  arm64_relocate_new_kernel
 	 * uses physical addressing to relocate the new image to its final
 	 * position and transfers control to the image entry point when the
@@ -203,12 +192,8 @@ void machine_kexec(struct kimage *kimage)
 	 * userspace (kexec-tools).
 	 * In kexec_file case, the kernel starts directly without purgatory.
 	 */
-	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start,
+	cpu_soft_restart(kimage->arch.kern_reloc, kimage->head, kimage->start,
-#ifdef CONFIG_KEXEC_FILE
 			 kimage->arch.dtb_mem);
-#else
-						0);
-#endif
 
 	BUG(); /* Should never get here. */
 }

arch/arm64/kernel/module-plts.c

@@ -131,7 +131,7 @@ u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs,
 }
 #endif
 
-#define cmp_3way(a,b)	((a) < (b) ? -1 : (a) > (b))
+#define cmp_3way(a, b)	((a) < (b) ? -1 : (a) > (b))
 
 static int cmp_rela(const void *a, const void *b)
 {

arch/arm64/kernel/perf_event.c

@@ -280,7 +280,7 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
 	return 0;
 }
 
-static struct attribute_group armv8_pmuv3_events_attr_group = {
+static const struct attribute_group armv8_pmuv3_events_attr_group = {
 	.name = "events",
 	.attrs = armv8_pmuv3_event_attrs,
 	.is_visible = armv8pmu_event_attr_is_visible,
@@ -300,7 +300,7 @@ static struct attribute *armv8_pmuv3_format_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group armv8_pmuv3_format_attr_group = {
+static const struct attribute_group armv8_pmuv3_format_attr_group = {
 	.name = "format",
 	.attrs = armv8_pmuv3_format_attrs,
 };
@@ -322,7 +322,7 @@ static struct attribute *armv8_pmuv3_caps_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group armv8_pmuv3_caps_attr_group = {
+static const struct attribute_group armv8_pmuv3_caps_attr_group = {
 	.name = "caps",
 	.attrs = armv8_pmuv3_caps_attrs,
 };
@@ -810,7 +810,7 @@ static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc,
 {
 	int idx;
 
-	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx ++) {
+	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx++) {
 		if (!test_and_set_bit(idx, cpuc->used_mask))
 			return idx;
 	}
@@ -1188,6 +1188,12 @@ static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu)
 				       armv8_pmuv3_map_event);
 }
 
+static int armv8_a78_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a78",
+				       armv8_pmuv3_map_event);
+}
+
 static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_e1",
@@ -1225,6 +1231,7 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "arm,cortex-a75-pmu",	.data = armv8_a75_pmu_init},
 	{.compatible = "arm,cortex-a76-pmu",	.data = armv8_a76_pmu_init},
 	{.compatible = "arm,cortex-a77-pmu",	.data = armv8_a77_pmu_init},
+	{.compatible = "arm,cortex-a78-pmu",	.data = armv8_a78_pmu_init},
 	{.compatible = "arm,neoverse-e1-pmu",	.data = armv8_e1_pmu_init},
 	{.compatible = "arm,neoverse-n1-pmu",	.data = armv8_n1_pmu_init},
 	{.compatible = "cavium,thunder-pmu",	.data = armv8_thunder_pmu_init},

arch/arm64/kernel/process.c

@@ -304,7 +304,7 @@ void __show_regs(struct pt_regs *regs)
 	}
 }
 
-void show_regs(struct pt_regs * regs)
+void show_regs(struct pt_regs *regs)
 {
 	__show_regs(regs);
 	dump_backtrace(regs, NULL, KERN_DEFAULT);
@@ -587,7 +587,7 @@ unsigned long get_wchan(struct task_struct *p)
 			ret = frame.pc;
 			goto out;
 		}
-	} while (count ++ < 16);
+	} while (count++ < 16);
 
 out:
 	put_task_stack(p);

arch/arm64/kernel/ptrace.c

@@ -194,6 +194,7 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 		}
 		arm64_force_sig_ptrace_errno_trap(si_errno, bkpt->trigger,
 						  desc);
+		return;
 	}
 #endif
 	arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc);

arch/arm64/kernel/relocate_kernel.S

@@ -17,28 +17,24 @@
 /*
  * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it.
  *
- * The memory that the old kernel occupies may be overwritten when coping the
+ * The memory that the old kernel occupies may be overwritten when copying the
  * new image to its final location.  To assure that the
  * arm64_relocate_new_kernel routine which does that copy is not overwritten,
  * all code and data needed by arm64_relocate_new_kernel must be between the
  * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end.  The
  * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec
- * control_code_page, a special page which has been set up to be preserved
+ * safe memory that has been set up to be preserved during the copy operation.
- * during the copy operation.
  */
 SYM_CODE_START(arm64_relocate_new_kernel)
-
 	/* Setup the list loop variables. */
 	mov	x18, x2				/* x18 = dtb address */
 	mov	x17, x1				/* x17 = kimage_start */
 	mov	x16, x0				/* x16 = kimage_head */
-	raw_dcache_line_size x15, x0		/* x15 = dcache line size */
 	mov	x14, xzr			/* x14 = entry ptr */
 	mov	x13, xzr			/* x13 = copy dest */
-
 	/* Check if the new image needs relocation. */
 	tbnz	x16, IND_DONE_BIT, .Ldone
-
+	raw_dcache_line_size x15, x1		/* x15 = dcache line size */
 .Lloop:
 	and	x12, x16, PAGE_MASK		/* x12 = addr */
 
@@ -47,44 +43,28 @@ SYM_CODE_START(arm64_relocate_new_kernel)
 	tbz	x16, IND_SOURCE_BIT, .Ltest_indirection
 
 	/* Invalidate dest page to PoC. */
-	mov     x0, x13
+	mov     x2, x13
-	add     x20, x0, #PAGE_SIZE
+	add     x20, x2, #PAGE_SIZE
 	sub     x1, x15, #1
-	bic     x0, x0, x1
+	bic     x2, x2, x1
-2:	dc      ivac, x0
+2:	dc      ivac, x2
-	add     x0, x0, x15
+	add     x2, x2, x15
-	cmp     x0, x20
+	cmp     x2, x20
 	b.lo    2b
 	dsb     sy
 
-	mov x20, x13
+	copy_page x13, x12, x1, x2, x3, x4, x5, x6, x7, x8
-	mov x21, x12
-	copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7
-
-	/* dest += PAGE_SIZE */
-	add	x13, x13, PAGE_SIZE
 	b	.Lnext
-
 .Ltest_indirection:
 	tbz	x16, IND_INDIRECTION_BIT, .Ltest_destination
-
+	mov	x14, x12			/* ptr = addr */
-	/* ptr = addr */
-	mov	x14, x12
 	b	.Lnext
-
 .Ltest_destination:
 	tbz	x16, IND_DESTINATION_BIT, .Lnext
-
+	mov	x13, x12			/* dest = addr */
-	/* dest = addr */
-	mov	x13, x12
-
 .Lnext:
-	/* entry = *ptr++ */
+	ldr	x16, [x14], #8			/* entry = *ptr++ */
-	ldr	x16, [x14], #8
+	tbz	x16, IND_DONE_BIT, .Lloop	/* while (!(entry & DONE)) */
-
-	/* while (!(entry & DONE)) */
-	tbz	x16, IND_DONE_BIT, .Lloop
-
 .Ldone:
 	/* wait for writes from copy_page to finish */
 	dsb	nsh

arch/arm64/kernel/setup.c

@@ -168,6 +168,21 @@ static void __init smp_build_mpidr_hash(void)
 		pr_warn("Large number of MPIDR hash buckets detected\n");
 }
 
+static void *early_fdt_ptr __initdata;
+
+void __init *get_early_fdt_ptr(void)
+{
+	return early_fdt_ptr;
+}
+
+asmlinkage void __init early_fdt_map(u64 dt_phys)
+{
+	int fdt_size;
+
+	early_fixmap_init();
+	early_fdt_ptr = fixmap_remap_fdt(dt_phys, &fdt_size, PAGE_KERNEL);
+}
+
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
 	int size;

arch/arm64/kernel/sleep.S

@@ -100,6 +100,7 @@ SYM_FUNC_END(__cpu_suspend_enter)
 	.pushsection ".idmap.text", "awx"
 SYM_CODE_START(cpu_resume)
 	bl	init_kernel_el
+	bl	switch_to_vhe
 	bl	__cpu_setup
 	/* enable the MMU early - so we can access sleep_save_stash by va */
 	adrp	x1, swapper_pg_dir

arch/arm64/kernel/stacktrace.c

@@ -44,6 +44,10 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	unsigned long fp = frame->fp;
 	struct stack_info info;
 
+	/* Terminal record; nothing to unwind */
+	if (!fp)
+		return -EINVAL;
+
 	if (fp & 0xf)
 		return -EINVAL;
 
@@ -104,15 +108,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 
 	frame->pc = ptrauth_strip_insn_pac(frame->pc);
 
