diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-01 15:04:29 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-01 15:04:29 -0700 |
| commit | 57c78a234e809e3a0516491e37ae5ccc6eeb21e8 (patch) | |
| tree | 2595806aeef867185a1472d6e4381255e26b8a84 | |
| parent | bcfeebbff3627093014c7948aec9cc4730e50c3d (diff) | |
| parent | 65266a7c6abfa1ad915a362c41bf38576607f1f9 (diff) | |
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Catalin Marinas:
- Support for 32-bit tasks on asymmetric AArch32 systems (on top of the
scheduler changes merged via the tip tree).
- More entry.S clean-ups and conversion to C.
- MTE updates: allow a preferred tag checking mode to be set per CPU
(the overhead of synchronous mode is smaller for some CPUs than
others); optimisations for kernel entry/exit path; optionally disable
MTE on the kernel command line.
- Kselftest improvements for SVE and signal handling, PtrAuth.
- Fix unlikely race where a TLBI could use stale ASID on an ASID
roll-over (found by inspection).
- Miscellaneous fixes: disable trapping of PMSNEVFR_EL1 to higher
exception levels; drop unnecessary sigdelsetmask() call in the
signal32 handling; remove BUG_ON when failing to allocate SVE state
(just signal the process); SYM_CODE annotations.
- Other trivial clean-ups: use macros instead of magic numbers, remove
redundant returns, typos.
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (56 commits)
arm64: Do not trap PMSNEVFR_EL1
arm64: mm: fix comment typo of pud_offset_phys()
arm64: signal32: Drop pointless call to sigdelsetmask()
arm64/sve: Better handle failure to allocate SVE register storage
arm64: Document the requirement for SCR_EL3.HCE
arm64: head: avoid over-mapping in map_memory
arm64/sve: Add a comment documenting the binutils needed for SVE asm
arm64/sve: Add some comments for sve_save/load_state()
kselftest/arm64: signal: Add a TODO list for signal handling tests
kselftest/arm64: signal: Add test case for SVE register state in signals
kselftest/arm64: signal: Verify that signals can't change the SVE vector length
kselftest/arm64: signal: Check SVE signal frame shows expected vector length
kselftest/arm64: signal: Support signal frames with SVE register data
kselftest/arm64: signal: Add SVE to the set of features we can check for
arm64: replace in_irq() with in_hardirq()
kselftest/arm64: pac: Fix skipping of tests on systems without PAC
Documentation: arm64: describe asymmetric 32-bit support
arm64: Remove logic to kill 32-bit tasks on 64-bit-only cores
arm64: Hook up cmdline parameter to allow mismatched 32-bit EL0
arm64: Advertise CPUs capable of running 32-bit applications in sysfs
...
69 files changed, 1843 insertions, 464 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 160b10c029c0..b46ef147616a 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -494,6 +494,15 @@ Description: AArch64 CPU registers 'identification' directory exposes the CPU ID registers for identifying model and revision of the CPU. +What: /sys/devices/system/cpu/aarch32_el0 +Date: May 2021 +Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org> +Description: Identifies the subset of CPUs in the system that can execute + AArch32 (32-bit ARM) applications. If present, the same format as + /sys/devices/system/cpu/{offline,online,possible,present} is used. + If absent, then all or none of the CPUs can execute AArch32 + applications and execve() will behave accordingly. + What: /sys/devices/system/cpu/cpu#/cpu_capacity Date: December 2016 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> @@ -640,3 +649,20 @@ Description: SPURR ticks for cpuX when it was idle. This sysfs interface exposes the number of SPURR ticks for cpuX when it was idle. + +What: /sys/devices/system/cpu/cpuX/mte_tcf_preferred +Date: July 2021 +Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org> +Description: Preferred MTE tag checking mode + + When a user program specifies more than one MTE tag checking + mode, this sysfs node is used to specify which mode should + be preferred when scheduling a task on that CPU. Possible + values: + + ================ ============================================== + "sync" Prefer synchronous mode + "async" Prefer asynchronous mode + ================ ============================================== + + See also: Documentation/arm64/memory-tagging-extension.rst diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2102467faad6..82c932105d31 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -287,6 +287,17 @@ do not want to use tracing_snapshot_alloc() as it needs to be done where GFP_KERNEL allocations are allowed. + allow_mismatched_32bit_el0 [ARM64] + Allow execve() of 32-bit applications and setting of the + PER_LINUX32 personality on systems where only a strict + subset of the CPUs support 32-bit EL0. When this + parameter is present, the set of CPUs supporting 32-bit + EL0 is indicated by /sys/devices/system/cpu/aarch32_el0 + and hot-unplug operations may be restricted. + + See Documentation/arm64/asymmetric-32bit.rst for more + information. + amd_iommu= [HW,X86-64] Pass parameters to the AMD IOMMU driver in the system. Possible values are: @@ -380,6 +391,9 @@ arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication support + arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension + support + ataflop= [HW,M68k] atarimouse= [HW,MOUSE] Atari Mouse diff --git a/Documentation/arm64/asymmetric-32bit.rst b/Documentation/arm64/asymmetric-32bit.rst new file mode 100644 index 000000000000..64a0b505da7d --- /dev/null +++ b/Documentation/arm64/asymmetric-32bit.rst @@ -0,0 +1,155 @@ +====================== +Asymmetric 32-bit SoCs +====================== + +Author: Will Deacon <will@kernel.org> + +This document describes the impact of asymmetric 32-bit SoCs on the +execution of 32-bit (``AArch32``) applications. + +Date: 2021-05-17 + +Introduction +============ + +Some Armv9 SoCs suffer from a big.LITTLE misfeature where only a subset +of the CPUs are capable of executing 32-bit user applications. On such +a system, Linux by default treats the asymmetry as a "mismatch" and +disables support for both the ``PER_LINUX32`` personality and +``execve(2)`` of 32-bit ELF binaries, with the latter returning +``-ENOEXEC``. If the mismatch is detected during late onlining of a +64-bit-only CPU, then the onlining operation fails and the new CPU is +unavailable for scheduling. + +Surprisingly, these SoCs have been produced with the intention of +running legacy 32-bit binaries. Unsurprisingly, that doesn't work very +well with the default behaviour of Linux. + +It seems inevitable that future SoCs will drop 32-bit support +altogether, so if you're stuck in the unenviable position of needing to +run 32-bit code on one of these transitionary platforms then you would +be wise to consider alternatives such as recompilation, emulation or +retirement. If neither of those options are practical, then read on. + +Enabling kernel support +======================= + +Since the kernel support is not completely transparent to userspace, +allowing 32-bit tasks to run on an asymmetric 32-bit system requires an +explicit "opt-in" and can be enabled by passing the +``allow_mismatched_32bit_el0`` parameter on the kernel command-line. + +For the remainder of this document we will refer to an *asymmetric +system* to mean an asymmetric 32-bit SoC running Linux with this kernel +command-line option enabled. + +Userspace impact +================ + +32-bit tasks running on an asymmetric system behave in mostly the same +way as on a homogeneous system, with a few key differences relating to +CPU affinity. + +sysfs +----- + +The subset of CPUs capable of running 32-bit tasks is described in +``/sys/devices/system/cpu/aarch32_el0`` and is documented further in +``Documentation/ABI/testing/sysfs-devices-system-cpu``. + +**Note:** CPUs are advertised by this file as they are detected and so +late-onlining of 32-bit-capable CPUs can result in the file contents +being modified by the kernel at runtime. Once advertised, CPUs are never +removed from the file. + +``execve(2)`` +------------- + +On a homogeneous system, the CPU affinity of a task is preserved across +``execve(2)``. This is not always possible on an asymmetric system, +specifically when the new program being executed is 32-bit yet the +affinity mask contains 64-bit-only CPUs. In this situation, the kernel +determines the new affinity mask as follows: + + 1. If the 32-bit-capable subset of the affinity mask is not empty, + then the affinity is restricted to that subset and the old affinity + mask is saved. This saved mask is inherited over ``fork(2)`` and + preserved across ``execve(2)`` of 32-bit programs. + + **Note:** This step does not apply to ``SCHED_DEADLINE`` tasks. + See `SCHED_DEADLINE`_. + + 2. Otherwise, the cpuset hierarchy of the task is walked until an + ancestor is found containing at least one 32-bit-capable CPU. The + affinity of the task is then changed to match the 32-bit-capable + subset of the cpuset determined by the walk. + + 3. On failure (i.e. out of memory), the affinity is changed to the set + of all 32-bit-capable CPUs of which the kernel is aware. + +A subsequent ``execve(2)`` of a 64-bit program by the 32-bit task will +invalidate the affinity mask saved in (1) and attempt to restore the CPU +affinity of the task using the saved mask if it was previously valid. +This restoration may fail due to intervening changes to the deadline +policy or cpuset hierarchy, in which case the ``execve(2)`` continues +with the affinity unchanged. + +Calls to ``sched_setaffinity(2)`` for a 32-bit task will consider only +the 32-bit-capable CPUs of the requested affinity mask. On success, the +affinity for the task is updated and any saved mask from a prior +``execve(2)`` is invalidated. + +``SCHED_DEADLINE`` +------------------ + +Explicit admission of a 32-bit deadline task to the default root domain +(e.g. by calling ``sched_setattr(2)``) is rejected on an asymmetric +32-bit system unless admission control is disabled by writing -1 to +``/proc/sys/kernel/sched_rt_runtime_us``. + +``execve(2)`` of a 32-bit program from a 64-bit deadline task will +return ``-ENOEXEC`` if the root domain for the task contains any +64-bit-only CPUs and admission control is enabled. Concurrent offlining +of 32-bit-capable CPUs may still necessitate the procedure described in +`execve(2)`_, in which case step (1) is skipped and a warning is +emitted on the console. + +**Note:** It is recommended that a set of 32-bit-capable CPUs are placed +into a separate root domain if ``SCHED_DEADLINE`` is to be used with +32-bit tasks on an asymmetric system. Failure to do so is likely to +result in missed deadlines. + +Cpusets +------- + +The affinity of a 32-bit task on an asymmetric system may include CPUs +that are not explicitly allowed by the cpuset to which it is attached. +This can occur as a result of the following two situations: + + - A 64-bit task attached to a cpuset which allows only 64-bit CPUs + executes a 32-bit program. + + - All of the 32-bit-capable CPUs allowed by a cpuset containing a + 32-bit task are offlined. + +In both of these cases, the new affinity is calculated according to step +(2) of the process described in `execve(2)`_ and the cpuset hierarchy is +unchanged irrespective of the cgroup version. + +CPU hotplug +----------- + +On an asymmetric system, the first detected 32-bit-capable CPU is +prevented from being offlined by userspace and any such attempt will +return ``-EPERM``. Note that suspend is still permitted even if the +primary CPU (i.e. CPU 0) is 64-bit-only. + +KVM +--- + +Although KVM will not advertise 32-bit EL0 support to any vCPUs on an +asymmetric system, a broken guest at EL1 could still attempt to execute +32-bit code at EL0. In this case, an exit from a vCPU thread in 32-bit +mode will return to host userspace with an ``exit_reason`` of +``KVM_EXIT_FAIL_ENTRY`` and will remain non-runnable until successfully +re-initialised by a subsequent ``KVM_ARM_VCPU_INIT`` operation. diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst index a9192e7a231b..3f9d86557c5e 100644 --- a/Documentation/arm64/booting.rst +++ b/Documentation/arm64/booting.rst @@ -207,10 +207,17 @@ Before jumping into the kernel, the following conditions must be met: software at a higher exception level to prevent execution in an UNKNOWN state. - - SCR_EL3.FIQ must have the same value across all CPUs the kernel is - executing on. - - The value of SCR_EL3.FIQ must be the same as the one present at boot - time whenever the kernel is executing. + For all systems: + - If EL3 is present: + + - SCR_EL3.FIQ must have the same value across all CPUs the kernel is + executing on. + - The value of SCR_EL3.FIQ must be the same as the one present at boot + time whenever the kernel is executing. + + - If EL3 is present and the kernel is entered at EL2: + + - SCR_EL3.HCE (bit 8) must be initialised to 0b1. For systems with a GICv3 interrupt controller to be used in v3 mode: - If EL3 is present: @@ -311,6 +318,28 @@ Before jumping into the kernel, the following conditions must be met: - ZCR_EL2.LEN must be initialised to the same value for all CPUs the kernel will execute on. + For CPUs with the Scalable Matrix Extension (FEAT_SME): + + - If EL3 is present: + + - CPTR_EL3.ESM (bit 12) must be initialised to 0b1. + + - SCR_EL3.EnTP2 (bit 41) must be initialised to 0b1. + + - SMCR_EL3.LEN must be initialised to the same value for all CPUs the + kernel will execute on. + + - If the kernel is entered at EL1 and EL2 is present: + + - CPTR_EL2.TSM (bit 12) must be