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

Pull arm64 updates from Will Deacon:
 "A sizeable pile of arm64 updates for 5.8.

  Summary below, but the big two features are support for Branch Target
  Identification and Clang's Shadow Call stack. The latter is currently
  arm64-only, but the high-level parts are all in core code so it could
  easily be adopted by other architectures pending toolchain support

  Branch Target Identification (BTI):

   - Support for ARMv8.5-BTI in both user- and kernel-space. This allows
     branch targets to limit the types of branch from which they can be
     called and additionally prevents branching to arbitrary code,
     although kernel support requires a very recent toolchain.

   - Function annotation via SYM_FUNC_START() so that assembly functions
     are wrapped with the relevant "landing pad" instructions.

   - BPF and vDSO updates to use the new instructions.

   - Addition of a new HWCAP and exposure of BTI capability to userspace
     via ID register emulation, along with ELF loader support for the
     BTI feature in .note.gnu.property.

   - Non-critical fixes to CFI unwind annotations in the sigreturn
     trampoline.

  Shadow Call Stack (SCS):

   - Support for Clang's Shadow Call Stack feature, which reserves
     platform register x18 to point at a separate stack for each task
     that holds only return addresses. This protects function return
     control flow from buffer overruns on the main stack.

   - Save/restore of x18 across problematic boundaries (user-mode,
     hypervisor, EFI, suspend, etc).

   - Core support for SCS, should other architectures want to use it
     too.

   - SCS overflow checking on context-switch as part of the existing
     stack limit check if CONFIG_SCHED_STACK_END_CHECK=y.

  CPU feature detection:

   - Removed numerous "SANITY CHECK" errors when running on a system
     with mismatched AArch32 support at EL1. This is primarily a concern
     for KVM, which disabled support for 32-bit guests on such a system.

   - Addition of new ID registers and fields as the architecture has
     been extended.

  Perf and PMU drivers:

   - Minor fixes and cleanups to system PMU drivers.

  Hardware errata:

   - Unify KVM workarounds for VHE and nVHE configurations.

   - Sort vendor errata entries in Kconfig.

  Secure Monitor Call Calling Convention (SMCCC):

   - Update to the latest specification from Arm (v1.2).

   - Allow PSCI code to query the SMCCC version.

  Software Delegated Exception Interface (SDEI):

   - Unexport a bunch of unused symbols.

   - Minor fixes to handling of firmware data.

  Pointer authentication:

   - Add support for dumping the kernel PAC mask in vmcoreinfo so that
     the stack can be unwound by tools such as kdump.

   - Simplification of key initialisation during CPU bringup.

  BPF backend:

   - Improve immediate generation for logical and add/sub instructions.

  vDSO:

   - Minor fixes to the linker flags for consistency with other
     architectures and support for LLVM's unwinder.

   - Clean up logic to initialise and map the vDSO into userspace.

  ACPI:

   - Work around for an ambiguity in the IORT specification relating to
     the "num_ids" field.

   - Support _DMA method for all named components rather than only PCIe
     root complexes.

   - Minor other IORT-related fixes.

  Miscellaneous:

   - Initialise debug traps early for KGDB and fix KDB cacheflushing
     deadlock.

   - Minor tweaks to early boot state (documentation update, set
     TEXT_OFFSET to 0x0, increase alignment of PE/COFF sections).

   - Refactoring and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (148 commits)
  KVM: arm64: Move __load_guest_stage2 to kvm_mmu.h
  KVM: arm64: Check advertised Stage-2 page size capability
  arm64/cpufeature: Add get_arm64_ftr_reg_nowarn()
  ACPI/IORT: Remove the unused __get_pci_rid()
  arm64/cpuinfo: Add ID_MMFR4_EL1 into the cpuinfo_arm64 context
  arm64/cpufeature: Add remaining feature bits in ID_AA64PFR1 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64PFR0 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64ISAR0 register
  arm64/cpufeature: Add remaining feature bits in ID_MMFR4 register
  arm64/cpufeature: Add remaining feature bits in ID_PFR0 register
  arm64/cpufeature: Introduce ID_MMFR5 CPU register
  arm64/cpufeature: Introduce ID_DFR1 CPU register
  arm64/cpufeature: Introduce ID_PFR2 CPU register
  arm64/cpufeature: Make doublelock a signed feature in ID_AA64DFR0
  arm64/cpufeature: Drop TraceFilt feature exposure from ID_DFR0 register
  arm64/cpufeature: Add explicit ftr_id_isar0[] for ID_ISAR0 register
  arm64: mm: Add asid_gen_match() helper
  firmware: smccc: Fix missing prototype warning for arm_smccc_version_init
  arm64: vdso: Fix CFI directives in sigreturn trampoline
  arm64: vdso: Don't prefix sigreturn trampoline with a BTI C instruction
  ...