-	/*
-	 * Frames created upon entry from EL0 have NULL FP and PC values, so
-	 * don't bother reporting these. Frames created by __noreturn functions
-	 * might have a valid FP even if PC is bogus, so only terminate where
-	 * both are NULL.
-	 */
-	if (!frame->fp && !frame->pc)
-		return -EINVAL;
-
 	return 0;
 }
 NOKPROBE_SYMBOL(unwind_frame);

arch/arm64/kernel/syscall.c

@@ -65,35 +65,6 @@ static inline bool has_syscall_work(unsigned long flags)
 int syscall_trace_enter(struct pt_regs *regs);
 void syscall_trace_exit(struct pt_regs *regs);
 
-#ifdef CONFIG_ARM64_ERRATUM_1463225
-DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
-
-static void cortex_a76_erratum_1463225_svc_handler(void)
-{
-	u32 reg, val;
-
-	if (!unlikely(test_thread_flag(TIF_SINGLESTEP)))
-		return;
-
-	if (!unlikely(this_cpu_has_cap(ARM64_WORKAROUND_1463225)))
-		return;
-
-	__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 1);
-	reg = read_sysreg(mdscr_el1);
-	val = reg | DBG_MDSCR_SS | DBG_MDSCR_KDE;
-	write_sysreg(val, mdscr_el1);
-	asm volatile("msr daifclr, #8");
-	isb();
-
-	/* We will have taken a single-step exception by this point */
-
-	write_sysreg(reg, mdscr_el1);
-	__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0);
-}
-#else
-static void cortex_a76_erratum_1463225_svc_handler(void) { }
-#endif /* CONFIG_ARM64_ERRATUM_1463225 */
-
 static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 			   const syscall_fn_t syscall_table[])
 {
@@ -120,7 +91,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	 * (Similarly for HVC and SMC elsewhere.)
 	 */
 
-	cortex_a76_erratum_1463225_svc_handler();
 	local_daif_restore(DAIF_PROCCTX);
 
 	if (flags & _TIF_MTE_ASYNC_FAULT) {

arch/arm64/kernel/topology.c

@@ -199,76 +199,38 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
 	return 0;
 }
 
-static inline bool
-enable_policy_freq_counters(int cpu, cpumask_var_t valid_cpus)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-
-	if (!policy) {
-		pr_debug("CPU%d: No cpufreq policy found.\n", cpu);
-		return false;
-	}
-
-	if (cpumask_subset(policy->related_cpus, valid_cpus))
-		cpumask_or(amu_fie_cpus, policy->related_cpus,
-			   amu_fie_cpus);
-
-	cpufreq_cpu_put(policy);
-
-	return true;
-}
-
 static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
 #define amu_freq_invariant() static_branch_unlikely(&amu_fie_key)
 
-static int __init init_amu_fie(void)
+static void amu_fie_setup(const struct cpumask *cpus)
 {
-	bool invariance_status = topology_scale_freq_invariant();
+	bool invariant;
-	cpumask_var_t valid_cpus;
-	bool have_policy = false;
-	int ret = 0;
 	int cpu;
 
-	if (!zalloc_cpumask_var(&valid_cpus, GFP_KERNEL))
+	/* We are already set since the last insmod of cpufreq driver */
-		return -ENOMEM;
+	if (unlikely(cpumask_subset(cpus, amu_fie_cpus)))
+		return;
 
-	if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) {
+	for_each_cpu(cpu, cpus) {
-		ret = -ENOMEM;
-		goto free_valid_mask;
-	}
-
-	for_each_present_cpu(cpu) {
 		if (!freq_counters_valid(cpu) ||
 		    freq_inv_set_max_ratio(cpu,
 					   cpufreq_get_hw_max_freq(cpu) * 1000,
 					   arch_timer_get_rate()))
-			continue;
+			return;
-
-		cpumask_set_cpu(cpu, valid_cpus);
-		have_policy |= enable_policy_freq_counters(cpu, valid_cpus);
 	}
 
-	/*
+	cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus);
-	 * If we are not restricted by cpufreq policies, we only enable
+
-	 * the use of the AMU feature for FIE if all CPUs support AMU.
+	invariant = topology_scale_freq_invariant();
-	 * Otherwise, enable_policy_freq_counters has already enabled
+
-	 * policy cpus.
+	/* We aren't fully invariant yet */
-	 */
+	if (!invariant && !cpumask_equal(amu_fie_cpus, cpu_present_mask))
-	if (!have_policy && cpumask_equal(valid_cpus, cpu_present_mask))
+		return;
-		cpumask_or(amu_fie_cpus, amu_fie_cpus, valid_cpus);
 
-	if (!cpumask_empty(amu_fie_cpus)) {
-		pr_info("CPUs[%*pbl]: counters will be used for FIE.",
-			cpumask_pr_args(amu_fie_cpus));
 	static_branch_enable(&amu_fie_key);
-	}
 
-	/*
+	pr_debug("CPUs[%*pbl]: counters will be used for FIE.",
-	 * If the system is not fully invariant after AMU init, disable
+		 cpumask_pr_args(cpus));
-	 * partial use of counters for frequency invariance.
-	 */
-	if (!topology_scale_freq_invariant())
-		static_branch_disable(&amu_fie_key);
 
 	/*
 	 * Task scheduler behavior depends on frequency invariance support,
@@ -276,15 +238,50 @@ static int __init init_amu_fie(void)
 	 * a result of counter initialisation and use, retrigger the build of
 	 * scheduling domains to ensure the information is propagated properly.
 	 */
-	if (invariance_status != topology_scale_freq_invariant())
+	if (!invariant)
 		rebuild_sched_domains_energy();
+}
 
-free_valid_mask:
+static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val,
-	free_cpumask_var(valid_cpus);
+				 void *data)
+{
+	struct cpufreq_policy *policy = data;
+
+	if (val == CPUFREQ_CREATE_POLICY)
+		amu_fie_setup(policy->related_cpus);
+
+	/*
+	 * We don't need to handle CPUFREQ_REMOVE_POLICY event as the AMU
+	 * counters don't have any dependency on cpufreq driver once we have
+	 * initialized AMU support and enabled invariance. The AMU counters will
+	 * keep on working just fine in the absence of the cpufreq driver, and
+	 * for the CPUs for which there are no counters available, the last set
+	 * value of freq_scale will remain valid as that is the frequency those
+	 * CPUs are running at.
+	 */
+
+	return 0;
+}
+
+static struct notifier_block init_amu_fie_notifier = {
+	.notifier_call = init_amu_fie_callback,
+};
+
+static int __init init_amu_fie(void)
+{
+	int ret;
+
+	if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = cpufreq_register_notifier(&init_amu_fie_notifier,
+					CPUFREQ_POLICY_NOTIFIER);
+	if (ret)
+		free_cpumask_var(amu_fie_cpus);
 
 	return ret;
 }
-late_initcall_sync(init_amu_fie);
+core_initcall(init_amu_fie);
 
 bool arch_freq_counters_available(const struct cpumask *cpus)
 {

arch/arm64/kernel/traps.c

@@ -45,7 +45,7 @@
 #include <asm/system_misc.h>
 #include <asm/sysreg.h>
 
-static const char *handler[]= {
+static const char *handler[] = {
 	"Synchronous Abort",
 	"IRQ",
 	"FIQ",

arch/arm64/kernel/vdso/Makefile

@@ -44,7 +44,6 @@ endif
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
-obj-y += vdso.o
 targets += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 

arch/arm64/kernel/vdso/gen_vdso_offsets.sh

@@ -13,4 +13,4 @@
 
 LC_ALL=C
 sed -n -e 's/^00*/0/' -e \
-'s/^\([0-9a-fA-F]*\) . VDSO_\([a-zA-Z0-9_]*\)$/\#define vdso_offset_\2\t0x\1/p'
+'s/^\([0-9a-fA-F]*\) . VDSO_\([a-zA-Z0-9_]*\)$/\#define vdso_offset_\2 0x\1/p'

arch/arm64/kernel/vdso32/Makefile

@@ -155,7 +155,6 @@ c-obj-vdso-gettimeofday := $(addprefix $(obj)/, $(c-obj-vdso-gettimeofday))
 asm-obj-vdso := $(addprefix $(obj)/, $(asm-obj-vdso))
 obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
 
-obj-y += vdso.o
 targets += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 

arch/arm64/kernel/vmlinux.lds.S

@@ -316,3 +316,11 @@ ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE,
  * If padding is applied before .head.text, virt<->phys conversions will fail.
  */
 ASSERT(_text == KIMAGE_VADDR, "HEAD is misaligned")
+
+ASSERT(swapper_pg_dir - reserved_pg_dir == RESERVED_SWAPPER_OFFSET,
+       "RESERVED_SWAPPER_OFFSET is wrong!")
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ASSERT(swapper_pg_dir - tramp_pg_dir == TRAMP_SWAPPER_OFFSET,
+       "TRAMP_SWAPPER_OFFSET is wrong!")
+#endif

arch/arm64/kvm/arm.c

@@ -1967,6 +1967,9 @@ static int __init early_kvm_mode_cfg(char *arg)
 		return 0;
 	}
 