initialised to 0b0. + + - CPTR_EL2.SMEN (bits 25:24) must be initialised to 0b11. + + - SCTLR_EL2.EnTP2 (bit 60) must be initialised to 0b1. + + - SMCR_EL2.LEN must be initialised to the same value for all CPUs the + kernel will execute on. + The requirements described above for CPU mode, caches, MMUs, architected timers, coherency and system registers apply to all CPUs. All CPUs must enter the kernel in the same exception level. Where the values documented diff --git a/Documentation/arm64/index.rst b/Documentation/arm64/index.rst index 97d65ba12a35..4f840bac083e 100644 --- a/Documentation/arm64/index.rst +++ b/Documentation/arm64/index.rst @@ -10,6 +10,7 @@ ARM64 Architecture acpi_object_usage amu arm-acpi + asymmetric-32bit booting cpu-feature-registers elf_hwcaps diff --git a/Documentation/arm64/memory-tagging-extension.rst b/Documentation/arm64/memory-tagging-extension.rst index b540178a93f8..7b99c8f428eb 100644 --- a/Documentation/arm64/memory-tagging-extension.rst +++ b/Documentation/arm64/memory-tagging-extension.rst @@ -77,14 +77,20 @@ configurable behaviours: address is unknown). The user can select the above modes, per thread, using the -``prctl(PR_SET_TAGGED_ADDR_CTRL, flags, 0, 0, 0)`` system call where -``flags`` contain one of the following values in the ``PR_MTE_TCF_MASK`` +``prctl(PR_SET_TAGGED_ADDR_CTRL, flags, 0, 0, 0)`` system call where ``flags`` +contains any number of the following values in the ``PR_MTE_TCF_MASK`` bit-field: -- ``PR_MTE_TCF_NONE`` - *Ignore* tag check faults +- ``PR_MTE_TCF_NONE`` - *Ignore* tag check faults + (ignored if combined with other options) - ``PR_MTE_TCF_SYNC`` - *Synchronous* tag check fault mode - ``PR_MTE_TCF_ASYNC`` - *Asynchronous* tag check fault mode +If no modes are specified, tag check faults are ignored. If a single +mode is specified, the program will run in that mode. If multiple +modes are specified, the mode is selected as described in the "Per-CPU +preferred tag checking modes" section below. + The current tag check fault mode can be read using the ``prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0)`` system call. @@ -120,13 +126,39 @@ in the ``PR_MTE_TAG_MASK`` bit-field. interface provides an include mask. An include mask of ``0`` (exclusion mask ``0xffff``) results in the CPU always generating tag ``0``. +Per-CPU preferred tag checking mode +----------------------------------- + +On some CPUs the performance of MTE in stricter tag checking modes +is similar to that of less strict tag checking modes. This makes it +worthwhile to enable stricter checks on those CPUs when a less strict +checking mode is requested, in order to gain the error detection +benefits of the stricter checks without the performance downsides. To +support this scenario, a privileged user may configure a stricter +tag checking mode as the CPU's preferred tag checking mode. + +The preferred tag checking mode for each CPU is controlled by +``/sys/devices/system/cpu/cpu<N>/mte_tcf_preferred``, to which a +privileged user may write the value ``async`` or ``sync``. The default +preferred mode for each CPU is ``async``. + +To allow a program to potentially run in the CPU's preferred tag +checking mode, the user program may set multiple tag check fault mode +bits in the ``flags`` argument to the ``prctl(PR_SET_TAGGED_ADDR_CTRL, +flags, 0, 0, 0)`` system call. If the CPU's preferred tag checking +mode is in the task's set of provided tag checking modes (this will +always be the case at present because the kernel only supports two +tag checking modes, but future kernels may support more modes), that +mode will be selected. Otherwise, one of the modes in the task's mode +set will be selected in a currently unspecified manner. + Initial process state --------------------- On ``execve()``, the new process has the following configuration: - ``PR_TAGGED_ADDR_ENABLE`` set to 0 (disabled) -- Tag checking mode set to ``PR_MTE_TCF_NONE`` +- No tag checking modes are selected (tag check faults ignored) - ``PR_MTE_TAG_MASK`` set to 0 (all tags excluded) - ``PSTATE.TCO`` set to 0 - ``PROT_MTE`` not set on any of the initial memory maps @@ -251,11 +283,13 @@ Example of correct usage return EXIT_FAILURE; /* - * Enable the tagged address ABI, synchronous MTE tag check faults and - * allow all non-zero tags in the randomly generated set. + * Enable the tagged address ABI, synchronous or asynchronous MTE + * tag check faults (based on per-CPU preference) and allow all + * non-zero tags in the randomly generated set. */ if (prctl(PR_SET_TAGGED_ADDR_CTRL, - PR_TAGGED_ADDR_ENABLE | PR_MTE_TCF_SYNC | (0xfffe << PR_MTE_TAG_SHIFT), + PR_TAGGED_ADDR_ENABLE | PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC | + (0xfffe << PR_MTE_TAG_SHIFT), 0, 0, 0)) { perror("prctl() failed"); return EXIT_FAILURE; diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 1110d386f3b4..c744b1e7b356 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -157,8 +157,11 @@ Image: vmlinux Image.%: Image $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -zinstall install: - $(Q)$(MAKE) $(build)=$(boot) $@ +install: install-image := Image +zinstall: install-image := Image.gz +install zinstall: + $(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \ + $(boot)/$(install-image) System.map "$(INSTALL_PATH)" PHONY += vdso_install vdso_install: diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index cd3414898d10..ebe80faab883 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -35,11 +35,3 @@ $(obj)/Image.lzma: $(obj)/Image FORCE $(obj)/Image.lzo: $(obj)/Image FORCE $(call if_changed,lzo) - -install: - $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \ - $(obj)/Image System.map "$(INSTALL_PATH)" - -zinstall: - $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \ - $(obj)/Image.gz System.map "$(INSTALL_PATH)" diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 9bb9d11750d7..cdfa2a242e9f 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -552,7 +552,7 @@ cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap) u64 mask = GENMASK_ULL(field + 3, field); /* Treat IMPLEMENTATION DEFINED functionality as unimplemented */ - if (val == 0xf) + if (val == ID_AA64DFR0_PMUVER_IMP_DEF) val = 0; if (val > cap) { @@ -657,7 +657,8 @@ static inline bool system_supports_4kb_granule(void) val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN4_SHIFT); - return val == ID_AA64MMFR0_TGRAN4_SUPPORTED; + return (val >= ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX); } static inline bool system_supports_64kb_granule(void) @@ -669,7 +670,8 @@ static inline bool system_supports_64kb_granule(void) val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN64_SHIFT); - return val == ID_AA64MMFR0_TGRAN64_SUPPORTED; + return (val >= ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX); } static inline bool system_supports_16kb_granule(void) @@ -681,7 +683,8 @@ static inline bool system_supports_16kb_granule(void) val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN16_SHIFT); - return val == ID_AA64MMFR0_TGRAN16_SUPPORTED; + return (val >= ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX); } static inline bool system_supports_mixed_endian_el0(void) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index b83fb24954b7..3198acb2aad8 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -149,8 +149,17 @@ ubfx x1, x1, #ID_AA64MMFR0_FGT_SHIFT, #4 cbz x1, .Lskip_fgt_\@ - msr_s SYS_HDFGRTR_EL2, xzr - msr_s SYS_HDFGWTR_EL2, xzr + mov x0, xzr + mrs x1, id_aa64dfr0_el1 + ubfx x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 + cmp x1, #3 + b.lt .Lset_fgt_\@ + /* Disable PMSNEVFR_EL1 read and write traps */ + orr x0, x0, #(1 << 62) + +.Lset_fgt_\@: + msr_s SYS_HDFGRTR_EL2, x0 + msr_s SYS_HDFGWTR_EL2, x0 msr_s SYS_HFGRTR_EL2, xzr msr_s SYS_HFGWTR_EL2, xzr msr_s SYS_HFGITR_EL2, xzr diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 8d1c8dcb87fd..97932fbf973d 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -213,10 +213,8 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; /* AArch32 EABI. */ #define EF_ARM_EABI_MASK 0xff000000 -#define compat_elf_check_arch(x) (system_supports_32bit_el0() && \ - ((x)->e_machine == EM_ARM) && \ - ((x)->e_flags & EF_ARM_EABI_MASK)) - +int compat_elf_check_arch(const struct elf32_hdr *); +#define compat_elf_check_arch compat_elf_check_arch #define compat_start_thread compat_start_thread /* * Unlike the native SET_PERSONALITY macro, the compat version maintains diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 4afbc45b8bb0..339477dca551 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -55,8 +55,8 @@ asmlinkage void el0t_32_error_handler(struct pt_regs *regs); asmlinkage void call_on_irq_stack(struct pt_regs *regs, void (*func)(struct pt_regs *)); -asmlinkage void enter_from_user_mode(void); -asmlinkage void exit_to_user_mode(void); +asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs); + void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); void do_bti(struct pt_regs *regs); @@ -73,6 +73,7 @@ void do_el0_svc(struct pt_regs *regs); void do_el0_svc_compat(struct pt_regs *regs); void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr); void do_serror(struct pt_regs *regs, unsigned int esr); +void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags); void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index c072161d5c65..9a62884183e5 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -45,7 +45,6 @@ extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); -extern void fpsimd_bind_task_to_cpu(void); extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, void *sve_state, unsigned int sve_vl); diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 059204477ce6..00a2c0b69c2b 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -94,6 +94,7 @@ .endm /* SVE instruction encodings for non-SVE-capable assemblers */ +/* (pre binutils 2.28, all kernel capable clang versions support SVE) */ /* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */ .macro _sve_str_v nz, nxbase, offset=0 diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 3512184cfec1..96dc0f7da258 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -65,8 +65,8 @@ #define EARLY_KASLR (0) #endif -#define EARLY_ENTRIES(vstart, vend, shift) (((vend) >> (shift)) \ - - ((vstart) >> (shift)) + 1 + EARLY_KASLR) +#define EARLY_ENTRIES(vstart, vend, shift) \ + ((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + EARLY_KASLR) #define EARLY_PGDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT)) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 824a3655dd93..f1745a843414 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -243,9 +243,7 @@ static inline const void *__tag_set(const void *addr, u8 tag) #ifdef CONFIG_KASAN_HW_TAGS #define arch_enable_tagging_sync() mte_enable_kernel_sync() #define arch_enable_tagging_async() mte_enable_kernel_async() -#define arch_set_tagging_report_once(state) mte_set_report_once(state) #define arch_force_async_tag_fault() mte_check_tfsr_exit() -#define arch_init_tags(max_tag) mte_init_tags(max_tag) #define arch_get_random_tag() mte_get_random_tag() #define arch_get_mem_tag(addr) mte_get_mem_tag(addr) #define arch_set_mem_tag_range(addr, size, tag, init) \ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 75beffe2ee8a..e9c30859f80c 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -27,11 +27,32 @@ typedef struct { } mm_context_t; /* - * This macro is only used by the TLBI and low-level switch_mm() code, - * neither of which can race with an ASID change. We therefore don't - * need to reload the counter using atomic64_read(). + * We use atomic64_read() here because the ASID for an 'mm_struct' can + * be reallocated when scheduling one of its threads following a + * rollover event (see new_context() and flush_context()). In this case, + * a concurrent TLBI (e.g. via try_to_unmap_one() and ptep_clear_flush()) + * may use a stale ASID. This is fine in principle as the new ASID is + * guaranteed to be clean in the TLB, but the TLBI routines have to take + * care to handle the following race: + * + * CPU 0 CPU 1 CPU 2 + * + * // ptep_clear_flush(mm) + * xchg_relaxed(pte, 0) + * DSB ISHST + * old = ASID(mm) + * | <rollover> + * | new = new_context(mm) + * \-----------------> atomic_set(mm->context.id, new) + * cpu_switch_mm(mm) + * // Hardware walk of pte using new ASID + * TLBI(old) + * + * In this scenario, the barrier on CPU 0 and the dependency on CPU 1 + * ensure that the page-table walker on CPU 1 *must* see the invalid PTE + * written by CPU 0. */ -#define ASID(mm) ((mm)->context.id.counter & 0xffff) +#define ASID(mm) (atomic64_read(&(mm)->context.id) & 0xffff) static inline bool arm64_kernel_unmapped_at_el0(void) { diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index eeb210997149..f4ba93d4ffeb 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -231,6 +231,19 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, update_saved_ttbr0(tsk, next); } +static inline const struct cpumask * +task_cpu_possible_mask(struct task_struct *p) +{ + if (!static_branch_unlikely(&arm64_mismatched_32bit_el0)) + return cpu_possible_mask; + + if (!is_compat_thread(task_thread_info(p))) + return cpu_possible_mask; + + return system_32bit_el0_cpumask(); +} +#define task_cpu_possible_mask task_cpu_possible_mask + void verify_cpu_asid_bits(void); void post_ttbr_update_workaround(void); diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index d952352bd008..22420e1f8c03 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -130,10 +130,6 @@ static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag, void