1 files changed, 105 insertions, 57 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 819d62a9d89f..552d36cacc05 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -9,6 +9,7 @@ config ARM64
 	select ACPI_MCFG if (ACPI && PCI)
 	select ACPI_SPCR_TABLE if ACPI
 	select ACPI_PPTT if ACPI
+	select ARCH_BINFMT_ELF_STATE
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_PREP_COHERENT
@@ -33,6 +34,7 @@ config ARM64
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAVE_ELF_PROT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
@@ -62,9 +64,12 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_GNU_PROPERTY
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_USE_SYM_ANNOTATIONS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
+	select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
 	select ARCH_SUPPORTS_NUMA_BALANCING
@@ -525,13 +530,13 @@ config ARM64_ERRATUM_1418040
 
 	  If unsure, say Y.
 
-config ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+config ARM64_WORKAROUND_SPECULATIVE_AT
 	bool
 
 config ARM64_ERRATUM_1165522
-	bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	bool "Cortex-A76: 1165522: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
-	select ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+	select ARM64_WORKAROUND_SPECULATIVE_AT
 	help
 	  This option adds a workaround for ARM Cortex-A76 erratum 1165522.
 
@@ -541,10 +546,23 @@ config ARM64_ERRATUM_1165522
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1319367
+	bool "Cortex-A57/A72: 1319537: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	default y
+	select ARM64_WORKAROUND_SPECULATIVE_AT
+	help
+	  This option adds work arounds for ARM Cortex-A57 erratum 1319537
+	  and A72 erratum 1319367
+
+	  Cortex-A57 and A72 cores could end-up with corrupted TLBs by
+	  speculating an AT instruction during a guest context switch.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_1530923
-	bool "Cortex-A55: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	bool "Cortex-A55: 1530923: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
-	select ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+	select ARM64_WORKAROUND_SPECULATIVE_AT
 	help
 	  This option adds a workaround for ARM Cortex-A55 erratum 1530923.
 
@@ -554,6 +572,9 @@ config ARM64_ERRATUM_1530923
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_REPEAT_TLBI
+	bool
+
 config ARM64_ERRATUM_1286807
 	bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation"
 	default y
@@ -570,22 +591,6 @@ config ARM64_ERRATUM_1286807
 	  invalidated has been observed by other observers. The
 	  workaround repeats the TLBI+DSB operation.
 
-config ARM64_WORKAROUND_SPECULATIVE_AT_NVHE
-	bool
-
-config ARM64_ERRATUM_1319367
-	bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
-	default y
-	select ARM64_WORKAROUND_SPECULATIVE_AT_NVHE
-	help
-	  This option adds work arounds for ARM Cortex-A57 erratum 1319537
-	  and A72 erratum 1319367
-
-	  Cortex-A57 and A72 cores could end-up with corrupted TLBs by
-	  speculating an AT instruction during a guest context switch.
-
-	  If unsure, say Y.
-
 config ARM64_ERRATUM_1463225
 	bool "Cortex-A76: Software Step might prevent interrupt recognition"
 	default y
@@ -695,6 +700,35 @@ config CAVIUM_TX2_ERRATUM_219
 
 	  If unsure, say Y.
 
+config FUJITSU_ERRATUM_010001
+	bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
+	default y
+	help
+	  This option adds a workaround for Fujitsu-A64FX erratum E#010001.
+	  On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
+	  accesses may cause undefined fault (Data abort, DFSC=0b111111).
+	  This fault occurs under a specific hardware condition when a
+	  load/store instruction performs an address translation using:
+	  case-1  TTBR0_EL1 with TCR_EL1.NFD0 == 1.
+	  case-2  TTBR0_EL2 with TCR_EL2.NFD0 == 1.
+	  case-3  TTBR1_EL1 with TCR_EL1.NFD1 == 1.
+	  case-4  TTBR1_EL2 with TCR_EL2.NFD1 == 1.
+
+	  The workaround is to ensure these bits are clear in TCR_ELx.
+	  The workaround only affects the Fujitsu-A64FX.
+
+	  If unsure, say Y.
+
+config HISILICON_ERRATUM_161600802
+	bool "Hip07 161600802: Erroneous redistributor VLPI base"
+	default y
+	help
+	  The HiSilicon Hip07 SoC uses the wrong redistributor base
+	  when issued ITS commands such as VMOVP and VMAPP, and requires
+	  a 128kB offset to be applied to the target address in this commands.
+
+	  If unsure, say Y.
+
 config QCOM_FALKOR_ERRATUM_1003
 	bool "Falkor E1003: Incorrect translation due to ASID change"
 	default y
@@ -706,9 +740,6 @@ config QCOM_FALKOR_ERRATUM_1003
 	  is unchanged. Work around the erratum by invalidating the walk cache
 	  entries for the trampoline before entering the kernel proper.
 