+	if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode()))
+		return 0;
+
 	return -EINVAL;
 }
 early_param("kvm-arm.mode", early_kvm_mode_cfg);

arch/arm64/kvm/hyp/nvhe/hyp-init.S

@@ -191,7 +191,7 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
 	/* Initialize EL2 CPU state to sane values. */
-	init_el2_state nvhe			// Clobbers x0..x2
+	init_el2_state				// Clobbers x0..x2
 
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28

arch/arm64/mm/Makefile

@@ -6,6 +6,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_PTDUMP_CORE)	+= ptdump.o
 obj-$(CONFIG_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
+obj-$(CONFIG_TRANS_TABLE)	+= trans_pgd.o
 obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 obj-$(CONFIG_ARM64_MTE)		+= mteswap.o

arch/arm64/mm/fault.c

@@ -564,7 +564,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr,
 		mmap_read_lock(mm);
 	} else {
 		/*
-		 * The above down_read_trylock() might have succeeded in which
+		 * The above mmap_read_trylock() might have succeeded in which
 		 * case, we'll have missed the might_sleep() from down_read().
 		 */
 		might_sleep();
@@ -875,44 +875,12 @@ static void debug_exception_exit(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(debug_exception_exit);
 
-#ifdef CONFIG_ARM64_ERRATUM_1463225
-DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
-
-static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
-{
-	if (user_mode(regs))
-		return 0;
-
-	if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa))
-		return 0;
-
-	/*
-	 * We've taken a dummy step exception from the kernel to ensure
-	 * that interrupts are re-enabled on the syscall path. Return back
-	 * to cortex_a76_erratum_1463225_svc_handler() with debug exceptions
-	 * masked so that we can safely restore the mdscr and get on with
-	 * handling the syscall.
-	 */
-	regs->pstate |= PSR_D_BIT;
-	return 1;
-}
-#else
-static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
-{
-	return 0;
-}
-#endif /* CONFIG_ARM64_ERRATUM_1463225 */
-NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler);
-
 void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 			struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_debug_fault_info(esr);
 	unsigned long pc = instruction_pointer(regs);
 
-	if (cortex_a76_erratum_1463225_debug_handler(regs))
-		return;
-
 	debug_exception_enter(regs);
 
 	if (user_mode(regs) && !is_ttbr0_addr(pc))

arch/arm64/mm/mmap.c

@@ -5,20 +5,11 @@
  * Copyright (C) 2012 ARM Ltd.
  */
 
-#include <linux/elf.h>
-#include <linux/fs.h>
-#include <linux/memblock.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/export.h>
-#include <linux/shm.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/mm.h>
 #include <linux/io.h>
-#include <linux/personality.h>
+#include <linux/memblock.h>
-#include <linux/random.h>
+#include <linux/types.h>
 
-#include <asm/cputype.h>
+#include <asm/page.h>
 
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This might go

arch/arm64/mm/mmu.c

@@ -628,7 +628,7 @@ static bool arm64_early_this_cpu_has_bti(void)
 	if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
 		return false;
 
-	pfr1 = read_sysreg_s(SYS_ID_AA64PFR1_EL1);
+	pfr1 = __read_sysreg_by_encoding(SYS_ID_AA64PFR1_EL1);
 	return cpuid_feature_extract_unsigned_field(pfr1,
 						    ID_AA64PFR1_BT_SHIFT);
 }
@@ -1094,6 +1094,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end,
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
+	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
 	return vmemmap_populate_basepages(start, end, node, altmap);
 }
 #else	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
@@ -1107,6 +1108,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	pud_t *pudp;
 	pmd_t *pmdp;
 
+	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
 	do {
 		next = pmd_addr_end(addr, end);
 

arch/arm64/mm/proc.S

@@ -291,17 +291,7 @@ skip_pgd:
 	/* We're done: fire up the MMU again */
 	mrs	x17, sctlr_el1
 	orr	x17, x17, #SCTLR_ELx_M
-	msr	sctlr_el1, x17
+	set_sctlr_el1	x17
-	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
 
 	/* Set the flag to zero to indicate that we're all done */
 	str	wzr, [flag_ptr]
@@ -464,8 +454,8 @@ SYM_FUNC_START(__cpu_setup)
 #endif
 	msr	mair_el1, x5
 	/*
-	 * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
+	 * Set/prepare TCR and TTBR. TCR_EL1.T1SZ gets further
-	 * both user and kernel.
+	 * adjusted if the kernel is compiled with 52bit VA support.
 	 */
 	mov_q	x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
 			TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \

arch/arm64/mm/ptdump.c

@@ -324,6 +324,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info)
 	st = (struct pg_state){
 		.seq = s,
 		.marker = info->markers,
+		.level = -1,
 		.ptdump = {
 			.note_page = note_page,
 			.range = (struct ptdump_range[]){