mte_enable_kernel_sync(void); void mte_enable_kernel_async(void); -void mte_init_tags(u64 max_tag); - -void mte_set_report_once(bool state); -bool mte_report_once(void); #else /* CONFIG_ARM64_MTE */ @@ -165,19 +161,6 @@ static inline void mte_enable_kernel_async(void) { } -static inline void mte_init_tags(u64 max_tag) -{ -} - -static inline void mte_set_report_once(bool state) -{ -} - -static inline bool mte_report_once(void) -{ - return false; -} - #endif /* CONFIG_ARM64_MTE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 58c7f80f5596..3f93b9e0b339 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -16,8 +16,6 @@ #include <asm/pgtable-types.h> -extern u64 gcr_kernel_excl; - void mte_clear_page_tags(void *addr); unsigned long mte_copy_tags_from_user(void *to, const void __user *from, unsigned long n); @@ -43,7 +41,6 @@ void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); void mte_suspend_enter(void); -void mte_suspend_exit(void); long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, @@ -72,9 +69,6 @@ static inline void mte_thread_switch(struct task_struct *next) static inline void mte_suspend_enter(void) { } -static inline void mte_suspend_exit(void) -{ -} static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg) { return 0; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index f09bf5c02891..dfa76afa0ccf 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -715,7 +715,7 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) return (pud_t *)__va(p4d_page_paddr(p4d)); } -/* Find an entry in the frst-level page table. */ +/* Find an entry in the first-level page table. */ #define pud_offset_phys(dir, addr) (p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) #define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index 28a78b67d9b4..efb098de3a84 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -10,6 +10,9 @@ #include <asm/memory.h> #include <asm/sysreg.h> +#define PR_PAC_ENABLED_KEYS_MASK \ + (PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY) + #ifdef CONFIG_ARM64_PTR_AUTH /* * Each key is a 128-bit quantity which is split across a pair of 64-bit @@ -117,9 +120,9 @@ static __always_inline void ptrauth_enable(void) \ /* enable all keys */ \ if (system_supports_address_auth()) \ - set_task_sctlr_el1(current->thread.sctlr_user | \ - SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \ - SCTLR_ELx_ENDA | SCTLR_ELx_ENDB); \ + ptrauth_set_enabled_keys(current, \ + PR_PAC_ENABLED_KEYS_MASK, \ + PR_PAC_ENABLED_KEYS_MASK); \ } while (0) #define ptrauth_thread_switch_user(tsk) \ @@ -146,7 +149,4 @@ static __always_inline void ptrauth_enable(void) #define ptrauth_thread_switch_kernel(tsk) #endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */ -#define PR_PAC_ENABLED_KEYS_MASK \ - (PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY) - #endif /* __ASM_POINTER_AUTH_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index b6517fd03d7b..ee2bdc1b9f5b 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -16,6 +16,12 @@ */ #define NET_IP_ALIGN 0 +#define MTE_CTRL_GCR_USER_EXCL_SHIFT 0 +#define MTE_CTRL_GCR_USER_EXCL_MASK 0xffff + +#define MTE_CTRL_TCF_SYNC (1UL << 16) +#define MTE_CTRL_TCF_ASYNC (1UL << 17) + #ifndef __ASSEMBLY__ #include <linux/build_bug.h> @@ -153,7 +159,7 @@ struct thread_struct { #endif #endif #ifdef CONFIG_ARM64_MTE - u64 gcr_user_excl; + u64 mte_ctrl; #endif u64 sctlr_user; }; @@ -253,7 +259,7 @@ extern void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); -void set_task_sctlr_el1(u64 sctlr); +void update_sctlr_el1(u64 sctlr); /* Thread switching */ extern struct task_struct *cpu_switch_to(struct task_struct *prev, diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index 89cba2622b79..6a75d7ecdcaa 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -37,7 +37,7 @@ static __must_check inline bool may_use_simd(void) */ return !WARN_ON(!system_capabilities_finalized()) && system_supports_fpsimd() && - !in_irq() && !irqs_disabled() && !in_nmi() && + !in_hardirq() && !irqs_disabled() && !in_nmi() && !this_cpu_read(fpsimd_context_busy); } diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 7b9c3acba684..f2e06e7c0a31 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -11,6 +11,7 @@ #include <linux/bits.h> #include <linux/stringify.h> +#include <linux/kasan-tags.h> /* * ARMv8 ARM reserves the following encoding for system registers: @@ -698,8 +699,7 @@ (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_EL1_SA0 | \ SCTLR_EL1_SED | SCTLR_ELx_I | SCTLR_EL1_DZE | SCTLR_EL1_UCT | \ SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \ - SCTLR_ELx_ATA | SCTLR_EL1_ATA0 | ENDIAN_SET_EL1 | SCTLR_EL1_UCI | \ - SCTLR_EL1_EPAN | SCTLR_EL1_RES1) + ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_EPAN | SCTLR_EL1_RES1) /* MAIR_ELx memory attributes (used by Linux) */ #define MAIR_ATTR_DEVICE_nGnRnE UL(0x00) @@ -847,12 +847,16 @@ #define ID_AA64MMFR0_ASID_SHIFT 4 #define ID_AA64MMFR0_PARANGE_SHIFT 0 -#define ID_AA64MMFR0_TGRAN4_NI 0xf -#define ID_AA64MMFR0_TGRAN4_SUPPORTED 0x0 -#define ID_AA64MMFR0_TGRAN64_NI 0xf -#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0 -#define ID_AA64MMFR0_TGRAN16_NI 0x0 -#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1 +#define ID_AA64MMFR0_TGRAN4_NI 0xf +#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN64_NI 0xf +#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN16_NI 0x0 +#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN 0x1 +#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX 0xf + #define ID_AA64MMFR0_PARANGE_48 0x5 #define ID_AA64MMFR0_PARANGE_52 0x6 @@ -1028,16 +1032,16 @@ #if defined(CONFIG_ARM64_4K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX #elif defined(CONFIG_ARM64_16K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0xF +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX #elif defined(CONFIG_ARM64_64K_PAGES) #define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN +#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX #endif #define MVFR2_FPMISC_SHIFT 4 @@ -1067,6 +1071,21 @@ #define SYS_GCR_EL1_RRND (BIT(16)) #define SYS_GCR_EL1_EXCL_MASK 0xffffUL +#ifdef CONFIG_KASAN_HW_TAGS +/* + * KASAN always uses a whole byte for its tags. With CONFIG_KASAN_HW_TAGS it + * only uses tags in the range 0xF0-0xFF, which we map to MTE tags 0x0-0xF. + */ +#define __MTE_TAG_MIN (KASAN_TAG_MIN & 0xf) +#define __MTE_TAG_MAX (KASAN_TAG_MAX & 0xf) +#define __MTE_TAG_INCL GENMASK(__MTE_TAG_MAX, __MTE_TAG_MIN) +#define KERNEL_GCR_EL1_EXCL (SYS_GCR_EL1_EXCL_MASK & ~__MTE_TAG_INCL) +#else +#define KERNEL_GCR_EL1_EXCL SYS_GCR_EL1_EXCL_MASK +#endif + +#define KERNEL_GCR_EL1 (SYS_GCR_EL1_RRND | KERNEL_GCR_EL1_EXCL) + /* RGSR_EL1 Definitions */ #define SYS_RGSR_EL1_TAG_MASK 0xfUL #define SYS_RGSR_EL1_SEED_SHIFT 8 diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index cc3f5a33ff9c..412a3b9a3c25 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -245,9 +245,10 @@ static inline void flush_tlb_all(void) static inline void flush_tlb_mm(struct mm_struct *mm) { - unsigned long asid = __TLBI_VADDR(0, ASID(mm)); + unsigned long asid; dsb(ishst); + asid = __TLBI_VADDR(0, ASID(mm)); __tlbi(aside1is, asid); __tlbi_user(aside1is, asid); dsb(ish); @@ -256,9 +257,10 @@ static inline void flush_tlb_mm(struct mm_struct *mm) static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, unsigned long uaddr) { - unsigned long addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); + unsigned long addr; dsb(ishst); + addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); __tlbi(vale1is, addr); __tlbi_user(vale1is, addr); } @@ -283,9 +285,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, { int num = 0; int scale = 0; - unsigned long asid = ASID(vma->vm_mm); - unsigned long addr; - unsigned long pages; + unsigned long asid, addr, pages; start = round_down(start, stride); end = round_up(end, stride); @@ -305,10 +305,11 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, } dsb(ishst); + asid = ASID(vma->vm_mm); /* * When the CPU does not support TLB range operations, flush the TLB - * entries one by one at the granularity of 'stride'. If the the TLB + * entries one by one at the granularity of 'stride'. If the TLB * range ops are supported, then: * * 1. If 'pages' is odd, flush the first page through non-range diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index c85670692afa..551427ae8cc5 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -52,7 +52,7 @@ int main(void) DEFINE(THREAD_KEYS_KERNEL, offsetof(struct task_struct, thread.keys_kernel)); #endif #ifdef CONFIG_ARM64_MTE - DEFINE(THREAD_GCR_EL1_USER, offsetof(struct task_struct, thread.gcr_user_excl)); + DEFINE(THREAD_MTE_CTRL, offsetof(struct task_struct, thread.mte_ctrl)); #endif BLANK(); DEFINE(S_X0, offsetof(struct pt_regs, regs[0])); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0ead8bfedf20..b2770d753ba3 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -67,6 +67,7 @@ #include <linux/crash_dump.h> #include <linux/sort.h> #include <linux/stop_machine.h> +#include <linux/sysfs.h> #include <linux/types.h> #include <linux/minmax.h> #include <linux/mm.h> @@ -1321,6 +1322,31 @@ const struct cpumask *system_32bit_el0_cpumask(void) return cpu_possible_mask; } +static int __init parse_32bit_el0_param(char *str) +{ + allow_mismatched_32bit_el0 = true; + return 0; +} +early_param("allow_mismatched_32bit_el0", parse_32bit_el0_param); + +static ssize_t aarch32_el0_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct cpumask *mask = system_32bit_el0_cpumask(); + + return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(mask)); +} +static const DEVICE_ATTR_RO(aarch32_el0); + +static int __init aarch32_el0_sysfs_init(void) +{ + if (!allow_mismatched_32bit_el0) + return 0; + + return device_create_file(cpu_subsys.dev_root, &dev_attr_aarch32_el0); +} +device_initcall(aarch32_el0_sysfs_init); + static bool has_32bit_el0(const struct arm64_cpu_capabilities *entry, int scope) { if (!has_cpuid_feature(entry, scope)) @@ -1561,8 +1587,6 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) if (!cpu) arm64_use_ng_mappings = true; - - return; } #else static void @@ -1734,7 +1758,7 @@ static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused) u64 val = read_sysreg_s(SYS_CLIDR_EL1); /* Check that CLIDR_EL1.LOU{U,IS} are both 0 */ - WARN_ON(val & (7 << 27 | 7 << 21)); + WARN_ON(CLIDR_LOUU(val) || CLIDR_LOUIS(val)); } #ifdef CONFIG_ARM64_PAN @@ -1843,6 +1867,9 @@ static void bti_enable(const struct arm64_cpu_capabilities *__unused) #ifdef CONFIG_ARM64_MTE static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) { + sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ATA | SCTLR_EL1_ATA0); + isb(); + /* * Clear the tags in the zero page. This needs to be done via the * linear map which has the Tagged attribute. @@ -2901,15 +2928,38 @@ void __init setup_cpu_features(void) static int enable_mismatched_32bit_el0(unsigned int cpu) { + /* + * The first 32-bit-capable CPU we detected and so can no longer + * be offlined by userspace. -1 indicates we haven't yet onlined + * a 32-bit-capable CPU. + */ + static int lucky_winner = -1; + struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0); if (cpu_32bit) { cpumask_set_cpu(cpu, cpu_32bit_el0_mask); static_branch_enable_cpuslocked(&arm64_mismatched_32bit_el0); - setup_elf_hwcaps(compat_elf_hwcaps); } + if (cpumask_test_cpu(0, cpu_32bit_el0_mask) == cpu_32bit) + return 0; + + if (lucky_winner >= 0) + return 0; + + /* + * We've detected a mismatch. We need to keep one of our CPUs with + * 32-bit EL0 online so that is_cpu_allowed() doesn't end up rejecting + * every CPU in the system for a 32-bit task. + */ + lucky_winner = cpu_32bit ? cpu : cpumask_any_and(cpu_32bit_el0_mask, + cpu_active_mask); + get_cpu_device(lucky_winner)->offline_disabled = true; + setup_elf_hwcaps(compat_elf_hwcaps); + pr_info("Asymmetric 32-bit EL0 support detected on CPU %u; CPU hot-unplug disabled on CPU %u\n", + cpu, lucky_winner); return 0; } diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index db8b2e2d02c2..32f9796c4ffe 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -26,10 +26,14 @@ #include <asm/system_misc.h> /* + * Handle IRQ/context state management when entering from kernel mode. + * Before this function is called it is not safe to call regular kernel code, + * intrumentable code, or any code which may trigger an exception. + * * This is intended to match the logic in irqentry_enter(), handling the kernel * mode transitions only. */ -static void noinstr enter_from_kernel_mode(struct pt_regs *regs) +static __always_inline void __enter_from_kernel_mode(struct pt_regs *regs) { regs->exit_rcu = false; @@ -45,20 +49,26 @@ static void noinstr enter_from_kernel_mode(struct pt_regs *regs) lockdep_hardirqs_off(CALLER_ADDR0); rcu_irq_enter_check_tick(); trace_hardirqs_off_finish(); +} +static void noinstr enter_from_kernel_mode(struct pt_regs *regs) +{ + __enter_from_kernel_mode(regs); mte_check_tfsr_entry(); } /* + * Handle IRQ/context state management when exiting to kernel mode. + * After this function returns it is not safe to call regular kernel code, + * intrumentable code, or any code which may trigger an exception. + * * This is intended to match the logic in irqentry_exit(), handling the kernel * mode transitions only, and with preemption handled elsewhere. */ -static void noinstr exit_to_kernel_mode(struct pt_regs *regs) +static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs) { lockdep_assert_irqs_disabled(); - mte_check_tfsr_exit(); - if (interrupts_enabled(regs)) { if (regs->exit_rcu) { trace_hardirqs_on_prepare(); @@ -75,6 +85,71 @@ static void noinstr exit_to_kernel_mode(struct pt_regs *regs) } } +static void noinstr exit_to_kernel_mode(struct pt_regs *regs) +{ + mte_check_tfsr_exit(); + __exit_to_kernel_mode(regs); +} + +/* + * Handle IRQ/context state management when entering from user mode. + * Before this function is called it is not safe to call regular kernel code, + * intrumentable code, or any code which may trigger an exception. + */ +static __always_inline void __enter_from_user_mode(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit_irqoff(); + trace_hardirqs_off_finish(); +} + +static __always_inline void enter_from_user_mode(struct pt_regs *regs) +{ + __enter_from_user_mode(); +} + +/* + * Handle IRQ/context state management when exiting to user mode. + * After this function returns it is not safe to call regular kernel code, + * intrumentable code, or any code which may trigger an exception. + */ +static __always_inline void __exit_to_user_mode(void) +{ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + user_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +static __always_inline void prepare_exit_to_user_mode(struct pt_regs *regs) +{ + unsigned long flags; + + local_daif_mask(); + + flags = READ_ONCE(current_thread_info()->flags); + if (unlikely(flags & _TIF_WORK_MASK)) + do_notify_resume(regs, flags); +} + +static __always_inline void exit_to_user_mode(struct pt_regs *regs) +{ + prepare_exit_to_user_mode(regs); + mte_check_tfsr_exit(); + __exit_to_user_mode(); +} + +asmlinkage void noinstr asm_exit_to_user_mode(struct pt_regs *regs) +{ + exit_to_user_mode(regs); +} + +/* + * Handle IRQ/context state management when entering an NMI from user/kernel + * mode. Before this function is called it is not safe to call regular kernel + * code, intrumentable code, or any code which may trigger an exception. + */ static void noinstr arm64_enter_nmi(struct pt_regs *regs) { regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); @@ -88,6 +163,11 @@ static void noinstr arm64_enter_nmi(struct pt_regs *regs) ftrace_nmi_enter(); } +/* + * Handle IRQ/context state management when exiting an NMI from user/kernel + * mode. After this function returns it is not safe to call regular kernel + * code, intrumentable code, or any code which may trigger an exception. + */ static void noinstr arm64_exit_nmi(struct pt_regs *regs) { bool restore = regs->lockdep_hardirqs; @@ -105,6 +185,40 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs) __nmi_exit(); } +/* + * Handle IRQ/context state management when entering a debug exception from + * kernel mode. Before this function is called it is not safe to call regular + * kernel code, intrumentable code, or any code which may trigger an exception. + */ +static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs) +{ + regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); + + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_nmi_enter(); + + trace_hardirqs_off_finish(); +} + +/* + * Handle IRQ/context state management when exiting a debug exception from + * kernel mode. After this function returns it is not safe to call regular + * kernel code, intrumentable code, or any code which may trigger an exception. + */ +static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs) +{ + bool restore = regs->lockdep_hardirqs; + + if (restore) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + } + + rcu_nmi_exit(); + if (restore) + lockdep_hardirqs_on(CALLER_ADDR0); +} + static void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) @@ -265,30 +379,6 @@ static void noinstr el1_undef(struct pt_regs *regs) exit_to_kernel_mode(regs); } -static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs) -{ - regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); - - lockdep_hardirqs_off(CALLER_ADDR0); - rcu_nmi_enter(); - - trace_hardirqs_off_finish(); -} - -static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs) -{ - bool restore = regs->lockdep_hardirqs; - - if (restore) { - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - } - - rcu_nmi_exit(); - if (restore) - lockdep_hardirqs_on(CALLER_ADDR0); -} - static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -382,31 +472,14 @@ asmlinkage void noinstr el1h_64_error_handler(struct pt_regs *regs) arm64_exit_nmi(regs); } -asmlinkage void noinstr enter_from_user_mode(void) -{ - lockdep_hardirqs_off(CALLER_ADDR0); - CT_WARN_ON(ct_state() != CONTEXT_USER); - user_exit_irqoff(); - trace_hardirqs_off_finish(); -} - -asmlinkage void noinstr exit_to_user_mode(void) -{ - mte_check_tfsr_exit(); - - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - user_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); -} - static void noinstr el0_da(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_mem_abort(far, esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr) @@ -421,37 +494,42 @@ static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr) if (!is_ttbr0_addr(far)) arm64_apply_bp_hardening(); - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_mem_abort(far, esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_fpsimd_acc(esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_sve_acc(esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_fpsimd_exc(esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_sysinstr(esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr) @@ -461,37 +539,42 @@ static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr) if (!is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(far, esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(regs->sp, esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_undef(struct pt_regs *regs) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_undefinstr(regs); + exit_to_user_mode(regs); } static void noinstr el0_bti(struct pt_regs *regs) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_bti(regs); + exit_to_user_mode(regs); } static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); bad_el0_sync(regs, 0, esr); + exit_to_user_mode(regs); } static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) @@ -499,23 +582,26 @@ static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ unsigned long far = read_sysreg(far_el1); - enter_from_user_mode(); + enter_from_user_mode(regs); do_debug_exception(far, esr, regs); local_daif_restore(DAIF_PROCCTX); + exit_to_user_mode(regs); } static void noinstr el0_svc(struct pt_regs *regs) { - enter_from_user_mode(); + enter_from_user_mode(regs); cortex_a76_erratum_1463225_svc_handler(); do_el0_svc(regs); + exit_to_user_mode(regs); } static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_ptrauth_fault(regs, esr); + exit_to_user_mode(regs); } asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) @@ -574,7 +660,7 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) static void noinstr el0_interrupt(struct pt_regs *regs, void (*handler)(struct pt_regs *)) { - enter_from_user_mode(); + enter_from_user_mode(regs); write_sysreg(DAIF_PROCCTX_NOIRQ, daif); @@ -582,6 +668,8 @@ static void noinstr el0_interrupt(struct pt_regs *regs, arm64_apply_bp_hardening(); do_interrupt_handler(regs, handler); + + exit_to_user_mode(regs); } static void noinstr __el0_irq_handler_common(struct pt_regs *regs) @@ -608,12 +696,13 @@ static void noinstr __el0_error_handler_common(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_ERRCTX); arm64_enter_nmi(regs); do_serror(regs, esr); arm64_exit_nmi(regs); local_daif_restore(DAIF_PROCCTX); + exit_to_user_mode(regs); } asmlinkage void noinstr el0t_64_error_handler(struct pt_regs *regs) @@ -624,16 +713,18 @@ asmlinkage void noinstr el0t_64_error_handler(struct pt_regs *regs) #ifdef CONFIG_COMPAT static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr) { - enter_from_user_mode(); + enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); do_cp15instr(esr, regs); + exit_to_user_mode(regs); } static void noinstr el0_svc_compat(struct pt_regs *regs) { - enter_from_user_mode(); + enter_from_user_mode(regs); cortex_a76_erratum_1463225_svc_handler(); do_el0_svc_compat(regs); + exit_to_user_mode(regs); } asmlinkage void noinstr el0t_32_sync_handler(struct pt_regs *regs) diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index 0a7a64753878..196e921f61de 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -33,11 +33,24 @@ SYM_FUNC_END(fpsimd_load_state) #ifdef CONFIG_ARM64_SVE +/* + * Save the SVE state + * + * x0 - pointer to buffer for state + * x1 - pointer to storage for FPSR + */ SYM_FUNC_START(sve_save_state) sve_save 0, x1, 2 ret SYM_FUNC_END(sve_save_state) +/* + * Load the SVE state + * + * x0 - pointer to buffer for state + * x1 - pointer to storage for FPSR + * x2 - VQ-1 + */ SYM_FUNC_START(sve_load_state) sve_load 0, x1, x2, 3, x4 ret diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 863d44f73028..bc6d5a970a13 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -29,16 +29,6 @@ #include <asm/asm-uaccess.h> #include <asm/unistd.h> -/* - * Context tracking and irqflag tracing need to instrument transitions between - * user and kernel mode. - */ - .macro user_enter_irqoff -#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS) - bl exit_to_user_mode -#endif - .endm - .macro clear_gp_regs .irp n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29 mov x\n, xzr @@ -133,42 +123,46 @@ alternative_cb_end .endm /* Check for MTE asynchronous tag check faults */ - .macro check_mte_async_tcf, tmp, ti_flags + .macro check_mte_async_tcf, tmp, ti_flags, thread_sctlr #ifdef CONFIG_ARM64_MTE .arch_extension lse alternative_if_not ARM64_MTE b 1f alternative_else_nop_endif + /* + * Asynchronous tag check faults are only possible in ASYNC (2) or + * ASYM (3) modes. In each of these modes bit 1 of SCTLR_EL1.TCF0 is + * set, so skip the check if it is unset. + */ + tbz \thread_sctlr, #(SCTLR_EL1_TCF0_SHIFT + 1), 1f mrs_s \tmp, SYS_TFSRE0_EL1 tbz \tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f /* Asynchronous TCF occurred for TTBR0 access, set the TI flag */ mov \tmp, #_TIF_MTE_ASYNC_FAULT add \ti_flags, tsk, #TSK_TI_FLAGS stset \tmp, [\ti_flags] - msr_s SYS_TFSRE0_EL1, xzr 1: #endif .endm /* Clear the MTE asynchronous tag check faults */ - .macro clear_mte_async_tcf + .macro clear_mte_async_tcf thread_sctlr #ifdef CONFIG_ARM64_MTE alternative_if ARM64_MTE + /* See comment in check_mte_async_tcf above. */ + tbz \thread_sctlr, #(SCTLR_EL1_TCF0_SHIFT + 1), 1f dsb ish msr_s SYS_TFSRE0_EL1, xzr +1: alternative_else_nop_endif #endif .endm - .macro mte_set_gcr, tmp, tmp2 + .macro mte_set_gcr, mte_ctrl, tmp #ifdef CONFIG_ARM64_MTE - /* - * Calculate and set the exclude mask preserving - * the RRND (bit[16]) setting. - */ - mrs_s \tmp2, SYS_GCR_EL1 - bfi \tmp2, \tmp, #0, #16 - msr_s SYS_GCR_EL1, \tmp2 + ubfx \tmp, \mte_ctrl, #MTE_CTRL_GCR_USER_EXCL_SHIFT, #16 + orr \tmp, \tmp, #SYS_GCR_EL1_RRND + msr_s SYS_GCR_EL1, \tmp #endif .endm @@ -177,10 +171,8 @@ alternative_else_nop_endif alternative_if_not ARM64_MTE b 1f alternative_else_nop_endif - ldr_l \tmp, gcr_kernel_excl - - mte_set_gcr \tmp, \tmp2 - isb + mov \tmp, KERNEL_GCR_EL1 + msr_s SYS_GCR_EL1, \tmp 1: #endif .endm @@ -190,7 +182,7 @@ alternative_else_nop_endif alternative_if_not ARM64_MTE b 1f alternative_else_nop_endif - ldr \tmp, [\tsk, #THREAD_GCR_EL1_USER] + ldr \tmp, [\tsk, #THREAD_MTE_CTRL] mte_set_gcr \tmp, \tmp2 1: @@ -231,8 +223,8 @@ alternative_else_nop_endif disable_step_tsk x19, x20 /* Check for asynchronous tag check faults in user space */ - check_mte_async_tcf x22, x23 - apply_ssbd 1, x22, x23 + ldr x0, [tsk, THREAD_SCTLR_USER] + check_mte_async_tcf x22, x23, x0 #ifdef CONFIG_ARM64_PTR_AUTH alternative_if ARM64_HAS_ADDRESS_AUTH @@ -245,7 +237,6 @@ alternative_if ARM64_HAS_ADDRESS_AUTH * was disabled on kernel exit then we would have left the kernel IA * installed so there is no need to install it again. */ - ldr x0, [tsk, THREAD_SCTLR_USER] tbz x0, SCTLR_ELx_ENIA_SHIFT, 1f __ptrauth_keys_install_kernel_nosync tsk, x20, x22, x23 b 2f @@ -254,12 +245,26 @@ alternative_if ARM64_HAS_ADDRESS_AUTH orr x0, x0, SCTLR_ELx_ENIA msr sctlr_el1, x0 2: - isb alternative_else_nop_endif #endif + apply_ssbd 1, x22, x23 + mte_set_kernel_gcr x22, x23 + /* + * Any non-self-synchronizing system register updates required for + * kernel entry should be placed before this point. + */ +alternative_if ARM64_MTE + isb + b 1f +alternative_else_nop_endif +alternative_if ARM64_HAS_ADDRESS_AUTH + isb +alternative_else_nop_endif +1: + scs_load tsk .else add x21, sp, #PT_REGS_SIZE @@ -362,6 +367,10 @@ alternative_else_nop_endif 3: scs_save tsk + /* Ignore asynchronous tag check faults in the uaccess routines */ + ldr x0, [tsk, THREAD_SCTLR_USER] + clear_mte_async_tcf x0 + #ifdef CONFIG_ARM64_PTR_AUTH alternative_if ARM64_HAS_ADDRESS_AUTH /* @@ -371,7 +380,6 @@ alternative_if ARM64_HAS_ADDRESS_AUTH * * No kernel C function calls after this. */ - ldr x0, [tsk, THREAD_SCTLR_USER] tbz x0, SCTLR_ELx_ENIA_SHIFT, 1f __ptrauth_keys_install_user tsk, x0, x1, x2 b 2f @@ -474,18 +482,6 @@ SYM_CODE_END(__swpan_exit_el0) /* GPRs used by entry code */ tsk .req x28 // current thread_info -/* - * Interrupt handling. - */ - .macro gic_prio_kentry_setup, tmp:req -#ifdef CONFIG_ARM64_PSEUDO_NMI - alternative_if ARM64_HAS_IRQ_PRIO_MASKING - mov \tmp, #(GIC_PRIO_PSR_I_SET | GIC_PRIO_IRQON) - msr_s SYS_ICC_PMR_EL1, \tmp - alternative_else_nop_endif -#endif - .endm - .text /* @@ -517,12 +513,13 @@ SYM_CODE_START(vectors) SYM_CODE_END(vectors) #ifdef CONFIG_VMAP_STACK +SYM_CODE_START_LOCAL(__bad_stack) /* * We detected an overflow in kernel_ventry, which switched to the * overflow stack. Stash the