-config ARM64_WORKAROUND_REPEAT_TLBI
-	bool
-
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
 	default y
@@ -730,25 +761,6 @@ config QCOM_QDF2400_ERRATUM_0065
 
 	  If unsure, say Y.
 
-config SOCIONEXT_SYNQUACER_PREITS
-	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
-	default y
-	help
-	  Socionext Synquacer SoCs implement a separate h/w block to generate
-	  MSI doorbell writes with non-zero values for the device ID.
-
-	  If unsure, say Y.
-
-config HISILICON_ERRATUM_161600802
-	bool "Hip07 161600802: Erroneous redistributor VLPI base"
-	default y
-	help
-	  The HiSilicon Hip07 SoC uses the wrong redistributor base
-	  when issued ITS commands such as VMOVP and VMAPP, and requires
-	  a 128kB offset to be applied to the target address in this commands.
-
-	  If unsure, say Y.
-
 config QCOM_FALKOR_ERRATUM_E1041
 	bool "Falkor E1041: Speculative instruction fetches might cause errant memory access"
 	default y
@@ -759,22 +771,12 @@ config QCOM_FALKOR_ERRATUM_E1041
 
 	  If unsure, say Y.
 
-config FUJITSU_ERRATUM_010001
-	bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
+config SOCIONEXT_SYNQUACER_PREITS
+	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
 	default y
 	help
-	  This option adds a workaround for Fujitsu-A64FX erratum E#010001.
-	  On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
-	  accesses may cause undefined fault (Data abort, DFSC=0b111111).
-	  This fault occurs under a specific hardware condition when a
-	  load/store instruction performs an address translation using:
-	  case-1  TTBR0_EL1 with TCR_EL1.NFD0 == 1.
-	  case-2  TTBR0_EL2 with TCR_EL2.NFD0 == 1.
-	  case-3  TTBR1_EL1 with TCR_EL1.NFD1 == 1.
-	  case-4  TTBR1_EL2 with TCR_EL2.NFD1 == 1.
-
-	  The workaround is to ensure these bits are clear in TCR_ELx.
-	  The workaround only affects the Fujitsu-A64FX.
+	  Socionext Synquacer SoCs implement a separate h/w block to generate
+	  MSI doorbell writes with non-zero values for the device ID.
 
 	  If unsure, say Y.
 
@@ -1026,6 +1028,10 @@ config ARCH_HAS_CACHE_LINE_SIZE
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y if PGTABLE_LEVELS > 2
 
+# Supported by clang >= 7.0
+config CC_HAVE_SHADOW_CALL_STACK
+	def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18)
+
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	---help---
@@ -1585,6 +1591,48 @@ endmenu
 
 menu "ARMv8.5 architectural features"
 
+config ARM64_BTI
+	bool "Branch Target Identification support"
+	default y
+	help
+	  Branch Target Identification (part of the ARMv8.5 Extensions)
+	  provides a mechanism to limit the set of locations to which computed
+	  branch instructions such as BR or BLR can jump.
+
+	  To make use of BTI on CPUs that support it, say Y.
+
+	  BTI is intended to provide complementary protection to other control
+	  flow integrity protection mechanisms, such as the Pointer
+	  authentication mechanism provided as part of the ARMv8.3 Extensions.
+	  For this reason, it does not make sense to enable this option without
+	  also enabling support for pointer authentication.  Thus, when
+	  enabling this option you should also select ARM64_PTR_AUTH=y.
+
+	  Userspace binaries must also be specifically compiled to make use of
+	  this mechanism.  If you say N here or the hardware does not support
+	  BTI, such binaries can still run, but you get no additional
+	  enforcement of branch destinations.
+
+config ARM64_BTI_KERNEL
+	bool "Use Branch Target Identification for kernel"
+	default y
+	depends on ARM64_BTI
+	depends on ARM64_PTR_AUTH
+	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
+	depends on !CC_IS_GCC || GCC_VERSION >= 100100
+	depends on !(CC_IS_CLANG && GCOV_KERNEL)
+	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
+	help
+	  Build the kernel with Branch Target Identification annotations
+	  and enable enforcement of this for kernel code. When this option
+	  is enabled and the system supports BTI all kernel code including
+	  modular code must have BTI enabled.
+
+config CC_HAS_BRANCH_PROT_PAC_RET_BTI
+	# GCC 9 or later, clang 8 or later
+	def_bool $(cc-option,-mbranch-protection=pac-ret+leaf+bti)
+
 config ARM64_E0PD
 	bool "Enable support for E0PD"
 	default y