arch/arm64/mm/trans_pgd.c

@@ -0,0 +1,324 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Transitional page tables for kexec and hibernate
+ *
+ * This file derived from: arch/arm64/kernel/hibernate.c
+ *
+ * Copyright (c) 2020, Microsoft Corporation.
+ * Pavel Tatashin <pasha.tatashin@soleen.com>
+ *
+ */
+
+/*
+ * Transitional tables are used during system transferring from one world to
+ * another: such as during hibernate restore, and kexec reboots. During these
+ * phases one cannot rely on page table not being overwritten. This is because
+ * hibernate and kexec can overwrite the current page tables during transition.
+ */
+
+#include <asm/trans_pgd.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <linux/suspend.h>
+#include <linux/bug.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+
+static void *trans_alloc(struct trans_pgd_info *info)
+{
+	return info->trans_alloc_page(info->trans_alloc_arg);
+}
+
+static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
+{
+	pte_t pte = READ_ONCE(*src_ptep);
+
+	if (pte_valid(pte)) {
+		/*
+		 * Resume will overwrite areas that may be marked
+		 * read only (code, rodata). Clear the RDONLY bit from
+		 * the temporary mappings we use during restore.
+		 */
+		set_pte(dst_ptep, pte_mkwrite(pte));
+	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
+		/*
+		 * debug_pagealloc will removed the PTE_VALID bit if
+		 * the page isn't in use by the resume kernel. It may have
+		 * been in use by the original kernel, in which case we need
+		 * to put it back in our copy to do the restore.
+		 *
+		 * Before marking this entry valid, check the pfn should
+		 * be mapped.
+		 */
+		BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
+	}
+}
+
+static int copy_pte(struct trans_pgd_info *info, pmd_t *dst_pmdp,
+		    pmd_t *src_pmdp, unsigned long start, unsigned long end)
+{
+	pte_t *src_ptep;
+	pte_t *dst_ptep;
+	unsigned long addr = start;
+
+	dst_ptep = trans_alloc(info);
+	if (!dst_ptep)
+		return -ENOMEM;
+	pmd_populate_kernel(NULL, dst_pmdp, dst_ptep);
+	dst_ptep = pte_offset_kernel(dst_pmdp, start);
+
+	src_ptep = pte_offset_kernel(src_pmdp, start);
+	do {
+		_copy_pte(dst_ptep, src_ptep, addr);
+	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
+
+	return 0;
+}
+
+static int copy_pmd(struct trans_pgd_info *info, pud_t *dst_pudp,
+		    pud_t *src_pudp, unsigned long start, unsigned long end)
+{
+	pmd_t *src_pmdp;
+	pmd_t *dst_pmdp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	if (pud_none(READ_ONCE(*dst_pudp))) {
+		dst_pmdp = trans_alloc(info);
+		if (!dst_pmdp)
+			return -ENOMEM;
+		pud_populate(NULL, dst_pudp, dst_pmdp);
+	}
+	dst_pmdp = pmd_offset(dst_pudp, start);
+
+	src_pmdp = pmd_offset(src_pudp, start);
+	do {
+		pmd_t pmd = READ_ONCE(*src_pmdp);
+
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(pmd))
+			continue;
+		if (pmd_table(pmd)) {
+			if (copy_pte(info, dst_pmdp, src_pmdp, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pmd(dst_pmdp,
+				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
+		}
+	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_pud(struct trans_pgd_info *info, p4d_t *dst_p4dp,
+		    p4d_t *src_p4dp, unsigned long start,
+		    unsigned long end)
+{
+	pud_t *dst_pudp;
+	pud_t *src_pudp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	if (p4d_none(READ_ONCE(*dst_p4dp))) {
+		dst_pudp = trans_alloc(info);
+		if (!dst_pudp)
+			return -ENOMEM;
+		p4d_populate(NULL, dst_p4dp, dst_pudp);
+	}
+	dst_pudp = pud_offset(dst_p4dp, start);
+
+	src_pudp = pud_offset(src_p4dp, start);
+	do {
+		pud_t pud = READ_ONCE(*src_pudp);
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			continue;
+		if (pud_table(pud)) {
+			if (copy_pmd(info, dst_pudp, src_pudp, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pud(dst_pudp,
+				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
+		}
+	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp,
+		    pgd_t *src_pgdp, unsigned long start,
+		    unsigned long end)
+{
+	p4d_t *dst_p4dp;
+	p4d_t *src_p4dp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	dst_p4dp = p4d_offset(dst_pgdp, start);
+	src_p4dp = p4d_offset(src_pgdp, start);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(READ_ONCE(*src_p4dp)))
+			continue;
+		if (copy_pud(info, dst_p4dp, src_p4dp, addr, next))
+			return -ENOMEM;
+	} while (dst_p4dp++, src_p4dp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_page_tables(struct trans_pgd_info *info, pgd_t *dst_pgdp,
+			    unsigned long start, unsigned long end)
+{
+	unsigned long next;
+	unsigned long addr = start;
+	pgd_t *src_pgdp = pgd_offset_k(start);
+
+	dst_pgdp = pgd_offset_pgd(dst_pgdp, start);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(READ_ONCE(*src_pgdp)))
+			continue;
+		if (copy_p4d(info, dst_pgdp, src_pgdp, addr, next))
+			return -ENOMEM;
+	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
+
+	return 0;
+}
+
+/*
+ * Create trans_pgd and copy linear map.
+ * info:	contains allocator and its argument
+ * dst_pgdp:	new page table that is created, and to which map is copied.
+ * start:	Start of the interval (inclusive).
+ * end:		End of the interval (exclusive).
+ *
+ * Returns 0 on success, and -ENOMEM on failure.
+ */
+int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **dst_pgdp,
+			  unsigned long start, unsigned long end)
+{
+	int rc;
+	pgd_t *trans_pgd = trans_alloc(info);
+
+	if (!trans_pgd) {
+		pr_err("Failed to allocate memory for temporary page tables.\n");
+		return -ENOMEM;
+	}
+
+	rc = copy_page_tables(info, trans_pgd, start, end);
+	if (!rc)
+		*dst_pgdp = trans_pgd;
+
+	return rc;
+}
+
+/*
+ * Add map entry to trans_pgd for a base-size page at PTE level.
+ * info:	contains allocator and its argument
+ * trans_pgd:	page table in which new map is added.
+ * page:	page to be mapped.
+ * dst_addr:	new VA address for the page
+ * pgprot:	protection for the page.
+ *
+ * Returns 0 on success, and -ENOMEM on failure.
+ */
+int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
+		       void *page, unsigned long dst_addr, pgprot_t pgprot)
+{
+	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	pgdp = pgd_offset_pgd(trans_pgd, dst_addr);
+	if (pgd_none(READ_ONCE(*pgdp))) {
+		p4dp = trans_alloc(info);
+		if (!pgdp)
+			return -ENOMEM;
+		pgd_populate(NULL, pgdp, p4dp);
+	}
+
+	p4dp = p4d_offset(pgdp, dst_addr);
+	if (p4d_none(READ_ONCE(*p4dp))) {
+		pudp = trans_alloc(info);
+		if (!pudp)
+			return -ENOMEM;
+		p4d_populate(NULL, p4dp, pudp);
+	}
+
+	pudp = pud_offset(p4dp, dst_addr);
+	if (pud_none(READ_ONCE(*pudp))) {
+		pmdp = trans_alloc(info);
+		if (!pmdp)
+			return -ENOMEM;
+		pud_populate(NULL, pudp, pmdp);
+	}
+
+	pmdp = pmd_offset(pudp, dst_addr);
+	if (pmd_none(READ_ONCE(*pmdp))) {
+		ptep = trans_alloc(info);
+		if (!ptep)
+			return -ENOMEM;
+		pmd_populate_kernel(NULL, pmdp, ptep);
+	}
+
+	ptep = pte_offset_kernel(pmdp, dst_addr);
+	set_pte(ptep, pfn_pte(virt_to_pfn(page), pgprot));
+
+	return 0;
+}
+
+/*
+ * The page we want to idmap may be outside the range covered by VA_BITS that
+ * can be built using the kernel's p?d_populate() helpers. As a one off, for a
+ * single page, we build these page tables bottom up and just assume that will
+ * need the maximum T0SZ.
+ *
+ * Returns 0 on success, and -ENOMEM on failure.
+ * On success trans_ttbr0 contains page table with idmapped page, t0sz is set to
+ * maximum T0SZ for this page.
+ */
+int trans_pgd_idmap_page(struct trans_pgd_info *info, phys_addr_t *trans_ttbr0,
+			 unsigned long *t0sz, void *page)
+{
+	phys_addr_t dst_addr = virt_to_phys(page);
+	unsigned long pfn = __phys_to_pfn(dst_addr);
+	int max_msb = (dst_addr & GENMASK(52, 48)) ? 51 : 47;
+	int bits_mapped = PAGE_SHIFT - 4;
+	unsigned long level_mask, prev_level_entry, *levels[4];
+	int this_level, index, level_lsb, level_msb;
+
+	dst_addr &= PAGE_MASK;
+	prev_level_entry = pte_val(pfn_pte(pfn, PAGE_KERNEL_EXEC));
+
+	for (this_level = 3; this_level >= 0; this_level--) {
+		levels[this_level] = trans_alloc(info);
+		if (!levels[this_level])
+			return -ENOMEM;
+
+		level_lsb = ARM64_HW_PGTABLE_LEVEL_SHIFT(this_level);
+		level_msb = min(level_lsb + bits_mapped, max_msb);
+		level_mask = GENMASK_ULL(level_msb, level_lsb);
+
+		index = (dst_addr & level_mask) >> level_lsb;
+		*(levels[this_level] + index) = prev_level_entry;
+
+		pfn = virt_to_pfn(levels[this_level]);
+		prev_level_entry = pte_val(pfn_pte(pfn,
+						   __pgprot(PMD_TYPE_TABLE)));
+
+		if (level_msb == max_msb)
+			break;
+	}
+
+	*trans_ttbr0 = phys_to_ttbr(__pfn_to_phys(pfn));
+	*t0sz = TCR_T0SZ(max_msb + 1);
+
+	return 0;
+}

drivers/char/random.c

@@ -1261,8 +1261,6 @@ void add_interrupt_randomness(int irq, int irq_flags)
 	cycles_t		cycles = random_get_entropy();
 	__u32			c_high, j_high;
 	__u64			ip;
-	unsigned long		seed;
-	int			credit = 0;
 
 	if (cycles == 0)
 		cycles = get_reg(fast_pool, regs);
@@ -1298,23 +1296,12 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_pool->last = now;
 	__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool));
-
-	/*
-	 * If we have architectural seed generator, produce a seed and
-	 * add it to the pool.  For the sake of paranoia don't let the
-	 * architectural seed generator dominate the input from the
-	 * interrupt noise.
-	 */
-	if (arch_get_random_seed_long(&seed)) {
-		__mix_pool_bytes(r, &seed, sizeof(seed));
-		credit = 1;
-	}
 	spin_unlock(&r->lock);
 
 	fast_pool->count = 0;
 
 	/* award one bit for the contents of the fast pool */
-	credit_entropy_bits(r, credit + 1);
+	credit_entropy_bits(r, 1);
 }
 EXPORT_SYMBOL_GPL(add_interrupt_randomness);
 

drivers/firmware/smccc/smccc.c

@@ -5,16 +5,22 @@
 
 #define pr_fmt(fmt) "smccc: " fmt
 
+#include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/arm-smccc.h>
+#include <asm/archrandom.h>
 
 static u32 smccc_version = ARM_SMCCC_VERSION_1_0;
 static enum arm_smccc_conduit smccc_conduit = SMCCC_CONDUIT_NONE;
 
+bool __ro_after_init smccc_trng_available = false;
+
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit)
 {
 	smccc_version = version;
 	smccc_conduit = conduit;
+
+	smccc_trng_available = smccc_probe_trng();
 }
 
 enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)

drivers/perf/arm-cci.c

@@ -1026,12 +1026,11 @@ static void pmu_event_set_period(struct perf_event *event)
 
 static irqreturn_t pmu_handle_irq(int irq_num, void *dev)
 {
-	unsigned long flags;
 	struct cci_pmu *cci_pmu = dev;
 	struct cci_pmu_hw_events *events = &cci_pmu->hw_events;
 	int idx, handled = IRQ_NONE;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+	raw_spin_lock(&events->pmu_lock);
 
 	/* Disable the PMU while we walk through the counters */
 	__cci_pmu_disable(cci_pmu);
@@ -1061,7 +1060,7 @@ static irqreturn_t pmu_handle_irq(int irq_num, void *dev)
 
 	/* Enable the PMU and sync possibly overflowed counters */
 	__cci_pmu_enable_sync(cci_pmu);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+	raw_spin_unlock(&events->pmu_lock);
 
 	return IRQ_RETVAL(handled);
 }
@@ -1376,7 +1375,7 @@ static struct attribute *pmu_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group pmu_attr_group = {
+static const struct attribute_group pmu_attr_group = {
 	.attrs = pmu_attrs,
 };
 

drivers/perf/arm-cmn.c

@@ -616,7 +616,7 @@ static struct attribute *arm_cmn_cpumask_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group arm_cmn_cpumask_attr_group = {
+static const struct attribute_group arm_cmn_cpumask_attr_group = {
 	.attrs = arm_cmn_cpumask_attrs,
 };
 