exception regs, and head to our overflow * handler. */ -__bad_stack: + /* Restore the original x0 value */ mrs x0, tpidrro_el0 @@ -542,6 +539,7 @@ __bad_stack: /* Time to die */ bl handle_bad_stack ASM_BUG() +SYM_CODE_END(__bad_stack) #endif /* CONFIG_VMAP_STACK */ @@ -585,37 +583,13 @@ SYM_CODE_START_LOCAL(ret_to_kernel) kernel_exit 1 SYM_CODE_END(ret_to_kernel) -/* - * "slow" syscall return path. - */ SYM_CODE_START_LOCAL(ret_to_user) - disable_daif - gic_prio_kentry_setup tmp=x3 -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - ldr x19, [tsk, #TSK_TI_FLAGS] - and x2, x19, #_TIF_WORK_MASK - cbnz x2, work_pending -finish_ret_to_user: - user_enter_irqoff - /* Ignore asynchronous tag check faults in the uaccess routines */ - clear_mte_async_tcf + ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step enable_step_tsk x19, x2 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK bl stackleak_erase #endif kernel_exit 0 - -/* - * Ok, we need to do extra processing, enter the slow path. - */ -work_pending: - mov x0, sp // 'regs' - mov x1, x19 - bl do_notify_resume - ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step - b finish_ret_to_user SYM_CODE_END(ret_to_user) .popsection // .entry.text @@ -781,6 +755,8 @@ SYM_CODE_START(ret_from_fork) mov x0, x20 blr x19 1: get_current_task tsk + mov x0, sp + bl asm_exit_to_user_mode b ret_to_user SYM_CODE_END(ret_from_fork) NOKPROBE(ret_from_fork) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index e57b23f95284..5a294f20e9de 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -162,6 +162,8 @@ extern void __percpu *efi_sve_state; DEFINE_PER_CPU(bool, fpsimd_context_busy); EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); +static void fpsimd_bind_task_to_cpu(void); + static void __get_cpu_fpsimd_context(void) { bool busy = __this_cpu_xchg(fpsimd_context_busy, true); @@ -518,12 +520,6 @@ void sve_alloc(struct task_struct *task) /* This is a small allocation (maximum ~8KB) and Should Not Fail. */ task->thread.sve_state = kzalloc(sve_state_size(task), GFP_KERNEL); - - /* - * If future SVE revisions can have larger vectors though, - * this may cease to be true: - */ - BUG_ON(!task->thread.sve_state); } @@ -943,6 +939,10 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs) } sve_alloc(current); + if (!current->thread.sve_state) { + force_sig(SIGKILL); + return; + } get_cpu_fpsimd_context(); @@ -1112,7 +1112,7 @@ void fpsimd_signal_preserve_current_state(void) * The caller must have ownership of the cpu FPSIMD context before calling * this function. */ -void fpsimd_bind_task_to_cpu(void) +static void fpsimd_bind_task_to_cpu(void) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index c5c994a73a64..17962452e31d 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -177,7 +177,7 @@ SYM_CODE_END(preserve_boot_args) * to be composed of multiple pages. (This effectively scales the end index). * * vstart: virtual address of start of range - * vend: virtual address of end of range + * vend: virtual address of end of range - we map [vstart, vend] * shift: shift used to transform virtual address into index * ptrs: number of entries in page table * istart: index in table corresponding to vstart @@ -214,17 +214,18 @@ SYM_CODE_END(preserve_boot_args) * * tbl: location of page table * rtbl: address to be used for first level page table entry (typically tbl + PAGE_SIZE) - * vstart: start address to map - * vend: end address to map - we map [vstart, vend] + * vstart: virtual address of start of range + * vend: virtual address of end of range - we map [vstart, vend - 1] * flags: flags to use to map last level entries * phys: physical address corresponding to vstart - physical memory is contiguous * pgds: the number of pgd entries * * Temporaries: istart, iend, tmp, count, sv - these need to be different registers - * Preserves: vstart, vend, flags - * Corrupts: tbl, rtbl, istart, iend, tmp, count, sv + * Preserves: vstart, flags + * Corrupts: tbl, rtbl, vend, istart, iend, tmp, count, sv */ .macro map_memory, tbl, rtbl, vstart, vend, flags, phys, pgds, istart, iend, tmp, count, sv + sub \vend, \vend, #1 add \rtbl, \tbl, #PAGE_SIZE mov \sv, \rtbl mov \count, #0 diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 53a381a7f65d..d8e606fe3c21 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -54,6 +54,7 @@ static const struct ftr_set_desc pfr1 __initconst = { .override = &id_aa64pfr1_override, .fields = { { "bt", ID_AA64PFR1_BT_SHIFT }, + { "mte", ID_AA64PFR1_MTE_SHIFT}, {} }, }; @@ -100,6 +101,7 @@ static const struct { { "arm64.nopauth", "id_aa64isar1.gpi=0 id_aa64isar1.gpa=0 " "id_aa64isar1.api=0 id_aa64isar1.apa=0" }, + { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "kaslr.disabled=1" }, }; diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 36f51b0e438a..9d314a3bad3b 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -4,6 +4,7 @@ */ #include <linux/bitops.h> +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/prctl.h> @@ -22,9 +23,7 @@ #include <asm/ptrace.h> #include <asm/sysreg.h> -u64 gcr_kernel_excl __ro_after_init; - -static bool report_fault_once = true; +static DEFINE_PER_CPU_READ_MOSTLY(u64, mte_tcf_preferred); #ifdef CONFIG_KASAN_HW_TAGS /* Whether the MTE asynchronous mode is enabled. */ @@ -101,26 +100,6 @@ int memcmp_pages(struct page *page1, struct page *page2) return ret; } -void mte_init_tags(u64 max_tag) -{ - static bool gcr_kernel_excl_initialized; - - if (!gcr_kernel_excl_initialized) { - /* - * The format of the tags in KASAN is 0xFF and in MTE is 0xF. - * This conversion extracts an MTE tag from a KASAN tag. - */ - u64 incl = GENMASK(FIELD_GET(MTE_TAG_MASK >> MTE_TAG_SHIFT, - max_tag), 0); - - gcr_kernel_excl = ~incl & SYS_GCR_EL1_EXCL_MASK; - gcr_kernel_excl_initialized = true; - } - - /* Enable the kernel exclude mask for random tags generation. */ - write_sysreg_s(SYS_GCR_EL1_RRND | gcr_kernel_excl, SYS_GCR_EL1); -} - static inline void __mte_enable_kernel(const char *mode, unsigned long tcf) { /* Enable MTE Sync Mode for EL1. */ @@ -160,16 +139,6 @@ void mte_enable_kernel_async(void) } #endif -void mte_set_report_once(bool state) -{ - WRITE_ONCE(report_fault_once, state); -} - -bool mte_report_once(void) -{ - return READ_ONCE(report_fault_once); -} - #ifdef CONFIG_KASAN_HW_TAGS void mte_check_tfsr_el1(void) { @@ -193,14 +162,26 @@ void mte_check_tfsr_el1(void) } #endif -static void set_gcr_el1_excl(u64 excl) +static void mte_update_sctlr_user(struct task_struct *task) { - current->thread.gcr_user_excl = excl; - /* - * SYS_GCR_EL1 will be set to current->thread.gcr_user_excl value - * by mte_set_user_gcr() in kernel_exit, + * This must be called with preemption disabled and can only be called + * on the current or next task since the CPU must match where the thread + * is going to run. The caller is responsible for calling + * update_sctlr_el1() later in the same preemption disabled block. */ + unsigned long sctlr = task->thread.sctlr_user; + unsigned long mte_ctrl = task->thread.mte_ctrl; + unsigned long pref, resolved_mte_tcf; + + pref = __this_cpu_read(mte_tcf_preferred); + resolved_mte_tcf = (mte_ctrl & pref) ? pref : mte_ctrl; + sctlr &= ~SCTLR_EL1_TCF0_MASK; + if (resolved_mte_tcf & MTE_CTRL_TCF_ASYNC) + sctlr |= SCTLR_EL1_TCF0_ASYNC; + else if (resolved_mte_tcf & MTE_CTRL_TCF_SYNC) + sctlr |= SCTLR_EL1_TCF0_SYNC; + task->thread.sctlr_user = sctlr; } void mte_thread_init_user(void) @@ -212,15 +193,14 @@ void mte_thread_init_user(void) dsb(ish); write_sysreg_s(0, SYS_TFSRE0_EL1); clear_thread_flag(TIF_MTE_ASYNC_FAULT); - /* disable tag checking */ - set_task_sctlr_el1((current->thread.sctlr_user & ~SCTLR_EL1_TCF0_MASK) | - SCTLR_EL1_TCF0_NONE); - /* reset tag generation mask */ - set_gcr_el1_excl(SYS_GCR_EL1_EXCL_MASK); + /* disable tag checking and reset tag generation mask */ + set_mte_ctrl(current, 0); } void mte_thread_switch(struct task_struct *next) { + mte_update_sctlr_user(next); + /* * Check if an async tag exception occurred at EL1. * @@ -248,44 +228,25 @@ void mte_suspend_enter(void) mte_check_tfsr_el1(); } -void mte_suspend_exit(void) -{ - if (!system_supports_mte()) - return; - - sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, gcr_kernel_excl); - isb(); -} - long set_mte_ctrl(struct task_struct *task, unsigned long arg) { - u64 sctlr = task->thread.sctlr_user & ~SCTLR_EL1_TCF0_MASK; - u64 gcr_excl = ~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) & - SYS_GCR_EL1_EXCL_MASK; + u64 mte_ctrl = (~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) & + SYS_GCR_EL1_EXCL_MASK) << MTE_CTRL_GCR_USER_EXCL_SHIFT; if (!system_supports_mte()) return 0; - switch (arg & PR_MTE_TCF_MASK) { - case PR_MTE_TCF_NONE: - sctlr |= SCTLR_EL1_TCF0_NONE; - break; - case PR_MTE_TCF_SYNC: - sctlr |= SCTLR_EL1_TCF0_SYNC; - break; - case PR_MTE_TCF_ASYNC: - sctlr |= SCTLR_EL1_TCF0_ASYNC; - break; - default: - return -EINVAL; - } - - if (task != current) { - task->thread.sctlr_user = sctlr; - task->thread.gcr_user_excl = gcr_excl; - } else { - set_task_sctlr_el1(sctlr); - set_gcr_el1_excl(gcr_excl); + if (arg & PR_MTE_TCF_ASYNC) + mte_ctrl |= MTE_CTRL_TCF_ASYNC; + if (arg & PR_MTE_TCF_SYNC) + mte_ctrl |= MTE_CTRL_TCF_SYNC; + + task->thread.mte_ctrl = mte_ctrl; + if (task == current) { + preempt_disable(); + mte_update_sctlr_user(task); + update_sctlr_el1(task->thread.sctlr_user); + preempt_enable(); } return 0; @@ -294,24 +255,18 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg) long get_mte_ctrl(struct task_struct *task) { unsigned long ret; - u64 incl = ~task->thread.gcr_user_excl & SYS_GCR_EL1_EXCL_MASK; + u64 mte_ctrl = task->thread.mte_ctrl; + u64 incl = (~mte_ctrl >> MTE_CTRL_GCR_USER_EXCL_SHIFT) & + SYS_GCR_EL1_EXCL_MASK; if (!system_supports_mte()) return 0; ret = incl << PR_MTE_TAG_SHIFT; - - switch (task->thread.sctlr_user & SCTLR_EL1_TCF0_MASK) { - case SCTLR_EL1_TCF0_NONE: - ret |= PR_MTE_TCF_NONE; - break; - case SCTLR_EL1_TCF0_SYNC: - ret |= PR_MTE_TCF_SYNC; - break; - case SCTLR_EL1_TCF0_ASYNC: + if (mte_ctrl & MTE_CTRL_TCF_ASYNC) ret |= PR_MTE_TCF_ASYNC; - break; - } + if (mte_ctrl & MTE_CTRL_TCF_SYNC) + ret |= PR_MTE_TCF_SYNC; return ret; } @@ -450,3 +405,54 @@ int mte_ptrace_copy_tags(struct task_struct *child, long request, return ret; } + +static ssize_t mte_tcf_preferred_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + switch (per_cpu(mte_tcf_preferred, dev->id)) { + case MTE_CTRL_TCF_ASYNC: + return sysfs_emit(buf, "async\n"); + case MTE_CTRL_TCF_SYNC: + return sysfs_emit(buf, "sync\n"); + default: + return sysfs_emit(buf, "???\n"); + } +} + +static ssize_t mte_tcf_preferred_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + u64 tcf; + + if (sysfs_streq(buf, "async")) + tcf = MTE_CTRL_TCF_ASYNC; + else if (sysfs_streq(buf, "sync")) + tcf = MTE_CTRL_TCF_SYNC; + else + return -EINVAL; + + device_lock(dev); + per_cpu(mte_tcf_preferred, dev->id) = tcf; + device_unlock(dev); + + return count; +} +static DEVICE_ATTR_RW(mte_tcf_preferred); + +static int register_mte_tcf_preferred_sysctl(void) +{ + unsigned int cpu; + + if (!system_supports_mte()) + return 0; + + for_each_possible_cpu(cpu) { + per_cpu(mte_tcf_preferred, cpu) = MTE_CTRL_TCF_ASYNC; + device_create_file(get_cpu_device(cpu), + &dev_attr_mte_tcf_preferred); + } + + return 0; +} +subsys_initcall(register_mte_tcf_preferred_sysctl); diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index d07788dad388..b4044469527e 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1055,7 +1055,7 @@ static void __armv8pmu_probe_pmu(void *info) dfr0 = read_sysreg(id_aa64dfr0_el1); pmuver = cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_PMUVER_SHIFT); - if (pmuver == 0xf || pmuver == 0) + if (pmuver == ID_AA64DFR0_PMUVER_IMP_DEF || pmuver == 0) return; cpu_pmu->pmuver = pmuver; diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c index 60901ab0a7fe..2708b620b4ae 100644 --- a/arch/arm64/kernel/pointer_auth.c +++ b/arch/arm64/kernel/pointer_auth.c @@ -67,7 +67,7 @@ static u64 arg_to_enxx_mask(unsigned long arg) int ptrauth_set_enabled_keys(struct task_struct *tsk, unsigned long keys, unsigned long enabled) { - u64 sctlr = tsk->thread.sctlr_user; + u64 sctlr; if (!system_supports_address_auth()) return -EINVAL; @@ -78,12 +78,14 @@ int ptrauth_set_enabled_keys(struct task_struct *tsk, unsigned long keys, if ((keys & ~PR_PAC_ENABLED_KEYS_MASK) || (enabled & ~keys)) return -EINVAL; + preempt_disable(); + sctlr = tsk->thread.sctlr_user; sctlr &= ~arg_to_enxx_mask(keys); sctlr |= arg_to_enxx_mask(enabled); + tsk->thread.sctlr_user = sctlr; if (tsk == current) - set_task_sctlr_el1(sctlr); - else - tsk->thread.sctlr_user = sctlr; + update_sctlr_el1(sctlr); + preempt_enable(); return 0; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index c8989b999250..2bd270cd603e 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -21,6 +21,7 @@ #include <linux/mman.h> #include <linux/mm.h> #include <linux/nospec.h> +#include <linux/sched.h> #include <linux/stddef.h> #include <linux/sysctl.h> #include <linux/unistd.h> @@ -163,7 +164,7 @@ static void print_pstate(struct pt_regs *regs) u64 pstate = regs->pstate; if (compat_user_mode(regs)) { - printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c)\n", + printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c %cDIT %cSSBS)\n", pstate, pstate & PSR_AA32_N_BIT ? 'N' : 'n', pstate & PSR_AA32_Z_BIT ? 'Z' : 'z', @@ -174,12 +175,14 @@ static void print_pstate(struct pt_regs *regs) pstate & PSR_AA32_E_BIT ? "BE" : "LE", pstate & PSR_AA32_A_BIT ? 'A' : 'a', pstate & PSR_AA32_I_BIT ? 'I' : 'i', - pstate & PSR_AA32_F_BIT ? 'F' : 'f'); + pstate & PSR_AA32_F_BIT ? 