@@ -1150,7 +1150,7 @@ static int arm_cmn_commit_txn(struct pmu *pmu)
 static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct arm_cmn *cmn;
-	unsigned int target;
+	unsigned int i, target;
 
 	cmn = hlist_entry_safe(node, struct arm_cmn, cpuhp_node);
 	if (cpu != cmn->cpu)
@@ -1161,6 +1161,8 @@ static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	perf_pmu_migrate_context(&cmn->pmu, cpu, target);
+	for (i = 0; i < cmn->num_dtcs; i++)
+		irq_set_affinity_hint(cmn->dtc[i].irq, cpumask_of(target));
 	cmn->cpu = target;
 	return 0;
 }
@@ -1502,7 +1504,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
 	struct arm_cmn *cmn;
 	const char *name;
 	static atomic_t id;
-	int err, rootnode, this_id;
+	int err, rootnode;
 
 	cmn = devm_kzalloc(&pdev->dev, sizeof(*cmn), GFP_KERNEL);
 	if (!cmn)
@@ -1549,14 +1551,9 @@ static int arm_cmn_probe(struct platform_device *pdev)
 		.cancel_txn = arm_cmn_end_txn,
 	};
 
-	this_id = atomic_fetch_inc(&id);
+	name = devm_kasprintf(cmn->dev, GFP_KERNEL, "arm_cmn_%d", atomic_fetch_inc(&id));
-	if (this_id == 0) {
-		name = "arm_cmn";
-	} else {
-		name = devm_kasprintf(cmn->dev, GFP_KERNEL, "arm_cmn_%d", this_id);
 	if (!name)
 		return -ENOMEM;
-	}
 
 	err = cpuhp_state_add_instance(arm_cmn_hp_state, &cmn->cpuhp_node);
 	if (err)

drivers/perf/arm_dmc620_pmu.c

@@ -159,7 +159,7 @@ static struct attribute *dmc620_pmu_events_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group dmc620_pmu_events_attr_group = {
+static const struct attribute_group dmc620_pmu_events_attr_group = {
 	.name = "events",
 	.attrs = dmc620_pmu_events_attrs,
 };
@@ -222,7 +222,7 @@ static struct attribute *dmc620_pmu_formats_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group dmc620_pmu_format_attr_group = {
+static const struct attribute_group dmc620_pmu_format_attr_group = {
 	.name	= "format",
 	.attrs	= dmc620_pmu_formats_attrs,
 };
@@ -717,6 +717,7 @@ static struct platform_driver dmc620_pmu_driver = {
 	.driver	= {
 		.name		= DMC620_DRVNAME,
 		.acpi_match_table = dmc620_acpi_match,
+		.suppress_bind_attrs = true,
 	},
 	.probe	= dmc620_pmu_device_probe,
 	.remove	= dmc620_pmu_device_remove,

drivers/perf/arm_pmu.c

@@ -577,7 +577,7 @@ static struct attribute *armpmu_common_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group armpmu_common_attr_group = {
+static const struct attribute_group armpmu_common_attr_group = {
 	.attrs = armpmu_common_attrs,
 };
 

drivers/perf/arm_smmuv3_pmu.c

@@ -493,7 +493,7 @@ static struct attribute *smmu_pmu_cpumask_attrs[] = {
 	NULL
 };
 
-static struct attribute_group smmu_pmu_cpumask_group = {
+static const struct attribute_group smmu_pmu_cpumask_group = {
 	.attrs = smmu_pmu_cpumask_attrs,
 };
 
@@ -548,7 +548,7 @@ static umode_t smmu_pmu_event_is_visible(struct kobject *kobj,
 	return 0;
 }
 
-static struct attribute_group smmu_pmu_events_group = {
+static const struct attribute_group smmu_pmu_events_group = {
 	.name = "events",
 	.attrs = smmu_pmu_events,
 	.is_visible = smmu_pmu_event_is_visible,
@@ -583,7 +583,7 @@ static struct attribute *smmu_pmu_identifier_attrs[] = {
 	NULL
 };
 
-static struct attribute_group smmu_pmu_identifier_group = {
+static const struct attribute_group smmu_pmu_identifier_group = {
 	.attrs = smmu_pmu_identifier_attrs,
 	.is_visible = smmu_pmu_identifier_attr_visible,
 };
@@ -602,7 +602,7 @@ static struct attribute *smmu_pmu_formats[] = {
 	NULL
 };
 
-static struct attribute_group smmu_pmu_format_group = {
+static const struct attribute_group smmu_pmu_format_group = {
 	.name = "format",
 	.attrs = smmu_pmu_formats,
 };

drivers/perf/arm_spe_pmu.c

@@ -54,7 +54,7 @@ struct arm_spe_pmu {
 	struct hlist_node			hotplug_node;
 
 	int					irq; /* PPI */
-
+	u16					pmsver;
 	u16					min_period;
 	u16					counter_sz;
 
@@ -146,7 +146,7 @@ static struct attribute *arm_spe_pmu_cap_attr[] = {
 	NULL,
 };
 
-static struct attribute_group arm_spe_pmu_cap_group = {
+static const struct attribute_group arm_spe_pmu_cap_group = {
 	.name	= "caps",
 	.attrs	= arm_spe_pmu_cap_attr,
 };
@@ -227,7 +227,7 @@ static struct attribute *arm_spe_pmu_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group arm_spe_pmu_format_group = {
+static const struct attribute_group arm_spe_pmu_format_group = {
 	.name	= "format",
 	.attrs	= arm_spe_pmu_formats_attr,
 };
@@ -247,7 +247,7 @@ static struct attribute *arm_spe_pmu_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group arm_spe_pmu_group = {
+static const struct attribute_group arm_spe_pmu_group = {
 	.attrs	= arm_spe_pmu_attrs,
 };
 
@@ -655,6 +655,18 @@ static irqreturn_t arm_spe_pmu_irq_handler(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
+static u64 arm_spe_pmsevfr_res0(u16 pmsver)
+{
+	switch (pmsver) {
+	case ID_AA64DFR0_PMSVER_8_2:
+		return SYS_PMSEVFR_EL1_RES0_8_2;
+	case ID_AA64DFR0_PMSVER_8_3:
+	/* Return the highest version we support in default */
+	default:
+		return SYS_PMSEVFR_EL1_RES0_8_3;
+	}
+}
+
 /* Perf callbacks */
 static int arm_spe_pmu_event_init(struct perf_event *event)
 {
@@ -670,7 +682,7 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 	    !cpumask_test_cpu(event->cpu, &spe_pmu->supported_cpus))
 		return -ENOENT;
 
-	if (arm_spe_event_to_pmsevfr(event) & SYS_PMSEVFR_EL1_RES0)
+	if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
 		return -EOPNOTSUPP;
 
 	if (attr->exclude_idle)
@@ -937,6 +949,7 @@ static void __arm_spe_pmu_dev_probe(void *info)
 			fld, smp_processor_id());
 		return;
 	}
+	spe_pmu->pmsver = (u16)fld;
 
 	/* Read PMBIDR first to determine whether or not we have access */
 	reg = read_sysreg_s(SYS_PMBIDR_EL1);

drivers/perf/fsl_imx8_ddr_perf.c

@@ -133,7 +133,7 @@ static struct attribute *ddr_perf_identifier_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group ddr_perf_identifier_attr_group = {
+static const struct attribute_group ddr_perf_identifier_attr_group = {
 	.attrs = ddr_perf_identifier_attrs,
 	.is_visible = ddr_perf_identifier_attr_visible,
 };
@@ -188,7 +188,7 @@ static struct attribute *ddr_perf_filter_cap_attr[] = {
 	NULL,
 };
 
-static struct attribute_group ddr_perf_filter_cap_attr_group = {
+static const struct attribute_group ddr_perf_filter_cap_attr_group = {
 	.name = "caps",
 	.attrs = ddr_perf_filter_cap_attr,
 };
@@ -209,7 +209,7 @@ static struct attribute *ddr_perf_cpumask_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group ddr_perf_cpumask_attr_group = {
+static const struct attribute_group ddr_perf_cpumask_attr_group = {
 	.attrs = ddr_perf_cpumask_attrs,
 };
 
@@ -265,7 +265,7 @@ static struct attribute *ddr_perf_events_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group ddr_perf_events_attr_group = {
+static const struct attribute_group ddr_perf_events_attr_group = {
 	.name = "events",
 	.attrs = ddr_perf_events_attrs,
 };
@@ -281,7 +281,7 @@ static struct attribute *ddr_perf_format_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group ddr_perf_format_attr_group = {
+static const struct attribute_group ddr_perf_format_attr_group = {
 	.name = "format",
 	.attrs = ddr_perf_format_attrs,
 };

drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c

@@ -319,7 +319,7 @@ static struct attribute *hisi_ddrc_pmu_identifier_attrs[] = {
 	NULL
 };
 
-static struct attribute_group hisi_ddrc_pmu_identifier_group = {
+static const struct attribute_group hisi_ddrc_pmu_identifier_group = {
 	.attrs = hisi_ddrc_pmu_identifier_attrs,
 };
 

drivers/perf/hisilicon/hisi_uncore_hha_pmu.c

@@ -331,7 +331,7 @@ static struct attribute *hisi_hha_pmu_identifier_attrs[] = {
 	NULL
 };
 