'F' : 'f', + pstate & PSR_AA32_DIT_BIT ? '+' : '-', + pstate & PSR_AA32_SSBS_BIT ? '+' : '-'); } else { const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >> PSR_BTYPE_SHIFT]; - printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO %cTCO BTYPE=%s)\n", + printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO %cTCO %cDIT %cSSBS BTYPE=%s)\n", pstate, pstate & PSR_N_BIT ? 'N' : 'n', pstate & PSR_Z_BIT ? 'Z' : 'z', @@ -192,6 +195,8 @@ static void print_pstate(struct pt_regs *regs) pstate & PSR_PAN_BIT ? '+' : '-', pstate & PSR_UAO_BIT ? '+' : '-', pstate & PSR_TCO_BIT ? '+' : '-', + pstate & PSR_DIT_BIT ? '+' : '-', + pstate & PSR_SSBS_BIT ? '+' : '-', btype_str); } } @@ -468,16 +473,13 @@ static void erratum_1418040_thread_switch(struct task_struct *prev, write_sysreg(val, cntkctl_el1); } -static void compat_thread_switch(struct task_struct *next) -{ - if (!is_compat_thread(task_thread_info(next))) - return; - - if (static_branch_unlikely(&arm64_mismatched_32bit_el0)) - set_tsk_thread_flag(next, TIF_NOTIFY_RESUME); -} - -static void update_sctlr_el1(u64 sctlr) +/* + * __switch_to() checks current->thread.sctlr_user as an optimisation. Therefore + * this function must be called with preemption disabled and the update to + * sctlr_user must be made in the same preemption disabled block so that + * __switch_to() does not see the variable update before the SCTLR_EL1 one. + */ +void update_sctlr_el1(u64 sctlr) { /* * EnIA must not be cleared while in the kernel as this is necessary for @@ -489,19 +491,6 @@ static void update_sctlr_el1(u64 sctlr) isb(); } -void set_task_sctlr_el1(u64 sctlr) -{ - /* - * __switch_to() checks current->thread.sctlr as an - * optimisation. Disable preemption so that it does not see - * the variable update before the SCTLR_EL1 one. - */ - preempt_disable(); - current->thread.sctlr_user = sctlr; - update_sctlr_el1(sctlr); - preempt_enable(); -} - /* * Thread switching. */ @@ -518,7 +507,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, ssbs_thread_switch(next); erratum_1418040_thread_switch(prev, next); ptrauth_thread_switch_user(next); - compat_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case @@ -579,6 +567,28 @@ unsigned long arch_align_stack(unsigned long sp) return sp & ~0xf; } +#ifdef CONFIG_COMPAT +int compat_elf_check_arch(const struct elf32_hdr *hdr) +{ + if (!system_supports_32bit_el0()) + return false; + + if ((hdr)->e_machine != EM_ARM) + return false; + + if (!((hdr)->e_flags & EF_ARM_EABI_MASK)) + return false; + + /* + * Prevent execve() of a 32-bit program from a deadline task + * if the restricted affinity mask would be inadmissible on an + * asymmetric system. + */ + return !static_branch_unlikely(&arm64_mismatched_32bit_el0) || + !dl_task_check_affinity(current, system_32bit_el0_cpumask()); +} +#endif + /* * Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY. */ @@ -588,8 +598,20 @@ void arch_setup_new_exec(void) if (is_compat_task()) { mmflags = MMCF_AARCH32; + + /* + * Restrict the CPU affinity mask for a 32-bit task so that + * it contains only 32-bit-capable CPUs. + * + * From the perspective of the task, this looks similar to + * what would happen if the 64-bit-only CPUs were hot-unplugged + * at the point of execve(), although we try a bit harder to + * honour the cpuset hierarchy. + */ if (static_branch_unlikely(&arm64_mismatched_32bit_el0)) - set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); + force_compatible_cpus_allowed_ptr(current); + } else if (static_branch_unlikely(&arm64_mismatched_32bit_el0)) { + relax_compatible_cpus_allowed_ptr(current); } current->mm->context.flags = mmflags; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index b381a1ee9ea7..e26196a33cf4 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -845,6 +845,11 @@ static int sve_set(struct task_struct *target, } sve_alloc(target); + if (!target->thread.sve_state) { + ret = -ENOMEM; + clear_tsk_thread_flag(target, TIF_SVE); + goto out; + } /* * Ensure target->thread.sve_state is up to date with target's diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 1a0e2b56378b..9fe70b12b34f 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -290,6 +290,11 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ sve_alloc(current); + if (!current->thread.sve_state) { + clear_thread_flag(TIF_SVE); + return -ENOMEM; + } + err = __copy_from_user(current->thread.sve_state, (char __user const *)user->sve + SVE_SIG_REGS_OFFSET, @@ -912,21 +917,7 @@ static void do_signal(struct pt_regs *regs) restore_saved_sigmask(); } -static bool cpu_affinity_invalid(struct pt_regs *regs) -{ - if (!compat_user_mode(regs)) - return false; - - /* - * We're preemptible, but a reschedule will cause us to check the - * affinity again. - */ - return !cpumask_test_cpu(raw_smp_processor_id(), - system_32bit_el0_cpumask()); -} - -asmlinkage void do_notify_resume(struct pt_regs *regs, - unsigned long thread_flags) +void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { do { if (thread_flags & _TIF_NEED_RESCHED) { @@ -952,19 +943,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, if (thread_flags & _TIF_NOTIFY_RESUME) { tracehook_notify_resume(regs); rseq_handle_notify_resume(NULL, regs); - - /* - * If we reschedule after checking the affinity - * then we must ensure that TIF_NOTIFY_RESUME - * is set so that we check the affinity again. - * Since tracehook_notify_resume() clears the - * flag, ensure that the compiler doesn't move - * it after the affinity check. - */ - barrier(); - - if (cpu_affinity_invalid(regs)) - force_sig(SIGKILL); } if (thread_flags & _TIF_FOREIGN_FPSTATE) diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index d3be01c46bec..d984282b979f 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -46,8 +46,6 @@ struct compat_aux_sigframe { unsigned long end_magic; } __attribute__((__aligned__(8))); -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set) { compat_sigset_t cset; @@ -190,10 +188,8 @@ static int compat_restore_sigframe(struct pt_regs *regs, unsigned long psr; err = get_sigset_t(&set, &sf->uc.uc_sigmask); - if (err == 0) { - sigdelsetmask(&set, ~_BLOCKABLE); + if (err == 0) set_current_blocked(&set); - } __get_user_error(regs->regs[0], &sf->uc.uc_mcontext.arm_r0, err); __get_user_error(regs->regs[1], &sf->uc.uc_mcontext.arm_r1, err); diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 938ce6fbee8a..19ee7c33769d 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -76,7 +76,6 @@ void notrace __cpu_suspend_exit(void) spectre_v4_enable_mitigation(NULL); /* Restore additional feature-specific configuration */ - mte_suspend_exit(); ptrauth_suspend_exit(); } diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index b506a4b1e38c..fccfe363e567 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -185,7 +185,7 @@ u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn) break; default: if (aarch64_get_imm_shift_mask(type, &mask, &shift) < 0) { - pr_err("aarch64_insn_decode_immediate: unknown immediate encoding %d\n", + pr_err("%s: unknown immediate encoding %d\n", __func__, type); return 0; } @@ -215,7 +215,7 @@ u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type, break; default: if (aarch64_get_imm_shift_mask(type, &mask, &shift) < 0) { - pr_err("aarch64_insn_encode_immediate: unknown immediate encoding %d\n", + pr_err("%s: unknown immediate encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 349c488765ca..9ae24e3b72be 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -309,24 +309,11 @@ static void die_kernel_fault(const char *msg, unsigned long addr, static void report_tag_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - static bool reported; - bool is_write; - - if (READ_ONCE(reported)) - return; - - /* - * This is used for KASAN tests and assumes that no MTE faults - * happened before running the tests. - */ - if (mte_report_once()) - WRITE_ONCE(reported, true); - /* * SAS bits aren't set for all faults reported in EL1, so we can't * find out access size. */ - is_write = !!(esr & ESR_ELx_WNR); + bool is_write = !!(esr & ESR_ELx_WNR); kasan_report(addr, 0, is_write, regs->pc); } #else diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 35936c5ae1ce..d35c90d2e47a 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -437,8 +437,7 @@ SYM_FUNC_START(__cpu_setup) mov x10, #MAIR_ATTR_NORMAL_TAGGED bfi mair, x10, #(8 * MT_NORMAL_TAGGED), #8 - /* initialize GCR_EL1: all non-zero tags excluded by default */ - mov x10, #(SYS_GCR_EL1_RRND | SYS_GCR_EL1_EXCL_MASK) + mov x10, #KERNEL_GCR_EL1 msr_s SYS_GCR_EL1, x10 /* diff --git a/include/linux/kasan-tags.h b/include/linux/kasan-tags.h new file mode 100644 index 000000000000..4f85f562512c --- /dev/null +++ b/include/linux/kasan-tags.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KASAN_TAGS_H +#define _LINUX_KASAN_TAGS_H + +#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */ +#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */ +#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ + +#ifdef CONFIG_KASAN_HW_TAGS +#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */ +#else +#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */ +#endif + +#endif /* LINUX_KASAN_TAGS_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 964c41ed303e..43bd7f713c39 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -235,14 +235,15 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_SHIFT 1 -# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_SYNC (1UL << 1) +# define PR_MTE_TCF_ASYNC (1UL << 2) +# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) /* MTE tag inclusion mask */ # define PR_MTE_TAG_SHIFT 3 # define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) +/* Unused; kept only for source compatibility */ +# define PR_MTE_TCF_SHIFT 1 /* Control reclaim behavior when allocating memory */ #define PR_SET_IO_FLUSHER 57 diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 8f7b0b2f6e11..8be9d4b3b259 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -53,7 +53,6 @@ static int kasan_test_init(struct kunit *test) } multishot = kasan_save_enable_multi_shot(); - kasan_set_tagging_report_once(false); fail_data.report_found = false; kunit_add_named_resource(test, NULL, NULL, &resource, "kasan_data", &fail_data); @@ -62,7 +61,6 @@ static int kasan_test_init(struct kunit *test) static void kasan_test_exit(struct kunit *test) { - kasan_set_tagging_report_once(true); kasan_restore_multi_shot(multishot); KUNIT_EXPECT_FALSE(test, fail_data.report_found); } diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 4ea8c368b5b8..e4c16f6b6680 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -142,8 +142,6 @@ void kasan_init_hw_tags_cpu(void) if (kasan_arg == KASAN_ARG_OFF) return; - hw_init_tags(KASAN_TAG_MAX); - /* * Enable async mode only when explicitly requested through * the command line. @@ -250,12 +248,6 @@ void kasan_free_pages(struct page *page, unsigned int order) #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -void kasan_set_tagging_report_once(bool state) -{ - hw_set_tagging_report_once(state); -} -EXPORT_SYMBOL_GPL(kasan_set_tagging_report_once); - void kasan_enable_tagging_sync(void) { hw_enable_tagging_sync(); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index d739cdd1621a..fff93b0bcb08 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -3,6 +3,7 @@ #define __MM_KASAN_KASAN_H #include <linux/kasan.h> +#include <linux/kasan-tags.h> #include <linux/kfence.h> #include <linux/stackdepot.h> @@ -51,16 +52,6 @@ extern bool kasan_flag_async __ro_after_init; #define KASAN_MEMORY_PER_SHADOW_PAGE (KASAN_GRANULE_SIZE << PAGE_SHIFT) -#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */ -#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */ -#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ - -#ifdef CONFIG_KASAN_HW_TAGS -#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */ -#else -#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */ -#endif - #ifdef CONFIG_KASAN_GENERIC #define KASAN_FREE_PAGE 0xFF /* page was freed */ #define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ @@ -299,12 +290,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #ifndef arch_enable_tagging_async #define arch_enable_tagging_async() #endif -#ifndef arch_init_tags -#define arch_init_tags(max_tag) -#endif -#ifndef arch_set_tagging_report_once -#define arch_set_tagging_report_once(state) -#endif #ifndef arch_force_async_tag_fault #define arch_force_async_tag_fault() #endif @@ -320,8 +305,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_enable_tagging_sync() arch_enable_tagging_sync() #define hw_enable_tagging_async() arch_enable_tagging_async() -#define hw_init_tags(max_tag) arch_init_tags(max_tag) -#define hw_set_tagging_report_once(state) arch_set_tagging_report_once(state) #define hw_force_async_tag_fault() arch_force_async_tag_fault() #define hw_get_random_tag() arch_get_random_tag() #define hw_get_mem_tag(addr) arch_get_mem_tag(addr) @@ -332,19 +315,16 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_enable_tagging_sync() #define hw_enable_tagging_async() -#define hw_set_tagging_report_once(state) #endif /* CONFIG_KASAN_HW_TAGS */ #if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -void kasan_set_tagging_report_once(bool state); void kasan_enable_tagging_sync(void); void kasan_force_async_fault(void); #else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ -static inline void kasan_set_tagging_report_once(bool state) { } static inline void kasan_enable_tagging_sync(void) { } static inline void kasan_force_async_fault(void) { } diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index d66f76d2a650..b67395903b9b 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -1,5 +1,7 @@ fpsimd-test +rdvl-sve sve-probe-vls sve-ptrace sve-test +vec-syscfg vlset diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index a57009d3a0dc..f2abdd6ba12e 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -1,17 +1,22 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -I../../../../../usr/include/ -TEST_GEN_PROGS := sve-ptrace sve-probe-vls -TEST_PROGS_EXTENDED := fpsimd-test fpsimd-stress sve-test sve-stress vlset +TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg +TEST_PROGS_EXTENDED := fpsimd-test fpsimd-stress \ + rdvl-sve \ + sve-test sve-stress \ + vlset all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) fpsimd-test: fpsimd-test.o $(CC) -nostdlib $^ -o $@ +rdvl-sve: rdvl-sve.o rdvl.o sve-ptrace: sve-ptrace.o sve-ptrace-asm.o -sve-probe-vls: sve-probe-vls.o +sve-probe-vls: sve-probe-vls.o rdvl.o sve-test: sve-test.o $(CC) -nostdlib $^ -o $@ +vec-syscfg: vec-syscfg.o rdvl.o vlset: vlset.o include ../../lib.mk diff --git a/tools/testing/selftests/arm64/fp/TODO b/tools/testing/selftests/arm64/fp/TODO new file mode 100644 index 000000000000..b6b7ebfcf362 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/TODO @@ -0,0 +1,4 @@ +- Test unsupported values in the ABIs. +- More coverage for ptrace (eg, vector length conversions). +- Coverage for signals. +- Test PR_SVE_VL_INHERITY after a double fork. diff --git a/tools/testing/selftests/arm64/fp/rdvl-sve.c b/tools/testing/selftests/arm64/fp/rdvl-sve.c new file mode 100644 index 000000000000..7f8a13a18f5d --- /dev/null +++ b/tools/testing/selftests/arm64/fp/rdvl-sve.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <stdio.h> + +#include "rdvl.h" + +int main(void) +{ + int vl = rdvl_sve(); + + printf("%d\n", vl); + + return 0; +} diff --git a/tools/testing/selftests/arm64/fp/rdvl.S b/tools/testing/selftests/arm64/fp/rdvl.S new file mode 100644 index 000000000000..c916c1c9defd --- /dev/null +++ b/tools/testing/selftests/arm64/fp/rdvl.S @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021 ARM Limited. + +.arch_extension sve + +.globl rdvl_sve +rdvl_sve: + hint 34 // BTI C + rdvl x0, #1 + ret diff --git a/tools/testing/selftests/arm64/fp/rdvl.h b/tools/testing/selftests/arm64/fp/rdvl.h new file mode 100644 index 000000000000..7c9d953fc9e7 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/rdvl.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef RDVL_H +#define RDVL_H + +int rdvl_sve(void); + +#endif diff --git a/tools/testing/selftests/arm64/fp/sve-probe-vls.c b/tools/testing/selftests/arm64/fp/sve-probe-vls.c index 76e138525d55..a24eca7a4ecb 100644 --- a/tools/testing/selftests/arm64/fp/sve-probe-vls.c +++ b/tools/testing/selftests/arm64/fp/sve-probe-vls.c @@ -13,6 +13,7 @@ #include <asm/sigcontext.h> #include "../../kselftest.h" +#include "rdvl.h" int main(int argc, char **argv) { @@ -38,6 +39,10 @@ int main(int argc, char **argv) vl &= PR_SVE_VL_LEN_MASK; + if (rdvl_sve() != vl) + ksft_exit_fail_msg("PR_SVE_SET_VL reports %d, RDVL %d\n", + vl, rdvl_sve()); + if (!sve_vl_valid(vl)) ksft_exit_fail_msg("VL %d invalid\n", vl); vq = sve_vq_from_vl(vl); diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c new file mode 100644 index 000000000000..c02071dcb563 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -0,0 +1,593 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 ARM Limited. + * Original author: Mark Brown <broonie@kernel.org> + */ +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <asm/sigcontext.h> +#include <asm/hwcap.h> + +#include "../../kselftest.h" +#include "rdvl.h" + +#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) + +#define ARCH_MIN_VL SVE_VL_MIN + +struct vec_data { + const char *name; + unsigned long hwcap_type; + unsigned long hwcap; + const char *rdvl_binary; + int (*rdvl)(void); + + int prctl_get; + int prctl_set; + const char *default_vl_file; + + int default_vl; + int min_vl; + int max_vl; +}; + + +static struct vec_data vec_data[] = { + { + .name = "SVE", + .hwcap_type = AT_HWCAP, + .hwcap = HWCAP_SVE, + .rdvl = rdvl_sve, + .rdvl_binary = "./rdvl-sve", + .prctl_get = PR_SVE_GET_VL, + .prctl_set = PR_SVE_SET_VL, + .default_vl_file = "/proc/sys/abi/sve_default_vector_length", + }, +}; + +static int stdio_read_integer(FILE *f, const char *what, int *val) +{ + int n = 0; + int ret; + + ret = fscanf(f, "%d%*1[\n]%n", val, &n); + if (ret < 1 || n < 1) { + ksft_print_msg("failed to parse integer from %s\n", what); + return -1; + } + + return 0; +} + +/* Start a new process and return the vector length it sees */ +static int get_child_rdvl(struct vec_data *data) +{ + FILE *out; + int pipefd[2]; + pid_t pid, child; + int read_vl, ret; + + ret = pipe(pipefd); + if (ret == -1) { + ksft_print_msg("pipe() failed: %d (%s)\n", + errno, strerror(errno)); + return -1; + } + + fflush(stdout); + + child = fork(); + if (child == -1) { + ksft_print_msg("fork() failed: %d (%s)\n", + errno, strerror(errno)); + close(pipefd[0]); + close(pipefd[1]); + return -1; + } + + /* Child: put vector length on the pipe */ + if (child == 0) { + /* + * Replace stdout with the pipe, errors to stderr from + * here as kselftest prints to stdout. + */ + ret = dup2(pipefd[1], 1); + if (ret == -1) { + fprintf(stderr, "dup2() %d\n", errno); + exit(EXIT_FAILURE); + } + + /* exec() a new binary which puts the VL on stdout */ + ret = execl(data->rdvl_binary, data->rdvl_binary, NULL); + fprintf(stderr, "execl(%s) failed: %d\n", + data->rdvl_binary, errno, strerror(errno)); + + exit(EXIT_FAILURE); + } + + close(pipefd[1]); + + /* Parent; wait for the exit status from the child & verify it */ + do { + pid = wait(&ret); + if (pid == -1) { + ksft_print_msg("wait() failed: %d (%s)\n", + errno, strerror(errno)); + close(pipefd[0]); + return -1; + } + } while (pid != child); + + assert(pid == child); + + if (!WIFEXITED(ret)) { + ksft_print_msg("child exited abnormally\n"); + close(pipefd[0]); + return -1; + } + + if (WEXITSTATUS(ret) != 0) { + ksft_print_msg("child returned error %d\n", + WEXITSTATUS(ret)); + close(pipefd[0]); + return -1; + } + + out = fdopen(pipefd[0], "r"); + if (!out) { + ksft_print_msg("failed to open child stdout\n"); + close(pipefd[0]); + return -1; + } + + ret = stdio_read_integer(out, "child", &read_vl); + fclose(out); + if (ret != 0) + return ret; + + return read_vl; +} + +static int file_read_integer(const char *name, int *val) +{ + FILE *f; + int ret; + + f = fopen(name, "r"); + if (!f) { + ksft_test_result_fail("Unable to open %s: %d (%s)\n", + name, errno, + strerror(errno)); + return -1; + } + + ret = stdio_read_integer(f, name, val); + fclose(f); + + return ret; +} + +static int file_write_integer(const char *name, int val) +{ + FILE *f; + int ret; + + f = fopen(name, "w"); + if (!f) { + ksft_test_result_fail("Unable to open %s: %d (%s)\n", + name, errno, + strerror(errno)); + return -1; + } + + fprintf(f, "%d", val); + fclose(f); + if (ret < 0) { + ksft_test_result_fail("Error writing %d to %s\n", + val, name); + return -1; + } + + return 0; +} + +/* + * Verify that we can read the default VL via proc, checking that it + * is set in a freshly spawned child. + */ +static void proc_read_default(struct vec_data *data) +{ + int default_vl, child_vl, ret; + + ret = file_read_integer(data->default_vl_file, &default_vl); + if (ret != 0) + return; + + /* Is this the actual default seen by new processes? */ + child_vl = get_child_rdvl(data); + if (child_vl != default_vl) { + ksft_test_result_fail("%s is %d but child VL is %d\n", + data->default_vl_file, + default_vl, child_vl); + return; + } + + ksft_test_result_pass("%s default vector length %d\n", data->name, + default_vl); + data->default_vl = default_vl; +} + +/* Verify that we can write a minimum value and have it take effect */ +static void proc_write_min(struct vec_data *data) +{ + int ret, new_default, child_vl; + + if (geteuid() != 0) { + ksft_test_result_skip("Need to be root to write to /proc\n"); + return; + } + + ret = file_write_integer(data->default_vl_file, ARCH_MIN_VL); + if (ret != 0) + return; + + /* What was the new value? */ + ret = file_read_integer(data->default_vl_file, &new_default); + if (ret != 0) + return; + + /* Did it take effect in a new process? */ + child_vl = get_child_rdvl(data); + if (child_vl != new_default) { + ksft_test_result_fail("%s is %d but child VL is %d\n", + data->default_vl_file, + new_default, child_vl); + return; + } + + ksft_test_result_pass("%s minimum vector length %d\n", data->name, + new_default); + data->min_vl = new_default; + + file_write_integer(data->default_vl_file, data->default_vl); +} + +/* Verify that we can write a maximum value and have it take effect */ +static void proc_write_max(struct vec_data *data) +{ + int ret, new_default, child_vl; + + if (geteuid() != 0) { + ksft_test_result_skip("Need to be root to write to /proc\n"); + return; + } + + /* -1 is accepted by the /proc interface as the maximum VL */ + ret = file_write_integer(data->default_vl_file, -1); + if (ret != 0) + return; + + /* What was the new value? */ + ret = file_read_integer(data->default_vl_file, &new_default); + if (ret != 0) + return; + + /* Did it take effect in a new process? */ + child_vl = get_child_rdvl(data); + if (child_vl != new_default) { + ksft_test_result_fail("%s is %d but child VL is %d\n", + data->default_vl_file, + new_default, child_vl); + return; + } + + ksft_test_result_pass("%s maximum vector length %d\n", data->name, + new_default); + data->max_vl = new_default; + + file_write_integer(data->default_vl_file, data->default_vl); +} + +/* Can we read back a VL from prctl? */ +static void prctl_get(struct vec_data *data) +{ + int ret; + + ret = prctl(data->prctl_get); + if (ret == -1) { + ksft_test_result_fail("%s prctl() read failed: %d (%s)\n", + data->name, errno, strerror(errno)); + return; + } + + /* Mask out any flags */ + ret &= PR_SVE_VL_LEN_MASK; + + /* Is that what we can read back directly? */ + if (ret == data->rdvl()) + ksft_test_result_pass("%s current VL is %d\n", + data->name, ret); + else + ksft_test_result_fail("%s prctl() VL %d but RDVL is %d\n", + data->name, ret, data->rdvl()); +} + +/* Does the prctl let us set the VL we already have? */ +static void prctl_set_same(struct vec_data *data) +{ + int cur_vl = data->rdvl(); + int ret; + + ret = prctl(data->prctl_set, cur_vl); + if (ret < 0) { + ksft_test_result_fail("%s prctl set failed: %d (%s)\n", + data->name, errno, strerror(errno)); + return; + } + + if (cur_vl != data->rdvl()) + ksft_test_result_pass("%s current VL is %d\n", + data->name, ret); + else + ksft_test_result_fail("%s prctl() VL %d but RDVL is %d\n", + data->name, ret, data->rdvl()); +} + +/* Can we set a new VL for this process? */ +static void prctl_set(struct vec_data *data) +{ + int ret; + + if (data->min_vl == data->max_vl) { + ksft_test_result_skip("%s only one VL supported\n", + data->name); + return; + } + + /* Try to set the minimum VL */ + ret = prctl(data->prctl_set, data->min_vl); + if (ret < 0) { + ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n", + data->name, data->min_vl, + errno, strerror(errno)); + return; + } + + if ((ret & PR_SVE_VL_LEN_MASK) != data->min_vl) { + ksft_test_result_fail("%s prctl set %d but return value is %d\n", + data->name, data->min_vl, data->rdvl()); + return; + } + + if (data->rdvl() != data->min_vl) { + ksft_test_result_fail("%s set %d but RDVL is %d\n", + data->name, data->min_vl, data->rdvl()); + return; + } + + /* Try to set the maximum VL */ + ret = prctl(data->prctl_set, data->max_vl); + if (ret < 0) { + ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n", + data->name, data->max_vl, + errno, strerror(errno)); + return; + } + + if ((ret & PR_SVE_VL_LEN_MASK) != data->max_vl) { + ksft_test_result_fail("%s prctl() set %d but return value is %d\n", + data->name, data->max_vl, data->rdvl()); + return; + } + + /* The _INHERIT flag should not be present when we read the VL */ + ret = prctl(data->prctl_get); + if (ret == -1) { + ksft_test_result_fail("%s prctl() read failed: %d (%s)\n", + data->name, errno, strerror(errno)); + return; + } + + if (ret & PR_SVE_VL_INHERIT) { + ksft_test_result_fail("%s prctl() reports _INHERIT\n", + data->name); + return; + } + + ksft_test_result_pass("%s prctl() set min/max\n", data->name); +} + +/* If we didn't request it a new VL shouldn't affect the child */ +static void prctl_set_no_child(struct vec_data *data) +{ + int ret, child_vl; + + if (data->min_vl == data->max_vl) { + ksft_test_result_skip("%s only one VL supported\n", + data->name); + return; + } + + ret = prctl(data->prctl_set, data->min_vl); + if (ret < 0) { + ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n", + data->name, data->min_vl, + errno, strerror(errno)); + return; + } + + /* Ensure the default VL is different */ + ret = file_write_integer(data->default_vl_file, data->max_vl); + if (ret != 0) + return; + + /* Check that the child has the default we just set */ + child_vl = get_child_rdvl(data); + if (child_vl != data->max_vl) { + ksft_test_result_fail("%s is %d but child VL is %d\n", + data->default_vl_file, + data->max_vl, child_vl); + return; + } + + ksft_test_result_pass("%s vector length used default\n", data->name); + + file_write_integer(data->default_vl_file, data->default_vl); +} + +/* If we didn't request it a new VL shouldn't affect the child */ +static void prctl_set_for_child(struct vec_data *data) +{ + int ret, child_vl; + + if (data->min_vl == data->max_vl) { + ksft_test_result_skip("%s only one VL supported\n", + data->name); + return; + } + + ret = prctl(data->prctl_set, data->min_vl | PR_SVE_VL_INHERIT); + if (ret < 0) { + ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n", + data->name, data->min_vl, + errno, strerror(errno)); + return; + } + + /* The _INHERIT flag should be present when we read the VL */ + ret = prctl(data->prctl_get); + if (ret == -1) { + ksft_test_result_fail("%s prctl() read failed: %d (%s)\n", + data->name, errno, strerror(errno)); + return; + } + if (!