-static struct attribute_group hisi_hha_pmu_identifier_group = {
+static const struct attribute_group hisi_hha_pmu_identifier_group = {
 	.attrs = hisi_hha_pmu_identifier_attrs,
 };
 

drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c

@@ -321,7 +321,7 @@ static struct attribute *hisi_l3c_pmu_identifier_attrs[] = {
 	NULL
 };
 
-static struct attribute_group hisi_l3c_pmu_identifier_group = {
+static const struct attribute_group hisi_l3c_pmu_identifier_group = {
 	.attrs = hisi_l3c_pmu_identifier_attrs,
 };
 

drivers/perf/qcom_l2_pmu.c

@@ -649,7 +649,7 @@ static struct attribute *l2_cache_pmu_cpumask_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group l2_cache_pmu_cpumask_group = {
+static const struct attribute_group l2_cache_pmu_cpumask_group = {
 	.attrs = l2_cache_pmu_cpumask_attrs,
 };
 
@@ -665,7 +665,7 @@ static struct attribute *l2_cache_pmu_formats[] = {
 	NULL,
 };
 
-static struct attribute_group l2_cache_pmu_format_group = {
+static const struct attribute_group l2_cache_pmu_format_group = {
 	.name = "format",
 	.attrs = l2_cache_pmu_formats,
 };
@@ -700,7 +700,7 @@ static struct attribute *l2_cache_pmu_events[] = {
 	NULL
 };
 
-static struct attribute_group l2_cache_pmu_events_group = {
+static const struct attribute_group l2_cache_pmu_events_group = {
 	.name = "events",
 	.attrs = l2_cache_pmu_events,
 };

drivers/perf/qcom_l3_pmu.c

@@ -630,7 +630,7 @@ static struct attribute *qcom_l3_cache_pmu_formats[] = {
 	NULL,
 };
 
-static struct attribute_group qcom_l3_cache_pmu_format_group = {
+static const struct attribute_group qcom_l3_cache_pmu_format_group = {
 	.name = "format",
 	.attrs = qcom_l3_cache_pmu_formats,
 };
@@ -663,7 +663,7 @@ static struct attribute *qcom_l3_cache_pmu_events[] = {
 	NULL
 };
 
-static struct attribute_group qcom_l3_cache_pmu_events_group = {
+static const struct attribute_group qcom_l3_cache_pmu_events_group = {
 	.name = "events",
 	.attrs = qcom_l3_cache_pmu_events,
 };
@@ -685,7 +685,7 @@ static struct attribute *qcom_l3_cache_pmu_cpumask_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group qcom_l3_cache_pmu_cpumask_attr_group = {
+static const struct attribute_group qcom_l3_cache_pmu_cpumask_attr_group = {
 	.attrs = qcom_l3_cache_pmu_cpumask_attrs,
 };
 

drivers/perf/xgene_pmu.c

@@ -1234,10 +1234,9 @@ static irqreturn_t xgene_pmu_isr(int irq, void *dev_id)
 	u32 intr_mcu, intr_mcb, intr_l3c, intr_iob;
 	struct xgene_pmu_dev_ctx *ctx;
 	struct xgene_pmu *xgene_pmu = dev_id;
-	unsigned long flags;
 	u32 val;
 
-	raw_spin_lock_irqsave(&xgene_pmu->lock, flags);
+	raw_spin_lock(&xgene_pmu->lock);
 
 	/* Get Interrupt PMU source */
 	val = readl(xgene_pmu->pcppmu_csr + PCPPMU_INTSTATUS_REG);
@@ -1273,7 +1272,7 @@ static irqreturn_t xgene_pmu_isr(int irq, void *dev_id)
 		}
 	}
 
-	raw_spin_unlock_irqrestore(&xgene_pmu->lock, flags);
+	raw_spin_unlock(&xgene_pmu->lock);
 
 	return IRQ_HANDLED;
 }

fs/xfs/xfs_file.c

@@ -1376,17 +1376,19 @@ xfs_filemap_pfn_mkwrite(
 	return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true);
 }
 
-static void
+static vm_fault_t
 xfs_filemap_map_pages(
 	struct vm_fault		*vmf,
 	pgoff_t			start_pgoff,
 	pgoff_t			end_pgoff)
 {
 	struct inode		*inode = file_inode(vmf->vma->vm_file);
+	vm_fault_t ret;
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	filemap_map_pages(vmf, start_pgoff, end_pgoff);
+	ret = filemap_map_pages(vmf, start_pgoff, end_pgoff);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	return ret;
 }
 
 static const struct vm_operations_struct xfs_file_vm_ops = {

include/linux/arm-smccc.h

@@ -102,6 +102,37 @@
 			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
 			   0x21)
 
+/* TRNG entropy source calls (defined by ARM DEN0098) */
+#define ARM_SMCCC_TRNG_VERSION					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_32,			\
+			   ARM_SMCCC_OWNER_STANDARD,		\
+			   0x50)
+
+#define ARM_SMCCC_TRNG_FEATURES					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_32,			\
+			   ARM_SMCCC_OWNER_STANDARD,		\
+			   0x51)
+
+#define ARM_SMCCC_TRNG_GET_UUID					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_32,			\
+			   ARM_SMCCC_OWNER_STANDARD,		\
+			   0x52)
+
+#define ARM_SMCCC_TRNG_RND32					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_32,			\
+			   ARM_SMCCC_OWNER_STANDARD,		\
+			   0x53)
+
+#define ARM_SMCCC_TRNG_RND64					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD,		\
+			   0x53)
+
 /*
  * Return codes defined in ARM DEN 0070A
  * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C

include/linux/mm.h

@@ -514,11 +514,14 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags)
  * pgoff should be used in favour of virtual_address, if possible.
  */
 struct vm_fault {
+	const struct {
 		struct vm_area_struct *vma;	/* Target VMA */
-	unsigned int flags;		/* FAULT_FLAG_xxx flags */
 		gfp_t gfp_mask;			/* gfp mask to be used for allocations */
 		pgoff_t pgoff;			/* Logical page offset based on vma */
 		unsigned long address;		/* Faulting virtual address */
+	};
+	unsigned int flags;		/* FAULT_FLAG_xxx flags
+					 * XXX: should really be 'const' */
 	pmd_t *pmd;			/* Pointer to pmd entry matching
 					 * the 'address' */
 	pud_t *pud;			/* Pointer to pud entry matching
@@ -542,8 +545,8 @@ struct vm_fault {
 					 * is not NULL, otherwise pmd.
 					 */
 	pgtable_t prealloc_pte;		/* Pre-allocated pte page table.
-					 * vm_ops->map_pages() calls
+					 * vm_ops->map_pages() sets up a page
-					 * alloc_set_pte() from atomic context.
+					 * table from atomic context.
 					 * do_fault_around() pre-allocates
 					 * page table to avoid allocation from
 					 * atomic context.
@@ -578,7 +581,7 @@ struct vm_operations_struct {
 	vm_fault_t (*fault)(struct vm_fault *vmf);
 	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
 			enum page_entry_size pe_size);
-	void (*map_pages)(struct vm_fault *vmf,
+	vm_fault_t (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 	unsigned long (*pagesize)(struct vm_area_struct * area);
 
@@ -988,7 +991,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 	return pte;
 }
 
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page);
+vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
+void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr);
+
 vm_fault_t finish_fault(struct vm_fault *vmf);
 vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 #endif
@@ -2622,7 +2627,7 @@ extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern vm_fault_t filemap_fault(struct vm_fault *vmf);
-extern void filemap_map_pages(struct vm_fault *vmf,
+extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
 

include/linux/pgtable.h

@@ -1314,6 +1314,17 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #endif
 }
 
+/*
+ * the ordering of these checks is important for pmds with _page_devmap set.
+ * if we check pmd_trans_unstable() first we will trip the bad_pmd() check
+ * inside of pmd_none_or_trans_huge_or_clear_bad(). this will end up correctly
+ * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
+ */
+static inline int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
 #ifndef CONFIG_NUMA_BALANCING
 /*
  * Technically a PTE can be PROTNONE even when not doing NUMA balancing but