(ret & PR_SVE_VL_INHERIT)) { + ksft_test_result_fail("%s prctl() does not report _INHERIT\n", + data->name); + return; + } + + /* Ensure the default VL is different */ + ret = file_write_integer(data->default_vl_file, data->max_vl); + if (ret != 0) + return; + + /* Check that the child inherited our VL */ + child_vl = get_child_rdvl(data); + if (child_vl != data->min_vl) { + ksft_test_result_fail("%s is %d but child VL is %d\n", + data->default_vl_file, + data->min_vl, child_vl); + return; + } + + ksft_test_result_pass("%s vector length was inherited\n", data->name); + + file_write_integer(data->default_vl_file, data->default_vl); +} + +/* _ONEXEC takes effect only in the child process */ +static void prctl_set_onexec(struct vec_data *data) +{ + int ret, child_vl; + + if (data->min_vl == data->max_vl) { + ksft_test_result_skip("%s only one VL supported\n", + data->name); + return; + } + + /* Set a known value for the default and our current VL */ + ret = file_write_integer(data->default_vl_file, data->max_vl); + if (ret != 0) + return; + + ret = prctl(data->prctl_set, data->max_vl); + if (ret < 0) { + ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n", + data->name, data->min_vl, + errno, strerror(errno)); + return; + } + + /* Set a different value for the child to have on exec */ + ret = prctl(data->prctl_set, data->min_vl | PR_SVE_SET_VL_ONEXEC); + if (ret < 0) { + ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n", + data->name, data->min_vl, + errno, strerror(errno)); + return; + } + + /* Our current VL should stay the same */ + if (data->rdvl() != data->max_vl) { + ksft_test_result_fail("%s VL changed by _ONEXEC prctl()\n", + data->name); + return; + } + + /* Check that the child inherited our VL */ + child_vl = get_child_rdvl(data); + if (child_vl != data->min_vl) { + ksft_test_result_fail("Set %d _ONEXEC but child VL is %d\n", + data->min_vl, child_vl); + return; + } + + ksft_test_result_pass("%s vector length set on exec\n", data->name); + + file_write_integer(data->default_vl_file, data->default_vl); +} + +typedef void (*test_type)(struct vec_data *); + +static const test_type tests[] = { + /* + * The default/min/max tests must be first and in this order + * to provide data for other tests. + */ + proc_read_default, + proc_write_min, + proc_write_max, + + prctl_get, + prctl_set, + prctl_set_no_child, + prctl_set_for_child, + prctl_set_onexec, +}; + +int main(void) +{ + int i, j; + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(tests) * ARRAY_SIZE(vec_data)); + + for (i = 0; i < ARRAY_SIZE(vec_data); i++) { + struct vec_data *data = &vec_data[i]; + unsigned long supported; + + supported = getauxval(data->hwcap_type) & data->hwcap; + + for (j = 0; j < ARRAY_SIZE(tests); j++) { + if (supported) + tests[j](data); + else + ksft_test_result_skip("%s not supported\n", + data->name); + } + } + + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/arm64/mte/.gitignore b/tools/testing/selftests/arm64/mte/.gitignore index bc3ac63f3314..d1fe4ddf1669 100644 --- a/tools/testing/selftests/arm64/mte/.gitignore +++ b/tools/testing/selftests/arm64/mte/.gitignore @@ -1,4 +1,5 @@ check_buffer_fill +check_gcr_el1_cswitch check_tags_inclusion check_child_memory check_mmap_options diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c index f50ac31920d1..0328a1e08f65 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.c +++ b/tools/testing/selftests/arm64/mte/mte_common_util.c @@ -298,7 +298,7 @@ int mte_default_setup(void) int ret; if (!(hwcaps2 & HWCAP2_MTE)) { - ksft_print_msg("FAIL: MTE features unavailable\n"); + ksft_print_msg("SKIP: MTE features unavailable\n"); return KSFT_SKIP; } /* Get current mte mode */ diff --git a/tools/testing/selftests/arm64/pauth/pac.c b/tools/testing/selftests/arm64/pauth/pac.c index 592fe538506e..b743daa772f5 100644 --- a/tools/testing/selftests/arm64/pauth/pac.c +++ b/tools/testing/selftests/arm64/pauth/pac.c @@ -25,13 +25,15 @@ do { \ unsigned long hwcaps = getauxval(AT_HWCAP); \ /* data key instructions are not in NOP space. This prevents a SIGILL */ \ - ASSERT_NE(0, hwcaps & HWCAP_PACA) TH_LOG("PAUTH not enabled"); \ + if (!(hwcaps & HWCAP_PACA)) \ + SKIP(return, "PAUTH not enabled"); \ } while (0) #define ASSERT_GENERIC_PAUTH_ENABLED() \ do { \ unsigned long hwcaps = getauxval(AT_HWCAP); \ /* generic key instructions are not in NOP space. This prevents a SIGILL */ \ - ASSERT_NE(0, hwcaps & HWCAP_PACG) TH_LOG("Generic PAUTH not enabled"); \ + if (!(hwcaps & HWCAP_PACG)) \ + SKIP(return, "Generic PAUTH not enabled"); \ } while (0) void sign_specific(struct signatures *sign, size_t val) @@ -256,7 +258,7 @@ TEST(single_thread_different_keys) unsigned long hwcaps = getauxval(AT_HWCAP); /* generic and data key instructions are not in NOP space. This prevents a SIGILL */ - ASSERT_NE(0, hwcaps & HWCAP_PACA) TH_LOG("PAUTH not enabled"); + ASSERT_PAUTH_ENABLED(); if (!(hwcaps & HWCAP_PACG)) { TH_LOG("WARNING: Generic PAUTH not enabled. Skipping generic key checks"); nkeys = NKEYS - 1; @@ -299,7 +301,7 @@ TEST(exec_changed_keys) unsigned long hwcaps = getauxval(AT_HWCAP); /* generic and data key instructions are not in NOP space. This prevents a SIGILL */ - ASSERT_NE(0, hwcaps & HWCAP_PACA) TH_LOG("PAUTH not enabled"); + ASSERT_PAUTH_ENABLED(); if (!(hwcaps & HWCAP_PACG)) { TH_LOG("WARNING: Generic PAUTH not enabled. Skipping generic key checks"); nkeys = NKEYS - 1; diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 78c902045ca7..c1742755abb9 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* +sve_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index f96baf1cef1a..ebe8694dbef0 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -33,10 +33,12 @@ */ enum { FSSBS_BIT, + FSVE_BIT, FMAX_END }; #define FEAT_SSBS (1UL << FSSBS_BIT) +#define FEAT_SVE (1UL << FSVE_BIT) /* * A descriptor used to describe and configure a test case. diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 2de6e5ed5e25..6836510a522f 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -26,6 +26,7 @@ static int sig_copyctx = SIGTRAP; static char const *const feats_names[FMAX_END] = { " SSBS ", + " SVE ", }; #define MAX_FEATS_SZ 128 @@ -263,6 +264,8 @@ int test_init(struct tdescr *td) */ if (getauxval(AT_HWCAP) & HWCAP_SSBS) td->feats_supported |= FEAT_SSBS; + if (getauxval(AT_HWCAP) & HWCAP_SVE) + td->feats_supported |= FEAT_SVE; if (feats_ok(td)) fprintf(stderr, "Required Features: [%s] supported\n", diff --git a/tools/testing/selftests/arm64/signal/testcases/TODO b/tools/testing/selftests/arm64/signal/testcases/TODO new file mode 100644 index 000000000000..110ff9fd195d --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/TODO @@ -0,0 +1,2 @@ +- Validate that register contents are saved and restored as expected. +- Support and validate extra_context. diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c new file mode 100644 index 000000000000..bb50b5adbf10 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Attempt to change the SVE vector length in a signal hander, this is not + * supported and is expected to segfault. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sve_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SVE_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SVE_VL_LEN_MASK; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least two VLs */ + if (nvls < 2) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static int fake_sigreturn_sve_change_vl(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *sve; + + /* Get a signal context with a SVE frame in it */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + if (head->size != sizeof(struct sve_context)) { + fprintf(stderr, "SVE register state active, skipping\n"); + return 1; + } + + sve = (struct sve_context *)head; + + /* No changes are supported; init left us at minimum VL so go to max */ + fprintf(stderr, "Attempting to change VL from %d to %d\n", + sve->vl, vls[0]); + sve->vl = vls[0]; + + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_SVE_CHANGE", + .descr = "Attempt to change SVE VL", + .feats_required = FEAT_SVE, + .sig_ok = SIGSEGV, + .timeout = 3, + .init = sve_get_vls, + .run = fake_sigreturn_sve_change_vl, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c new file mode 100644 index 000000000000..4b2418aa08a9 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that the SVE register context in signal frames is set up as + * expected. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sve_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SVE_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SVE_VL_LEN_MASK; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least one VL */ + if (nvls < 1) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static void setup_sve_regs(void) +{ + /* RDVL x16, #1 so we should have SVE regs; real data is TODO */ + asm volatile(".inst 0x04bf5030" : : : "x16" ); +} + +static int do_one_sve_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, + unsigned int vl) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *sve; + + fprintf(stderr, "Testing VL %d\n", vl); + + if (prctl(PR_SVE_SET_VL, vl) == -1) { + fprintf(stderr, "Failed to set VL\n"); + return 1; + } + + /* + * Get a signal context which should have a SVE frame and registers + * in it. + */ + setup_sve_regs(); + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + sve = (struct sve_context *)head; + if (sve->vl != vl) { + fprintf(stderr, "Got VL %d, expected %d\n", sve->vl, vl); + return 1; + } + + /* The actual size validation is done in get_current_context() */ + fprintf(stderr, "Got expected size %u and VL %d\n", + head->size, sve->vl); + + return 0; +} + +static int sve_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + int i; + + for (i = 0; i < nvls; i++) { + /* + * TODO: the signal test helpers can't currently cope + * with signal frames bigger than struct sigcontext, + * skip VLs that will trigger that. + */ + if (vls[i] > 64) + continue; + + if (do_one_sve_vl(td, si, uc, vls[i])) + return 1; + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "SVE registers", + .descr = "Check that we get the right SVE registers reported", + .feats_required = FEAT_SVE, + .timeout = 3, + .init = sve_get_vls, + .run = sve_regs, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sve_vl.c b/tools/testing/selftests/arm64/signal/testcases/sve_vl.c new file mode 100644 index 000000000000..92904653add1 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sve_vl.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Check that the SVE vector length reported in signal contexts is the + * expected one. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +unsigned int vl; + +static bool get_sve_vl(struct tdescr *td) +{ + int ret = prctl(PR_SVE_GET_VL); + if (ret == -1) + return false; + + vl = ret; + + return true; +} + +static int sve_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *sve; + + /* Get a signal context which should have a SVE frame in it */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + sve = (struct sve_context *)head; + + if (sve->vl != vl) { + fprintf(stderr, "sigframe VL %u, expected %u\n", + sve->vl, vl); + return 1; + } else { + fprintf(stderr, "got expected VL %u\n", vl); + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "SVE VL", + .descr = "Check that we get the right SVE VL reported", + .feats_required = FEAT_SVE, + .timeout = 3, + .init = get_sve_vl, + .run = sve_vl, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c index 61ebcdf63831..8c2a57fc2f9c 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.c +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -50,12 +50,38 @@ bool validate_extra_context(struct extra_context *extra, char **err) return true; } +bool validate_sve_context(struct sve_context *sve, char **err) +{ + /* Size will be rounded up to a multiple of 16 bytes */ + size_t regs_size + = ((SVE_SIG_CONTEXT_SIZE(sve_vq_from_vl(sve->vl)) + 15) / 16) * 16; + + if (!sve || !err) + return false; + + /* Either a bare sve_context or a sve_context followed by regs data */ + if ((sve->head.size != sizeof(struct sve_context)) && + (sve->head.size != regs_size)) { + *err = "bad size for SVE context"; + return false; + } + + if (!sve_vl_valid(sve->vl)) { + *err = "SVE VL invalid"; + + return false; + } + + return true; +} + bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) { bool terminated = false; size_t offs = 0; int flags = 0; struct extra_context *extra = NULL; + struct sve_context *sve = NULL; struct _aarch64_ctx *head = (struct _aarch64_ctx *)uc->uc_mcontext.__reserved; @@ -90,9 +116,8 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) case SVE_MAGIC: if (flags & SVE_CTX) *err = "Multiple SVE_MAGIC"; - else if (head->size != - sizeof(struct sve_context)) - *err = "Bad size for sve_context"; + /* Size is validated in validate_sve_context() */ + sve = (struct sve_context *)head; flags |= SVE_CTX; break; case EXTRA_MAGIC: @@ -137,6 +162,9 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) if (flags & EXTRA_CTX) if (!validate_extra_context(extra, err)) return false; + if (flags & SVE_CTX) + if (!validate_sve_context(sve, err)) + return false; head = GET_RESV_NEXT_HEAD(head); } |