mm/filemap.c

@@ -42,6 +42,8 @@
 #include <linux/psi.h>
 #include <linux/ramfs.h>
 #include <linux/page_idle.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -2915,74 +2917,163 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
-void filemap_map_pages(struct vm_fault *vmf,
+static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
+{
+	struct mm_struct *mm = vmf->vma->vm_mm;
+
+	/* Huge page is mapped? No need to proceed. */
+	if (pmd_trans_huge(*vmf->pmd)) {
+		unlock_page(page);
+		put_page(page);
+		return true;
+	}
+
+	if (pmd_none(*vmf->pmd) && PageTransHuge(page)) {
+	    vm_fault_t ret = do_set_pmd(vmf, page);
+	    if (!ret) {
+		    /* The page is mapped successfully, reference consumed. */
+		    unlock_page(page);
+		    return true;
+	    }
+	}
+
+	if (pmd_none(*vmf->pmd)) {
+		vmf->ptl = pmd_lock(mm, vmf->pmd);
+		if (likely(pmd_none(*vmf->pmd))) {
+			mm_inc_nr_ptes(mm);
+			pmd_populate(mm, vmf->pmd, vmf->prealloc_pte);
+			vmf->prealloc_pte = NULL;
+		}
+		spin_unlock(vmf->ptl);
+	}
+
+	/* See comment in handle_pte_fault() */
+	if (pmd_devmap_trans_unstable(vmf->pmd)) {
+		unlock_page(page);
+		put_page(page);
+		return true;
+	}
+
+	return false;
+}
+
+static struct page *next_uptodate_page(struct page *page,
+				       struct address_space *mapping,
+				       struct xa_state *xas, pgoff_t end_pgoff)
+{
+	unsigned long max_idx;
+
+	do {
+		if (!page)
+			return NULL;
+		if (xas_retry(xas, page))
+			continue;
+		if (xa_is_value(page))
+			continue;
+		if (PageLocked(page))
+			continue;
+		if (!page_cache_get_speculative(page))
+			continue;
+		/* Has the page moved or been split? */
+		if (unlikely(page != xas_reload(xas)))
+			goto skip;
+		if (!PageUptodate(page) || PageReadahead(page))
+			goto skip;
+		if (PageHWPoison(page))
+			goto skip;
+		if (!trylock_page(page))
+			goto skip;
+		if (page->mapping != mapping)
+			goto unlock;
+		if (!PageUptodate(page))
+			goto unlock;
+		max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
+		if (xas->xa_index >= max_idx)
+			goto unlock;
+		return page;
+unlock:
+		unlock_page(page);
+skip:
+		put_page(page);
+	} while ((page = xas_next_entry(xas, end_pgoff)) != NULL);
+
+	return NULL;
+}
+
+static inline struct page *first_map_page(struct address_space *mapping,
+					  struct xa_state *xas,
+					  pgoff_t end_pgoff)
+{
+	return next_uptodate_page(xas_find(xas, end_pgoff),
+				  mapping, xas, end_pgoff);
+}
+
+static inline struct page *next_map_page(struct address_space *mapping,
+					 struct xa_state *xas,
+					 pgoff_t end_pgoff)
+{
+	return next_uptodate_page(xas_next_entry(xas, end_pgoff),
+				  mapping, xas, end_pgoff);
+}
+
+vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 			     pgoff_t start_pgoff, pgoff_t end_pgoff)
 {
-	struct file *file = vmf->vma->vm_file;
+	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	pgoff_t last_pgoff = start_pgoff;
-	unsigned long max_idx;
+	unsigned long addr;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct page *head, *page;
 	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
+	vm_fault_t ret = 0;
 
 	rcu_read_lock();
-	xas_for_each(&xas, head, end_pgoff) {
+	head = first_map_page(mapping, &xas, end_pgoff);
-		if (xas_retry(&xas, head))
+	if (!head)
-			continue;
+		goto out;
-		if (xa_is_value(head))
-			goto next;
 
-		/*
+	if (filemap_map_pmd(vmf, head)) {
-		 * Check for a locked page first, as a speculative
+		ret = VM_FAULT_NOPAGE;
-		 * reference may adversely influence page migration.
+		goto out;
-		 */
+	}
-		if (PageLocked(head))
-			goto next;
-		if (!page_cache_get_speculative(head))
-			goto next;
 
-		/* Has the page moved or been split? */
+	addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT);
-		if (unlikely(head != xas_reload(&xas)))
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
-			goto skip;
+	do {
 		page = find_subpage(head, xas.xa_index);
-
+		if (PageHWPoison(page))
-		if (!PageUptodate(head) ||
-				PageReadahead(page) ||
-				PageHWPoison(page))
-			goto skip;
-		if (!trylock_page(head))
-			goto skip;
-
-		if (head->mapping != mapping || !PageUptodate(head))
-			goto unlock;
-
-		max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
-		if (xas.xa_index >= max_idx)
 			goto unlock;
 
 		if (mmap_miss > 0)
 			mmap_miss--;
 
-		vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
+		addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
-		if (vmf->pte)
 		vmf->pte += xas.xa_index - last_pgoff;
 		last_pgoff = xas.xa_index;
-		if (alloc_set_pte(vmf, page))
+
+		if (!pte_none(*vmf->pte))
 			goto unlock;
+
+		/* We're about to handle the fault */
+		if (vmf->address == addr)
+			ret = VM_FAULT_NOPAGE;
+
+		do_set_pte(vmf, page, addr);
+		/* no need to invalidate: a not-present page won't be cached */
+		update_mmu_cache(vma, addr, vmf->pte);
 		unlock_page(head);
-		goto next;
+		continue;
 unlock:
 		unlock_page(head);
-skip:
 		put_page(head);
-next:
+	} while ((head = next_map_page(mapping, &xas, end_pgoff)) != NULL);
-		/* Huge page is mapped? No need to proceed. */
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
-		if (pmd_trans_huge(*vmf->pmd))
+out:
-			break;
-	}
 	rcu_read_unlock();
 	WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
+	return ret;
 }
 EXPORT_SYMBOL(filemap_map_pages);
 

mm/khugepaged.c

@@ -991,38 +991,41 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 
 static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 					struct vm_area_struct *vma,
-					unsigned long address, pmd_t *pmd,
+					unsigned long haddr, pmd_t *pmd,
 					int referenced)
 {
 	int swapped_in = 0;
 	vm_fault_t ret = 0;
+	unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE);
+
+	for (address = haddr; address < end; address += PAGE_SIZE) {
 		struct vm_fault vmf = {
 			.vma = vma,
 			.address = address,
+			.pgoff = linear_page_index(vma, haddr),
 			.flags = FAULT_FLAG_ALLOW_RETRY,
 			.pmd = pmd,
-		.pgoff = linear_page_index(vma, address),
 		};
 
 		vmf.pte = pte_offset_map(pmd, address);
-	for (; vmf.address < address + HPAGE_PMD_NR*PAGE_SIZE;
-			vmf.pte++, vmf.address += PAGE_SIZE) {
 		vmf.orig_pte = *vmf.pte;
-		if (!is_swap_pte(vmf.orig_pte))
+		if (!is_swap_pte(vmf.orig_pte)) {
+			pte_unmap(vmf.pte);
 			continue;
+		}
 		swapped_in++;
 		ret = do_swap_page(&vmf);
 
 		/* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */
 		if (ret & VM_FAULT_RETRY) {
 			mmap_read_lock(mm);
-			if (hugepage_vma_revalidate(mm, address, &vmf.vma)) {
+			if (hugepage_vma_revalidate(mm, haddr, &vma)) {
 				/* vma is no longer available, don't continue to swapin */
 				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
 			}
 			/* check if the pmd is still valid */
-			if (mm_find_pmd(mm, address) != pmd) {
+			if (mm_find_pmd(mm, haddr) != pmd) {
 				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
 			}
@@ -1031,11 +1034,7 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 			return false;
 		}
-		/* pte is unmapped now, we need to map it */
-		vmf.pte = pte_offset_map(pmd, vmf.address);
 	}
-	vmf.pte--;
-	pte_unmap(vmf.pte);
 
 	/* Drain LRU add pagevec to remove extra pin on the swapped in pages */
 	if (swapped_in)

mm/memory.c

@@ -134,6 +134,18 @@ static inline bool arch_faults_on_old_pte(void)
 }
 #endif
 
+#ifndef arch_wants_old_prefaulted_pte
+static inline bool arch_wants_old_prefaulted_pte(void)
+{
+	/*
+	 * Transitioning a PTE from 'old' to 'young' can be expensive on
+	 * some architectures, even if it's performed in hardware. By
+	 * default, "false" means prefaulted entries will be 'young'.
+	 */
+	return false;
+}
+#endif
+
 static int __init disable_randmaps(char *s)
 {
 	randomize_va_space = 0;
@@ -3503,7 +3515,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	if (pte_alloc(vma->vm_mm, vmf->pmd))
 		return VM_FAULT_OOM;
 
-	/* See the comment in pte_alloc_one_map() */
+	/* See comment in handle_pte_fault() */
 	if (unlikely(pmd_trans_unstable(vmf->pmd)))
 		return 0;
 
@@ -3643,66 +3655,6 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 	return ret;
 }
 
-/*
- * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
- * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
- * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
- * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
- */
-static int pmd_devmap_trans_unstable(pmd_t *pmd)
-{
-	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
-}
-
-static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-
-	if (!pmd_none(*vmf->pmd))
-		goto map_pte;
-	if (vmf->prealloc_pte) {
-		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
-		if (unlikely(!pmd_none(*vmf->pmd))) {
-			spin_unlock(vmf->ptl);
-			goto map_pte;
-		}
-
-		mm_inc_nr_ptes(vma->vm_mm);
-		pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
-		spin_unlock(vmf->ptl);
-		vmf->prealloc_pte = NULL;
-	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) {
-		return VM_FAULT_OOM;
-	}
-map_pte:
-	/*
-	 * If a huge pmd materialized under us just retry later.  Use
-	 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
-	 * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
-	 * under us and then back to pmd_none, as a result of MADV_DONTNEED
-	 * running immediately after a huge pmd fault in a different thread of
-	 * this mm, in turn leading to a misleading pmd_trans_huge() retval.
-	 * All we have to ensure is that it is a regular pmd that we can walk
-	 * with pte_offset_map() and we can do that through an atomic read in
-	 * C, which is what pmd_trans_unstable() provides.
-	 */
-	if (pmd_devmap_trans_unstable(vmf->pmd))
-		return VM_FAULT_NOPAGE;
-
-	/*
-	 * At this point we know that our vmf->pmd points to a page of ptes
-	 * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
-	 * for the duration of the fault.  If a racing MADV_DONTNEED runs and
-	 * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
-	 * be valid and we will re-check to make sure the vmf->pte isn't
-	 * pte_none() under vmf->ptl protection when we return to
-	 * alloc_set_pte().
-	 */
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
-	return 0;
-}
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void deposit_prealloc_pte(struct vm_fault *vmf)
 {
@@ -3717,7 +3669,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf)
 	vmf->prealloc_pte = NULL;
 }
 
-static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
+vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -3775,76 +3727,41 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	return ret;
 }
 #else
-static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
+vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
-	BUILD_BUG();
+	return VM_FAULT_FALLBACK;
-	return 0;
 }
 #endif
 
-/**
+void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
- * alloc_set_pte - setup new PTE entry for given page and add reverse page
- * mapping. If needed, the function allocates page table or use pre-allocated.
- *
- * @vmf: fault environment
- * @page: page to map
- *
- * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on
- * return.
- *
- * Target users are page handler itself and implementations of
- * vm_ops->map_pages.
- *
- * Return: %0 on success, %VM_FAULT_ code in case of error.
- */
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	bool prefault = vmf->address != addr;
 	pte_t entry;
-	vm_fault_t ret;
-
-	if (pmd_none(*vmf->pmd) && PageTransCompound(page)) {
-		ret = do_set_pmd(vmf, page);
-		if (ret != VM_FAULT_FALLBACK)
-			return ret;
-	}
-
-	if (!vmf->pte) {
-		ret = pte_alloc_one_map(vmf);
-		if (ret)
-			return ret;
-	}
-
-	/* Re-check under ptl */
-	if (unlikely(!pte_none(*vmf->pte))) {
-		update_mmu_tlb(vma, vmf->address, vmf->pte);
-		return VM_FAULT_NOPAGE;
-	}
 
 	flush_icache_page(vma, page);
 	entry = mk_pte(page, vma->vm_page_prot);
+
+	if (prefault && arch_wants_old_prefaulted_pte())
+		entry = pte_mkold(entry);
+	else
 		entry = pte_sw_mkyoung(entry);
+
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	/* copy-on-write page */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, vmf->address, false);
+		page_add_new_anon_rmap(page, vma, addr, false);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, false);
 	}
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
+	set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
-
-	/* no need to invalidate: a not-present page won't be cached */
-	update_mmu_cache(vma, vmf->address, vmf->pte);
-
-	return 0;
 }
 
-
 /**
  * finish_fault - finish page fault once we have prepared the page to fault
  *
@@ -3862,12 +3779,12 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
  */
 vm_fault_t finish_fault(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page;
-	vm_fault_t ret = 0;
+	vm_fault_t ret;
 
 	/* Did we COW the page? */
-	if ((vmf->flags & FAULT_FLAG_WRITE) &&
+	if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
-	    !(vmf->vma->vm_flags & VM_SHARED))
 		page = vmf->cow_page;
 	else
 		page = vmf->page;
@@ -3876,11 +3793,37 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	 * check even for read faults because we might have lost our CoWed
 	 * page
 	 */
-	if (!(vmf->vma->vm_flags & VM_SHARED))
+	if (!(vma->vm_flags & VM_SHARED)) {
-		ret = check_stable_address_space(vmf->vma->vm_mm);
+		ret = check_stable_address_space(vma->vm_mm);
-	if (!ret)
+		if (ret)
-		ret = alloc_set_pte(vmf, page);
+			return ret;
-	if (vmf->pte)
+	}
+
+	if (pmd_none(*vmf->pmd)) {
+		if (PageTransCompound(page)) {
+			ret = do_set_pmd(vmf, page);
+			if (ret != VM_FAULT_FALLBACK)
+				return ret;
+		}
+
+		if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
+			return VM_FAULT_OOM;
+	}
+
+	/* See comment in handle_pte_fault() */
+	if (pmd_devmap_trans_unstable(vmf->pmd))
+		return 0;
+
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+				      vmf->address, &vmf->ptl);
+	ret = 0;
+	/* Re-check under ptl */
+	if (likely(pte_none(*vmf->pte)))
+		do_set_pte(vmf, page, vmf->address);
+	else
+		ret = VM_FAULT_NOPAGE;
+
+	update_mmu_tlb(vma, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
 }
@@ -3951,13 +3894,12 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 	pgoff_t start_pgoff = vmf->pgoff;
 	pgoff_t end_pgoff;
 	int off;
-	vm_fault_t ret = 0;
 
 	nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT;
 	mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK;
 
-	vmf->address = max(address & mask, vmf->vma->vm_start);
+	address = max(address & mask, vmf->vma->vm_start);
-	off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+	off = ((vmf->address - address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
 	start_pgoff -= off;
 
 	/*
@@ -3965,7 +3907,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 	 *  the vma or nr_pages from start_pgoff, depending what is nearest.
 	 */
 	end_pgoff = start_pgoff -
-		((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
+		((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
 		PTRS_PER_PTE - 1;
 	end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1,
 			start_pgoff + nr_pages - 1);
@@ -3973,31 +3915,11 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 	if (pmd_none(*vmf->pmd)) {
 		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
 		if (!vmf->prealloc_pte)
-			goto out;
+			return VM_FAULT_OOM;
 		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
-	vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
+	return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
-
-	/* Huge page is mapped? Page fault is solved */
-	if (pmd_trans_huge(*vmf->pmd)) {
-		ret = VM_FAULT_NOPAGE;
-		goto out;
-	}
-
-	/* ->map_pages() haven't done anything useful. Cold page cache? */
-	if (!vmf->pte)
-		goto out;
-
-	/* check if the page fault is solved */
-	vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT);
-	if (!pte_none(*vmf->pte))
-		ret = VM_FAULT_NOPAGE;
-	pte_unmap_unlock(vmf->pte, vmf->ptl);
-out:
-	vmf->address = address;
-	vmf->pte = NULL;
-	return ret;
 }
 
 static vm_fault_t do_read_fault(struct vm_fault *vmf)
@@ -4353,7 +4275,18 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		 */
 		vmf->pte = NULL;
 	} else {
-		/* See comment in pte_alloc_one_map() */
+		/*
+		 * If a huge pmd materialized under us just retry later.  Use
+		 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead
+		 * of pmd_trans_huge() to ensure the pmd didn't become
+		 * pmd_trans_huge under us and then back to pmd_none, as a
+		 * result of MADV_DONTNEED running immediately after a huge pmd
+		 * fault in a different thread of this mm, in turn leading to a
+		 * misleading pmd_trans_huge() retval. All we have to ensure is
+		 * that it is a regular pmd that we can walk with
+		 * pte_offset_map() and we can do that through an atomic read
+		 * in C, which is what pmd_trans_unstable() provides.
+		 */
 		if (pmd_devmap_trans_unstable(vmf->pmd))
 			return 0;
 		/*

mm/nommu.c

@@ -1668,10 +1668,11 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
-void filemap_map_pages(struct vm_fault *vmf,
+vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff)
 {
 	BUG();
+	return 0;
 }
 EXPORT_SYMBOL(filemap_map_pages);
 

mm/shmem.c

@@ -1520,11 +1520,11 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
 {
 	struct vm_area_struct pvma;
 	struct page *page;
-	struct vm_fault vmf;
+	struct vm_fault vmf = {
+		.vma = &pvma,
+	};
 
 	shmem_pseudo_vma_init(&pvma, info, index);
-	vmf.vma = &pvma;
-	vmf.address = 0;
 	page = swap_cluster_readahead(swap, gfp, &vmf);
 	shmem_pseudo_vma_destroy(&pvma);
 

mm/swapfile.c

@@ -1951,8 +1951,6 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	si = swap_info[type];
 	pte = pte_offset_map(pmd, addr);
 	do {
-		struct vm_fault vmf;
-
 		if (!is_swap_pte(*pte))
 			continue;
 
@@ -1968,9 +1966,12 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		swap_map = &si->swap_map[offset];
 		page = lookup_swap_cache(entry, vma, addr);
 		if (!page) {
-			vmf.vma = vma;
+			struct vm_fault vmf = {
-			vmf.address = addr;
+				.vma = vma,
-			vmf.pmd = pmd;
+				.address = addr,
+				.pmd = pmd,
+			};
+
 			page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
 						&vmf);
 		}

tools/testing/selftests/arm64/mte/check_buffer_fill.c

@@ -81,7 +81,7 @@ static int check_buffer_underflow_by_byte(int mem_type, int mode,
 		last_index = 0;
 		/* Set some value in tagged memory and make the buffer underflow */
 		for (j = sizes[i] - 1; (j >= -underflow_range) &&
-				       (cur_mte_cxt.fault_valid == false); j--) {
+				       (!cur_mte_cxt.fault_valid); j--) {
 			ptr[j] = '1';
 			last_index = j;
 		}